公开(公告)号：US11700518B2

公开(公告)日：2023-07-11

申请号：US16884892

申请日：2020-05-27

申请人： Wuxian Shi ,  Yiqun Ge ,  Wen Tong ,  Qifan Zhang

发明人： Wuxian Shi ,  Yiqun Ge ,  Wen Tong ,  Qifan Zhang

IPC分类号： H04W4/70 ,  G06N3/08 ,  G06N3/045

CPC分类号： H04W4/70 ,  G06N3/045 ,  G06N3/08

摘要： Methods and apparatuses for feature-driven communications are described. A set of features describing an observed subject is transmitted by a transmitting electronic device (ED) to a base station (BS). The BS translates the received features to another set of transmission features to be transmitted to a receiving ED. The receiving ED recovers information about the subject from the features received from the BS.

公开(公告)号：US10785681B1

公开(公告)日：2020-09-22

申请号：US16428396

申请日：2019-05-31

申请人： Yiqun Ge ,  Wuxian Shi ,  Wen Tong ,  Qifan Zhang

发明人： Yiqun Ge ,  Wuxian Shi ,  Wen Tong ,  Qifan Zhang

IPC分类号： H04L29/06 ,  H04W28/06 ,  G06K9/62 ,  H04W4/70 ,  G06N3/04 ,  G06N3/08 ,  H04W84/04

摘要： Methods and apparatuses for feature-driven machine-to-machine communications are described. At a feature encoder, features are extracted from sensed raw information, to generate features that compress the raw information by a compression ratio. The feature encoder implements a probabilistic encoder to generate the features, each feature providing information about a respective probability distribution that each represents one or more aspects of the subject. The probabilistic encoder is designed to provide a compression ratio that satisfies a predetermined physical channel capacity limit for a transmission channel. The features are transmitted over the transmission channel.

公开(公告)号：US12021572B2

公开(公告)日：2024-06-25

申请号：US18080932

申请日：2022-12-14

申请人： Yiqun Ge ,  Wuxian Shi ,  Wen Tong

发明人： Yiqun Ge ,  Wuxian Shi ,  Wen Tong

IPC分类号： H04B17/26 ,  H04B17/373 ,  H04L25/02 ,  H04L25/03 ,  H04W24/10

CPC分类号： H04B17/26 ,  H04B17/373 ,  H04L25/0254 ,  H04L25/03165 ,  H04W24/10

摘要： A wireless network can generate candidate signal configurations for physical transmissions to or from a user equipment (UE) in a radio environment. The generation of candidate signal configurations can be performed using a first neural network that is associated with the UE. These signal configurations can then be evaluated using a second neural network that is associated with the radio environment. The second neural network can be trained using measurements from previous physical transmissions in the radio environment. The trained second neural network generates a reward value that is associated with the candidate signal configurations. The first neural network is then trained using the reward values from the second neural network to produce improved candidate signal configurations. When a signal configuration that produces a suitable reward value is generated, this signal configuration can be used for the physical transmission in the radio environment.

公开(公告)号：US11424856B2

公开(公告)日：2022-08-23

申请号：US16929477

申请日：2020-07-15

申请人： Yiqun Ge ,  Wuxian Shi ,  Wen Tong

发明人： Yiqun Ge ,  Wuxian Shi ,  Wen Tong

IPC分类号： G11C29/00 ,  H04L1/00 ,  G06N3/08 ,  G06F17/18

摘要： A method and apparatus for encoding source information for transmission over a transmission channel is disclosed. The method involves causing a source encoder to generate a plurality of feature probability distributions representing aspects of the source information. The method also involves receiving the plurality of feature probability distributions at an input of a distribution channel encoder, the distribution channel encoder being implemented using a polarization stream network. The method further involves causing the distribution channel encoder to transform the plurality of feature probability distributions into a dimension-extended output plurality of distribution codewords for transmission over the transmission channel. Methods and apparatus for decoding the output plurality of distribution codewords to regenerate the source information is also disclosed.

公开(公告)号：US11533115B2

公开(公告)日：2022-12-20

申请号：US16412908

申请日：2019-05-15

申请人： Yiqun Ge ,  Wuxian Shi ,  Wen Tong

发明人： Yiqun Ge ,  Wuxian Shi ,  Wen Tong

IPC分类号： H04B17/26 ,  H04L25/02 ,  H04W24/10 ,  H04B17/373 ,  H04L25/03

摘要： A wireless network can generate candidate signal configurations for physical transmissions to or from a user equipment (UE) in a radio environment. The generation of candidate signal configurations can be performed using a first neural network that is associated with the UE. These signal configurations can then be evaluated using a second neural network that is associated with the radio environment. The second neural network can be trained using measurements from previous physical transmissions in the radio environment. The trained second neural network generates a reward value that is associated with the candidate signal configurations. The first neural network is then trained using the reward values from the second neural network to produce improved candidate signal configurations. When a signal configuration that produces a suitable reward value is generated, this signal configuration can be used for the physical transmission in the radio environment.

