СИСТЕМА И СПОСОБ ДЛЯ РАСПРОСТРАНЕНИЯ ИНФОРМАЦИИ С ИСПОЛЬЗОВАНИЕМ МОДИФИЦИРОВАННЫХ НУКЛЕИНОВЫХ КИСЛОТ

Настоящее изобретение относится к области биоинформатики. Предложен способ для приготовления улучшенной вычислительной системы, основанной на нуклеиновых кислотах, включающий синтезирование в водном растворе варианта системы молекулярных вычислений, отличающегося включением химической модификации, изменяющей энергию гибридизации молекул нуклеиновых кислот в системе. Также рассмотрена вычислительная система, основанная на нуклеиновых кислотах и содержащая химические модификации в соответствии со способом по настоящему изобретению. Предложенное изобретение позволяет увеличивать вероятность желаемых событий связывания молекул нуклеиновых кислот в составе системы. 2 н. и 14 з.п. ф-лы, 8 ил.

СЕРВЕРНАЯ ВЫЧИСЛИТЕЛЬНАЯ СИСТЕМА

Изобретение относится к области компьютерной техники, обеспечивающей возможность определения финансовых трендов и выполнения системного анализа. Технический результат заключается в снижении нагрузки на вычислительные мощности для выполнения финансовых трендов и системного анализа данных. Технический результат достигается за счет серверной вычислительной системы, содержащей запоминающее устройство, к которому имеет доступ серверная вычислительная система и в котором хранится генный пул серверной вычислительной системы, содержащий множество генов, каждый из которых определяет множество индикаторов и, по меньшей мере, одно действие, соответствующее индикаторам, причем каждый класс связан с соответствующим подмножеством индикаторов, коммуникационный порт, через который серверная вычислительная система получает и записывает в запоминающее устройство гены из клиентских компьютеров, включая первое подмножество генов, которые получены из клиентских компьютеров, которым был присвоен первый класс ...

СПОСОБЫ И УСТРОЙСТВО ДЛЯ ИНТЕГРИРОВАНИЯ СИСТЕМАТИЧЕСКОГО ПРОРЕЖИВАНИЯ ДАННЫХ В ОСНОВАННЫЙ НА ГЕНЕТИЧЕСКОМ АЛГОРИТМЕ ВЫБОР ПОДМНОЖЕСТВА ПРИЗНАКОВ

Изобретения относятся к способам и устройству для интегрирования систематического прореживания данных в основанные на генетических алгоритмах системы выбора подмножества признаков для извлечения данных, уменьшения ложно положительных результатов, компьютеризированного обнаружения, компьютеризированной диагностики и искусственного интеллекта. Техническим результатом является улучшение точности классификации и уменьшение ложно положительных результатов. Способ содержит этапы: выбирают набор данных обучения из набора обучающих прецедентов с использованием систематического прореживания данных и создают классификатор на основании набора данных обучения с использованием способа классификации. 4 н. и 11 з.п. ф-лы, 14 ил., 4 табл.

Система генерации тестовых данных

Изобретение относится к тестированию программного обеспечения. Техническим результатом заявляемого изобретения является повышение быстродействия и качества генерации тестов. Для этого в системе присутствует блок генерации функции приспособленности, который соединен с блоком генерации популяции, который подсоединен к генератору измененной популяции, имеющий связь с блоком фиксации отработки, причем блок фиксации отработки соединен встречной связью с генератором измененной популяции. Данный метод генерации позволяет увеличить быстродействие, а также качество подбора тестовых данных. Генетический алгоритм осуществляет поиск баланса между эффективностью и качеством решений за счет «выживания сильнейших альтернативных решений» в неопределенных и нечетких условиях. 3 ил.

УСТРОЙСТВО АППАРАТНОЙ РЕАЛИЗАЦИИ ВЕРОЯТНОСТНЫХ ГЕНЕТИЧЕСКИХ АЛГОРИТМОВ

Изобретение относится к аппаратным системам, реализующим вероятностные генетические алгоритмы. Техническим результатом является снижение вычислительных затрат на проведение эволюционного поиска и обеспечение автономности функционирования объекта при принятии решений в изменяющейся среде. Для этого устройство содержит блок инициализации, блок вычисления величины элитной области, блок генерации прерываний, блок микропрограммного управления, блок адресного указателя, блок генерации популяции, блок формирования разрядности хромосомы, блок мультиплексоров, блок памяти, блок вычисления критерия, блок отбора, блок формирования элитной области, блок вычисления вероятности. 12 ил., 2 табл.

ОПТИМИЗАТОР ПРОИЗВОДСТВА ДЛЯ УПРАВЛЕНИЯ ЦЕПОЧКАМИ ПОСТАВОК

Изобретение относится к области оптимизатора производства для управления цепочками поставок. Техническим результатом является обеспечение возможности вычисления за приемлемое время высококачественных решений для задачи управления цепочками поставок (УЦП). В одном из вариантов осуществления настоящего изобретения предложен способ оптимизации задачи УЦП. Для генерации решения относительно производства для производственных аспектов задачи УЦП может быть использована методика оптимизации, основанная на генетическом алгоритме, а для генерации решения для аспектов распределения задачи УЦП может быть использована методика оптимизации, основанная на принципе «муравейника». Совместное функционирование методики оптимизации, основанной на генетическом алгоритме, и методики оптимизации, основанной на принципе «муравейника», обеспечивает быстрое определение высококачественных решений задачи УЦП. 3 н. и 24 з.п. ф-лы, 9 ил.

КОНТРОЛЛЕР УПРАВЛЕНИЯ ОБУЧЕНИЕМ НЕЙРОННОЙ СЕТИ С ГЕНЕТИЧЕСКИМ АЛГОРИТМОМ

Изобретение относится к интеллектуальным контроллерам, использующим генетический алгоритм для поиска структуры нейронной сети и весовых коэффициентов ее синаптических связей. Техническим результатом является повышение скоростных характеристик поиска структуры нейронной сети и упрощение конечной реализации системы управления на базе контроллера. Устройство содержит объект управления, блок обучения нейронной сети, блок оценки производительности нейронной сети, блок данных, блок нейронной сети, блок управления, блок генетического алгоритма, блок истории хромосом и блок оценки хромосом. 1 ил.

СИСТЕМЫ И СПОСОБЫ ДНК-ВЫЧИСЛЕНИЙ, ОСНОВАННЫЕ НА ПРИМЕНЕНИИ МЕТИЛИРОВАНИЯ

... 1. Способ применения логики, основанной на метилировании, включающий: ! генерацию логического выражения, в состав которого входят переменные, имеющие множество значений, включающее метилированную переменную и отрицание упомянутой метилированной переменной, соответствующее неметилированной переменной; ! метилирование смеси или образца; ! изменение состояния метилирования образца на обратный; ! разделение упомянутой смеси или образца путем применения одной или нескольких методик разделения с целью выделения хотя бы одной разделенной смеси; ! декодирование хотя бы одной разделенной смеси; и ! считывание по крайней мере одной разделенной смеси для связывания упомянутого логического выражения и упомянутого декодирования. ! 2. Способ по п.1, при котором он является эффективным в проверке биомаркеров и/или создании, или идентификации новых биомаркеров. ! 3. Способ по п.1, когда одна или несколько методик разделения включают в себя получение ряда проб. ! 4. Способ по п.1, при котором считывание ...

СПОСОБ ОПРЕДЕЛЕНИЯ МИНЕРАЛЬНОГО СОСТАВА ПОРОД ПО ДАННЫМ ГЕОФИЗИЧЕСКИХ ИССЛЕДОВАНИЙ СКВАЖИН

SIMULTANE EVOLUTION EINES MEHRTEILIGEN PROGRAMMS

Vorrichtung und Verfahren zum verschlüsselten Sicherheitsmarkierung zum Schutz von Wertgegenständen.

Vorrichtung und Verfahren zum verschlüsselten Sicherheitsmarkierung zum Schutz von Wertgegenständen.

DNA computer has a number of bioreactors connected to a channel system with parallel filter arrays for each, with selective filters of the same selection linked to specific bioreactors for mathematical operations

A DNA computer has a number of bioreactors (T1-T5), linked to a channel system with connections for feeds and outflows, filled with enzymes and other additives to carry out molecular biological operations and DNA sequences. The DNA computer has a number of bioreactors (T1-T5), linked to a channel system with connections for feeds and outflows, to be filled with enzymes and other additives to carry out molecular biological operations and DNA sequences. At least one additional bioreactor (T6) has an inflow from the channel system. A parallel array of filters (F1-F6) is in the flow path from each bioreactor, each filter having individual selection characteristics, with a duplication of the filtered DNA sequences at each filtering. The outflows from the filters are linked to the bioreactor inflows so that filters with the same characteristics are connected to the same bioreactor to take the DNA sequences for the desired results. The DNA result is coded in a specific length and/or base series ...

Prozesssteuerungs- und optimierungstechnik unter Verwendung immunologischer Konzepte

Prozesssteuerungssystem zur Steuerung eines Prozesses, aufweisend: eine Steuerung, angepasst, um einen Satz von Ziel-Steuerungssignalwerten zu verwenden, um ein oder mehrere Prozesssteuerungssignale zur Verwendung bei der Steuerung eines oder mehrerer Feldgeräte innerhalb des Prozesses zu erzeugen, und einen kommunikativ mit der Steuerung gekoppelten Optimierer, angepasst, um während des Online Betriebes den Satz von Ziel-Steuerungssignalwerten zu entwickeln, der Online Betrieb aufweisend: (a) eine stochastische Optimierungsbetriebsart, die zu einem stabilen Betrieb des Prozesses korrespondiert und (b) eine Regelungsbetriebsart, die zu einem geänderten Zustand des Prozesses korrespondiert, und aufweisend: (A) einen Speicher zur Speicherung einer Mehrzahl von Prozesssteuerungsstatus, (B) eine mit dem Speicher kommunikativ gekoppelte Optimierungseinheit, angepasst, um die gespeicherte Mehrzahl von Prozesssteuerungsstatus zu verwenden, um eine Reihe von Ziel-Steuerungssignalwerten zur Verwendung ...

Reduktion von Angepasstheitsbeurteilungen unter Verwendung von Gruppierungstechniken und Neuronalnetzwerkmengen

Method for optimizing configuration of pick-and-place machine

Consumer model

System design using artifical intelligence

Differential evolution method oriented to agile satellite multi-target task planning

The method includes: converting a solution set space formed by a decision variable into a population; initializing the population and algorithm parameters of the population; generating a donation vector, a trial vector, and a subgeneration according to the algorithm parameters of the population; adding the subgeneration into the population to obtain a mutational population , and decoding an individual to obtain adaptability; determining whether a current quantity of iterations i is less than a total quantity of iterations; if so, selecting an individual in the mutational population, generating a new population, and updating algorithm parameters of a corresponding population; otherwise, removing a dominated solution in an elite solution set, and adding a non-dominated solution in the mutational population into solutions that are not dominated by an individual in the elite solution set, so as to update the elite solution set; and step 8: sorting individuals in the elite solution set, and ...

Personalized genetic testing

The present disclosure provides methods and systems for personalized genetic testing of a subject. In some embodiments, a sequencing assay is performed on a biological sample from the subject, which then leads to genetic information related to the subject. Next, nucleic acid molecules are array-synthesized or selected based on the genetic information derived from data of the sequencing assay. At least some of the nucleic acid molecules may then be used in an assay which may provide additional information on one or more biological samples from the subject or a biological relative of the subject.

Autonomous search and track using a wide FOV

A surveillance system (105) comprises a sensor manager 155, a target detection module 175, and a sensor 165. The target detection module receives imagery developed from the sensor and is configured to detect objects of interest within the imagery. The sensor manager sends command messages, indicating where the sensor should survey. The system is configured to analyse the detected objects of interest using an exploration - exploitation algorithm to determine where to survey with the sensor. The system could be used on unmanned aerial vehicles (UAVs) equipped with sensors to survey areas from a remote location. The sensor could be a camera mounted on a Pan Tilt Zoom (PTZ) apparatus allowing it to point in any direction and to control its zoom. The objects of interest could be associated with rewards and the system configured to maximise or minimise the reward. Also described is an associated sensor manager and a method of operating a surveillance system.

Hardware design using evolutionary algorithms

CHEMICAL CIRCUIT OF NUCLEIC ACID CIRCUIT ELEMENTS

PRODUCTION OF CHEMICAL MARKINGS

STEGANOGRAPHIE ON DNA BASIS

HEURISTIC CLASSIFICATION PROCEDURE

HARDWARE DRAFT USING EVOLUTIONARY ALGORITHMS

GENETIC SYNTHESIS OF NEURAL NETWORKS.

CHEMICAL CIRCUIT OF NUCLEIC ACID CIRCUIT ELEMENTS

CHEMICAL CIRCUIT OF NUCLEIC ACID CIRCUIT ELEMENTS

CHEMICAL CIRCUIT OF NUCLEIC ACID CIRCUIT ELEMENTS

CHEMICAL CIRCUIT OF NUCLEIC ACID CIRCUIT ELEMENTS

CHEMICAL CIRCUIT OF NUCLEIC ACID CIRCUIT ELEMENTS

CHEMICAL CIRCUIT OF NUCLEIC ACID CIRCUIT ELEMENTS

CHEMICAL CIRCUIT OF NUCLEIC ACID CIRCUIT ELEMENTS

CHEMICAL CIRCUIT OF NUCLEIC ACID CIRCUIT ELEMENTS

CHEMICAL CIRCUIT OF NUCLEIC ACID CIRCUIT ELEMENTS

CHEMICAL CIRCUIT OF NUCLEIC ACID CIRCUIT ELEMENTS

CHEMICAL CIRCUIT OF NUCLEIC ACID CIRCUIT ELEMENTS

CHEMICAL CIRCUIT OF NUCLEIC ACID CIRCUIT ELEMENTS

Constrained stable matching strategy-based flexible job-shop scheduling method

A constrained stable matching strategy-based flexible job-shop scheduling method, belonging to the field of job-shop scheduling. The design solution of said method comprises: a . generating an initial chromosome population by means of integer coding, and initializing relevant parameters; b. performing crossover and mutation on parent chromosomes, so as to obtain child chromosomes; c . grouping the child chromosomes and the parent chromosomes into a set of chromosomes to be selected, and selecting the next generation of chromosomes therefrom by means of constrained stable matching operation; and d. if a termination condition is satisfied, terminating the algorithm; and if not, returning to step b. The present invention introduces a constrained stable matching strategy to the process of selecting child chromosomes to solve the multi-target flexible job-shop scheduling problem, overcoming the disadvantages of population distribution and poor convergence of the existing multi-target flexible ...

Extensible markup language genetic algorithm

Method, system and computer software for providing a genomic web portal

Method and apparatus for identifying components of a system with a response characteristic

Methods for produced labeled nucleic acids or proteins

Methods of storing information using nucleic acids

The present invention relates to methods of storing data using one or more nucleic acids.

IOT BASED GENERIC FRAMEWORK FOR COMPUTER SECURITY USING ARTIFICIAL IMMUNE SYSTEM

IOT BASED GENERIC FRAMEWORK FOR COMPUTER SECURITY USING ARTIFICIAL IMMUNE SYSTEM The present invention relates to a generic framework for computer security using artificial immune system. System is presented as an example of a system developed around the current understanding of the immune system. This system explains capability of an Artificial Immune Systems to capture the basic elements of the immune system and demonstrates the some of its main properties. As natural immune system have features like diversity, distributed computation, error tolerance, dynamic learning and adaptation and self-monitoring these are integrated in the invented generalized framework for Artificial Immune Systems which is utilized for the computer security. The natural human immune system has encouraged scientists, engineers and researchers for discovering powerful information processing algorithms to solve multifarious engineering tasks. The Artificial Immune Systems can be applied to many domains like classification ...

Distributed hierarchical evolutionary modeling and visualization of empirical data

Digital image improvement through genetic image evolution

Hybridization of polynucleotides conjugated with chromophores and fluorophores to generate donor-to-donor energy transfer system

METHOD AND APPARATUS FOR IDENTIFYING COMPONENTS OF A SYSTEM WITH A RESPONSE CHARACTERISTIC

A method for identifying components of a system from data generated from the system, which exhibit a response pattern associated with a test condition applied to the system, comprising the steps of specifying design factors to specify a response pattern for the test condition and identifying a linear combination of components from the input data which correlate with the response pattern.

PRODUCTION OPTIMIZER FOR SUPPLY CHAIN MANAGEMENT

... ²²²One embodiment of the invention provides a method for optimizing a supply ²chain management (SCM) problem. A genetic algorithm optimization technique may ²be used to generate a production solution for the production side of an SCM ²problem and an ant colony optimization technique may be used to generate a ²solution for the distribution side of the SCM problem. Together, the genetic ²algorithm optimization technique and the ant colony optimization technique ²operate to quickly identify high-quality solutions to an SCM problem.² ...

METHOD OF PREDICTING DIAMETRAL CREEP OF CANDU REACTOR PRESSURE TUBES

A PT diametral creep prediction method of CANDU includes classifying creep data consisting of input-output data pairs (x1,.multidot., x4, y r) from nuclear power plants into training data and verification data; inputting arbitrary variables at an initial time to operate a genetic algorithm to randomly generate an initial chromosome including membership function parameters; calculating a fitness function of the genetic algorithm; determining whether a degree of fitness of the fitness function is greater than a predetermined value; altering the variables through genetic manipulation including selection, crossing and modification to continuously improve the genetic algorithm, if the degree of fitness of the fitness function is less than the predetermined value; generating a membership function based on an SC method; calculating consequent parameters of a fuzzy rule function using a least-squares method; revising an FNN creep prediction model with the membership function and the consequent ...

HARDWARE DESIGN USING EVOLUTION ALGORITHMS

The design of a hardware component such as a digital filter can be optimised by taking an initial population of filter designs and encoding them as chromosomes. The fitness of each chromosome is then evaluated and parent chromosomes are then selected based on the fitness criteria. Offspring chromosomes are then generated ussing genetic operations such as mutation and crossover from the pool of offspring, and optionally parents, individuals are selected to survive using a combination of Pareto fronts based on non- dominated individuals and clustering. The process is repeated or until a termination criteria is satisfied.

