Настройки

Укажите год
-

Небесная энциклопедия

Космические корабли и станции, автоматические КА и методы их проектирования, бортовые комплексы управления, системы и средства жизнеобеспечения, особенности технологии производства ракетно-космических систем

Подробнее
-

Мониторинг СМИ

Мониторинг СМИ и социальных сетей. Сканирование интернета, новостных сайтов, специализированных контентных площадок на базе мессенджеров. Гибкие настройки фильтров и первоначальных источников.

Подробнее

Форма поиска

Поддерживает ввод нескольких поисковых фраз (по одной на строку). При поиске обеспечивает поддержку морфологии русского и английского языка
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Укажите год
Укажите год
Применить Всего найдено 13. Отображено 13.
28-07-2023 дата публикации

Preparation method of burdock root oligosaccharide with probiotic function

Номер: CN116496425A
Автор: HUANG WUYANG, CUI LI, LI YING, ZHANG XIAOXIAO, ZENG FENG, ZHAO XUAN, CHAI ZHI, FENG JIN
Принадлежит:

The invention relates to a preparation method of burdock root oligosaccharide with a probiotic function, and belongs to the technical field of agricultural product processing. The method comprises the following steps: slicing a fresh burdock root raw material, performing enzyme deactivation, performing drying, performing hot water extraction, performing starch removal, performing concentration, performing deproteinization, performing alcohol precipitation, performing freeze-drying, performing redissolution, performing ultrafiltration, performing purification and performing freeze-drying, and is characterized in that the obtained burdock root oligosaccharide is high in purity and good in uniformity, the sugar content is 93.45%, the peak molecular weight Mp is 2473Da, the weight-average molecular weight Mw is 2544Da, the number-average molecular weight Mn is 2120Da, and the content of the burdock root oligosaccharide is 93.45%. The arctium lappa root oligomeric dextrose can promote in-vitro ...

Подробнее
Номер записи: 1
12-05-2023 дата публикации

Intelligent man-machine interaction method based on viewpoint tracking

Номер: CN116110108A
Автор: XING JIANCHUAN, LIU ZIRAN, ZENG FENG, CHEN YANG, ZHOU CHUNWEN, FU YU, YANG BUYU
Принадлежит:

The invention discloses an intelligent man-machine interaction method based on viewpoint tracking, and belongs to the technical field of man-machine interaction based on viewpoint tracking. The method comprises the following steps: acquiring an image through a camera of a computer, performing face detection on the acquired image, and extracting a face image based on a face detection frame; performing face feature point detection on the face image to obtain face feature points of the face image; performing head posture estimation on the face feature points to obtain an eye image, and performing viewpoint tracking processing based on deep learning and man-machine interaction processing based on viewpoint tracking. According to the method, the viewpoint of the user is tracked in real time by using a deep learning algorithm only through a camera of a computer without any other hardware equipment under the condition of no constraint, the facial posture change of the user is monitored, and the ...

Подробнее
Номер записи: 2
28-04-2023 дата публикации

Directional voice separation method based on deep neural network

Номер: CN116030824A
Автор: XING JIANCHUAN, ZENG FENG, FU YU, CHEN YANG, ZHOU CHUNWEN, LIU ZIRAN
Принадлежит:

The invention discloses a directional voice separation method based on a deep neural network, and belongs to the technical field of voice processing. The method comprises the following steps: extracting time-frequency spectrum features of voice: extracting time-frequency spectrum features of mixed human voice and pure human voice, the time-frequency spectrum features of the pure human voice being used for training a human voice separation network; extracting a voiceprint vector of the voice by using a voiceprint encoder so as to extract a voiceprint vector of a reference voice different from the pure voice; a human voice separation network is constructed and trained, and an activation function of the human voice separation network adopts a Mish function; and jointly inputting the time-frequency spectrum and the voiceprint vector into a human voice separation network, and outputting a target human voice extracted from the mixed human voice. According to the invention, the processing performance ...

Подробнее
Номер записи: 3
23-05-2019 дата публикации

REAL-TIME DETECTION METHOD AND APPARATUS FOR DGA DOMAIN NAME

Номер: WO2019096099A1
Автор: ZENG, Feng, CHANG, Shuo, WAN, Xiaochuan
Принадлежит:

A real-time detection method and apparatus for a DGA domain name. An original domain name is translated into a multi-dimensional numeric vector; the multi-dimensional numeric vector is input into a deep learning model pre-trained based on an ImageNet data set, to generate a domain name feature; a domain name classifier is trained based on the generated domain name feature; and a DGA domain name is classified and predicted based on the domain name classifier obtained by training. The method firstly uses a deep learning model pre-trained based on an ImageNet data set, from the field of visual image classification and detection, for real-time detection of a DGA domain name, avoiding the process of high-intensity training and parameter weight adjustment for the deep learning model in DGA domain name detection. The detection rate is higher, and detection speed is faster.