公开(公告)号：US10979202B2

公开(公告)日：2021-04-13

申请号：US16534653

申请日：2019-08-07

申请人： Yiqun Ge ,  Wuxian Shi ,  Wen Tong

发明人： Yiqun Ge ,  Wuxian Shi ,  Wen Tong

IPC分类号： H04L5/00 ,  G06N3/08 ,  G06F17/18 ,  G06N20/20 ,  G06N3/04

摘要： Methods and apparatuses for measuring a distance between two signal distributions in a common signal space are described. A measurement network is configured to receive first and second signal distributions as input and output a measurement of a Wasserstein distance between the first and second signal distributions. The measurement network may be implemented using a neural network.

公开(公告)号：US11361223B2

公开(公告)日：2022-06-14

申请号：US16937863

申请日：2020-07-24

申请人： Yiqun Ge ,  Wuxian Shi ,  Wen Tong

发明人： Yiqun Ge ,  Wuxian Shi ,  Wen Tong

IPC分类号： G06N3/08 ,  H04B7/06

摘要： A multi-beam transmission method is provided for transmitting using an N-beam transmitter to a receiver having K receive beams. In the transmitter, a non-linear encoder implemented by a machine learning block, and a linear encoder are trained using gradient descent back propagation that relies on feedback from the receiver. For each input to be transmitted the machine learning block is used to process the input to produce N/K sets of L outputs. The linear encoder is used to perform linear encoding on each set of L outputs to produce a respective set of K outputs so as to produce N/K sets of K encoded outputs overall and N encoded outputs overall. One of the N/K sets of K outputs from each set of K beams. In order to allow a generalization to different SNRs, and to allow for time varying channel conditions, the non-linear layers, implemented in the non-linear encoder, are responsible for extracting features and regenerating the features, while the linear layers implemented in the linear encoder, are responsible for more generalization.

公开(公告)号：US11252004B2

公开(公告)日：2022-02-15

申请号：US16834494

申请日：2020-03-30

申请人： Yiqun Ge ,  Wuxian Shi ,  Wen Tong

发明人： Yiqun Ge ,  Wuxian Shi ,  Wen Tong

IPC分类号： H04L27/26 ,  H04W72/04 ,  H04J13/00 ,  G06N3/08 ,  H04L5/00 ,  G06N3/04

摘要： A method and apparatus for multiple-access wireless transmission is disclosed. The method involves mapping a plurality of signals onto a multi-dimensional non-Gaussian source manifold, the plurality of signals including signals targeted for transmission to a plurality of receivers. The method also involves transforming the source manifold into a multi-dimensional target manifold using a polarization stream network. The method further involves generating a multiple-access transmission waveform for transmission to the plurality of receivers, the multiple-access transmission waveform being based on the target manifold.

公开(公告)号：US10447435B2

公开(公告)日：2019-10-15

申请号：US15651390

申请日：2017-07-17

申请人： Wuxian Shi ,  Yiqun Ge

发明人： Wuxian Shi ,  Yiqun Ge

IPC分类号： H04L1/00 ,  H03M13/45 ,  H03M13/13 ,  H03M13/00 ,  H04W88/02 ,  H04W88/08

摘要： In reduced-stage polar decoding, a received word that is based on an N-bit codeword of a polar code is decoded using fewer than log2N Log Likelihood Ratio (LLR) stages. Decoding uses a reduced stage decoding configuration. In an embodiment, such a configuration includes at least one higher-order LLR stage with nodes implementing functions that are based on a combination of lower-order polar code kernels.

公开(公告)号：US20170019222A1

公开(公告)日：2017-01-19

申请号：US15203498

申请日：2016-07-06

申请人： Yiqun Ge ,  Wuxian Shi

发明人： Yiqun Ge ,  Wuxian Shi

IPC分类号： H04L5/00 ,  H04B7/26

CPC分类号： H04L5/0007 ,  H04B7/2628

摘要： Methods and devices are disclosed for receiving and decoding sparsely encoded data sequences using a message passing algorithm (MPA) or maximum likelihood sequence estimation (MLSE). Such data sequences may be used in wireless communications systems supporting multiple access, such as sparse code multiple access (SCMA) systems. The Methods and devices reduce the number of states in a search space for each received signal and associated function node based on a search threshold based on a characteristic related to the received signal and/or to a quality of a resource element over which the received signal is transmitted.

摘要翻译： 公开了使用消息传递算法（MPA）或最大似然序列估计（MLSE）来接收和解码稀疏编码的数据序列的方法和装置。 这样的数据序列可以用于支持多个接入的无线通信系统，例如稀疏码多址（SCMA）系统。 方法和装置基于与接收信号相关的特征和/或资源元素的质量，基于搜索阈值来减少每个接收信号和相关联功能节点在搜索空间中的状态数量， 被传送。