METHOD AND SYSTEM FOR EVOLUTIONARY PHENOGENETIC ENGINEERING

Method and system for facilitating the design of a species of artifact through a process of participative refinement; this process being analogous to natural selection as it operates within biological populations. In this invention, genetic data structures are employed to encode designs. Participants publish these encoded designs on a communication network, such as the Internet, to establish a population of variant genotypes. These genotypes are then subject to human guided mutation and recombination, resulting in the progressive improvement of the corresponding designs.

METHODS OF CODING AND DECODING INFORMATION

The invention relates to information coding/decoding. As a result, the effectiveness of antinoise coding and decoding is enhanced due to the increase in the volume of transmitted and received information and due to the decrease in the number of elements used for coding/ decoding. During the coding method implementation a data array to be coded is divided into logically complete chunks, each of which is associated with at least one element of the molecular genetic system used for the coding; the set of elements in the system is supplemented by relevant indexing information consisting of i data bits; each code combination of data bits is supplemented by a combination of k check bits which is defined depending on i data bits combination; each piece of i+k bit data in binary form is written as a multiplet of the molecular genetic system consisting of the n number of nitrogenous bases or corresponding amino acids. The information to be coded is recorded together with a) the value n, whereas ...

ALIGNMENT AND VARIANT SEQUENCING ANALYSIS PIPELINE

Provided are systems and methods for analyzing genetic sequence data from next generation sequence (NGS) platforms. Also provided are methods for the preparation of samples for nucleic acid sequence analysis by NGS. Variant calling is performed with a modified GATK variant caller. Mapping the reads to a genomic reference sequence is performed with a Burrows Wheeler Aligner (BWA) and does not comprise soft clipping. The genomic reference sequence is GRCh37.1 human genome reference. The sequencing method comprises emulsion PCR (emPCR), rolling circle amplification, or solid-phase amplification. In some embodiments, the solid-phase amplification is clonal bridge amplification.

METHODS FOR IMPROVED PRODUCTION AND DISTRIBUTION

A computer-implemented system and method for producing and distributing at least one product from at least one plant to at least one customer where discretized plant production data, filtered customer sourcing data, forecasted customer demand data, and forecasted plant electricity pricing data are input into a modified genetic algorithm and an electronic processor solves the modified genetic algorithm and outputs the solution to an interface. The system and method is flexible and can incorporate data as it becomes available to yield intermediate solutions for quick decision making.

METHODS OF STORING INFORMATION USING NUCLEIC ACIDS

The present invention relates to methods of storing data using one or more nucleic acids including converting a format of information into a plurality of bit sequences of a bit stream with each having a corresponding bit barcode, converting the plurality of bit sequences to a plurality of corresponding oligonucleotide sequences using one bit per base encoding, synthesizing the plurality of corresponding oligonucleotide sequences, and storing the synthesized plurality of corresponding oligonucleotide sequences.

HYBRIDIZATION OF POLYNUCLEOTIDES CONJUGATED WITH CHROMOPHORES AND FLUOROPHORES TO GENERATE DONOR-TO-DONOR ENERGY TRANSFER SYSTEM

... 2123133 9309128 PCTABS00022 The present invention contemplates chromophore-containing polynucleotides having at least two donor chromophores operatively linked to the polynucleotide by linker arms, such that the chromophores are positioned by linkage along the length of the polynucleotide at a donor-donor transfer distance, and at least one fluorescing acceptor chromophore operatively linked to the polynucleotide by a linker arm, such that the fluorescing acceptor chromophore is positioned by linkage at a donor-acceptor transfer distance from at least one of the donor chromophores, to form a photonic structure for collecting photonic energy and transferring the energy to an acceptor chromophore, and methods using the photonic structures.

AFFINITY BASED SELF-ASSEMBLY SYSTEMS AND DEVICES FOR PHOTONIC AND ELECTRONIC APPLICATIONS

This invention relates to techniques which utilize programmable functionalized self-assembling nucleic acids, nucleic acid modified structures, and other selective affinity or binding moieties as building blocks. The invention is a method for the fabrication of micro scale and nanoscale devices comprising the steps of: fabricating first component devices on a first support, releasing at least one first component device from the first support, transporting the first component device to a second support, and attaching the first component device to the second support. The invention also provides for orienting a structure in an electric field, reacting affinity sequences, and assembling chromophoric structures by photoactivation.

Casting workshop production plan optimization method considering melting furnace and sand mold size

Internet-of-Vehicles optimal vehicle-mounted monitoring point-based air quality evaluation system and method

Microgrid multi-objective real-time rolling optimization method

Production-data-driven dynamic job-shop scheduling rule intelligent selection method

Product function gene modeling system and method

The invention discloses a product function gene modeling system and method. The system comprises a behavior describing unit, a overall function determining unit and a overall function decomposing unit, wherein the behavior describing unit is used for describing the functional relation of parts among products; the overall function determining unit is used for analyzing functional requirements suggested by users, grasping the core of the overall design task to obtain the design requirements of the products and abstracting the overall function of the products; the overall function decomposing unit is used for decomposing the overall function into a plurality of simple subfunctions. The system also comprises a product function reasoning module which further comprises an FTML file reading unit, a function element matrix converting unit, a matrix adjusting unit and an FTML film converting unit. Aiming at function design knowledge and design object knowledge, the invention provides the function ...

DNA logic cascade circuit and processing method, device and medium

Wavelet image de-noising method and device based on genetic algorithm

Online prediction method for iron ore sintering bed permeability states

Non-coherent scattering radar data inversion method based on genetic algorithm

Method applied to remote health monitoring offline service task scheduling with soft time window

Complex structure blank processing and positioning method based on three-dimensional inverse solution

network synchronization performance optimization method based on a genetic algorithm

Scheduling optimization method of digital micro-fluidic chip based on improved whale optimization algorithm

Method for increasing gear hob processing accuracy

Three-dimensional multi-target positioning method based on genetic algorithm

Time-sharing leasing equipment management optimization recommendation system based on evolution thinking

Method for deploying and optimizing relay nodes in a wireless sensor network

A genetic algorithm for a heterogeneous system

Road extraction method and system based on SVM and genetic algorithm

Novel water-light complementary multi-objective optimization operation method

Image retrieval method based on multiple intelligent algorithms and image fusion technology

Unsupervised image division method based on multi-target immune cluster integration

The invention discloses an unsupervised image division method based on a multi-target immune cluster integration technology, which mainly solves the problems of poor global optimization capability, single evaluation index, single division scheme form and difficult selection of a plurality of division schemes in the traditional technology. The method comprises the following steps of: (1) extracting gray scale information and wavelet energy information of an image to be divided; (2) sampling the image by using an area-based sampling policy to generate a test sample set; (3) selecting different characteristic vectors to form a plurality of test sample sets; (3) generating a primary division scheme by using an evolution cluster based on a multi-target immune algorithm; (5) integrating and learning an optimal division scheme in the primary division scheme; (6) marking the class of the pixel points of the image according to the selected division scheme; and (7) outputting the image division result ...

Data discretization method, device, equipment and medium

The neural network method for determining quantization strategies, Image recognition method and apparatus

Plant protection unmanned plane cluster job task allocation method and device

Intelligent feature identification method facing STEP-NC 2.5D manufacturing features

Method for getting expert system knowledge based on support vector machine

The invention provides a method for getting expert system knowledge based on a support vector machine. A rule extracting process based on the support vector machine comprises data preprocessing, clustering of support vectors, extracting and simplifying of a super-rectangular rule, and sample identifying based on the rule. The method has the advantages that after the feature extracting and the rule simplifying are carried out, the extracted rule is more concise and is easier to explain; when a clustering and distributing matrix is calculated, only the support vectors are clustered and identified, so the calculation amount is greatly reduced; the rule extracting method is advanced, and the diagnosing and identifying rate is higher; the support vector machine is an emerging classifying technique for data mining, and has a solid theoretical foundation and a favorable generalizing performance; and the method can be used for effectively getting the rule of the expert system knowledge, and the ...

PGSA-GA mixed algorithm-based fault section positioning method

Circuit structure optimization method based on tracing coding and genetic algorithm

Method for allocating cargo positions for cargoes in three-dimensional warehouse

The invention relates to a method for allocating cargo positions for cargoes in a three-dimensional warehouse. The method comprises the following steps that an original group is obtained; the weighted average method is used for calculating the individual fitness of each cargo position represented with position coordinates; comparing is carried out, and the individual with the highest fitness is recorded; the genetic algorithm is adopted to carry out individual copy, cross, variation and individual variation on the individuals in the original group, and a new group is obtained; whether the set number of iterations is achieved or not is judged, if yes, the weighted average algorithm is used for calculating the individual fitness for the new group; comparing is carried out, and the individual with the highest fitness is recorded; the highest fitness of the new group and the highest fitness of the original group are compared, the individual with the highest fitness is selected, and the cargo ...

Computer system for economic management data analysis

Locomotive automatic driving control prediction model machine learning method

Differential evolution geomagnetic navigation method based on grid features

Staged replacing method for renewing genetic populations

The invention discloses a staged replacing method for renewing genetic populations. In the method, the populations are treated at three stages according to a practical situation after selection, cross and variation, the proper populations are directly retained to a next generation, the populations in the middle are replaced by the proper populations through a clone selection method, and residual improper populations are replaced by nascent populations. By the aid of the method, the whole population keeps diversity, premature convergence is avoided, the usage rate of the superior populations is increased, and accordingly, genetic algorithm performance can be improved.

Simulation method for finite element of laser welding temperature field based on BP neural network and genetic algorithm GA

Multi-target genetic optimization compressed sensing image reconstruction method based on ridgelet dictionary

power failure system recovery path optimization method based on redundant coding correction

Method for quantifying amplitude of a response of a biological network

One or more measurement signatures are derived from a knowledge base of casual biological facts, where a signature is a collection of measured node entities and their expected directions of change with respect to a reference node. The knowledge base may be a directed network of experimentally-observed casual relationships among biological entities and processes, and a reference node represents a perturbation. A degree of activation of a signature is then assessed by scoring one or more “differential” data sets against the signature to compute an amplitude score. The amplitude score quantifies fold-changes of measurements in the signature. In one particular embodiment, the amplitude score is a weighted average of adjusted log-fold changes of measured node entities in the signature, wherein an adjustment applied to the log-fold changes is based on their expected direction of change. In an alternative embodiment, the amplitude score is based on quantity effects.

Extracting data

Information can be extracted from unstructured documents using embodiments described herein. An entity recognition may be performed on an unstructured document and found entities may be annotated. Annotating includes inserting tags around the found entities to generate marked entities. A rule is applied to each of the marked entities in the unstructured document to generate a confidence value for every marked entity, wherein the rule comprises a plurality of prefixes for a target entity and a plurality of suffixes for the target entity. A marked entity with the highest confidence value is selected as an extraction target.

Controlling quarantining and biasing in cataclysms for optimization simulations

Some embodiments are directed to generating a first probability value that represents a percentage of times that first bit values for a given bit position of a first plurality of candidate solutions equate to a pre-defined number, where the first plurality of candidate solutions has converged on a sub-optimal solution during a simulation of an optimization problem using an optimization algorithm. Some embodiments are further directed to generating a second probability value that is inversely biased from the first probability value; and generating a second plurality of candidate solutions with the second probability value, where the second plurality of candidate solutions are inversely biased from the first bit values for the given bit position.

Systems and methods for generating missing rules matching a minimal set of objects

A method ( 1500 ) for generating a Generalized Missing Rule (GMR). The method involves receiving descriptions of First Scopes (FSs) that are admissible for a First Rule Project (FRP). FRP comprises first rules. Each FS is defined by at least one object characterizing a case. An Expanded Set of Scope Descriptions (ESSD) is generated by adding descriptions of Second Scopes (SSs) covered by FRP to the descriptions of FSs. An Implicit Description (ID) of FSs and SSs is produced. An Incomplete Most-General Scope (IMGS) is identified from FSs and SSs using ID. IMGS is a scope which is defined by a minimal set of objects, is admissible for FRP and covers at least one case which is not treated by a Second Rule Project (SRP). A Missing Case (MC) of IMGS is identified. MC is not treated by FRP. GMR is generated using MC and IMGS.

Method for quantifying amplitude of a response of a biological network

One or more measurement signatures are derived from a knowledge base of casual biological facts, where a signature is a collection of measured node entities and their expected directions of change with respect to a reference node. The knowledge base may be a directed network of experimentally-observed casual relationships among biological entities and processes, and a reference node represents a perturbation. A degree of activation of a signature is then assessed by scoring one or more “differential” data sets against the signature to compute an amplitude score. The amplitude score quantifies fold-changes of measurements in the signature. In one particular embodiment, the amplitude score is a weighted average of adjusted log-fold changes of measured node entities in the signature, wherein an adjustment applied to the log-fold changes is based on their expected direction of change. In an alternative embodiment, the amplitude score is based on quantity effects.

System and Method for Using Genetic Algorithm for Optimization of Targeting Systems, Based on Aggregated Scoring Models

In our presentation here, as examples, we describe methods and systems with various optimization techniques. More specifically, they are directed to methods for applying genetic algorithms, and the use of genetic algorithms in optimizing targeting systems that use an aggregated scoring model. In general, the genetic algorithm principle gives guidelines for constructing practical search techniques when the number of possible trials is extremely large. The examples and other features and advantages of the system and method for using Genetic Algorithm for Optimization of Targeting Systems are described.

Controlling quarantining and biasing in cataclysms for optimization simulations

Some examples are directed to determining a frequency of occurrence of a first value in a component of a first plurality of candidate solutions for an optimization problem where the first plurality of candidate solutions has converged on a sub-optimal solution during a computer simulation that tests fitness of the first plurality of candidate solutions. Some examples are further directed to determining a second value that is inversely biased from the frequency of occurrence of the first value. Some examples are further directed to including the second value in a component of at least a portion of a second plurality of candidate solutions, where the component of the at least the portion of the second plurality of candidate solutions corresponds to the component of the first plurality of candidate solutions.

Evolutionary Scheduling of Utility Consumers

A computer-based method to schedule utility consumers includes creating a first generation of vectors using a processor. A vector is made up of a set of operation periods within a time period for consumers of a utility. The method also includes producing, using a processor, one or more successive generations of vectors from the first generation of vectors to create a descendant generation of vectors, and selecting a vector of the descendant generation of vectors based on a fitness function. Then operation periods from the vector of the descendant generation of vectors are provided over a computer communication medium to control operation of the consumers of the utility. 1. A computer-based method to schedule utility consumers comprising:obtaining a list of consumers of a utility to be scheduled, constraints for valid periods of operation for said consumers;creating a first generation of chromosomes by using a processor to randomly generate periods of operation within said constraints, wherein a gene represents a period of operation within a time period for a consumer of the utility and each chromosome comprises a gene for each of said consumers;producing, using a processor, successive generations of chromosomes from the first generation of chromosomes to create a descendant generation of chromosomes, wherein the descendant generation of chromosomes is a successive generation of chromosomes;selecting a chromosome of the descendant generation of chromosomes based on a fitness function; andproviding periods of operation from genes of said selected chromosome over a computer communication medium to control operation of the consumers of the utility; mating at least two chromosomes of a previous generation of chromosomes to produce each chromosome of a successive generation of chromosomes;', 'mutating one or more chromosomes of the successive generation of chromosomes;', 'adding at least some of the previous generation of chromosomes to the successive generation of ...

Method and system for energy control management

In order to reduce computation time and cost involved with determining one or more optimal parameters for a pre-cooling strategy, for a modeled system, a two-step genetic algorithms is used to optimize energy consumption of the modeled system with respect to cost of the energy consumption. A first step of the two-step genetic algorithms determines a population of potential solutions that are used to initialize a second step of the two-step genetic algorithm. The second step of the two-step genetic algorithm determines the one or more optimal parameters for the pre-cooling strategy from the population output by the first genetic algorithm.

Mixed off-site/on-site prediction computation for reducing wireless reconnection time of a computing device

A method, system, and device for reducing connection time to a wireless access point includes recording wireless connection information in a log, remotely computing parameters as a function of past wireless connection information in the log, generating an ordered list of wireless access points most likely to be available for reconnection at a desired time as a function of recent wireless connection information in the log, and directly probing a wireless access point instead of initiating a wireless access point scan. In some embodiments, remotely computing parameters as a function of past wireless connection information in the log comprises performing genetic programming operations to generate prediction programs for later prediction of wireless access points most likely to be available for reconnection at a desired time.

INTELLIGENT SERVER MIGRATION PLATFORM

Systems, methods and apparatus are provided for an intelligent server platform using genetic algorithms to execute a server migration based on fitness. The platform may locate hardware and software artifacts and map functional relationships between artifacts. Artifacts may be clustered based on interdependency to ensure that functionally related artifacts are migrated as a unit. The platform may apply a fitness protocol to generate a fitness score for each cluster and select clusters based on fitness score. The platform may apply a crossover protocol to optimize selected clusters for compliance with enterprise standards. The platform may iterate through the crossover protocol and modify a convergence goal based on populations of successive generations. The platform may rank artifacts and generate a protocol for migration. The platform may execute the migration in accordance with the migration protocol. 1. An intelligent server migration platform using genetic algorithms to execute an optimized migration of applications to a destination domain , the platform comprising: identify a first-generation population of hardware and software artifacts in the source domain; and', 'using a machine-learning algorithm, generate one or more clusters from the first-generation population, each cluster comprising a set of functionally related artifacts;, 'a population layer configured to apply a fitness function to the hardware and software artifacts in each cluster to generate a fitness score for the cluster;', 'select clusters having a fitness score above a predetermined threshold; and', 'generate a convergence goal for the migration based at least in part on the fitness scores of the selected clusters;, 'a fitness layer configured to validate each hardware and software artifact in a selected cluster against an enterprise standard; and', 'in response to validation of the software and hardware artifacts, cross over the selected cluster to a second-generation population;, 'a ...

