Maximum Likelihood identification for Linear Dynamic Systems with finite Gaussian mixture noise distribution

被引:1
|
作者
Bittner, Gustavo [1 ]
Orellana, Rafael [1 ]
Carvajal, Rodrigo [1 ]
Aguero, Juan C. [1 ]
机构
[1] Univ Tecn Federico Santa Maria, Valparaiso, Chile
关键词
Gaussian Mixture Model; Linear Dynamical Systems; Maximum Likelihood; Non-Gaussian Noise Distribution; TRACKING;
D O I
10.1109/chilecon47746.2019.8987642
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper considers the identification of a linear dynamic system driven by a non -Gaussian noise distribution. The noise is approximated by a finite Gaussian mixture, whilst the parameters of the system and the parameters that approximate the noise distribution are simultaneously estimated using the principle of Maximum Likelihood. To this end, a global optimization algorithm is utilized to solve the resulting non-convex optimization problem. It is shown that our approach improves the accuracy of the estimates, when compared with classic estimation techniques such as the prediction error method (PEM), in terms of covariance of the estimation error, while also obtaining an approximation of the noise distribution. The benefits of the proposed technique are illustrated by numerical simulations.
引用
收藏
页数:7
相关论文
共 50 条
  • [21] Gaussian maximum likelihood blind multichannel multiuser identification
    Deneire, L
    Slock, DTM
    [J]. 48TH IEEE VEHICULAR TECHNOLOGY CONFERENCE, VOLS 1-3, 1998, : 189 - 193
  • [22] Maximum likelihood least squares identification for systems with autoregressive moving average noise
    Wang, Wei
    Ding, Feng
    Dai, Jiyang
    [J]. APPLIED MATHEMATICAL MODELLING, 2012, 36 (05) : 1842 - 1853
  • [23] Maximum likelihood binary detection in improper complex Gaussian noise
    Aghaei, Amirhossein S.
    Plataniotis, Konstantinos N.
    Pasupathy, Subbarayan
    [J]. 2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 3209 - 3212
  • [24] ON THE NONPARAMETRIC MAXIMUM LIKELIHOOD ESTIMATOR FOR GAUSSIAN LOCATION MIXTURE DENSITIES WITH APPLICATION TO GAUSSIAN DENOISING
    Saha, Sujayam
    Guntuboyina, Adityanand
    [J]. ANNALS OF STATISTICS, 2020, 48 (02): : 738 - 762
  • [25] Performance analysis of MIMO maximum likelihood receivers with channel correlation, colored Gaussian noise, and linear prefiltering
    Kiessling, M
    Speidel, J
    Geng, N
    Reinhardt, M
    [J]. 2003 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS, VOLS 1-5: NEW FRONTIERS IN TELECOMMUNICATIONS, 2003, : 3026 - 3030
  • [26] Maximum likelihood estimation of Gaussian mixture models without matrix operations
    Hien D. Nguyen
    Geoffrey J. McLachlan
    [J]. Advances in Data Analysis and Classification, 2015, 9 : 371 - 394
  • [27] Two Iterative Algorithms for Maximum Likelihood Esitimation of Gaussian Mixture Parameter
    Liu, Feng
    Wang, Pingbo
    Wang, Yu
    Huang, Jinxin
    [J]. 2013 NINTH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION (ICNC), 2013, : 1454 - 1458
  • [28] Maximum likelihood estimation of Gaussian mixture models without matrix operations
    Nguyen, Hien D.
    McLachlan, Geoffrey J.
    [J]. ADVANCES IN DATA ANALYSIS AND CLASSIFICATION, 2015, 9 (04) : 371 - 394
  • [29] Maximum likelihood estimation of Gaussian mixture models using stochastic search
    Ari, Caglar
    Aksoy, Selim
    Arikan, Orhan
    [J]. PATTERN RECOGNITION, 2012, 45 (07) : 2804 - 2816
  • [30] A MAXIMUM-LIKELIHOOD IDENTIFICATION METHOD FOR STABLE AUTOREGRESSIVE LINEAR-SYSTEMS
    INABA, H
    SHIOYA, I
    ICHINO, M
    [J]. INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE, 1982, 13 (01) : 21 - 37