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 3. Отображено 3.
30-04-2018 дата публикации

METHOD FOR MEASURING ENERGY CONSUMPTION BASED ON BODY/EXERCISE SIGNAL AND DEVICE THEREOF

Номер: KR1020180043517A
Принадлежит:

The present invention provides a method for accurately measuring energy consumption and a device thereof. The method for measuring energy consumption comprises the following steps of: receiving an exercise signal of a user measured by an exercise signal sensor and a bio-signal of the user measured by a bio-signal sensor; analyzing the exercise signal to determine whether the user is in a static state or a dynamic state; and selectively reflecting information on the exercise signal and information on the bio-signal according to the static state and the dynamic state to calculate energy consumption of the user. COPYRIGHT KIPO 2018 ...

Подробнее
25-06-2018 дата публикации

생체/운동 신호 기반의 에너지 소모량 측정 방법 및 장치

Номер: KR0101870630B1
Принадлежит: 한국과학기술연구원

... 에너지 소모량 측정 방법 및 장치는, 운동 신호 센서가 측정한 사용자의 운동 신호와 생체 신호 센서가 측정한 사용자의 생체 신호를 제공받고, 운동 신호를 분석하여 사용자가 정적 상태인지 동적 상태인지 여부를 판단하여, 정적 상태와 동적 상태에 따라 상기 운동 신호의 정보와 상기 생체 신호의 정보를 선택적으로 반영하여 상기 사용자의 에너지 소모량을 산출한다.

Подробнее
23-11-2016 дата публикации

METHOD FOR TRAINING TOP-DOWN SELECTIVE ATTENTION IN ARTIFICIAL NEURAL NETWORK

Номер: KR1020160134019A
Принадлежит:

The present invention provides a technology for technically implementing an ability of selective attention occurring in a human brain and applying the ability to a recognizer to arbitrarily increase precision. The technology includes: fixing, on the basis of a preset weighted value, a plurality of weighted values corresponding to connection strength over synapse obtained through learning of an artificial neural network based on a multilayer perceptron network, and suggesting a training pattern to an input layer including a plurality of neurons; performing operation in the artificial neural network corresponding to the training pattern and calculating an output for an input vector corresponding to a plurality of data over domain; and performing training over synapse based on top-down selective attention by comparing a data recognition rate based on a policy over domain through the calculated output to weight the corresponding output of the data having the highest recognition rate. The technology ...

Подробнее