A GENETIC METHOD FOR THE ACQUISITION AND TRACKING OF TIME VARYING SIGNALS

A coherent process for the acquiring and tracking of time varying signals includes receiving a time varying signal, sampling the received time varying signal, processing received data samples of the time varying signal using a global optimization method and processing received data samples of the time varying signal using a local optimization method. 1. A coherent process for the acquiring and tracking of time varying signals comprising:receiving a time varying signal;sampling the received time varying signal;processing received data samples of the time varying signal using a global optimization method; andprocessing received data samples of the time varying signal using a local optimization method.2. The method of claim 1 , wherein processing of the received data samples using the global optimization method and processing of the received data samples using the local optimization method occurs simultaneously.3. The method of claim 1 , wherein processing of the received data samples using the global optimization method comprises processing the received data samples using a genetic algorithm and processing of the received data samples using the local optimization method comprises processing the received data samples using an Amoeba algorithm.4. The method of claim 1 , wherein processing of the received data samples using the global optimization method comprises processing the received data samples using a simulated annealing algorithm and processing of the received data samples using the local optimization method comprises processing the received data samples using a Nelder-Mead method.5. The method of claim 1 , further comprising processing the received data samples using a Simplex algorithm.6. The method of claim 1 , further comprising processing the received data samples using a Complex algorithm.7. The method of claim 1 , wherein the time varying signal is transmitted using a multiple access technique claim 1 , wherein the multiple access technique comprises at ...

Method of generating features optimal to a dataset and classifier

A method of generating features optimal to a particular dataset and classifier is disclosed. A dataset of messages is inputted and a classifier is selected. An algebra of features is encoded. Computable features that are capable of describing the dataset from the algebra of features are selected. Irredundant features that are optimal for the classifier and the dataset are selected.

SYSTEM FOR COMPUTATIONAL RESOURCE PREDICTION AND SUBSEQUENT WORKLOAD PROVISIONING

The present disclosure describes a system, a method, and a product for computational resource prediction of user tasks and subsequent workload provisioning. The computational resource predictions for a user task is achieved using a twin machine learning and AI system based on probabilistic programing. The workload scheduling and assignment of the user task in a computing cluster with components having diverse hardware architectures are further managed by an automatic and intelligent assignment/provisioning engine based on various machine learning and AI models and reinforcement learning. The automatic workload scheduling and assignment engine is further configured to handle unpredicted uncertainty and adapt to constantly evolving system queues of the tasks submitted by the users to generate queuing/re-queuing, running/termination, and resource allocation/reallocation actions for user tasks. 1. A system comprising:a computer cluster including a set of computing platforms each corresponding to one of a plurality of different computing architectures; and receive input data, the input data comprising platform-independent task parameters and target metrics associated with a user task;', 'automatically generate a computing architecture and computing platform selection and computing resource prediction based on the input data and a hardware profile of the computer cluster using a computing resource prediction engine;', 'automatically map the user task to one or more of the set of computing platforms and to a scheduling action among a set of scheduling actions using a trained intelligent computing resource assignment engine;', 'automatically schedule the user task according to the scheduling action; and', 'automatically adjust the trained intelligent computing resource assignment engine by applying reinforcement learning based on newly acquired data associated with performing the scheduling action., 'an automatic and adaptive resource prediction and assignment circuitry for ...

GENERATIVE CONTENT SYSTEM AND METHODS THEREFOR

A generative content system is disclosed. According to implementations, the generative content system generates literal representations of an environment based on data collected from a plurality of data sources that are selected in correspondence of the environment. In embodiments, the literal representations are used to generate a 3D rendering of the environment. In some embodiments, the generative content is used to support a location-based service system that locates devices based on a literal representation of an area as represented by the signal strengths observed throughout the area. 1. A method comprising:receiving, by a processing system, a plurality of data instances from a plurality of data sources, the plurality of data sources having been selected in correspondence of an environment to be represented digitally;generating, by the processing system, a plurality of abstract instances based on the plurality of data instances, each abstract instance indicating a set of properties of one or more data instances to which the abstract instance corresponds, wherein the respective properties of each respective abstract instance include a data type of the data instance and one or more relationships between the abstract instance and other abstract instances;generating, by the processing system, an abstract representation corresponding to the environment based on the plurality of abstract instances, wherein generating the abstract representation includes generating a connection between a first abstract instance corresponding to a first data instance and a second abstract instance corresponding to a second data instance based on a relationship between the first data instance and the second data instance;analyzing, by the processing system, the abstract representation with respect to a fitness criteria to determine whether the abstract representation conforms to the fitness criteria;in response to determining that the abstract representation does not conform to the ...

Webinterface Presentation Using Artificial Neural Networks

Roughly described, the technology disclosed provides a so-called machine-learned conversion optimization (MLCO) system that uses artificial neural networks and evolutionary computations to efficiently identify most successful webpage designs in a search space without testing all possible webpage designs in the search space. The search space is defined based on webpage designs provided by marketers. Neural networks are represented as genomes. Neural networks map user attributes from live user traffic to different dimensions and dimension values of output funnels that are presented to the users in real time. The genomes are subjected to evolutionary operations like initialization, testing, competition, and procreation to identify parent genomes that perform well and offspring genomes that are likely to perform well. 1. A non-transitory computer readable storage medium impressed with computer program instructions to produce and deploy webinterfaces , the instructions , when executed on a processor , implement a method comprising:providing a presentation database which identifies a frontend element value for each of at least one available value of each dimension of a funnel of a webinterface;determining from a neural network funnel dimension values in dependence upon user attribute data;applying the determined funnel dimension values to the presentation database to determine frontend element values; andpresenting toward a user the funnel having the determined frontend element values.2. The non-transitory computer readable storage medium of claim 1 , wherein the webinterface represents a webpage.3. The non-transitory computer readable storage medium of claim 1 , wherein the webinterface represents a mobile application.4. The non-transitory computer readable storage medium of claim 1 , wherein the webinterface represents an e-mail.5. The non-transitory computer readable storage medium of claim 1 , wherein the webinterface represents a social media message.6. The non- ...

System and method for generating information for interaction with a user

A method for generating, by a first interactive electronic device of a first user, information for interaction with the first user includes: receiving, from a second interactive electronic device, information about an interaction between a second user and the second interactive electronic device; and generating interactive information to be provided to the first user, by applying the interactive information provided from the second interactive electronic device to a first AI learning model. At least a part of the method for generating interactive information may use a rule-based model, or an AI model trained according to at least one of a machine learning algorithm, a neural network algorithm, and a deep learning algorithm.

HOTSPOTS FOR PROBABILISTIC MODEL TESTING AND CYBER ANALYSIS

Techniques for identifying weaknesses in a probabilistic model such as an artificial neural network using an iterative process are disclosed. A seed file may be obtained and variant files generated therefrom. The variant files may be evaluated for their fitness, based upon the ability of the variant files to cause the probabilistic model to fail. The fittest variants, which may refer to those variants that are most successful in causing the model to fail, may be selected. From these selected variants, a next generation of variant files may be created. The next generation of variant files may be evaluated for their fitness. At each step of fitness evaluation or at the end of the iterative process, a map of the fittest variants may be generated to identify hotspots. These hotspots may reveal segments of code or a file that are problematic for the model, which can be used to improve the model. 1: A computer implemented method , comprising:determining a first fitness score for each of a population of electronic files generated from a seed file, the first fitness score being a difference between one and a probability, p, assigned by a probabilistic model to existence of a feature that does not exist in the electronic variant file;selecting a subset of the population of electronic files that have fitness scores that satisfy a predefined parameter, the selected subset constituting a first generation of variant electronic files;generating a second generation of variant electronic files for each first generation previously selected, each of the second generation of variant electronic files having at least one characteristic changed compared to the first generation of electronic files;determining second generation fitness scores for each member of the second generation, the second generation fitness scores being a difference between one and a probability, p, assigned by the probabilistic model to the existence of the feature that does not exist in a member of the second ...

ARCHITECTURE-INDEPENDENT APPROXIMATION DISCOVERY

Systems and methods for discovering approximations for compilers to apply through genetic programming and deterministic symbolic regression heuristics are provided. A method for discovering approximations for compilers and runtime optimization can include profiling a program to identify performance critical functions, determining appropriate candidates for approximation and developing application and architecture specific approximations through machine learning techniques, genetic programming, and deterministic heuristics. Such approximations can target any optimization goal, with a primary emphasis on parallelism, or can provide a set of Pareto-optimal tradeoffs. 1. A method for discovering and optimizing approximations , comprising:receiving an approximation candidate data structure, the approximation candidate data structure comprising a function identifier, a plurality of samples representative of a function associated with the function identifier, a global error probability metric, and an architecture identifier, wherein each sample comprises an input value and a corresponding output value;retrieving an architecture optimized fitness function based on the architecture identifier;determining, using one of a trained machine learning model or a machine learning algorithm, a plurality of approximation data structures, wherein each approximation data structure comprises an approximation function, an approximation function error, and an approximation function performance metric, wherein the plurality of approximation data structures is determined based at least on the plurality of samples representative of the function associated with the function identifier, the global error probability metric, and the architecture optimized fitness function;assigning a rank position to each approximation data structure of the plurality of approximation data structures, wherein the rank position is determined based on an approximation affinity generated using the global error ...

SYSTEM AND METHOD FOR ALLOCATING HUMAN RESOURCES BASED ON BIO INSPIRED MODELS

The present disclosure relates to system(s) and method(s) for allocating human resources based on bio inspired models. The system receives primary data associated with a product under development. The primary data may comprise a set of tasks associated with the product under development. Further, the system identifies a sub-set of human resources, from a set of human resources, maintained at a human resource database, based on a resource identification algorithm. Furthermore, the system extracts secondary human resource data associated with the sub-set of human resources from the human resource database. The system further allocates one or more human resources from the sub-set of human resources to each task from the set of tasks based on a resource allocation algorithm. The resource allocation algorithm is configured to analyse the secondary human resource data and the primary data to allocate the one or more human resources. 1. A method for allocating human resources based on bio inspired models , the method comprises steps of:receiving, by a processor, primary data associated with a product under development, wherein the primary data comprises a set of tasks associated with the product under development;identifying, by the processor, a sub-set of human resources from a set of human resources, maintained at a human resource database, based on a resource identification algorithm, wherein the resource identification algorithm is configured analyse the set of tasks in order to identify the sub-set of human resources;extracting, by the processor, secondary human resource data associated with each of the sub-set of human resources from the human resource database; andallocating, by the processor, one or more human resource from the sub-set of human resources to each task from the set of tasks based on a resource allocation algorithm, wherein the resource allocation algorithm is configured analyse secondary human resource data and the primary data for allocating one or ...

Information processing apparatus, information processing method, and computer-readable recording medium recording information processing program

An information processing apparatus includes: a memory; and a processor configured to: execute genetic processing on class classification programs of a set of class classification programs; acquire a distance between each learning data and an identification boundary regarding evaluation identifiers created by using first class learning data belonging to a first class and second class learning data belonging to a second class according to the class classification program; calculate a statistic amount of a distribution of a distance to the identification boundary for each of the first class learning data and the second class learning data; define a fitness calculation equation based on the statistic amounts of the first class learning data and the second class learning data; calculate the fitness of the class classification program; and determine whether or not to replace the class classification program with one of class classification programs of the set depending on the fitness.

NUCLEIC ACID MEMORY (NAM) / DIGITAL NUCLEIC ACID MEMORY (DNAM)

Compositions and methods for encoding and retrieving data into nucleic acid memory for storage. More specifically, data is encoded into spatial locations within a nucleic acid architecture, which allows the data to be retrieved using super resolution microscopy. The data is then interrogated for errors, the errors corrected, and the data is then decoded. 1. A nucleic acid memory architecture for data storage , comprising:a population of nucleic acid strands, wherein the population of nucleic acid strands comprises of data strands having an optional docking domain located at a data sites and structural strands and wherein the population of nucleic acid strands forms an indexed array when self-assembled.2. The nucleic acid memory architecture of claim 1 , wherein the architecture is an origami claim 1 , molecular canvas claim 1 , single stranded tiles claim 1 , or single stranded oligomer.3. The nucleic acid memory architecture of claim 2 , wherein the architecture is an origami.4. The nucleic acid memory architecture of claim 1 , further comprising an image strand claim 1 , wherein a dye is bound to the image strand.5. The nucleic acid memory architecture of claim 4 , wherein the image strand is bound to the optional docking domain.6. The nucleic acid memory architecture of claim 5 , wherein the data site is a data bit claim 5 , an index bit claim 5 , an orientation bit claim 5 , a parity bit claim 5 , a checksum bit claim 5 , and/or combinations thereof.7. The nucleic acid memory architecture of claim 5 , wherein the data site is represented by a (1) when the image strand is bound to the data strand.8. The nucleic acid memory architecture of claim 5 , wherein the data site is represented by a (0) when the data strand lacks the optional docking domain.9. The nucleic acid memory architecture of claim 2 , wherein the origami is a rectangular 2D nanostructure.10. The nucleic acid memory architecture of claim 1 , wherein the nucleic acid is DNA claim 1 , RNA claim 1 , ...

METHOD AND DEVICE FOR LEARNING A STRATEGY AND FOR IMPLEMENTING THE STRATEGY

A method for learning a strategy, which optimally adapts at least one parameter of an evolutionary algorithm. The method includes the following steps: initializing the strategy, which ascertains a parameterization of the parameter as a function of pieces of state information; learning the strategy with the aid of reinforcement learning, it being learned from interactions of the CMA-ES algorithm with a parameterization, determined with the aid of the strategy as a function of the pieces of state information, with the problem instance and with a reward signal, which parameterization is optimal for possible pieces of state information. 111-. (canceled)12. A computer-implemented method for learning a strategy , which optimally adapts at least one parameter of an evolutionary algorithm , the evolutionary algorithm being a Covariance Matrix Adaptation Evolution Strategy (CMA-ES) or differential evolution algorithm , the method comprising the following steps:initializing the strategy, which ascertains a parameterization of the parameter as a function of pieces of state information about a problem instance; andlearning the strategy using reinforcement learning, it being learned from interactions of the CMA-ES algorithm with a parameterization, determined using the strategy as a function of the pieces of state information, with the problem instance and with a reward signal, which parameterization is optimal for possible pieces of state information.13. The method as recited in claim 12 , wherein the parameter is a step size of the CMA-ES algorithm claim 12 , and/or a population size claim 12 , and/or a mutation rate claim 12 , and/or a crossover rate.14. The method as recited in claim 12 , wherein the pieces of state information include a present parameterization of the parameter and a cumulative path length claim 12 , and/or at least one value which is a difference between functional values of a function of the problem instance of a present iteration to be optimized and ...

Systems and Methods for Multi-Objective Evolutionary Algorithms with Category Discovery

Systems and methods are provided to engage in multi-tiered optimization where there may be a first multi-objective optimization and a second constraint optimization. The multi-objective optimization may be used to drive to one or more goals of the optimization problem. The constraint optimization or minimization may be used to drive towards a reduced and/or no constraint situation where the solution to the overall problem is feasible or near-feasible. 1. A method , comprising:identifying, by one or more processors, a plurality of items, including a first item and a second item;identifying, by the one or more processors, a plurality of categories, including a first category and a second category;providing, by the one or more processors, a first allocation of items by allocating the first item to the first category and the second item to the second category;identifying, by the one or more processors, one or more constraint models;determining, by the one or more processors and based at least in part on the one or more constraint models, that the first allocation of items is infeasible;providing, by the one or more processors, a second allocation of items by allocating the first item to a third category;determining, by the one or more processors and based at least in part on the one or more constraint models, that the second allocation is feasible; andproviding, by the one or more processors, the second allocation as a feasible solution to a multi-objective optimization problem.2. The method of claim 1 , further comprising:determining a first chromosome based at least in part on the second allocation;identifying at least one objective model;determining a set of objective values based at least in part on the at least one objective model and the first chromosome; andcomparing the set of respective objective values to one or more other sets of respective objective values to determine that the first chromosome is an optimized solution to the multi-objective optimization ...

Systems and Methods For Providing Data-Driven Evolution of Arbitrary Data Structures

A system and process for generalizing an evolutionary process applied to a particular domain involving different problems includes a researcher module for generating a configuration specification applicable to a particular problem. An evolution module parses the configuration specification into a representative tree structure, assembles policies for each node in the tree structure, and generates candidate genomes using the policies for each node in the tree structure. The policies may be applied to new data or data from prior runs to generate candidate genomes. The evolution module translates internal representations of the generated candidate genomes into known representations of the candidate genome for evaluation in accordance with the particular domain parameters by a candidate evaluation module.

ONLINE FRAUD PREVENTION USING GENETIC ALGORITHM SOLUTION

Online fraud prevention including receiving a rules set to detect fraud, mapping the rules set to a data set, mapping success data to members of the rules set, filtering the members of the rules set, and ordering members of the data set by giving priority to those members of the data set with a greater probability for being fraudulent based upon the success data of each member of the rule set in detecting fraud. Further, a receiver coupled to an application server to receive a rules set to detect fraud, and a server coupled to the application server, to map the rules set to a data set, and to map the success data to each members of the rules set. The server is used to order the various members of the data set by giving priority to those members of the data set with a greatest probability for being fraudulent. 1. (canceled)2. A system , comprising:one or more processors; anda non-transitory computer-readable medium having stored thereon instructions that are executable by the one or more processors to cause the system to perform operations comprising:generating a first plurality of transaction risk evaluation rules based on feature data corresponding to a first set of electronic transactions initiated by a plurality of different users, and wherein each of the first plurality of transaction risk evaluation rules has a corresponding feature evaluation set that utilizes one or more respective features from the feature data;determining initial evaluation results based on applying the first plurality of transaction risk evaluation rules to an evaluation set of electronic transactions; and selecting first and second transaction risk evaluation rules of the first plurality of transaction risk evaluation rules;', 'creating a genetically modified new transaction risk evaluation rule based on at least a first evaluation feature from a feature evaluation set for the first transaction risk evaluation rule and at least a second evaluation feature from a feature evaluation set for ...

Centralized framework for small batch manufacturing

Today, product developers with customized small batch production needs come across the problem of finding capable and flexible manufacturers, while manufacturers face underutilization due to inconsistent demand. In this disclosure, a digital manufacturing framework is presented to address the challenge of matching the underutilized manufacturers with the new product developers. This disclosure presents a Production as a Service (PaaS) framework to connect users (consumers or product developers) who have customized small batch manufacturing needs, with manufacturers that have existing underutilized resources. PaaS is a cloud-based, centralized framework based on a service oriented architecture (SOA) that abstracts the manufacturing steps of a product as individual (production) service requests. PaaS creates a market place for small-to-mid sized manufacturing industry by coordinating multiple manufacturers to provide the requested services. Using PaaS, the user is able to reach many capable manufacturers at once, and receive quotations for the production request. On the other end, PaaS reduces the effort required to find new customers and enables manufacturers to easily submit quotations to increase the utilization of their resources. 1. A computer-implemented method for selecting a manufacturing solution for manufacturing a product for a customer , where the manufacturing solution is comprised of two or more manufacturing processes , comprising:receiving a set of quotes for manufacturing the product, where each quote identifies a manufacturer providing the given quote, provides a listing of manufacturing processes in the given quote, a cost of the given quote, and a processing time for the given quote;receiving a set of precedence for the manufacturing processes which comprise the manufacturing solution;generating a set of candidate solutions from the set of quotes, where each candidate solution accounts for the set of precedence and is comprised of one or more ...

