利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

15146 条记录 (耗时 0.046 秒)

    Noise mitigation by guard-space reference calibration in 5G and 6G
    6.
    发明授权
    Noise mitigation by guard-space reference calibration in 5G and 6G 有权

    公开(公告)号：US12126477B2

    公开(公告)日：2024-10-22

    申请号：US18208928

    申请日：2023-06-13

    申请人： David E. Newman ,  R. Kemp Massengill

    发明人： David E. Newman ,  R. Kemp Massengill

    IPC分类号： H04L27/26 ,  H04L27/08 ,  H04L27/36 ,  H04L5/00

    CPC分类号： H04L27/2607 ,  H04L27/08 ,  H04L27/362 ,  H04L5/0007

    摘要： Noise and interference in 5G/6G messages can be corrected by including a predetermined reference signal in the guard space of each resource element of the message. Even highly variable noise and interference, fluctuating in time and in frequency, can be negated when the demodulation reference signals are positioned within each resource element of the message. In addition, if the guard-space reference signal varies excessively between resource elements, the associated message element can be flagged as likely faulted. Since the guard space is already included in the transmission, no additional resources or transmission power are required. Methods are also disclosed for retaining the signal processing features of prior-art guard space signals such as a cyclic prefix, at low to no cost.

    Low resolution OFDM receivers via deep learning
    7.
    发明授权
    Low resolution OFDM receivers via deep learning 有权

    公开(公告)号：US12126467B2

    公开(公告)日：2024-10-22

    申请号：US18164428

    申请日：2023-02-03

    申请人： Board of Regents, The University of Texas System

    发明人： Jeffrey Andrews ,  Eren Balevi

    IPC分类号： H04B1/00 ,  G06N3/08 ,  H04B1/40 ,  H04L5/00 ,  H04L25/02

    CPC分类号： H04L25/0254 ,  G06N3/08 ,  H04B1/0003 ,  H04B1/40 ,  H04L5/0007

    摘要： Various embodiments provide for deep learning-based architectures and design methodologies for an orthogonal frequency division multiplexing (OFDM) receiver under the constraint of one-bit complex quantization. Single bit quantization greatly reduces complexity and power consumption in the receivers, but makes accurate channel estimation and data detection difficult. This is particularly true for OFDM waveforms, which have high peak-to average (signal power) ratio in the time domain and fragile subcarrier orthogonality in the frequency domain. The severe distortion for one-bit quantization typically results in an error floor even at moderately low signal-to-noise-ratio (SNR) such as 5 dB. For channel estimation (using pilots), various embodiments use novel generative supervised deep neural networks (DNNs) that can be trained with a reasonable number of pilots. After channel estimation, a neural network-based receiver specifically, an autoencoder jointly learns a precoder and decoder for data symbol detection.