BR112023001200A2 - Rede neural de aprendizado profundo baseada em algoritmo de passagem de mensagem híbrida para um sistema de formação de feixe massivo - Google Patents
Rede neural de aprendizado profundo baseada em algoritmo de passagem de mensagem híbrida para um sistema de formação de feixe massivoInfo
- Publication number
- BR112023001200A2 BR112023001200A2 BR112023001200A BR112023001200A BR112023001200A2 BR 112023001200 A2 BR112023001200 A2 BR 112023001200A2 BR 112023001200 A BR112023001200 A BR 112023001200A BR 112023001200 A BR112023001200 A BR 112023001200A BR 112023001200 A2 BR112023001200 A2 BR 112023001200A2
- Authority
- BR
- Brazil
- Prior art keywords
- outputs
- linear
- linear encoder
- neural network
- network based
- Prior art date
Links
- 238000013528 artificial neural network Methods 0.000 title abstract 2
- 238000013135 deep learning Methods 0.000 title abstract 2
- 238000010801 machine learning Methods 0.000 abstract 2
- 238000000034 method Methods 0.000 abstract 2
- 230000005540 biological transmission Effects 0.000 abstract 1
- 230000001172 regenerating effect Effects 0.000 abstract 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
- H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
- H04B7/06—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
- H04B7/0613—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission
- H04B7/0615—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal
- H04B7/0617—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal for beam forming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
- H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
- H04B7/0408—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas using two or more beams, i.e. beam diversity
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
- H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
- H04B7/06—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
- H04B7/0686—Hybrid systems, i.e. switching and simultaneous transmission
- H04B7/0695—Hybrid systems, i.e. switching and simultaneous transmission using beam selection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Radio Transmission System (AREA)
- Error Detection And Correction (AREA)
Abstract
REDE NEURAL DE APRENDIZADO PROFUNDO BASEADA EM ALGORITMO DE PASSAGEM DE MENSAGEM HÍBRIDA PARA UM SISTEMA DE FORMAÇÃO DE FEIXE MASSIVO. Um método de transmissão multifeixe é fornecido para transmitir usando um transmissor de N feixes para um receptor tendo K feixes de recebimento. No transmissor, um codificador não linear implementado por um bloco de aprendizado de máquina e um codificador linear são treinados usando retropropagação descendente de gradiente que depende da realimentação a partir do receptor. Para cada entrada a ser transmitida, o bloco de aprendizado de máquina é usado para processar a entrada para produzir N/K conjuntos de L saídas. O codificador linear é usado para desempenhar codificação linear em cada conjunto de L saídas para produzir um respectivo conjunto de K saídas de modo a produzir N/K conjuntos de K saídas codificadas em geral e N saídas codificadas em geral. Um dos N/K conjuntos de K saídas a partir de cada conjunto de K feixes. A fim de permitir uma generalização para diferentes SNRs e permitir condições de canal variáveis no tempo, as camadas não lineares, implementadas no codificador não linear, são responsáveis por extrair recursos e regenerar os recursos, enquanto as camadas lineares implementadas no codificador linear, são responsáveis por mais generalização.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US16/937,863 US11361223B2 (en) | 2020-07-24 | 2020-07-24 | Hybrid message-passing-algorithm-based deep learning neural network for a massive beam-forming system |
| US16/937,863 | 2020-07-24 | ||
| PCT/CN2021/102520 WO2022017122A1 (en) | 2020-07-24 | 2021-06-25 | Hybrid message-passing-algorithm-based deep learning neural network for a massive beam-forming system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| BR112023001200A2 true BR112023001200A2 (pt) | 2023-03-28 |
| BR112023001200B1 BR112023001200B1 (pt) | 2024-02-15 |
Family
ID=79729677
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| BR112023001200-7A BR112023001200B1 (pt) | 2020-07-24 | 2021-06-25 | Método e aparelho de transmissão de múltiplos feixes |
Country Status (6)
| Country | Link |
|---|---|
| US (1) | US11361223B2 (pt) |
| EP (1) | EP4173155A4 (pt) |
| JP (1) | JP2023535198A (pt) |
| CN (1) | CN115836480A (pt) |
| BR (1) | BR112023001200B1 (pt) |
| WO (1) | WO2022017122A1 (pt) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11625610B2 (en) * | 2019-03-12 | 2023-04-11 | Samsung Electronics Co., Ltd | Multiple-input multiple-output (MIMO) detector selection using neural network |
| CN113840380A (zh) * | 2020-06-24 | 2021-12-24 | 华为技术有限公司 | 一种波束指示方法及通信装置 |
| CN114866119B (zh) * | 2022-04-15 | 2023-09-26 | 电子科技大学长三角研究院(湖州) | 一种非完美信道状态信息条件下的混合波束成形方法 |
| CN117256172A (zh) * | 2022-04-18 | 2023-12-19 | 北京小米移动软件有限公司 | 基于ai的csi上报方法、接收方法、装置及存储介质 |