REAL TIME ENSEMBLE SCORING OPTIMIZATION

Methods, computer program products, and systems are presented. The methods include, for instance: obtaining a request for a predicted ensemble score in real-time. A subset of base model instances is formed by use of a preconfigured priority policy. A fitness score of the formed subset, quantifying the accuracy of the subset, is calculated as a sum of weights respective to the base model instances in the subset. A number of base models represented in the subset is less than or equal to a number of all based models. 1. A computer implemented method for optimizing real-time ensemble scoring , comprising:obtaining, by one or more processor, a request for a predicted score in real-time;forming, by the one or more processor, a subset of two or more base model instances in order of rank for a preconfigured priority policy, wherein a number of base models represented in the subset is less than or equal to a number of the two or more based models; andcalculating, by the one or more processor, a fitness score of the formed subset as a sum of weights respective to the base model instances in the subset, wherein the fitness score quantifies the accuracy of the formed subset.2. The computer implemented method of claim 1 , further comprising:determining that the calculated fitness score satisfies an end condition;predicting an ensemble score by use of the subset corresponding to the fitness score, wherein the ensemble score is a sum of scores for all base model instances in the subset;ascertaining that the ensemble score satisfies the end condition; andproducing the ensemble score as the predicted score.3. The computer implemented method of claim 2 , further comprising:preparing, prior to the forming, a score log entry to record the subset from the forming, scores respective to the base model instances of the subset, and an ensemble score of the subset; andrecording, subsequent to predicting, the subset, the scores respective to the base model instances of the subset, and the ...

Fertilization precision control method for water and fertilizer integrated equipment and control system thereof

The present invention relates to a fertilization precision control method for water and fertilizer integrated equipment and a control system thereof. The method comprises the following steps: step S1, establishing a fertilization precision control model of the water and fertilizer integrated equipment; and step S2, solving an optimal solution of the fertilization precision control model by adopting estimation of distribution algorithms.

CASH LEVEL OPTIMIZATION WITH AUTOCALIBRATION

The disclosure concerns a computer-implemented method of optimizing the cash level of a cash device (), wherein the cash level indicates an amount of currency in at least one cash box of the cash device (), wherein the method comprises the following steps: iteratively optimizing, in an automated manner, a calibration () of the cash device (), wherein the calibration () comprises a plurality of parameters; and generating a plan () based at least in part on the calibration (), wherein the plan () indicates when and/or how the cash device () is to be serviced. 1. A system for optimizing efficiency of cash flow , comprising:at least one computing device comprising at least one storage device, at least one memory device, at least one network connection, and at least one user interface device;at least one network connected computing device comprising at least one network connected storage device, at least one network connected memory device, at least one network connected network connection;wherein the at least one computing device and the at least one network connected computing device are connected via a computer network;at least one cash point device connected to the computer network, and the at least one cash point device configured to provide at least one current cash levels, and at least one set of historical data to the at least one network connected computing device;wherein the at least one network connected computing device aggregates the at least current cash levels and the at least one set of historical data, and creates a set of aggregated current status indicators and a set of aggregated historical data;wherein the at least one computing device can access the aggregated current cash levels, the set of aggregated historical data, and the at least one computing device is configured to utilize a forecaster engine;an autocalibrator engine andan evaluator engine to evaluate the quality of a calibration data set;wherein the forecaster engine analyzes the aggregated ...

METHOD AND SYSTEM FOR PLANNING ITEM DELIVERIES

A method of or for routing delivery items to delivery locations using transport devices includes localizing the plurality of delivery items, determining the delivery locations for the plurality of delivery items and executing a genetic algorithm for outputting a routing plan. The genetic algorithm can be an adapted genetic routing algorithm. The routing system can comprise a computing system that can be configured to execute at least one genetic algorithm for at least one of: assigning the transport devices to the delivery items, assigning the transport devices to times of delivery, and routing the transport devices to the delivery locations. The controlling system can be configured to control the transport devices according to the output of the computing system. 120-. (canceled)21. A method for routing a plurality of delivery items to a plurality of delivery locations by a plurality of transport devices , the method comprising:(A) localizing the plurality of delivery items;(B) determining the delivery locations for the plurality of delivery items; and (i) assigning the transport devices to the delivery items; and/or', '(ii) assigning the transport devices to times of delivery; and/or', '(iii) routing the transport devices to the delivery locations., '(C) a data processing device executing a genetic algorithm for outputting a routing plan comprising at least one of22. The method of claim 21 , wherein the determining in (B) further comprises determining a respective time of delivery or a respective time window of delivery for at least one of the plurality of delivery items.23. The method of claim 21 , further comprising providing different kinds of transport devices claim 21 , the difference concerning at least one of:(i) sizes of the transport devices; and/or(ii) a number of delivery items the transport devices transport; and/or(iii) a size of delivery items the transport devices transport; and/or(iv) a way of travel the transport devices are configured to use.24. ...

SOLVING VEHICLE ROUTING PROBLEMS USING EVOLUTIONARY COMPUTING TECHNIQUES

According to one exemplary embodiment, a method for solving combinatorial optimization problems is provided. The method may include receiving a plurality of problem instance parameters associated with a graph. The method may also include determining a dynamic path change indicator exists. The method may then include initializing the graph based on the determining the dynamic path change indicator does not exist. The method may further include inserting a placeholder node and at least one placeholder node edge based on the determining the dynamic path change indicator exists. The method may also include reinitializing the graph with the inserted place holder node and the at least one placeholder node edge. The method may then include initializing the reinitialized graph. The method may further include executing a hybrid algorithm on the initialized graph or on the reinitialized graph, wherein the hybrid algorithm comprises an ant colony optimization algorithm and a genetic algorithm. 1one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:receiving a plurality of problem instance parameters associated with a graph, wherein the graph comprises a plurality of nodes and a plurality of edges, wherein each edge of the plurality of edges links two nodes of the plurality of nodes, and wherein at least one node of the plurality of nodes in the graph has an associated capacity requirement value;determining when a dynamic path change indicator exists;initializing the graph based on the determining the dynamic path change indicator does not exist;inserting a placeholder node and at least one placeholder node edge based on determining the dynamic path ...

CALCULATING A SOLUTION FOR AN OBJECTIVE FUNCTION BASED ON TWO OBJECTIVE FUNCTIONS

Provided is an apparatus including a processor and one or more computer readable mediums collectively including instructions that, when executed by the processor, cause the processor to: acquire a candidate for a solution of an optimization problem for optimizing a third objective function based on a first objective function and a second objective function; obtain, as another candidate for the solution of the optimization problem, a solution that optimizes the second objective function under a constraint corresponding to a value of the first objective function for the acquired candidate; and select the solution of the optimization problem from among the plurality of candidates for the solution of the optimization problem. Also provided as the first aspect are a method and non-transitory computer readable storage medium. 1. An apparatus comprising:a processor; and acquire a candidate for a solution of an optimization problem for optimizing a third objective function based on a first objective function and a second objective function;', 'obtain, as another candidate for the solution of the optimization problem, a solution that optimizes the second objective function under a constraint corresponding to a value of the first objective function for the acquired candidate; and', 'select the solution of the optimization problem from among the plurality of candidates for the solution of the optimization problem., 'one or more computer readable mediums collectively including instructions that, when executed by the processor, cause the processor to2. The apparatus according to claim 1 , wherein the second objective function has an objective function value based on a sum of objective function values for partial problems of the optimization problem.3. The apparatus according to claim 2 , wherein the first objective function has an objective function value based on a largest value or a smallest value of the objective function values for the plurality of partial problems obtained ...

Peak shaving control method for emergent source-grid coordination in case of faulty sending-end power grid

A peak shaving control method for emergent source-grid coordination in case of a faulty sending-end power grid. The method includes: S1: evaluating dispatchability of a cluster virtual wind power unit; S2: developing a method for calculating a dispatchability index of the cluster virtual wind power unit; S3: analyzing a source-load peak-shaving resource strategy; and S4: distributing a control strategy for tie-line peak shaving. The present disclosure has the following beneficial effects: In the present disclosure, real-time dispatchability of wind power participating in real-time power balance is first analyzed, specific evaluation indexes and calculation methods are provided, and calculation examples are given for verification. Then, an optimized real-time dispatch strategy is provided based on demand-side response resources, and DC and AC tie-lines are coordinated for operation. The peak shaving control method for emergent source-grid coordination when a sending-end power grid is faulty can ensure normal operation.

System and method for increasing data quality in a machine learning process

A method and system for increasing data quality of a dataset for semi-supervised machine learning analysis. The method includes: receiving known class label information for a portion of the data in the dataset; receiving clustering parameters from a user; determining a data cleanliness factor, and where the data cleanliness factor is below a predetermined cleanliness threshold: assigning data without class label information as a data point to a cluster using the clustering parameters, each cluster having a cluster class label associated with such cluster; and determining a measure of assignment, and where the measure of assignment for each data point is below a predetermined assignment threshold, receiving a class label for such data points, otherwise, assigning the respective cluster class label to each data point with the respective measure of assignment below the predetermined assignment threshold; and otherwise, outputting the dataset with associated class labels for machine learning analysis.

Topic Model Based Media Program Genome Generation For A Video Delivery System

In one embodiment, the method incorporates a first set of words that belong to a topic in a set of topics that correspond to a set of genomes in a model, the words being incorporated in the model via a first item in the model. Then, the method incorporates a relationship between a second set of words that are associated with topics in the set of topics via a second item in the model. The model is trained with respect to the first item and the second item to determine a probability distribution of terms for the set of topics based on analyzing textual information for a plurality of media programs. The method further scores terms for each of the plurality of media programs based on the trained model to rank topics that correspond to genomes, the genomes describing characteristics for each media program. 1. A method comprising:incorporating, by a computing device, a first set of words that belong to a topic in a set of topics that correspond to a set of genomes in a model, the words being incorporated in the model via a first item in the model;incorporating, by the computing device, a relationship between a second set of words that are associated with topics in the set of topics via a second item in the model;training, by the computing device, the model with respect to the first item and the second item to determine a probability distribution of terms for the set of topics based on analyzing textual information for a plurality of media programs; andscoring, by the computing device, terms for each of the plurality of media programs based on the trained model to rank topics that correspond to genomes, the genomes describing characteristics for each media program.2. The method of claim 1 , further comprising incorporating claim 1 , by the computing device claim 1 , a parameter that prevents topics from being submerged by other topics that are larger via a third item in the model.3. The method of claim 1 , wherein incorporating claim 1 , by the computing device claim 1 , ...

COMPACT AND LOW LOSS Y-JUNCTION FOR SUBMICRON SILICON WAVEGUIDE

A compact, low-loss and wavelength insensitive Y-junction for submicron silicon waveguides. The design was performed using FDTD and particle swarm optimization (PSO). The device was fabricated in a 248 nm CMOS line. Measured average insertion loss is 0.28±0.02 dB across an 8-inch wafer. The device footprint is less than 1.2 μm×2 μm, orders of magnitude smaller than MMI and directional couplers. 18-. (canceled)9. An optical splitter device comprising:at least one input port for inputting an optical signal in a propagation direction;a plurality of output ports for outputting a plurality of portions of the optical signal;a tapered section between the at least one input port and the plurality of output ports;wherein the tapered section increases in width from the at least one input port to a maximum width, and decreases in width from the maximum width towards the plurality of output ports, whereby the maximum width is greater than the width proximate the plurality of output ports.10. The device according to claim 9 , wherein each input port and each output port has a width of 0.5 μm.11. The device according to claim 10 , further comprising a gap between each output ports; wherein the gap has a width of 0.2 μm.12. The device according to claim 10 , wherein the maximum width is less than 1.4 μm.13. The device according to claim 12 , wherein a total length of the tapered section is less than 2 μm.14. The device according to claim 9 , wherein the tapered section is symmetrical in the propagation direction to ensure balanced output at the plurality of output ports.15. The device according to claim 9 , wherein the tapered section comprises silicon with a silicon oxide cladding.16. The device according to claim 9 , wherein the width of the tapered section proximate the half way point comprises the same maximum width.17. A method of fabricating an optical splitter comprising:providing a substrate with a device layer thereon; at least one input port for inputting an optical ...

INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND RECORDING MEDIUM

A model with few false reports and little missing detection is generated even if the number of models is large. A system analysis device includes a feature acquisition unit and a selection unit . The feature acquisition unit acquires a feature of a first data item. The selection unit selects a model for learning a relationship between the first data item and a second data item, based on the feature. 1. An information processing device comprising:a memory storing instructions; andone or more processors configured to execute the instructions to: acquire a feature of a first data item; andselect a model for learning a relationship between the first data item and a second data item, based on the feature.2. The information processing device according to claim 1 , wherein claim 1 ,as the feature of the first data item, a first fitness score that is a fitness score of the first data item for an autoregressive process is acquired, andwhether an autoregressive process of the first data item is to be included into the model or not is selected, based on the first fitness score.3. The information processing device according to claim 2 , whereinthe one or more processors configured to further execute the instructions to:learn a relationship between the first data item and the second data item by using the selected model; anddetect an abnormality in the first data item or the second data item by using the model used for learning the relationship.4. The information processing device according to claim 3 , whereinthe one or more processors configured to further execute the instructions to:calculate a second fitness score that is a fitness score of the model used for learning the relationship for the relationship, and extract a model for detecting the abnormality from the model used for learning the relationship, based on the second fitness score.5. The information processing device according to claim 4 , wherein claim 4 ,when the first fitness score is equal to or more than a first ...

FLEXIBLE JOB-SHOP SCHEDULING METHOD BASED ON LIMITED STABLE MATCHING STRATEGY

The present invention provides a flexible job-shop scheduling method based on a limited stable matching strategy, and belongs to the field of job-shop scheduling. The method adopts the following design solution: a. generating an initial chromosome population through integer coding and initializing relevant parameters; b. conducting crossover and mutation operations on parent chromosomes to obtain progeny chromosomes; c. combining the progeny chromosomes and the parent chromosomes into a set of to-be-selected chromosomes, and selecting a next generation of chromosomes from the set through limited stable matching operation; and d. stopping the algorithm if meeting cut-off conditions; otherwise turning to step b. The present invention introduces a limited stable matching strategy into the selection process of the progeny chromosomes to solve a multi-target flexible job-shop scheduling problem, so as to overcome the defects of insufficient population distribution and insufficient convergence in the existing method for solving the multi-target flexible job-shop scheduling problem when solving such problem, thereby obtaining excellent scheduling solution with good timeliness and high reliability. 1. A flexible job-shop scheduling method based on a limited stable matching strategy , comprising the following steps:(a) initializing related parameters: obtaining an initial chromosome population meeting constraint conditions through integer coding according to specific contents of a production order; determining a neighborhood of each subproblem; and calculating a fitness value;(b) selecting a parent chromosome from the neighborhood of each subproblem; generating progeny chromosomes through simulated binary crossover and polynomial mutation; and calculating a fitness value;(c) selecting progeny populations:{'sub': 1', '2', '2N', '1', '2', '2N', '1', 't', 'N', '1', 't', 'N, '(c1) combining a set of generated progeny chromosomes and a set of original parent chromosomes into a ...

PACKAGE METHOD OF RADIOACTIVE DISMANTLED PARTS

A packaging methodology for radioactive dismantled parts of nuclear facilities is provided. This methodology integrates voxelization and metaheuristic to discretize the irregular 3D shape of various dismantled parts and put them into the containers with greatest efficiency. To enumerate the possible locations and orientations of an irregular part effectively, the solid models of the dismantled parts are descripted to user-specified voxelization operations. Therefore, discretized parts and container yield a finite space of optimal solutions and make the evolution algorithm viable for optimization quest. This methodology improves the package efficiency of the radioactive dismantled parts to reduce the required quantity of the storage containers. 1. A method of packaging radioactive dismantled parts , comprising:flipping each dismantled part according to coordinates of the dismantled parts and a packaging condition to produce a bounding body for each dismantled part;proceeding with voxelization of each bounding body and proceeding discretization of each bounding body into a plurality of cubes, and proceeding with a Boolean algebra process on each cube and the dismantled parts respectively corresponding to each cube such that each cube is divided into a plurality of first cubes and a plurality of second cubes;proceeding with an analysis of the plurality of first cubes and the plurality of second cubes of each bounding body along an analysis axis such that each of the first cubes and the second cubes has a voxel-line-bunch on each analysis position;combining each voxel-line-bunch of each bounding body as a voxel model such that each dismantled part respectively corresponds to the voxel model to which each dismantled part belongs, wherein each voxel model has the position coordinates and the orientation codes;coding each dismantled part such that each dismantled part has a permutation number, and deciding a number of packaging boxes according to the permutation number, ...

DEVICE AND METHOD FOR OPTIMISING MODEL PERFORMANCE

A device for optimising model performance comprising: a memory resource storing a local model on an electronic device, the local model being obtained by the use of a machine learning process; a first processor configured to: obtain data at the electronic device; apply the local model to the data or further data derived from the data to obtain at least one local model result; generate a measure of the quality of the local model result, and send the data, further data derived from the data and/or the local model result through a communication device to a second processor for use in updating a global model based on the measure of the quality of the local model result. 1. A device for optimising model performance comprising:a memory resource storing a local model on an electronic device, the local model being obtained by the use of a machine learning process;a first processor configured to:obtain data at the electronic device;apply the local model to the data or further data derived from the data to obtain at least one local model result;generate a measure of the quality of the local model result, andsend the data, further data derived from the data and/or the local model result through a communication device to a second processor for use in updating a global model based on the measure of the quality of the local model result.2. The device according to claim 1 , wherein the second processor is configured to activate an update of the global model based on the measure of the quality of the local model result to obtain the updated global model.3. The device according to claim 1 , wherein the second processor is linked by a network to a plurality of electronic devices claim 1 , the second processor being configured to send updated global model data to at least one of the electronic devices and update the local model on the respective electronic devices based on the updated global model data.4. The device according to claim 1 , wherein the second processor is configured to ...

