中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

5 records (took 0.022 seconds)

    MACHINE LEARNING FOR CHANNEL ESTIMATION
    1.
    发明申请
    MACHINE LEARNING FOR CHANNEL ESTIMATION 审中-公开

    公开(公告)号：WO2020091842A3

    公开(公告)日：2020-05-07

    申请号：PCT/US2019/033174

    申请日：2019-05-20

    Applicant: PARALLEL WIRELESS, INC.

    Inventor： CAO, Yang ,  NANDA, Nihar

    IPC: H04W36/00 ,  H04W8/26 ,  H04L27/28

    Abstract: Performing training using superimposed pilot subcarriers to determine training data. Training that includes starting with a training duration (T) equal to a number of antennas (M) and running a Convolutional Neural Network (CNN) model using training samples to determine if a testing variance meets a predefined threshold. When the testing variance meets a predefined threshold, then reducing T by one half and repeating the running Convolutional Neural Network (CNN) model until the testing variance fails to meet the predefined threshold. When the testing variance fails to meet the predefined threshold, then multiplying T by two and using the new value of T as the new training duration to be used. Generating a run-time model based on the training data, updating the run-time model with new feedback data received from a User Equipment (UE), producing a DL channel estimation and an optimal precoding matrix from the DL channel estimation.

    MACHINE LEARNING FOR CHANNEL ESTIMATION
    2.
    发明申请
    MACHINE LEARNING FOR CHANNEL ESTIMATION 审中-公开

    公开(公告)号：WO2020091842A2

    公开(公告)日：2020-05-07

    申请号：PCT/US2019/033174

    申请日：2019-05-20

    Applicant: PARALLEL WIRELESS, INC.

    Inventor： CAO, Yang ,  NANDA, Nihar

    IPC: H04L25/02

    Abstract: Systems and methods are disclosed for performing training using superimposed pilot subcarriers to determine training data. The training includes starting with a training duration (T) equal to a number of antennas (M) and running a Convolutional Neural Network (CNN) model using training samples to determine if a testing variance meets a predefined threshold. When the testing variance meets a predefined threshold, then reducing T by one half and repeating the running Convolutional Neural Network (CNN) model until the testing variance fails to meet the predefined threshold. When the testing variance fails to meet the predefined threshold, then multiplying T by two and using the new value of T as the new training duration to be used. Generating a run-time model based on the training data, updating the run-time model with new feedback data received from a User Equipment (UE), producing a DL channel estimation from the run-time model; and producing an optimal precoding matrix from the DL channel estimation.

    DATA PIPELINE FOR SCALABLE ANALYTICS AND MANAGEMENT
    3.
    发明申请
    DATA PIPELINE FOR SCALABLE ANALYTICS AND MANAGEMENT 审中-公开

    公开(公告)号：WO2019157399A1

    公开(公告)日：2019-08-15

    申请号：PCT/US2019/017381

    申请日：2019-02-08

    Applicant: PARALLEL WIRELESS, INC.

    Inventor： NANDA, Nihar ,  PAPA, Steven

    IPC: G06F15/16

    Abstract: Systems and methods are disclosed for performing computations on data at an intelligent data pipe en route to a data store. In one embodiment, a method is disclosed, comprising: receiving metadata regarding a data stream from a data source; performing an analysis of the metadata at a service orchestrator; creating at least one container instance based on the analysis; streaming the data stream from the data source to a data sink via the at least one container; and processing the data stream as it passes through the at least one container instance, thereby enabling application-aware processing of data streams in real time prior to arrival at the data store.

Patent Agency Ranking