| CN115664471B (zh) * | 2022-08-31 | 2024-01-02 | 东南大学 | 基于宽学习的毫米波mimo基站协作波束选择方法 |
| CN115935261A (zh) * | 2022-12-30 | 2023-04-07 | 马鞍山思凯科技有限公司 | 基于工业互联网的群体设备非绝对正向反馈方法 |
| CN117095188B (zh) * | 2023-10-19 | 2023-12-29 | 中国南方电网有限责任公司 | 一种基于图像处理的电力安全加强方法及系统 |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4845640B2 (ja) | 2006-08-23 | 2011-12-28 | 富士通株式会社 | 無線通信システムおよび無線通信方法 |
| CN104539329B (zh) | 2014-12-11 | 2018-07-03 | 上海华为技术有限公司 | 一种天线及有源天线系统 |
| US10425878B2 (en) | 2017-01-09 | 2019-09-24 | Qualcomm Incorporated | Techniques to identify sets of multiple beams compatible with configurations for routing signals in a user equipment |
| US10187721B1 (en) * | 2017-06-22 | 2019-01-22 | Amazon Technologies, Inc. | Weighing fixed and adaptive beamformers |
| CN111357209B (zh) | 2017-11-21 | 2022-11-01 | 中兴通讯股份有限公司 | 在多波束无线通信网络中执行信道测量的方法、装置和系统 |
| EP3959848A4 (en) * | 2019-04-23 | 2022-06-22 | Deepsig Inc. | COMMUNICATION SIGNAL PROCESSING BY MEANS OF A MACHINE LEARNING NETWORK |
| US20210266875A1 (en) * | 2020-02-24 | 2021-08-26 | Qualcomm Incorporated | MACHINE LEARNING FOR ADDRESSING TRANSMIT (Tx) NON-LINEARITY |
-
2020
- 2020-07-24 US US16/937,863 patent/US11361223B2/en active Active
-
2021
- 2021-06-25 CN CN202180049190.4A patent/CN115836480A/zh active Pending
- 2021-06-25 EP EP21846831.2A patent/EP4173155A4/en active Pending
- 2021-06-25 WO PCT/CN2021/102520 patent/WO2022017122A1/en unknown
- 2021-06-25 JP JP2023504615A patent/JP2023535198A/ja active Pending
- 2021-06-25 BR BR112023001200-7A patent/BR112023001200B1/pt active IP Right Grant
Also Published As
| Publication number | Publication date |
|---|---|
| EP4173155A1 (en) | 2023-05-03 |
| US11361223B2 (en) | 2022-06-14 |
| JP2023535198A (ja) | 2023-08-16 |
| US20220036171A1 (en) | 2022-02-03 |
| BR112023001200B1 (pt) | 2024-02-15 |
| WO2022017122A1 (en) | 2022-01-27 |
| CN115836480A (zh) | 2023-03-21 |
| EP4173155A4 (en) | 2024-01-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| BR112023001200A2 (pt) | Rede neural de aprendizado profundo baseada em algoritmo de passagem de mensagem híbrida para um sistema de formação de feixe massivo | |
| BR112019022953A2 (pt) | Recuperação de falha de feixe em sistemas de comunicação sem fio | |
| BR112019000541A2 (pt) | métodos de superpixel para redes neurais convolucionais | |
| WO2022031726A3 (en) | System and method for carbon dioxide reactor control | |
| MX2019001219A (es) | Metodo de transmision de se?al piloto, equipo terminal y equipo de red. | |
| BR112019006471A2 (pt) | método de controle de potência de enlace ascendente e aparelho | |
| IN2014DE00528A (pt) | ||
| BR112016007080A2 (pt) | gerenciamento híbrido de handovers em uma rede de auto-organização (son) | |
| BRPI0417172A (pt) | aparelho de irradiação, e, sistema de irradiação | |
| DE602007014085D1 (de) | Effiziente cqi-signalisierung in mimo-systemen mit veränderlichen strahlzahlen | |
| KR20220035932A (ko) | 대역폭 증강을 위한 피처 딕셔너리 | |
| CY1121685T1 (el) | Αποτελεσματικη σηματοδοτηση cqi σε συστηματα μιμο με μεταβλητους αριθμους δεσμων | |
| BR112022008841A2 (pt) | Padrões de silenciamento de sinal de referência de posicionamento | |
| BR112023014264A2 (pt) | Método e aparelho de relatório e recebimento de informações de feixe | |
| ES2160838T3 (es) | Procedimiento y sistema para generar y transmitir rapidamente, con la ayuda de frecuencias vocales, una secuencia de caracteres. | |
| BR112023004496A2 (pt) | Quantização dinâmica para aprendizado profundo com eficiencia energética | |
| BR112020010870A2 (pt) | Método implementado por computador, e, nó de rede | |
| MX2023000126A (es) | Metodos, aparato y sistemas para autocodificador acondicionado por graficas (gcae) usando representaciones que facilitan la topologia. | |
| WO2021221977A3 (en) | Neural network training technique | |
| BR112019006773A2 (pt) | processo e instalação para tratar água produzida a partir de um campo de óleo e gás | |
| BR112021023060A2 (pt) | Processo para a conversão de glicolaldeído com um agente de aminação na presença de hidrogênio e de um catalisador em um reator de conversão de glicolaldeído | |
| EP4138039A3 (en) | System and method for hybrid lidar segmentation with outlier detection | |
| MY196256A (en) | Systems and Methods for Controlling Production and/or Distribution Lines | |
| EP4234766A3 (en) | Hydrogen production system and hydrogen production method | |
| MX2019006227A (es) | Metodos para controlar el indice de hinchamiento en poliestireno de alto impacto. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| B15K | Others concerning applications: alteration of classification |
Free format text: AS CLASSIFICACOES ANTERIORES ERAM: H04B 7/0408 , H04B 7/04 Ipc: H04B 7/06 (2006.01), H04B 7/0408 (2017.01), G06N 3 |
|
| B09A | Decision: intention to grant [chapter 9.1 patent gazette] | ||
| B16A | Patent or certificate of addition of invention granted [chapter 16.1 patent gazette] |
Free format text: PRAZO DE VALIDADE: 20 (VINTE) ANOS CONTADOS A PARTIR DE 25/06/2021, OBSERVADAS AS CONDICOES LEGAIS |