GENE EXPRESSION PROGRAMMING

Gene expression programming-based behavior monitoring is disclosed. A machine receives, as input, a plurality of data examples. A method can include receiving data indicating behaviors of the device, determining, using a gene expression programming (GEP) method, a data model that explains the data, and comparing further data indicating further behavior of the device to the data model to determine whether the further behavior is explained by the data model. 1. A technique for behavior monitoring of a device , the technique comprising:receiving data indicating behaviors of the device;determining, using a gene expression programming (GEP) method, a data model that explains the data; andcomparing further data indicating further behavior of the device to the data model to determine whether the further behavior is explained by the data model.2. The technique of claim 1 , wherein the GEP method includes determining whether to perform an alteration of an individual of a population based on a first seed value claim 1 , a second seed value claim 1 , a first function claim 1 , and a second different function.3. The technique of claim 2 , wherein the second function is orthogonal to the first function.4. The technique of claim 3 , wherein the first and second functions are cyclic.5. The technique of claim 4 , wherein the first and second functions are periodic.6. The technique of claim 5 , wherein:the first seed value is used as input to the first function to generate a first intermediate value;the second seed value is used as input to the second function to generate a second intermediate value;the first and second intermediate values are mathematically combined to generate a result; andthe determination of whether to alter the individual includes comparing the result to a threshold value and performing the alteration in response to determining the result is greater than the threshold value.7. The technique of claim 6 , wherein the first seed value is raised to a power before ...

Methods and apparatus for interactive evolutionary algorithms with respondent directed breeding

A method comprises displaying visual representations of a plurality of product alternatives each including at least one attribute variant to a respondent, receiving from the respondent an indication of a preferred one of the plurality of product alternatives, transmitting a request to the respondent to identify at least one attribute variant of a non-preferred product alternative that is preferred by the respondent to the corresponding attribute variant of the preferred one of the plurality of product alternatives and receiving a response from the respondent identifying at least one attribute variant of a non-preferred product alternative that is preferred by the respondent to the corresponding attribute variant of the preferred one of the plurality of product alternatives.

SYSTEM AND METHOD FOR PROPAGATING INFORMATION USING MODIFIED NUCLEIC ACIDS

Improvement is effected for a nucleic acid-based molecular computing system that is comprised of (i) a nucleic acid structure, (ii) at least one polynucleotide displacement molecule that can bind with the nucleic acid structure under hybridizing conditions, and (iii) a clashing polynucleotide molecule that competes with the polynucleotide displacement molecule for binding the nucleic acid structure under the hybridizing conditions. The method for such improvement entails incorporating chemical modification that inhibits the binding of the clashing molecule and the nucleic acid structure or facilitating the binding of the displacement molecule and the nucleic structure. 110-. (canceled)11. The system of claim 22 , wherein the input strand claim 22 , the target duplex claim 22 , and the clashing duplex form part of an enzyme-free claim 22 , nucleic acid logic gate selected from the group consisting of an AND gate claim 22 , a NOT gate claim 22 , an OR gate claim 22 , a NAND gate claim 22 , a NOR gate claim 22 , an XOR gate claim 22 , and an XNOR gate.12. (canceled)13. The system of claim 22 , wherein the first or the second chemical modification is selected from the group consisting of (i) replacing the sugar-phosphodiester backbone of said nucleosides with a pseudo-peptide backbone claim 22 , (ii) modifying the sugar moiety of said nucleosides claim 22 , and (iii) substituting an analogue for the nitrogenous base of at least one of said nucleosides.14. The system of claim 13 , wherein the first or the second chemical modification comprises replacing the sugar-phosphodiester backbone of said nucleosides with a pseudo-peptide backbone into which a guanidinium functional group is incorporated.15. The system of claim 14 , wherein the first or the second chemical modification comprises substituting a tricyclic cytosine analogue for the nitrogenous base of at least one of said nucleosides.16. The system of claim 14 , wherein the first or the second chemical modification ...

TRANSPORTATION SYSTEM AND METHOD FOR ALLOCATING FREQUENCIES OF TRANSIT SERVICES THEREIN

A method of dynamically allocating frequency settings of a transit service includes utilizing AVL/APC to determine travel time and demand variations within a day. Clusters of time periods are formed based thereon and the day is split up. For each of the time periods for which a new frequency setting will be allocated, frequency allocation ranges are computed within which waiting times at multi-modal transfer stops are reduced and a frequency allocation is selected using criteria including passenger demand coverage and operational costs reduction. A plurality of frequency setting solutions are computed using a Branch and Bound approach with Sequential Quadratic Programming (SQP) or a sequential genetic algorithm with exterior point penalization. Sensitivity of the frequency setting solutions is tested to determine a most operationally reliable frequency setting solution for the new frequency setting and a timetable of the transit service is updated accordingly. 1. A method of dynamically allocating frequency settings of a transit service , the method comprising:utilizing Automatic Vehicle Location (AVL) and Automated Passenger Counting (APC) data so as to determine travel time and demand variations within a day;forming clusters of time periods within the day based on the determined travel time and demand variations and splitting the day into the time periods;computing, for each of the time periods for which a new frequency setting will be allocated, frequency allocation ranges within which waiting times at multi-modal transfer stops are reduced and selecting a frequency allocation using criteria including at least a passenger demand coverage and an operational costs reduction;computing a plurality of frequency setting solutions using a Branch and Bound approach with Sequential Quadratic Programming (SQP) or a sequential genetic algorithm with exterior point penalization;testing sensitivity of the frequency setting solutions against different travel time and demand ...

METHOD AND APPARATUS FOR INTERACTIVE EVOLUTIONARY ALGORITHMS WITH RESPONDENT DIRECTED BREEDING

A method comprises displaying visual representations of a plurality of product alternatives each including at least one attribute variant to a respondent, receiving from the respondent an indication of a preferred one of the plurality of product alternatives, transmitting a request to the respondent to identify at least one attribute variant of a non-preferred product alternative that is preferred by the respondent to the corresponding attribute variant of the preferred one of the plurality of product alternatives and receiving a response from the respondent identifying at least one attribute variant of a non-preferred product alternative that is preferred by the respondent to the corresponding attribute variant of the preferred one of the plurality of product alternatives. 1. A method for optimizing generation of a product alternative to be presented via a presentation device , the method comprising:identifying, by executing an instruction with the processor, a first attribute of a product alternative as associated with one of a first performance level indicative of an affirmative user response to the first attribute or a second performance level indicative of a negative user response to the first attribute, the identifying based on one or more user inputs received in response to presentation of the product alternative;in response to identifying the first attribute as associated with the first performance level, reducing a number of user inputs processed by the processor indicative of a preferred attribute by identifying, by executing an instruction with the processor, a first product alternative based on the first attribute;in response to identifying the first attribute as associated with the second performance level, reducing a number of user inputs processed by the processor indicative of a non-preferred attribute by identifying, by executing an instruction with the processor, a second product alternative, the second product alternative to include a second ...

System and Method For Generating Parametric Activation Functions

The embodiments describe a technique for customizing activation functions automatically, resulting in reliable improvements in performance of deep learning networks. Evolutionary search is used to discover the general form of the function, and gradient descent to optimize its parameters for different parts of the network and over the learning process. The new approach discovers new parametric activation functions which improve performance over previous activation functions by utilizing a flexible search space that can represent activation functions in an arbitrary computation graph. In this manner, the activation functions are customized to both time and space for a given neural network architecture.

GENETIC MODELING FOR ATTRIBUTE SELECTION WITHIN A CLUSTER

Genetic modeling is used to generate new term sets from existing term sets within a population cluster. Term attributes corresponding to a first plurality of term sets are encoded as genes for a computer-executed genetic algorithm. Clients are clustered in categories based on client attributes. The genetics algorithm is applied to a category of clustered clients to distribute the term sets to clients in the category. A first subset of terms sets is removed after receiving, within a first duration of time, a number of client responses that falls below a first threshold. A second subset of term sets is retained after receiving, within a second duration of time, a number of client responses above a second threshold. The second subset is bred using the genetic algorithm and a second plurality of term sets is generated based on the results. 1. A computer-implemented method of automatically generating new term sets from existing term sets , the method comprising:providing a first plurality of term sets, each term set within the first plurality of term sets having a corresponding set of term attributes;encoding each term attribute among the set of term attributes as a gene for a computer-executed genetic algorithm;clustering clients into categories based on client attributes, wherein the client attributes correspond to attributes of clients to whom the term sets are to be transmitted;applying the computer-executed genetics algorithm to a category of clustered clients to distribute each of the first plurality of term sets to respective clients in the category of clustered clients;removing a first subset of terms sets from among the first plurality of term sets for the category of clustered clients after a first duration of time, the removing responsive to receiving a number of client responses to the term sets below a first threshold;retaining a second subset of term sets as successful term sets for the category of clustered clients from among the first plurality of term ...

METHOD, SYSTEM, AND COMPUTER PROGRAM PRODUCT FOR CONTROLLING GENETIC LEARNING FOR PREDICTIVE MODELS USING PREDEFINED STRATEGIES

Methods for controlling genetic learning for predictive models using predefined strategies may include, for each of a plurality of agents, selecting a type of predictive model. A strategy may be selected from predefined strategies. Candidate genomes may be generated and may include a plurality of genes. Each gene may be associated with a feature of the agent predictive model. A fit of each candidate genome to the agent strategy may be determined. A candidate genome may be selected based on the fit. For each of a plurality of epochs, a plurality of training iterations may be performed for each agent. A fitness of each agent predictive model may be determined. A subset of agents with a highest fitness may be determined. For each agent of the subset, at least one new agent may be generated. The genomes of the new agents may be merged with some genomes of the subset. 1. A method for controlling genetic learning for predictive models using predefined strategies , comprising: selecting, with at least one processor, a type of predictive model from a plurality of types of predictive models as an agent predictive model;', 'selecting, with at least one processor, a strategy from a plurality of predefined strategies as an agent strategy;', 'generating, with at least one processor, a plurality of candidate genomes, each candidate genome comprising a plurality of genes, each gene associated with a respective feature of the agent predictive model;', 'determining, with at least one processor, a fit of each candidate genome of the plurality of candidate genomes to the agent strategy; and', 'selecting, with at least one processor, a candidate genome from the plurality of candidate genomes as the agent genome based on the fit of the candidate genome;, 'for each agent of a plurality of agents [ performing, with at least one processor, a plurality of training iterations based on the agent predictive model and the agent genome; and', 'determining, with at least one processor, a fitness ...

Evolved inferential sensors for improved fault detection and isolation

A built-in fault-detection-and-isolation (FDI) test for a system that has measurable input operating conditions and output parameters is designed. Inferential sensors, which are functional combinations of the input operating conditions and the output parameters, are evolved using genetic programming so as to be rich in information pertaining to fault conditions of the system. Simulations, based on a system model, of various combinations of the input operating conditions and the fault conditions are performed so as to provide simulated values of the inferential sensors and the output parameters. Sensitivities of the inferential sensors and the output parameters to the fault conditions and to system uncertainties are calculated. The inferential sensors are repeatedly evolved until a termination condition is achieved. The built-in test is designed based on a combination of a selected input operating condition and one or more of the inferential sensors and/or the output parameters.

Training and Control System for Evolving Solutions to Data-Intensive Problems Using Epigenetic Enabled Individuals

Roughly described, a computer-implemented evolutionary system evolves candidate solutions to provided problems. It includes a memory storing a candidate gene database containing active and epigenetic individuals; a gene pool processor which tests only active individuals on training data and updates their fitness estimates; a competition module which selects active individuals for discarding in dependence upon both their updated fitness estimate and their testing experience level; and a gene harvesting module providing for deployment selected ones of the individuals from the gene pool. The gene database has an experience layered elitist pool, and individuals compete only with other individuals in their same layer. Certain individuals are made epigenetic in the procreation module, after which they are not subjected to testing and competition. Epigenetic individuals are retained in the candidate gene pool regardless of their fitness. An epigenetic individual can become an active individual by random chance in procreation. 1. A computer-implemented system for evolving solutions to a provided problem , for use with a training database containing training data samples for an environment of the problem , comprising:a memory storing a database having a candidate pool comprising a set of candidate individuals to solve the problem, each candidate individual identifying a plurality of conditions and at least one corresponding consequence to be asserted in dependence upon the conditions, each candidate individual further having associated therewith an indication of a respective fitness estimate indicating a level of success in solving the problem, and an epigenetic indication indicating epigenetic status of at least part of the candidate individual; and tests individuals from the candidate pool on the training data, each individual being tested undergoing a respective battery of at least one trial, each trial applying the conditions of the respective individual to the training ...

GLOBAL OPTIMAL PARTICLE FILTERING METHOD AND GLOBAL OPTIMAL PARTICLE FILTER

The invention relates to a global optimal particle filtering method and a global optimal particle filter. The problem of particle filter processing nonlinear and non-Gaussian signals is effectively solved. The main technical means is to use the Lamarck genetic natural law to construct a global optimal particle filter comprising: generating an initial particle set; using Unscented Kalman Filter to perform importance sampling on the initial particle set to obtain sampled particles; performing floating-point number encoding for each of the sampled particles to obtain an encoded particle set; setting an initial population; using the initial population as an original trial population to sequentially perform a Lamarck overwriting operation, a real number decoding operation, and an elite retention operation; using the real-number optimal candidate particle as a prediction sample for a next moment, and obtaining a state estimation value of a system. The invention is applicable to machine learning. 1. A global optimal particle filtering method , the method comprises steps of:step 1: generating an initial particle set;step 2: using an Unscented Kalman Filter to perform an importance sampling on the initial particle set to obtain sampled particles;step 3: performing a floating-point number encoding for each of the sampled particles to obtain an encoded particle set;step 4: setting an initial population according to the encoded particle set;step 5: using the initial population as an original trial population to sequentially perform a Lamarck overwriting operation, a real number decoding operation, and an elite retention operation; wherein the Lamarck overwriting operation refers to, according to a ratio between fitnesses of two parent candidate particles, passing a code of the parent with a higher fitness directly to an offspring of the parent with a lower fitness, replacing corresponding bits of its floating-point number, and retaining a parent particle with the higher fitness ...

FPGA-BASED RESEQUENCING ANALYSIS METHOD AND DEVICE

Proposed by the present disclosure are an FPGA-based resequencing analysis method and device, wherein the method comprises: receiving genomic resequencing data; using the resequencing data as an input of an FPGA, determining a comparison result in the resequencing process according to an output of the FPGA, and simultaneously performing sorting and deduplication processing on the comparison result: correcting a base quality value of the comparison result after sorting and deduplication processing; and detecting a mutation result according to the corrected comparison result. The described method may save program running time, save calculation costs, and improve resequencing efficiency. 1. A Field-Programmable Gate Array (FPGA)-based resequencing analysis method , comprising:receiving genome resequencing data;taking the genome resequencing data as an input of an FPGA, determining an alignment result in a process of resequencing based on an output of the FPGA, and at the same time, sorting and deduplicating the alignment result;subjecting a sorted and deduplicated alignment result to correction in accordance with a base quality value; anddetecting a variation result based on a corrected alignment result.2. The FPGA-based resequencing analysis method of claim 1 , wherein subsequent to receiving genome resequencing data claim 1 , the method further comprises:subjecting the genome resequencing data to hash-calculation based on a sequence of a preset length,taking the genome resequencing data as an input of an FPGA further comprisingtaking hash-calculated genome resequencing data as the input of the FPGA.3. The FPGA-based resequencing analysis method of claim 1 , wherein the genome resequencing data comprises basic genome resequencing data and parameter information describing the basic genome resequencing data claim 1 ,wherein subsequent to receiving genome resequencing data, the method further comprises:determining a first task for outputting the alignment result and a ...

Guiding metaheuristic to search for best of worst

Figures of merit by actual design parameters are tracked over iterations for candidate solutions that include both actual design parameters and actual context parameters. Instead of returning a current iteration figure of merit, a worst observed figure of merit for a set of actual design parameters is returned as the figure of merit for a candidate solution. Since the candidate solution includes both actual design parameters and actual context parameters and the worst observed figures of merit are tracked by actual design parameters, the figure of merit for a set of design parameters wilt be the worst of the observed worst case scenarios as defined by the actual context parameters over a run of a metaheuristic optimizer.

Methods of diagnosing disease using microflow cytometry

Disclosed are methods of diagnosing disease, such as clinically significant prostate cancer, in a patient. Also disclosed are methods for identifying a disease signature. The methods involve microflow (μFCM) cytometry to identify particle phenotypes and then using machine learning to determine whether the patient has the disease of interest or the particle phenotypes of a particle disease. The μFCM analysis workflow disclosed herein helps identify the most clinically useful information within μFCM data which may be overlooked by conventional gating analysis.

DIFFERENTIAL DYNAMIC HOST CONFIGURATION PROTOCOL LEASE ALLOCATION

Disclosed is a novel passive fingerprinting technique based on DHCP messages to determine the device type and operating system. DHCP implementations are shown to vary among device types and have an effect on DHCP lease durations. To improve network address utilization, without introducing any protocol changes, the present invention provides a new leasing strategy which takes into account device types. This strategy, compared to current approaches, improves the address utilization sixfold without considerably increasing DHCP overhead. 1. A method to set lease times values in a network protocol for a device , the method comprising:inspecting, at a host system, a network request packet generated by a client system;classifying the client system into a category from a plurality of categories based on the network request packet; andusing the category to associate a value of a lease time for the client system.2. The method of claim 1 , wherein the using the category to associate a value of a lease time for the client system includes receiving input from a user to the host system to associate the value of the lease time.3. The method of claim 1 , wherein the using the category to associate a value of a lease time for the client system includes automatically associating the value of the lease by historical data of request messages with a machine learning algorithm.4. The method of claim 3 , wherein the classifying the client system into a category from a plurality of categories based on the network request packet includes classifying with an algorithm for learning association rules.5. The method of claim 1 , wherein the using the category to associate a value of a lease time for the client system includes receiving input from a user to the host system to associate the value of the lease time and automatically associating the value of the lease by historical data of request messages with a learning algorithm.6. The method of claim 3 , wherein the automatically associating the ...

