Learning a Gaussian Mixture Model From Imperfect Training Data for Robust Channel Estimation

被引:5
|
作者
Fesl, Benedikt [1 ]
Turan, Nurettin [1 ]
Joham, Michael [1 ]
Utschick, Wolfgang [1 ]
机构
[1] Tech Univ Munich, Prof Methoden Signalverarbeitung, D-80333 Munich, Germany
关键词
Robust channel estimation; imperfect data; generative model; Gaussian mixture; OFDM system;
D O I
10.1109/LWC.2023.3260443
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this letter, we propose a Gaussian mixture model (GMM)-based channel estimator which is learned on imperfect training data, i.e., the training data are solely comprised of noisy and sparsely allocated pilot observations. In a practical application, recent pilot observations at the base station (BS) can be utilized for training. This is in sharp contrast to state-of-the-art machine learning (ML) techniques where a training dataset consisting of perfect channel state information (CSI) samples is a prerequisite, which is generally unaffordable. In particular, we propose an adapted training procedure for fitting the GMM which is a generative model that represents the distribution of all potential channels associated with a specific BS cell. To this end, the necessary modifications of the underlying expectation-maximization (EM) algorithm are derived. Numerical results show that the proposed estimator performs close to the case where perfect CSI is available for the training and exhibits a higher robustness against imperfections in the training data as compared to state-of-the-art ML techniques.
引用
收藏
页码:1066 / 1070
页数:5
相关论文
共 50 条
  • [1] Robust estimation for an imperfect test and repair model using Gaussian mixtures
    Wilson, Simon P.
    Goyal, Suresh
    SAFETY, RELIABILITY AND RISK ANALYSIS: THEORY, METHODS AND APPLICATIONS, VOLS 1-4, 2009, : 949 - +
  • [2] Gaussian Mixture Model Implementation for Population Stratification Estimation from Genomics Data
    Budiarto, Arif
    Mahesworo, Bharuno
    Hidayat, Alam Ahmad
    Nurlaila, Ika
    Pardamean, Bens
    5TH INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND COMPUTATIONAL INTELLIGENCE 2020, 2021, 179 : 202 - 210
  • [3] Robust image reconstruction enhancement based on Gaussian mixture model estimation
    Zhao, Fan
    Zhao, Jian
    Han, Xizhen
    Wang, He
    Liu, Bochao
    JOURNAL OF ELECTRONIC IMAGING, 2016, 25 (02)
  • [4] Collaborative Spectrum Sensing with Imperfect Gaussian Channel Estimation
    Chen, Yunfei
    Beaulieu, Norman C.
    2009 IEEE WIRELESS COMMUNICATIONS & NETWORKING CONFERENCE, VOLS 1-5, 2009, : 498 - +
  • [5] PARAMETER ESTIMATION OF GAUSSIAN MIXTURE MODEL UTILIZING BOUNDARY DATA
    Omachi, Masako
    Omachi, Shinichiro
    Aso, Hirotomo
    Saito, Tsuneo
    PROCEEDINGS OF THE 38TH INTERNATIONAL CONFERENCE ON COMPUTERS AND INDUSTRIAL ENGINEERING, VOLS 1-3, 2008, : 291 - 297
  • [6] Channel Estimation for Massive MIMO Using Gaussian-Mixture Bayesian Learning
    Institute of Communications Engineering, National Sun Yat-sen University, Kaohsiung
    804, Taiwan
    不详
    210096, China
    不详
    WC1E 7JE, United Kingdom
    不详
    802, Taiwan
    不详
    310, Taiwan
    IEEE Trans. Wireless Commun., 3 (1356-1368):
  • [7] Channel Estimation for Massive MIMO Using Gaussian-Mixture Bayesian Learning
    Wen, Chao-Kai
    Jin, Shi
    Wong, Kai-Kit
    Chen, Jung-Chieh
    Ting, Pangan
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2015, 14 (03) : 1356 - 1368
  • [8] PARAMETER ESTIMATION OF GAUSSIAN MIXTURE MODEL BASED ON VARIATIONAL BAYESIAN LEARNING
    Zhao, Linchang
    Shang, Zhaowei
    Qin, Anyong
    Tang, Yuan Yan
    PROCEEDINGS OF 2018 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS (ICMLC), VOL 1, 2018, : 99 - 104
  • [9] Improved Gaussian mixture model and Gaussian mixture regression for learning from demonstration based on Gaussian noise scattering
    Feng, Chunhua
    Liu, Zhuang
    Li, Weidong
    Lu, Xin
    Jing, Yanguo
    Ma, Yongsheng
    ADVANCED ENGINEERING INFORMATICS, 2025, 65
  • [10] DeepGUM: Learning Deep Robust Regression with a Gaussian-Uniform Mixture Model
    Lathuiliere, Stephane
    Mesejo, Pablo
    Alameda-Pineda, Xavier
    Horaud, Radu
    COMPUTER VISION - ECCV 2018, PT V, 2018, 11209 : 205 - 221