Подробнее
Номер записи: 4
07-04-2023 дата публикации

Auxiliary diagnosis device for cognitive memory dysfunction based on memory curve

Номер: CN115937092A
Автор: XING JIANCHUAN, KONG YUFENG, ZHOU CHUNWEN, CHEN YANG, ZENG FENG, FU YU
Принадлежит:

The invention discloses a cognitive memory dysfunction auxiliary diagnosis device based on a memory curve, and belongs to the technical field of memory cognitive auxiliary diagnosis. The auxiliary diagnosis device comprises a data preprocessing unit, a brain network feature acquisition unit, an activity signal feature extraction unit of a specified brain region, a memory model generation unit based on a memory curve and a cognitive memory dysfunction detection unit. The brain network feature acquisition unit is used for constructing a corresponding brain network based on the preprocessed nuclear magnetic resonance imaging data, performing brain network feature extraction, taking extracted activity signal features as input of the cognitive memory dysfunction detection unit, and outputting an auxiliary diagnosis result based on a preset detection model; and the auxiliary diagnosis is combined with an auxiliary diagnosis result and the brain network topological graph to generate a corresponding ...

Подробнее
Номер записи: 5
23-06-2023 дата публикации

Complex environment photoelectronic imaging weak and small target intelligent detection method

Номер: CN116310359A
Автор: XING JIANCHUAN, MO GUOKUN, ZENG FENG, CHEN YANG, ZHOU CHUNWEN, FU YU, WANG FEI
Принадлежит:

The invention discloses a complex environment photoelectronic imaging weak and small target intelligent detection method, and belongs to the technical field of target detection. The method comprises the following steps: carrying out size normalization processing on a to-be-detected image, then carrying out grouping convolution processing, carrying out downsampling, and then carrying out multi-scale feature extraction on a second feature map through a four-layer stacked residual module layer; performing multi-scale fusion processing on the output feature maps of the residual module layers of the second layer, the third layer and the fourth layer by adopting a stepped structure feature fusion mode to obtain a fused feature map; and finally, weak and small target detection processing is carried out on the fusion feature map through a classification detection determiner, and a weak and small target detection processing result is obtained. According to the invention, the detection network is ...

Подробнее
Номер записи: 6
28-07-2023 дата публикации

External parameter calibration method for mutual constraint of laser radar, camera and inertial sensor

Номер: CN116500595A
Автор: WANG SHUANG, DU XINQUAN, CHEN CAIFU, ZENG FENG, WANG GUIJIN
Принадлежит:

The invention discloses an external parameter calibration method for mutual constraint of a laser radar, a camera and an inertial sensor, and the method comprises the following steps: manufacturing a checkerboard radar reflecting plate, and forming a calibration system; statically calibrating the laser radar and the camera to obtain conversion external parameters from the laser radar to the camera; performing dynamic calibration on the inertial sensor from a visual angle and a laser radar angle; constructing a state estimator; constructing a minimization target, and obtaining conversion external parameters between the camera and the inertial sensor in the optimal state estimator; and obtaining the converted external parameters between the laser radar and the inertial sensor according to the mutual conversion relation between the external parameters, and completing the calibration of the external parameters. According to the method, the static calibration laser radar and the visual camera ...

Подробнее
Номер записи: 7
07-07-2023 дата публикации

External parameter calibration method for mutual constraint of laser radar, camera and inertial sensor

Номер: CN116400333A
Автор: DU XINQUAN, WANG SHUANG, ZENG FENG, CHEN CAIFU, WANG GUIJIN
Принадлежит:

The invention discloses an external parameter calibration method for mutual constraint of a laser radar, a camera and an inertial sensor, and the method comprises the following steps: manufacturing a checkerboard radar reflecting plate, and forming a calibration system; statically calibrating the laser radar and the camera to obtain conversion external parameters from the laser radar to the camera; performing dynamic calibration on the inertial sensor from a visual angle and a laser radar angle; constructing a residual error optimization model, and calculating a conversion external parameter between the camera and the inertial sensor by performing nonlinear optimization on a residual error by using a least square method; based on the mutual conversion relation between the external parameters, obtaining the conversion external parameters between the laser radar and the inertial sensor, and completing the calibration of the external parameters. According to the method, the static calibration ...