Optimizing the startup speed of a modular system using machine learning

Systems and methods use machine learning to find an efficient startup sequence for the components of an application. An example method includes receiving the plurality of components of the modular system and a mechanism for launching the modular system and invoking a machine-learning ordering tool to generate at least one startup sequence. The at least one startup sequence may be returned with corresponding launch metrics. The method may also include determining, based on launch metrics for the at least one startup sequence, whether an efficient sequence has been identified. Responsive to the efficient sequence being identified, the operations can include returning the efficient startup sequence, wherein the modular system is launched using the efficient startup sequence. Responsive to failing to identify the efficient sequence, the operations can include repeating the invoking and determining.

Monte carlo markov chain based quantum program optimization

From a quantum program a first mutant is generated using a processor and a memory, where the first mutant is a randomly-generated transformation of the quantum program. A quality score, a correctness distance, and a probability of acceptance corresponding to the first mutant are computed. An acceptance corresponding to the first mutant is determined according to the probability of acceptance. Upon determining that an acceptance of the first mutant corresponding to the probability of acceptance exceeds an acceptance threshold, the quantum program is replaced with the first mutant. Upon determining that the quality score exceeds a storage threshold and that the correctness distance is zero, the first mutant is stored. These actions are iterated until reaching an iteration limit.

OPTIMIZATION DEVICE AND CONTROL METHOD OF OPTIMIZATION DEVICE

An optimization device includes: a plurality of search parts; and a controller that controls the plurality of search parts, wherein, each of the plurality of search parts includes a state holding part configured to hold each of values of a plurality of state variables included in an evaluation function representing an energy value, an energy calculation part configured to calculate a change value of the energy value generated in a case where any one of the values of the plurality of state variables is changed, and a transition controller configured to stochastically determine whether or not to accept a state transition by a relative relation between the change value of the energy value and thermal excitation energy, based on a set temperature value, the change value, and a random number value. 1. An optimization device comprising:a plurality of search parts; anda controller that controls the plurality of search parts, a state holding part configured to hold each of values of a plurality of state variables included in an evaluation function representing an energy value,', 'an energy calculation part configured to calculate a change value of the energy value generated in a case where any one of the values of the plurality of state variables is changed, and', 'a transition controller configured to stochastically determine whether or not to accept a state transition by a relative relation between the change value of the energy value and thermal excitation energy, based on a set temperature value, the change value, and a random number value,, 'wherein, each of the plurality of search parts includes'} a temperature adjustment part configured to determine an update maximum temperature value based on information obtained by a ground state search in the plurality of search parts,', 'a selection part configured to divide the plurality of search parts into a plurality of groups including at least a first group and a second group, based on the determined update maximum ...

SYSTEM AND METHOD FOR PERFORMING FAST COMPUTATIONS USING QUANTUM COUNTING AND PSEUDO-RANDOM SETS

A method is provided for solving a computational problem that is reducible to a problem of counting solutions to an associated decision problem. The method includes, using a quantum computer, estimating a number of the solutions to the decision problem by determining if there is at least one solution to the decision problem that lies in a pseudo-random set. The method also includes outputting or using the estimated number of the solutions to the decision problem as a solution to the computational problem. Determining if there is at least one solution to the decision problem that lies in the pseudo-random set could include determining if there is a sequence of solutions to the decision problem that, taken together, lies in the pseudo-random set.

AUTOMATIC TASK DISTRIBUTION AND OPTIMIZATION USING MACHINE LEARNING AND ARTIFICIAL INTELLIGENCE

Task/resources are randomly assigned a number of times and a score for each solution of the random assignment is calculated. Using machine learning and artificial intelligence, a subset of the solutions is selected. Assignment of task/resource within the subset may be randomly changed, e.g., a task/resource assignment between two entities, a task/resource within the selected subset may be replaced with another task/resource (without swapping), etc. The additional solutions form a super solution with the selected subset and the score associated with the additional solutions are calculated. The process of selection of assignments, random changes to the assignment and calculating the scores associated with the new solutions is repeated a number of times until a certain condition is met, e.g., a number of iterations, time out, improvement between two iterations is less than a certain threshold, etc. Once the certain condition is satisfied, a solution is selected. 1. A computing device comprising:one or more processors;a non-transitory computer-readable medium storing machine learning algorithm instructions that, when executed by one or more processors of the computing device, cause the computing device to perform operations comprising:randomly assigning a plurality of hardware/software resources to a plurality of requesters of hardware/software resources to form a hardware/software resources assignment;determining a score associated with the hardware/software resources assignment, wherein the score is indicative of fitness of the assignment;repeating the random assignment of the plurality of hardware/software resources and the determining the score a number of times to form a set of solutions;selecting a subset of the set of solutions to form a subset solutions wherein the selecting is based on an unsupervised machine learning of the scores of the plurality of hardware/software resources assignments over the number of times;creating additional solutions by changing ...

APPARATUS AND METHOD FOR EXTRACTING NICKNAME LIST OF IDENTICAL USER IN ONLINE COMMUNITY

A method of extracting nicknames of identical user by an apparatus operated by at least one processor, the method includes receiving a posting uploaded to an online community from a server; extracting at least one feature information for identifying a posting writer who writes the posting, from the posting; and extracting nicknames of identical user with the posing writer, from a plurality of nicknames, based on similarity of the feature information with a predetermined reference or greater. 1. A method of extracting nicknames of identical user by an apparatus operated by at least one processor , the method comprising:receiving a posting uploaded to an online community from a server;extracting at least one feature information for identifying a posting writer who writes the posting, from the posting; andextracting nicknames of identical user with the posing writer, from a plurality of nicknames, based on similarity of the feature information with a predetermined reference or greater.2. The method of claim 1 , further comprising:selecting a candidate nickname group by excluding nicknames that are determined not to be the identical user from the plurality of nicknames,wherein the extracting the nicknames includesextracting the nicknames of the identical user from the candidate nickname group.3. The method of claim 2 , whereinnicknames with overlapping used time periods are determined not to be the identical user from the plurality of nicknames.4. The method of claim 1 , whereinthe extracting the feature information includesextracting at least one kind of feature information among word related feature information for identifying interest information of the posting writer, activity time related feature information of the posting writer, posting related feature information, and communication relationship related feature information between the posting writer and another user.5. The method of claim 4 , whereinthe word related feature information includesat least one ...

ARTIFICIAL INTELLIGENCE FOR CONTEXT CLASSIFIER

An artificial intelligence system comprises a computer network server connected to receive and analyze millions of simultaneous text and/or voice messages written by humans to be read and understood by humans. Key, or otherwise important words in sentences are recognized and arrayed. Each such word is contributed to a qualia generator that spawns the word into its possible contexts, themes, or other reasonable ambiguities that can exist at the level of sentences, paragraphs, and missives. A thesaurus-like table is employed to expand each word into a spread of discrete definitions. Several such spreads are used as templates on the others to find petals that exhibit a convergence of meaning. Once the context of a whole missive has been predicted, each paragraph is deconstructed into sub-contexts that are appropriate within the overall theme. Particular contexts identified are then useful to trigger an actionable output. 1. A message context classifier for sorting out messages that match predefined fields-of-interest , comprising:means for receiving streams of electronic messages having as yet undetermined contents, contexts, and sentiments communicated between senders and recipients;means for separating said streams of electronic messages into individual messages and missives from identifiable senders to identifiable recipients;means for deconstructing each said message and missive into its constituent words;means for disambiguating said constituent words by finding commonalities between them that exist for particular and predefined subject categories and fields-of-interest;means for estimating a most probable subject category and field-of-interest for an instant message and missive;means for evaluating a particular sentiment conveyed by the sender in said instant message and missive as confined to an estimate of a most probable subject category and field-of-interest;means for classifying said instant missive as warranting the attention of a user according to a match ...

PROGRAM GENERATION APPARATUS AND PROGRAM GENERATION METHOD

Each time evolution processing is performed, an information recording unit records increase-decrease information indicating a type of partial program changed in number between pre- and post-evolution individuals and difference between fitness levels calculated from the pre- and post-evolution individuals in a storage unit. A probability setting unit determines, per partial program, a contribution level indicating how much a partial program contributes to increasing a fitness level, based on the information stored in the storage unit within a predetermined period and sets a selection probability per partial program in such a manner that a partial program having a higher contribution level is given a higher selection probability. When the evolution processing is performed, a generation processing unit selects a partial program to be included in the post-evolution individual in mutation processing according to the set selection probabilities. 1. A program generation apparatus comprising:a memory; anda processor configured to perform a procedure including:generating an image processing program by determining, based on genetic programming, a combination of partial programs to be included in the image processing program from a plurality of partial programs, the generating including evolution processing for evolving an individual formed by a combination of partial programs selected from the plurality of partial programs;recording, in the memory, information indicating a type of partial program that has been changed in number between pre- and post-evolution individuals and indicating difference between fitness levels calculated based on the pre- and post-evolution individuals, respectively, each time the evolution processing is performed; anddetermining, for each of the plurality of partial programs, a contribution level indicating how much an individual partial program contributes to increasing a fitness level, based on information accumulated in the memory within a ...

Simulate segmentation method of cylinder and pie cake digital models

A simulate segmentation method of cylinder and pie cake digital models utilizes a three-dimensional model and a reference point to cope with various shapes of the nuclear reactor structures. The segmentation simulation of the nuclear reactor structure is conducted with genetic algorithm. The segmentation simulation of the nuclear reactor structure is achieved by using the genetic algorithm to perform a double selection mechanism on the cross-sectional area of the nuclear reactor structure to select the optimal configuration of the segmentation, thus minimizing the cross-sectional areas of the nuclear reactor structure. The cutter segments the nuclear reactor structure based on the optimal configuration of the segmentation, thereby achieving the purpose of minimizing the attrition rate of a cutter and segmenting the nuclear reactor structure.

METHOD FOR ARRAY ELEMENTS ARRANGEMENT OF L-SHAPED ARRAY ANTENNA BASED ON INHERITANCE OF ACQUIRED CHARACTER

A method for array elements arrangement of an L-shaped array antenna based on inheritance of acquired character. The method relates to the field of array elements design for L-shaped array antenna. In order to solve the problem that the arrangement of the current L-shaped array antenna system has a weak local ability, the invention firstly encodes for the J_K array, then calculates a fitness of each chromosome in the population, randomly selects two parent chromosomes according to a overwriting probability of inheritance of acquired character, calculates a percentage of gene delivery, performs a overwriting operation to generate a new population, repeats the overwriting operation to generate the final new population; calculates the fitness of each chromosome in the population, repeats the iteration until a predetermined termination condition is met, and obtains the optimal population gene; then determines the array elements arrangement of the L-shaped array antenna according to the optimal population gene. 2. The method for the array elements arrangement of the L-shaped array antenna based on the inheritance of the acquired character according to claim 1 , wherein the process of performing the mutation operation in step 4 is performed by using a uniform mutation method claim 1 , and a mutation probability is p; then generating the new population Gafter one optimization operation.3. The method for the array elements arrangement of the L-shaped array antenna based on the inheritance of the acquired character according to claim 2 , wherein the adjustment process in one adjustment of the initial population performed in step 2 is as follows:firstly, converting each generation of J+K binary strings into decimal digits, a value of the decimal digits converted by the binary strings correspondingly representing the array element spacing between the array element and the previous array element, i.e., obtaining the array element spacing D after the binary strings are restored; ...

METHOD FOR SEARCHING EXCITATION SIGNAL OF MOTOR, AND ELECTRONIC DEVICE

A method for searching an excitation signal for a motor and an electronic device. The method includes: randomly generating M excitation signals for the motor, and determining whether the M excitation signals allow vibration sense obtained after the motor is driven to be expected vibration sense; if yes, outputting this excitation signal as an optimal excitation signal; if no, calculating the M excitation signals according to a preset genetic algorithm to obtain a new generation of M excitation signals, and then determining whether the new generation of M excitation signals allow vibration sense obtained after the motor is driven to be the expected vibration sense, until the optimal excitation signal is obtained. In the present disclosure, the optimal excitation signal for obtaining the expected vibration sense after the motor is driven can be quickly found, and thus an efficiency thereof is high. 1. A method for searching an excitation signal for a motor , comprising:step A of randomly generating M excitation signals for the motor, wherein M is a positive integer;step B of determining whether the M excitation signals satisfy a preset condition, wherein the preset condition is satisfied when any one of the M excitation signals allows a vibration sense obtained after the motor is driven by the one excitation signal to he an expected vibration sense; performing step C if the M excitation signals satisfy the preset condition, or performing step D if the M excitation signals do not satisfy the preset condition;step C of outputting an optimal excitation signal of the M excitation signals as an excitation signal output as a result of the searching, wherein the optimal excitation signal is the excitation signal that allows the vibration sense obtained after the motor is driven by the excitation signal to be the expected vibration sense;step D of calculating the M excitation signals according to a preset genetic algorithm to obtain a new generation of M excitation signals; ...

QUERY-BASED MOLECULE OPTIMIZATION AND APPLICATIONS TO FUNCTIONAL MOLECULE DISCOVERY

A query-based generic end-to-end molecular optimization (“QMO”) system framework, method and computer program product for optimizing molecules, such as for accelerating drug discovery. The QMO framework decouples representation learning and guided search and applies to any plug-in encoder-decoder with continuous latent representations. QMO framework directly incorporates evaluations based on chemical modeling, analysis packages, and pre-trained machine-learned prediction models for efficient molecule optimization using a query-based guided search method based on zeroth order optimization. The QMO features efficient guided search with molecular property evaluations and constraints obtained using the predictive models and chemical modeling and analysis packages. QMO tasks include optimizing drug-likeness and penalized log P scores with similarity constraints and improving the target binding affinity of existing drugs to pathogens such as the SARS-CoV-2 main protease protein while preserving the desired drug properties. QMO tasks further improves optimizing antimicrobial peptides toward lower toxicity. 1. A query-based molecule optimization method comprising:modifying, by the at least one hardware processor, a sequence structure corresponding to a molecule to be optimized;running, by the at least one hardware processor, a plurality of machine learned prediction models for said modified sequence structure for predicting a respective plurality of properties of a molecule corresponding to said modified sequence structure and generating loss values as a measure of differences between respective plurality of property predictors and a corresponding respective plurality of specified threshold constraints, and using the generated loss values as a guide for further modifying said sequence structure for evaluation of the respective plurality of predicted properties; anddetermining by the at least one hardware processor whether said each of the plurality of properties predicted ...

Artificial Intelligence Guided Research and Development

Recommendations for new experiments are generated via a pipeline that includes a predictive model and a preference procedure. In one example, a definition of a development task includes experiment parameters that may be varied, the outcomes of interest and the desired goals or specifications. Existing experimental data is used by machine learning algorithms to train a predictive model. The software system generates candidate experiments and uses the trained predictive model to predict the outcomes of the candidate experiments based on their parameters. A merit function (referred to as a preference function) is calculated for the candidate experiments. The preference function is a function of the experiment parameters and/or the predicted outcomes. It may also be a function of features that are derived from these quantities. The candidate experiments are ranked based on the preference function. 1. A method implemented on a computer system comprising a processor , the processor executing instructions to effect a method for recommending candidate experiments , the method comprisingtraining a predictive model that predicts outcomes of experiments, wherein the training is based on known outcomes of previous experiments characterized by known parameters;generating a number of candidate experiments;using the predictive model to predict outcomes of the candidate experiments based on parameters of the candidate experiments; andrecommending from among the candidate experiments based at least in part on the predicted outcomes.2. The method of further comprising:running at least one of the recommended experiments; andfurther training the predictive model based on the outcomes of the recommended experiments.3. The method of wherein recommending from among the candidate experiments comprises:calculating values of a preference function for the candidate experiments, wherein the preference function is a function of a derived feature that is derived from the parameters and/or ...

Method and System for Finding a Solution to a Provided Problem Using Family Tree Based Priors in Bayesian Calculations in Evolution Based Optimization

A method for finding a best solution to a problem is provided. The method includes evolving candidate individuals in a candidate pool by testing each candidate individual of the candidate individuals to obtain test results, assigning a performance measure to each of the tested candidate individuals in dependence upon the test results, discarding candidate individuals from the candidate pool in dependence upon their assigned performance measure, and adding, to the candidate pool, a new candidate individual procreated from parent candidate individuals remaining in the candidate pool, and repeating the evolution steps to evolve the candidate individuals in the candidate pool. The method further includes selecting, as a winning candidate individual, a candidate individual from the candidate pool having a best probability to beat a predetermined score, the probability to beat the predetermined score being determined in dependence upon a Bayesian posterior probability distribution of a particular candidate individual.

Resource needs prediction in virtualized systems: generic proactive and self-adaptive solution

A method for real-time prediction of resource consumption by a system is provided that includes determining a real-time prediction of resource demand by the system. A Genetic Algorithm (GA) is used to dynamically determine an optimal size of a sliding window and an optimal number of predicted data within the real-time prediction of the resource demand. The data within the real-time prediction of the resource demand is adjusted based on an estimated probability of prediction errors and a variable padding, which is based on a mean of at least one previous standard deviation of the predicted data within the real-time prediction of the resource demand.

OPTIMIZATION OF PREDICTOR VARIABLES

A method and apparatus for optimization of predictor variables. The apparatus includes a value obtaining section to obtain a plurality of answers from an answer database, each answer including an answered value for each variable of a plurality of variables, the plurality of variables answered by each respondent of a plurality of respondents, a cost obtaining section to obtain a cost for answering each of the plurality of variables from a cost database, and a determining section to determine at least one predictor variable from the plurality of variables based on a prediction performance and an answering cost, the at least one predictor variable for predicting at least one remaining variable of the plurality of variables. 1. An apparatus for optimization of predictor variables , comprising:a value obtaining section to obtain a plurality of answers from an answer database, wherein each answer includes an answered value for each variable of a plurality of variables, the plurality of variables answered by each respondent of a plurality of respondents;a cost obtaining section to obtain a cost for answering each of the plurality of variables from a cost database; anda determining section to determine, using a processor, at least one predictor variable from the plurality of variables based on a prediction performance and an answering cost, the at least one predictor variable for predicting at least one remaining variable of the plurality of variables.2. The apparatus of claim 1 , wherein the determining section includes:a generating section to generate a prediction model for predicting a value of at least one remaining variable candidate based on a given value of at least one predictor variable candidate;an evaluating section to evaluate the at least one predictor variable candidate using an objective function, the objective function being a function of the prediction performance and the answering cost, wherein the prediction performance is derived from the prediction ...

