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 4. Отображено 4.
06-06-2023 дата публикации

RSSD positioning method in Gaussian mixed noise environment

Номер: CN116224221A
Автор: WU HUAFENG, ZHANG YUANYUAN, WANG WEIJUN, LIANG LINIAN
Принадлежит:

The invention relates to an RSSD positioning method in a Gaussian mixed noise environment, and the method comprises the steps: obtaining an RSS measurement value collected by an anchor node, and carrying out the calculation to obtain an RSSD value; constructing a non-convex maximum likelihood problem based on RSSD, and obtaining a diversified population based on reverse learning and a chaotic graph; and performing global search by adopting a self-adaptive variation strategy, and finally selecting to obtain an optimal individual through cross processing and abnormal value processing to serve as positioning information estimation of a target node. Compared with the prior art, the method constructs the non-convex maximum likelihood problem based on RSSD so as to avoid introduction of additional errors due to approximation; a feasible solution is obtained based on an improved differential evolution algorithm; diversified populations are obtained by combining reverse learning with a chaos graph ...

Подробнее
Номер записи: 1
25-08-2023 дата публикации

Marine ecological environment monitoring wireless sensor network node positioning method

Номер: CN116647817A
Автор: XIAN JIANGFENG, MA JUNLING, WU HUAFENG, YANG YONGSHENG, MEI XIAOJUN, CHEN XINQIANG, LI CHAOFENG, ZHANG QIANNAN, LIANG LINIAN
Принадлежит:

The invention relates to a marine ecological environment monitoring wireless sensor network node positioning method, which takes real-time movement of nodes and path loss and absorption effect of underwater communication into consideration, and performs joint estimation on node positions and path loss factors; an original non-convex problem is converted into a non-negative constraint least square framework, and an ocean node position optimal solution is searched based on two stages of an interior point method and a block coordinate updating method; in the first stage, a penalty function is used for reexpressing the problem according to an interior point method, and an approximate solution is solved; and in the second stage, the original problem is converted into a generalized trust region sub-problem, an approximate solution obtained by an interior point method is used as initial estimation of the second stage, iterative solution is carried out by combining a block coordinate updating method ...

Подробнее
Номер записи: 2
09-06-2023 дата публикации

Multi-target positioning method and device for relieving non-line-of-sight effect, and medium

Номер: CN116249070A
Автор: WU HUAFENG, ZHANG YUANYUAN, WANG WEIJUN, XIAN JIANGFENG, LIANG LINIAN, ZHANG QIANNAN
Принадлежит:

The invention relates to a multi-target positioning method and device for relieving a non-line-of-sight effect, and a medium, and the method comprises the following steps: obtaining RSSD data, and converting the RSSD data into a preset format; the RSSD data converted into the preset format are input into a pre-trained multi-target positioning model for relieving the non-line-of-sight effect, multi-target positioning information is obtained, multi-target positioning is completed, and the step of obtaining the pre-trained multi-target positioning model for relieving the non-line-of-sight effect comprises the substeps that the RSSD multi-target positioning model under the non-convex NLOS is constructed, an experimental data set is generated, and the experimental data set is stored in a database; each sample comprises real position information of a plurality of target nodes and corresponding RSSD data; and training the multi-target positioning model based on the experimental data set until ...

Подробнее
Номер записи: 3
18-07-2023 дата публикации

Real-time underwater acoustic positioning method based on IDE-BP neural network

Номер: CN116449294A
Автор: WU HUAFENG, ZHANG YUANYUAN, WANG WEIJUN, XIAN JIANGFENG, LIANG LINIAN, ZHANG QIANNAN
Принадлежит:

The invention relates to a real-time underwater acoustic positioning method based on an IDE-BP neural network, and the method comprises the following steps: obtaining a training sample set through constructing an acoustic positioning model which is based on non-convex RSS and considers path loss and absorption loss; constructing a BP neural network, obtaining initial network parameters of the BP neural network based on a differential evolution algorithm, training the BP neural network by using the training sample set, and obtaining a trained BP neural network; and acquiring underwater acoustic data, and performing underwater acoustic positioning by using the trained BP neural network. Compared with the prior art, the method has the advantages that the IDE algorithm is combined with the BP neural network to solve the RSS-based multi-target underwater acoustic positioning problem, and the method is high in precision and speed.

Подробнее
Номер записи: 4