Подробнее
Номер записи: 8
12-05-2023 дата публикации

Motor torque control method based on driver behavior characteristics

Номер: CN116101081A
Автор: ZENG JIAN, XIANG HUI, LIU DECAI, YIN LIANZUO, CHEN GUOLI, YUAN TAO, ZENG KAILIAN, ZENG FENG, LIN YUANZONG, LI JIANGHUA
Принадлежит:

The invention discloses a motor torque control method based on driver behavior characteristics. The motor torque control method comprises the following steps: 1) receiving and processing a vehicle acceleration signal, an accelerator pedal opening change rate signal and a vehicle steering angular velocity signal; 2) judging the driving behavior characteristic types of the driver, wherein the driving behavior characteristic types comprise a green hand type, a steady type and a radical type; and (3) according to the driving behavior characteristic type of the driver judged in the step (2), the motor torque compensation amount corresponding to the driving behavior characteristic type is obtained, and the motor target torque is adjusted.

Подробнее
Номер записи: 9
25-04-2023 дата публикации

Voiceprint recognition method based on deep neural network

Номер: CN116013328A
Автор: XING JIANCHUAN, ZENG FENG, FU YU, CHEN YANG, ZHOU CHUNWEN, MO GUOKUN
Принадлежит:

The invention discloses a voiceprint recognition method based on a deep neural network, and belongs to the technical field of voice processing. The method comprises the following steps: training a voiceprint feature extraction network and a voiceprint recognition scoring network, predicting voiceprint feature vectors of registered voices based on the trained voiceprint feature extraction network, and constructing a voiceprint feature database based on the registered voiceprint feature vectors; and obtaining a to-be-recognized acoustic feature, and obtaining a scoring result of the to-be-recognized acoustic feature and the voiceprint feature database based on the voiceprint recognition scoring network so as to determine a recognition result. The extracted voiceprint feature vector is finer and smoother, so that the voice feature is better reserved. The calculated amount in the speech preprocessing process is reduced through the extracted Fbank features, and the feature construction speed ...

Подробнее
Номер записи: 10
22-08-2023 дата публикации

High-precision three-dimensional mapping method fusing laser radar and binocular camera

Номер: CN116630570A
Автор: YANG NAN, WANG SHUANG, CHEN CAIFU, ZENG FENG, WANG GUIJIN
Принадлежит:

The invention discloses a high-precision three-dimensional mapping method fusing a laser radar and a binocular camera, and the method comprises the following steps: S1, obtaining initial binocular camera image data, and carrying out the data preprocessing of the initial binocular camera image data, and obtaining first feature point information; s2, acquiring laser radar point cloud information, and uniformly performing sliding window processing on the first feature point information and the laser radar point cloud information to obtain a camera pose and a road sign point position; and S3, performing three-dimensional mapping according to the camera pose and the road sign point position to obtain a high-precision map. Through point cloud filtering processing, the data volume of the point cloud to be processed is reduced, the efficiency of the SLAM system is improved, meanwhile, the weight of the point cloud in the point cloud filtering processing does not need to be manually set, and universality ...

Подробнее
Номер записи: 11
18-07-2023 дата публикации

Preparation method and application of anti-influenza virus polypeptide

Номер: CN116445548A
Автор: LIU LONG, LIU ZHIXIN, FU YANAN, ZENG FENG, HUANG CONGCONG
Принадлежит:

The invention relates to the technical field of molecular biology, in particular to a preparation method and application of an anti-influenza virus polypeptide. Compared with the prior art, an insect baculovirus expression system and an IMPACT purification system are combined for the first time to prepare the anti-influenza virus polypeptide, the polypeptide is expressed through the insect baculovirus expression system and secreted into supernatant through signal peptide, and the anti-influenza virus polypeptide is obtained. Self-cleavage purification is carried out through an IMPACT system, high-efficiency expression and high-efficiency purification are combined, the antiviral polypeptide can be efficiently produced, cRNA and vRNA synthesis of influenza viruses can be inhibited, and a remarkable virus inhibition effect is achieved.

Подробнее
Номер записи: 12
04-07-2023 дата публикации

Motion recognition method based on mobile terminal

Номер: CN116389639A
Автор: XING JIANCHUAN, YANG BUYU, ZHOU CHUNWEN, CHEN YANG, ZENG FENG, FU YU, ZHANG YANG
Принадлежит:

The invention discloses an action recognition method based on a mobile terminal, and belongs to the technical field of action recognition of the mobile terminal. The method comprises the steps that the acceleration of the mobile terminal is obtained, and if the acceleration of the x axis and the acceleration of the y axis are both larger than or equal to a first threshold value, the overturning state of the mobile terminal is recognized based on the acceleration; if the deviation between the accelerated speed of the x axis and the y axis and the first threshold value is within the specified range, the overturning state of the mobile terminal is recognized based on the linear accelerated speed; if the accelerations of the x axis and the y axis are both smaller than a first threshold value and the deviation of the accelerations is not within a specified range, the motion states of the mobile terminal are recognized in combination with the linear acceleration: constant speed and acceleration ...

Подробнее
Номер записи: 13