OPTIMIZATION METHOD FOR INDEPENDENT MICRO-GRID SYSTEM

The present application discloses a method for optimized design of an independent micro-grid system, the independent micro-grid system comprising diesel generators, wind powered generators, a photovoltaic array, and an energy storage battery, the optimization method referring specifically to a multi-objective optimization design model based on the independent micro-grid system. In terms of the optimization planning design model, the method takes into account a combined start-up mode for a plurality of diesel generators and a control strategy for coordinating between the energy storage battery and the diesel generators, such that the usage rate of renewable energy in the independent micro-grid is higher, and operations more economical and environmentally friendly. Regarding the stability of the system optimization planning design model, the method takes into account the reserve capacity needed for stability of the independent micro-grid. In terms of the solving algorithm of the optimization planning design model, the method employs a multi-objective genetic algorithm based on NSGA-II to implement multi-objective problem-solving, thereby allowing a multi-objective optimization of the three major objectives of economy, reliability, and environmental friendliness of an independent micro-grid system. 14-. (canceled)5. A method for optimizing an independent micro-grid system , wherein the independent micro-grid system comprises at least diesel generators , wind generators , a photovoltaic array and an energy storage battery , and the method comprises:obtaining device parameters of the diesel generators, the wind generators, the photovoltaic array and the energy storage battery; andperforming genetic algorithm solving and optimization by adopting a multi-objective genetic algorithm based on the device parameters of the diesel generators, the wind generators, the photovoltaic array and the energy storage battery, wherein a quasi-steady state simulation strategy is adopted ...

TRANSACTION EXECUTION METHOD AND SYSTEM

A system for making a remittance between persons and making payments offline, and for securely being able to conduct these transactions is disclosed. A participant terminal stores verified TX information to which is added a verified TX object, which represents a transaction (TX) and has been verified by a verifier. Each participant terminal stores unverified TX information to which is added an unverified TX object, which represents a TX and has not been verified by a verifier. When a TX arises between a first participant and a second participant, the first participant terminal and the second participant terminal mutually retain the same unverified TX object group including the unverified TX object of that TX. When the first participant terminal is online, verification of the unverified TX object is requested, and, when the verification is successful, that object is added to the verified TX information as a verified TX object. 1. A transaction execution system comprising a plurality of transaction execution units respectively equipped in a plurality of participant terminals , wherein:the plurality of participant terminals are a plurality of information processing terminals of a plurality of participants,at least one participant terminal among the plurality of participant terminals stores verified transaction information to which is added a verified transaction object, which represents a transaction and is an object that has been verified by a verifier,each of the plurality of participant terminals stores unverified transaction information to which is added an unverified transaction object, which represents a transaction and is an object that has not yet been verified by a verifier, receives, from a second transaction execution unit as a transaction execution unit in the second participant terminal, an unverified transaction object group as one or more unverified transaction objects included in the unverified transaction information in the second participant terminal ...

METHOD FOR SETTING PARAMETERS IN AN AUTONOMOUS WORKING DEVICE AND AN AUTONOMOUS WORKING DEVICE

A system and method are provided for setting parameters in an autonomous working device. The autonomous working device can be controlled based on a plurality of parameters. For each of a plurality of different working environments a set of sensor values is generated. The plurality of sets is partitioned into categories, each category corresponding to a prototypical working environment. The parameters for each category are optimized to find an optimized parameter set for each prototypical working environment. For an individual working environment, an individual set of sensor values that the sensors of the autonomous working device produce is generated. Based at least on the individual set of sensor values, the prototypical working environment showing highest similarity to the individual environment is determined, and the parameters in the autonomous working device are set according to the optimized parameter set corresponding to the determined prototypical working environment. 1. A method for setting parameters in an autonomous working device , the autonomous working device being controlled based on a plurality of parameters , the method comprising:generating for each of a plurality of different working environments a set of sensor values that sensors of the autonomous working device produce while being operated in the respective working environment;partitioning the plurality of sets of sensor values into categories, each category corresponding to a prototypical working environment;optimizing the parameters for each category to find an optimized parameter set for each prototypical working environment;generating for an individual working environment in which operation of the autonomous working device shall be performed an individual set of sensor values that the sensors of the autonomous working device produce while being operated in this individual working environment;determining, based at least on the individual set of sensor values, the prototypical working ...

Techniques for automatically generating designs having characteristic topologies for urban design projects

An urban design pipeline automatically generates design options for an urban design project. The urban design pipeline includes a geometry engine and an evaluation engine. The geometry engine analyzes design criteria, design objectives, and design heuristics associated with the urban design project and then generates numerous candidate designs. The design criteria specify a property boundary associated with a region of land to be developed. The design objectives indicate a specific type of topology that is derived from an existing urban layout. The design heuristics include different sets of construction rules for generating designs with specific types of topologies. The geometry engine generates candidate designs that conform to the property boundary and have topological characteristics in common with the existing urban layout.

ESTIMATING LATENT REWARD FUNCTIONS FROM EXPERIENCES

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for estimating latent reward functions from a set of experiences each experience specifying a respective sequence of state transitions of an environment being interacted with by an agent that is controlled using a respective latent policy. In one aspect, a method includes: generating a current Markov Decision Process (MDP); initializing a current assignment which assigns the set of experiences into a first number of partitions that are each associated with a respective latent reward function; updating the current assignment, including, for each experience: selecting a partition from a second number of candidate partitions; and assigning the experience to the selected partition; and updating the latent reward functions in accordance with a specified update rule; and updating the current MDP using latent features associated with particular latent reward functions that are determined to have highest posterior probability. 1. A method of estimating latent reward functions from a set of experiences , wherein each experience specifies a respective sequence of state transitions of an environment being interacted with by an agent that is controlled using a respective latent policy , and wherein each latent reward function specifies a corresponding reward to be received by the agent by performing a respective action at each state of the environment , the method comprising:{'claim-text': ['(i) generating a current Markov Decision Process (MDP) for use in characterizing agent interactions with the environment;', '(ii) initializing a current assignment which assigns the set of experiences into a first number of partitions that are each associated with a respective latent reward function;', {'claim-text': [{'claim-text': ['selecting a partition from a second number of candidate partitions by prioritizing for selection candidate partitions to which no experience is currently ...

Partitioning Using a Correlation Meta-Heuristic

A method for partitioning for a hypergraph including a plurality of nodes into a plurality of bins includes assigning each node of the hypergraph to one of the plurality of bins to generate a candidate solution, and for each pair of nodes in the candidate solution, calculating a weighted covariance based on the bin assignment of each node of the pairs of nodes in the candidate solution. The assigning and the calculating are repeated to generate an accumulated weighted covariance for the pairs of nodes, from which a seed partition of the hypergraph is generated. 1. A method for partitioning for a hypergraph including a plurality of nodes into a plurality of bins , comprising:assigning each node of the hypergraph to one of a plurality of bins to generate a candidate solution;for each pair of nodes in the candidate solution, calculating a weighted covariance based on the bin assignment of each node of the pairs of nodes in said candidate solution;repeating the assigning and the calculating a plurality of times, and generating an accumulated weighted covariance for the pairs of nodes; andgenerating a seed partition of said hypergraph using the accumulated weighted covariance.2. The method of claim 1 , further comprising:accumulating a weighted assignment value for each node; andgenerating the seed partition of said hypergraph using the accumulated weighted assignment value and the accumulated weighted covariance.3. The method of claim 1 , further comprising:utilizing a cost function to generate weights for the weighted covariance.4. The method of claim 1 , further comprising:utilizing a local search heuristic to transform one or more seed partitions into a candidate solution, to iterate the method.5. The method of claim 4 , wherein the seed partition in a final iteration is utilized for a coarse partitioning of a circuit description into a field programmable gate array (FPGA).6. The method of claim 1 , wherein generating the seed partition comprises:generating a weight ...

Geographic location based feed

Technologies for implementing geographic location based news feeds. A server computer indexes web content transmitted from a first client computer. And, the server computer, in response to receiving a search query from a second client computer, generates geographically filtered search results based on the search query from the second client computer and a geographic location tag of the search query. The geographically filtered search results can include parts of the web content transmitted from a first client computer corresponding to the search query and the geographic location tag of the search query. The server computer also transmits the geographically filtered search results to the second client computer to be displayed by the second client computer.

MODEL GENERATING METHOD AND MODEL GENERATING APPARATUS

A model generating method performed by a computer is provided. First, multiple models are generated by repeatedly executing genetic programming that receives a training data set as an input, and for each of the multiple models, a fitness value that represents a degree of conformity between a corresponding model of the multiple models and the training data set is generated. Next, an indicator is calculated for each of the multiple models, and the multiple models are classified into clusters, by using the indicator calculated for each of the multiple models. Next, a cluster to which the largest number of the models belong is selected from the clusters. Finally, from among models belonging to the selected cluster, a model with the greatest fitness value is selected. 1. A method performed by a computer , the method comprising:generating a plurality of models by repeatedly executing genetic programming that receives a training data set as an input;generating, for each of the plurality of models, a fitness value that represents a degree of conformity between a corresponding model of the plurality of models and the training data set;calculating an indicator for each of the plurality of models;classifying the plurality of models into a plurality of clusters, by using the indicator calculated for each of the plurality of models;selecting, from the clusters, a cluster to which a largest number of the models belong; andselecting, from models belonging to the selected cluster, a model with a greatest fitness value.2. The method according to claim 1 , whereinthe indicator represents magnitude of variation in output data with respect to variation in input data of a corresponding model; andthe indicator is expressed by a scalar quantity or a vector.3. The method according to claim 1 , whereinin the classifying of the plurality of models, the plurality of models are classified into the plurality of clusters so as to maximize a distance between the plurality of clusters, by using a ...

METHOD AND APPARATUS FOR DETERMINING A SET OF OPTIMAL COEFFICIENTS

The disclosed systems, structures, and methods are directed to a method for determining a set of N optimal coefficients to be supplied to an equalizer, the equalizer being employed in at least one of a serializer and a deserializer, the method comprising: receiving N different parameters, searching an initial set of N coefficients on an N-dimensional performance surface, in accordance with a genetic algorithm, wherein the N-dimensional performance surface corresponds to various coefficients in the N parameters, and fine tuning the initial set of N coefficients to provide the set of N optimal coefficients, in accordance with a gradient descent algorithm. 1. A method for determining a set of N optimal coefficients to be supplied to an equalizer , the equalizer being employed in at least one of a serializer and a deserializer , the method comprising:receiving N different operational parameters, each operational parameter including a plurality of coefficients; randomly selecting k sets of coefficients from the N operational parameters;', {'sub': '1', 'selecting first top sets sof coefficients from N operational parameters, in accordance with a cost function;'}, {'sub': 2', '1, 'evolving second sets sof coefficients in accordance with the first top sets sof coefficients;'}, {'sub': 3', '3', '2, 'randomly selecting other sets of coefficients in a controlled random manner and providing third sets sof coefficients, wherein the third sets sof coefficients includes the first set of coefficients Si and the second set of coefficients sand the other sets of coefficients;'}, {'sub': '4', 'randomly selecting fourth m sets sof coefficients from the N operational parameters; and'}, {'sub': 3', '4, 'providing the initial set of N coefficients in accordance with the third sets sof coefficients and the fourth sets sof coefficients; and'}], 'searching an initial set of N coefficients on an N-dimensional performance surface, in accordance with a genetic algorithm, wherein the N- ...

SYSTEM AND METHOD FOR AUTOMATIC LEARNING OF FUNCTIONS

A method and system learn functions to be associated with data fields of forms to be incorporated into an electronic document preparation system. The functions are essentially sets of operations required to calculate the data field. The method and system receive form data related to a data field that expects data values resulting from performing specific operations. The method and system utilize machine learning and training set data to generate, test, and evaluate candidate functions to determine acceptable functions. 1. A method performed by one or more processors of a system , the method comprising:receiving form data having a first data field for which a function needs to be determined;receiving training set data including a plurality of data values relating to the first data field;generating, for the first data field, two or more distinct candidate functions using a machine learning process based on genetic programming, wherein each of the two or more distinct candidate functions has one or more operators;generating, for each of the two or more distinct candidate functions, test data by applying the respective distinct candidate function to at least a portion of the training set data;generating matching data indicating how closely the test data matches at least a portion of the training set data; and splitting a first candidate function and a second candidate function into at least first and second component pieces using the machine learning process, wherein each component piece includes one or more operators of the corresponding original candidate function;', 'forming a new candidate function using the machine learning process by assembling at least the first component piece from the first candidate function with at least a portion of the second candidate function;', 'iterating between at least the splitting and assembling operations until test data of at least one of the new candidate functions matches the training set data within a predefined margin of error ...

MULTI-OBJECTIVE RECOMMENDATIONS IN A DATA ANALYTICS SYSTEM

A method to provide multi-objective recommendations. The method includes receiving user input indicating a plurality of objectives, where each of the plurality of objectives indicates a desired goal for a field of interest, receiving user input indicating a plurality of actionable fields, receiving user input indicating selection of one of a plurality of records in a data set, determining, based on applying an evolutionary algorithm, one or more candidate changes to values of the plurality of actionable fields of the selected record, determining, for each of the one or more candidate changes, a multi-objective score for that candidate change, selecting one or more of the one or more candidate changes to recommend to a user based on the multi-objective scores of the one or more candidate changes, and providing, for display to the user, the selected one or more candidate changes as recommended changes. 1. A method by one or more computing devices for providing multi-objective recommendations in a data analytics system , the method comprising:storing a data set including a plurality of records, wherein each of the plurality of records includes a plurality of fields;receiving user input indicating a plurality of objectives, wherein each of the plurality of objectives indicates a desired goal for a field of interest;receiving user input indicating a plurality of actionable fields;receiving user input indicating selection of one of the plurality of records in the data set;determining one or more candidate changes to values of the plurality of actionable fields of the selected record, wherein the one or more candidate changes are determined based on applying an evolutionary algorithm to a population of previously observed values of the plurality of actionable fields to find a non-dominated set with respect to the plurality of objectives;determining, for each of the one or more candidate changes, a multi-objective score for that candidate change based on predicted values of ...

DISCOVERING GENOMES TO USE IN MACHINE LEARNING TECHNIQUES

A facility for identifying combinations of feature and machine learning algorithm parameters, where each combination can be combined with one or more machine learning algorithms to train a model, is disclosed. The facility evaluates each genome based on the ability of a model trained using that genome and a machine learning algorithm to produce accurate results when applied to a validation data set by, for example, generating a fitness or validation score for the trained model and the corresponding genome used to train the model. Genomes that produce fitness scores that exceed a fitness threshold are selected for mutation, mutated, and the process is repeated. These trained models can then be applied to new data to generate predictions for the underlying subject matter. 3. The system of claim 2 , wherein the removing claim 2 , from the first genome claim 2 , of at least one feature corresponding to at least one feature vector of a first pair of feature vectors comprises:randomly selecting one of feature vector of the first pair of feature vectors,identifying, from among the features of the first genome, a feature corresponding to the randomly selected feature vector; andremoving, from the first genome, the identified feature.4. The system of claim 1 , further comprising:a fifth component configured to, for the first genome comprising a first set of features, generate a graph comprising a vertex for each feature of the first set of features;a sixth component configure to generate an edge between vertices whose corresponding features have a correlation value that exceeds a correlation threshold or a distance value that is less than a distance threshold; anda seventh component configured to remove vertices from the graph until no connected vertices remain in the graph.5. The system of claim 1 , further comprising:a machine configured to receive physiological signal data from at least one patient; apply at least one of the trained models to at least a portion of the ...

Artificial Intelligence Process Automation for Enterprise Business Communication

Disclosed is an automated electronic message processing system that utilizes a combination of machine learning and natural language processing to create a communication system with greater adaptability and capacity for learning. An extension and modification of the general genetic algorithm concept better enables the present system to learn the sense of messages and apply learnt responses to future communications.

FEATURE SUBSET EVOLUTION BY RANDOM DECISION FOREST ACCURACY

A genetic algorithm (GA) in combination with a random decision forest can be used to identify a feature subset related to an observed incident. The GA is used to select feature subsets for which data samples are obtained to train and test random decision forests per individual feature subset (“individual”) with respect to an observed incident. For each generation of a GA run, fitness values of the individuals are determined based on the testing of the corresponding random decision forest. At termination of the GA run, an individual representing a feature subset is identified as likely most related to the observed incident. The trained random decision forest corresponding to the individual or a subset of the trained random decision forest is used to predict or classify whether live values of the fittest feature subset indicate the observed incident. 1. A method comprising:searching with a genetic algorithm a solution space for a set one or more individuals most relevant to a previously observed incident, wherein the solution space is defined by monitored metrics of an application, wherein an individual comprises a bit array with elements of the bit array corresponding to different ones of the monitored metrics; training and testing a random decision forest with a training dataset and a testing dataset from a first time-series dataset, wherein the training and testing datasets comprise samples from the first time-series dataset that correspond to those of the monitored metrics indicated in the individual and a first of multiple types of observed incidents;', 'determining a fitness value for the individual based, at least in part, on the testing of the random decision forest; and, 'for each individual in each iteration of the searching,'}after satisfying a termination criterion of the genetic algorithm, identifying a feature subset as most relevant to the first type of observed incident based on at least a fittest individual and a first set of one or more decision ...

SYSTEM AND METHOD FOR ANAEROBIC DIGESTION PROCESS ASSESSMENT, OPTIMIZATION AND/OR CONTROL

Systems and methods are described for performing at least one of assessing, optimizing and/or controlling the performance of an Anaerobic Digestion (AD) plant. The system comprises a server that provides a user interface for allowing a user to enter user inputs to define various aspects of the AD plant operation and to view results of the simulation; a database for storing the inputs used for the simulation of the anaerobic digestion plant, the inputs including feedstock inputs, AD operational inputs, and simulation criteria; and a simulation engine that can be operated in an at least one of an off-line simulation mode for generating off-line simulator predictions, a near-line simulation mode for optimizing the performance of the system and an online mode for using machine learning to tune the performance of various models used in simulating the operation of the AD plant. 2. The system of claim 1 , wherein the feedstock model includes at least one steady state equation for determining an overall BMP or the feedstock model includes at least one transient sub-model for determining a cumulative methane yield.3. The system of claim 2 , wherein the at least one steady state equation determines at least one of a first BMP value due to chemical oxygen demand claim 2 , a second BMP value due to elemental composition (EC) and a third BMP value due to organic fraction composition claim 2 , wherein the BMP values are averaged when more than one BMP value is determined.4. The system of claim 2 , wherein the at least one transient sub-model for determining a cumulative methane yield include at least one of a first order kinetic model claim 2 , a Chen and Hashimoto model claim 2 , a Modified Gompertz model claim 2 , and a dual pooled first order kinetic model claim 2 , wherein outputs of the sub-models are averaged when at least two sub-models are used to determine the cumulative methane yield.5. The system of claim 1 , wherein the AD operational model is used to generate ...

