知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

20 records (took 0.018 seconds)

    HARDWARE ALLOCATION IN RFIC BASED ON MACHINE LEARNING
    1.
    发明公开
    HARDWARE ALLOCATION IN RFIC BASED ON MACHINE LEARNING 审中-公开

    公开(公告)号：US20230297803A1

    公开(公告)日：2023-09-21

    申请号：US17834845

    申请日：2022-06-07

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Shailesh CHAUDHARI ,  Hyukjoon KWON ,  Kee-Bong SONG ,  Dongwoon BAI

    IPC: G06K19/07 ,  G06N3/08

    CPC classification number: G06K19/0723 ,  G06N3/08

    Abstract: A system and method for configuring an RF network based on machine learning. In some embodiments, the method includes: receiving, by a first neural network, a first state and a first state transition, the first state including: one or more identifiers for available active ports, and a set of available connections between two or more circuit elements, each of the circuit elements being one of: (1) a first circuit type, (2) a second circuit type that operatively connects a circuit element of the first circuit type to one of the available active ports, and (3) the available active ports; and generating, by the first neural network, a first estimated quality value, for the first state transition.

    SYSTEMS AND METHODS FOR NOISE POWER ESTIMATION IN WIRELESS COMMUNICATIONS
    3.
    发明申请
    SYSTEMS AND METHODS FOR NOISE POWER ESTIMATION IN WIRELESS COMMUNICATIONS 有权

    公开(公告)号：US20250132955A1

    公开(公告)日：2025-04-24

    申请号：US18888144

    申请日：2024-09-17

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Mojtaba RAHMATI ,  Hyukjoon KWON ,  Dongwoon BAI

    IPC: H04L25/02 ,  H04L25/03

    Abstract: A system and a method are disclosed for noise power estimation in wireless communications. In some embodiments, the method includes: receiving a reference signal; generating a first channel estimate, based on the reference signal; calculating a first noise power estimate; calculating a corrected noise power estimate by applying a multiplicative correction based on a linear minimum mean square error filter weight to the first noise power estimate; receiving a transmission; and decoding the transmission, based on the corrected noise power estimate.

    APPARATUS FOR AND METHOD OF CHANNEL QUALITY PREDICTION THROUGH COMPUTATION OF MULTI-LAYER CHANNEL QUALITY METRIC
    6.
    发明申请
    APPARATUS FOR AND METHOD OF CHANNEL QUALITY PREDICTION THROUGH COMPUTATION OF MULTI-LAYER CHANNEL QUALITY METRIC 有权
    通过计算多层通道质量标准的通道质量预测的方法和方法

    公开(公告)号：US20160261316A1

    公开(公告)日：2016-09-08

    申请号：US15040437

    申请日：2016-02-10

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Dongwoon BAI ,  Jungwon LEE

    IPC: H04B7/04 ,  H04L1/20 ,  H04B17/309

    CPC classification number: H04B7/0413 ,  H04B17/309 ,  H04L1/203

    Abstract: An apparatus and method for a transceiver are provided. The apparatus for the transceiver includes a multiple input multiple output (MIMO) antenna; a transceiver connected to the MIMO antenna; and a processor configured to measure channel gain Hk, based on the received signal, where k is a sample index from 1 to K, Hk is an m×n matrix of complex channel gain known to the transceiver, measure noise variance σ2 of a channel, calculate a per-sample channel quality metric q(Hk, σ2) using at least one bound of mutual information; reduce a dimension of a channel quality metric vector (q(H1, σ2), . . . , q(HK, σ2)) by applying a dimension reduction function g(.); and estimate a block error rate (BLER) as a function of a dimension reduced channel quality metric g(q(H1, σ2), . . . , q(HK, σ2)).

    Abstract translation: 提供了一种用于收发器的装置和方法。 用于收发器的装置包括多输入多输出（MIMO）天线; 连接到MIMO天线的收发器; 以及处理器，被配置为基于接收信号来测量信道增益H k，其中k是从1到K的采样索引，Hk是收发器已知的复信道增益的m×n矩阵，测量信道的噪声方差σ2 ，使用互信息的至少一个界限来计算每采样信道质量度量q（Hk，σ2）; 通过应用维数减小函数g（。）来减小信道质量度量向量（q（H1，σ2），...，q（HK，σ2））的维数。 并且作为尺寸减小的信道质量度量g（q（H1，σ2），...，q（HK，σ2））的函数来估计块错误率（BLER）。

    APPARATUS AND METHOD FOR MODELING RANDOM PROCESS USING REDUCED LENGTH LEAST-SQUARES AUTOREGRESSIVE PARAMETER ESTIMATION
    10.
    发明申请
    APPARATUS AND METHOD FOR MODELING RANDOM PROCESS USING REDUCED LENGTH LEAST-SQUARES AUTOREGRESSIVE PARAMETER ESTIMATION 审中-公开

    公开(公告)号：US20180196906A1

    公开(公告)日：2018-07-12

    申请号：US15465181

    申请日：2017-03-21

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Binnan ZHUANG ,  Dongwoon BAI ,  Jungwon LEE

    IPC: G06F17/50

    CPC classification number: G06F17/5036 ,  G06F17/5072 ,  G06F17/5081

    Abstract: An apparatus and method for modelling a random process using reduced length least-squares autoregressive parameter estimation is herein disclosed. The apparatus includes an autocorrelation processor, configured to generate or estimate autocorrelations of length m for a stochastic process, where m is an integer; and a least-squares (LS) estimation processor connected to the autocorrelation processor and configured to model the stochastic process by estimating pth order autoregressive (AR) parameters using LS regression, where p is an integer much less than m. The method includes generating, by an autocorrelation processor, autocorrelations of length m for a stochastic process, where m is an integer; and modelling the stochastic process, by a least-squares estimation processor, by estimating pth order autoregressive (AR) parameters by least-squares (LS) regression, where p is an integer much less than m.

Patent Agency Ranking