EVOLUTIONARY MODELLING BASED NON-DISRUPTIVE SCHEDULING AND MANAGEMENT OF COMPUTATION JOBS

Various techniques are used to schedule computing jobs for execution by a computing resource. In an example method, a schedule is generated by selecting, for a first slot in the schedule, a first computing job based on a first priority of the first computing job with respect to a first characteristic. A second computing job is selected for a second slot in the schedule based on a second priority of the second computing job with respect to a second characteristic. The second slot occurs after the first slot in the schedule, and the second characteristic is different than the first characteristic. The first characteristic or the second characteristic includes an execution frequency. The computing jobs are executed based on the schedule. 1. A system , comprising:at least one processor; andmemory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising: selecting, for a first slot in the schedule, a first computing job based on a first priority of the first computing job with respect to a first characteristic; and', 'selecting, for a second slot in the schedule occurring after the first slot, a second computing job based on a second priority of the second computing job with respect to a second characteristic, the second characteristic being different than the first characteristic, the first characteristic or the second characteristic comprising execution frequencies of the computing jobs; and, 'generating a schedule of computing jobs bycause at least one computing resource to execute the computing jobs based on the schedule.2. The system of claim 1 , wherein the first characteristic or the second characteristic comprises execution durations of the computing jobs claim 1 , computing resource utilization levels of the computing jobs claim 1 , data utilization levels of the computing jobs claim 1 , functions of the computing jobs claim 1 , users associated with the computing jobs claim 1 , or ...

METHOD FOR ADJUSTING CONTINUOUS VARIABLE AND METHOD AND APPARATUS FOR ANALYZING CORRELATION USING THE SAME

Provided are a method for adjusting a continuous variable, a method and an apparatus for analyzing a correlation using the same. A method for adjusting a continuous variable according to an exemplary embodiment of the present disclosure is a method for adjusting a continuous variable by an apparatus including: determining at least one confounder from analysis data; classifying the analysis data into a plurality of subgroups having the same combination of confounders; and generating a new continuous variable for each subgroup based on a representative value of a continuous variable distribution. 1. A method for adjusting a continuous variable by an apparatus , comprising:determining at least one confounder from analysis data;classifying the analysis data into a plurality of subgroups having the same combination of confounders; andgenerating a new continuous variable for each subgroup based on a representative value of a continuous variable distribution.2. The method for adjusting a continuous variable according to claim 1 , wherein the determining includes:transforming clinical variables into categorical variables in the analysis data;calculating a significance probability (p-value) by comparing the clinical variable with the continuous variable; anddetermining the clinical variable having the significance probability which is smaller than a predetermined setting value, as the confounder.3. The method for adjusting a continuous variable according to claim 1 , wherein the generating of a new continuous variable includes:setting the representative value of the continuous variable distribution for each subgroup to be “real number”; andtransforming the continuous variable of each subgroup into a relative value with respect to the set “real number”.4. A method for analyzing a correlation using adjustment of a continuous variable to analyze a correlation between a continuous variable and a specific dependent variable for data to be analyzed by an apparatus claim 1 , the ...

GENE MUTATION IDENTIFICATION METHOD AND APPARATUS, AND STORAGE MEDIUM

The present disclosure relates to a gene mutation identification method and apparatus, and a storage medium. The method includes: obtaining at least one gene sequencing read segment corresponding to a gene mutation candidate site; determining a sequence feature and a non-sequence feature of the gene mutation candidate site according to attribute information of the at least one gene sequencing read segment, where the sequence feature is a feature related to the position of the site; and identifying gene mutation of the gene mutation candidate site based on the sequence feature and the non-sequence feature. According to embodiments of the present disclosure, the sequence feature and the non-sequence feature of the gene can be combined, thereby more comprehensively analyzing the features of a gene mutation site and improving accuracy of gene mutation identification. 1. A gene mutation identification method , comprising:obtaining at least one gene sequencing read segment corresponding to a gene mutation candidate site;determining a sequence feature and a non-sequence feature of the gene mutation candidate site according to attribute information of the at least one gene sequencing read segment, wherein the sequence feature is a feature related to the position of the site; andidentifying gene mutation of the gene mutation candidate site based on the sequence feature and the non-sequence feature.2. The method according to claim 1 , wherein the attribute information comprises sequence attribute information; and determining the sequence feature of the gene mutation candidate site according to the attribute information of the at least one gene sequencing read segment comprises:determining a preset site interval where the gene mutation candidate site is located according to gene position information of the gene mutation candidate site;obtaining the sequence attribute information of the at least one gene sequencing read segment at each site in the preset site interval, wherein ...

COMPACT AND LOW LOSS Y-JUNCTION FOR SUBMICRON SILICON WAVEGUIDE

A compact, low-loss and wavelength insensitive Y-junction for submicron silicon waveguides. The design was performed using FDTD and particle swarm optimization (PSO). The device was fabricated in a 248 nm CMOS line. Measured average insertion loss is 0.28±0.02 dB across an 8-inch wafer. The device footprint is less than 1.2 μm×2 μm, orders of magnitude smaller than MMI and directional couplers. 18-. (canceled)9. A submicron optical splitter device comprising:an input port for inputting a beam of light in a propagation direction;first and second output ports for outputting first and second portions of the beam of light;a tapered section between the input port and the output port;wherein the tapered section increases in width from the input port to a maximum width, and decreases in width from the maximum width towards the first and second output ports, whereby the maximum width is greater than the width proximate the first and second output ports.10. The device according to claim 9 , wherein the input port and the first and second output ports each has a width of 0.5 um.11. The device according to claim 10 , further comprising a gap between the first and second output ports; wherein the gap has a width of 0.2 um.12. The device according to claim 10 , wherein the maximum width is 1.4 um.13. The device according to claim 12 , wherein a total length of the tapered section is 2 um.14. The device according to claim 9 , wherein the tapered section is symmetrical in the propagation direction to ensure balanced output at the first and second output ports.15. The device according to claim 9 , wherein the tapered section comprises silicon with a silicon oxide cladding.16. The device according to claim 9 , wherein the width of the tapered section proximate the half way point comprises the same maximum width.17. The device according to claim 9 , wherein the tapered section is divided into a plurality of segments of equal length.18. The device according to claim 17 , wherein a ...

Systems and Methods for Multi-Objective Optimizations with Decision Variable Perturbations

Systems and methods are provided for providing an optimized solution to a multi-objective problem. Potential solutions may be generated from parent solutions to be evaluated according to multiple objectives of the multi-objective problem. If the potential solutions are infeasible, the potential solutions may be perturbed according to a perturbation model to bring the potential solution to feasibility, or at least a reduced level of constraints. The perturbation models may include a weight vector that indicates the amount of perturbation, such as in a forward and/or reverse direction, of decision variables of the potential solutions. In some cases, the perturbation models may be predetermined. In other cases, the perturbation models may be learned, such as based on training constraint data. Additionally, potential solutions may be generated in a secondary optimization where a constraint based optimization may be performed to drive to generating a feasible solution for further evaluation according to objective values.

SCHEDULING METHOD AND SYSTEM BASED ON IMPROVED VARIABLE NEIGHBORHOOD SEARCH AND DIFFERENTIAL EVOLUTION ALGORITHM

The present invention relates to a production batch scheduling method and system based on improved variable neighborhood search and differential evolution algorithms as well as a storage medium. The method is executed by a computer, and includes: setting algorithm parameters; building a neighborhood structure; initializing a population; determining an initial solution; calculating a fitness value; locally searching; selecting a male parent; performing individual recessive variation; regenerating the population; updating the initial solution; updating a neighborhood structure of algorithmic search; and judging whether a terminal condition of algorithm execution is met, outputting a global optimal solution of the algorithmic search if so, otherwise, returning to Step The present invention can obtain an approximate optimal solution in regard to a coordinated batch scheduling problem of production and transportation in the case of a manufacturer single machine based on a differential workpiece. 1. A production batch scheduling method based on improved variable neighborhood search and differential evolution algorithms , executed by a computer and comprising:{'b': '1', 'sub': 1', 'i', 'n', 'i, 'S. initializing an input parameter of an algorithm, comprising number n of workpieces, workpiece size s, a basic processing time p of the workpieces, an arrival time r of the workpieces, capacity C of a processing machine, and a time T of transporting the workpieces from a manufacturer to a customer, wherein a set of processing workpieces is marked as J={J, . . . , J, . . . , J} and Jindicates the i-th workpiece;'}{'b': '2', 'sub': max', 's', 'best', 's, 'S. setting an execution parameter of the algorithm, wherein the execution parameter comprises a maximum number of iterations I, a current number of iterations I−1, a population size Q, an initial solution Xof the algorithm, number top of outstanding individuals in a population, and a global optimal solution X=X;'}{'b': '3', 'sub': ...

CANDIDATE VISUALIZATION TECHNIQUES FOR USE WITH GENETIC ALGORITHMS

According to one embodiment, a method for generating a plurality of candidate visualizations. The method may include receiving a scenario description. The method may also include collecting a plurality of expert data using a training system based on the received scenario description. The method may further include generating at least one predictive model based on the collected plurality of expert data in order to execute the at least one generated predictive model during an application of a plurality of genetic algorithms. 1. A processor-implemented method for generating a plurality of candidate visualizations , the method comprising:receiving, by a processor, a scenario description;collecting a plurality of expert data using a training system based on the received scenario description; andgenerating at least one predictive model based on the collected plurality of expert data in order to execute the at least one generated predictive model during an application of a plurality of genetic algorithms.2. The method of claim 1 , wherein the plurality of expert data includes at least one of a plurality of action data claim 1 , a plurality of metric data claim 1 , and a plurality of opinion data.3. The method of claim 1 , wherein the training system collects the plurality of expert data through at least one of an expert selecting a preferred visualization within a plurality of candidate visualizations and an expert submitting an opinion related to the preferred visualization.4. The method of claim 1 , wherein the training system includes at least one of a central data storage facility claim 1 , a plurality of web-based deployment capabilities claim 1 , and scalability to a corresponding number of experts using the training system.5. The method of claim 1 , further comprising:updating the training system based on the at least one generated predictive model.6. The method of claim 1 , wherein generating the at least one predictive model may include using at least one of a ...

Methods, apparatus, and systems for generating a vegetation control plan

Vegetation control plans may be automatically generated using vegetation control information received from a variety of sources. Such vegetation control plans may aid farmers, other vegetation control personnel, and professionals when determining a vegetation control strategy, including treatment, and then guide the implementation of that strategy. Vegetation control plans may include a variety of recommended vegetation control practices and projected outcomes for the implementation of recommended vegetation control management practices.

SYSTEM AND METHOD FOR PREDICTING TRAIT INFORMATION OF INDIVIDUALS

The present disclosure relates to predicting trait information from the genetic information of individuals, and generating a model therefor. Learning is performed using a plurality of types of genetic information from a plurality of individuals, and a model for predicting trait information is generated. For said learning, it is possible to create images of the genetic information, and provide the same to said learning. The images in the present disclosure can store both sequence information and expression information. Moreover, the layout of genetic factors in the images can be optimized. Said learning can be performed as split learning, and the data after said split learning can be consolidated. 1. A system for predicting trait information on an individual , comprising:a storage unit for storing genetic information on a plurality of individuals and trait information on the plurality of individuals, the genetic information containing at least two types of information;a learning unit configured to learn a relationship between genetic information and trait information from the genetic information on the plurality of individuals and the trait information on the plurality of individuals; anda calculation unit for predicting trait information on an individual from genetic information on the individual based on the relationship between the genetic information and the trait information.2. The system of claim 1 , wherein the learning unit is configured to learn after forming an image of the genetic information on the plurality of individuals.3. The system of claim 1 , wherein the learning unit is configured to divide the genetic information on the plurality of individuals claim 1 , learn relationships between partial genetic information and trait information claim 1 , and integrate relationships between a plurality of pieces of partial genetic information and trait information to learn the relationship between the genetic information and the trait information.4. The system ...

NEURAL NETWORK EVOLUTION USING EXPEDITED GENETIC ALGORITHM FOR MEDICAL IMAGE DENOISING

Various embodiments for image denoising using a convolutional neural network (CCN) are described. A system may include at least one computing device and program instructions stored in memory and executable in the at least one computing device that, when executed, direct the at least one computing device to implement a genetic algorithm (GA) routine that identifies and optimizes a plurality of hyperparameters for use in denoising an image using the convolutional neural network. An image may be denoised using the convolutional neural network, where the image is denoised using the hyperparameters identified and optimized in the genetic algorithm routine. 1. A system for image denoising using a convolutional neural network (CCN) , comprising:at least one computing device; and perform a genetic algorithm (GA) routine that identifies and optimizes at least one hyperparameter for use in denoising an image using the convolutional neural network (CNN); and', 'denoise an image using the convolutional neural network (CCN), wherein the image is denoised by the convolutional neural network (CNN) using the at least one hyperparameter identified and optimized in the genetic algorithm (GA) routine., 'program instructions stored in memory and executable in the at least one computing device that, when executed, direct the at least one computing device to2. The system of claim 1 , wherein the at least one hyperparameter is a plurality of hyperparameters.3. The system of claim 2 , wherein the genetic algorithm (GA) routine utilizes a fitness score determined for each set of the plurality of hyperparameters.4. The system of claim 3 , wherein the fitness score is a restored image quality metric determined using a fitness function.5. The system of claim 1 , wherein the genetic algorithm routine is configured to perform at least one of: a selection operation claim 1 , a crossover operation claim 1 , and a mutation operation.6. The system of claim 1 , wherein the at least one computing ...

Methods and Systems for Pedigree Enrichment and Family-Based Analyses Within Pedigrees

Methods, non-transitory computer-implemented methods and systems for creating enriched pedigree are provided. Also provided are methods, non-transitory computer-implemented methods and systems for determining a disease-causing variant. 1. A system for identifying disease causing variant , the system comprising:a data processor and a memory coupled with the data processor, the processor being configured to:generate a first degree network of individuals based on sequencing data of a cohort;identify whether an individual in the first degree network as an affected or an unaffected, wherein the individual with at least one binary trait, extreme quantitative trait, or combination thereof is identified as affected and the individual without the at least one binary trait or the extreme quantitative trait is identified as unaffected; andgenerate at least one enriched pedigree containing the individuals including designation as affected or unaffected.2. The system of claim 1 , wherein the processor is further configured to perform segregation analysis to identify variant trait pairs that co-segregate within and across the at least one enriched pedigree.3. The system of claim 1 , wherein the processor is further configured to perform segregation analysis to analyze the variant trait pairs to determine the disease-causing variant.4. The system of claim 1 , wherein the sequencing data can be selected from the group consisting of exome sequencing data or whole genome sequencing data or genotype array data.5. The system of claim 1 , wherein the processor is further configured to identify the identified affected as unaffected if a prevalence of the at least one binary trait in the cohort is over 5%.6. The system of claim 1 , wherein the processor is further configured to identify the identified affected as unaffected if the at least one extreme quantitative trait of the individual is less than two standard deviations from a mean quantitative trait of the cohort.7. The system of ...

FAILURE PROBABILITY EVALUATION SYSTEM AND METHOD

The remaining life of a component of a mechanical system is predicted with high accuracy. A failure probability evaluation system evaluates a failure of a component of each mechanical system for a mechanical system group including a plurality of mechanical systems, and includes a failure history database for accumulating past failure history data about the mechanical system. A time-series operation database stores time-series physical quantity data representing an operating state of the mechanical system. A failure rate function identification unit calculates a failure rate function of a mechanical system by statistical processing based on the failure history data, and a damage model generation/update unit having a function of generating an explanatory variable expression of a failure rate function which minimizes a variation in life is defined by the failure rate function using the time-series physical quantity data. 1. A failure probability evaluation system for evaluating a failure of a component of each mechanical system for a mechanical system group including a plurality of mechanical systems , the failure probability evaluation system comprising:a failure history database for accumulating past failure history data about the mechanical system;a time-series operation database for storing time-series operation data representing an operating state of the mechanical system;a failure probability density function identification unit that calculates a failure probability density function of a mechanical system by statistical processing based on the failure history data; anda damage model generation/update unit having a function of generating an explanatory variable expression of a failure probability density function which minimizes a variation in life defined by the failure probability density function using the time-series operation data,wherein the failure probability density function identification unit provides a failure probability density function which ...

METHOD AND SYSTEM FOR TRAIN PERIODIC MESSAGE SCHEDULING BASED ON MULTI-OBJECTIVE EVOLUTIONARY ALGORITHM

The present invention provides a method and a system for train periodic message scheduling based on a multi-objective evolutionary algorithm, relating to the field of information and communications technology, mainly including: acquiring an MVB periodic message table; binary encoding the MVB periodic message table and initializing it randomly, to generate an iterative population; performing crossover and mutation operations on the individuals of the iterative population using a genetic algorithm, to update the iterative population; constructing an MVB periodic scheduling table that meets scheduling needs and minimizes the macro cycle according to a multi-objective algorithm and the updated iterative population; scheduling train periodic messages according to the MVB periodic scheduling table, thereby meeting the real-time requirement of periodic data transmission in actual scheduling scenarios. 1. A method for train periodic message scheduling based on a multi-objective evolutionary algorithm , comprising:acquiring an MVB periodic message table, where the MVB periodic message table includes K periodic messages to be transmitted; each of the periodic messages has a period, a processing time and a priority; and the MVB periodic message table corresponds to a macro cycle containing N micro cycles;binary encoding the MVB periodic message table and initializing it randomly, to generate an iterative population, where the iterative population includes M individuals; each of the individuals includes K binary codes; each of the binary codes is obtained from: binary encoding a sequential number of the micro cycle in which a periodic message is scheduled for the first time, and then initializing it randomly; and different binary codes correspond to different periodic messages;performing crossover and mutation operations on the individuals of the iterative population using a genetic algorithm, to update the iterative population, the number of individuals in the updated ...