Gauss process state-space model optimization algorithm with expectation maximization

A Gauss process state-space model trained in a laboratory cannot accurately simulate a nonlinear system in a non-laboratory environment. To solve this problem, a novel Gauss process state-space model optimization algorithm is proposed by combining the expectation–maximization algorithm with the Gaus...

Full description

Saved in:
Bibliographic Details
Main Authors: Hongqiang Liu, Haiyan Yang, Tao Zhang, Bo Pan
Format: Article
Language:English
Published: Wiley 2019-07-01
Series:International Journal of Distributed Sensor Networks
Online Access:https://doi.org/10.1177/1550147719862217
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850106894519107584
author Hongqiang Liu
Haiyan Yang
Tao Zhang
Bo Pan
author_facet Hongqiang Liu
Haiyan Yang
Tao Zhang
Bo Pan
author_sort Hongqiang Liu
collection DOAJ
description A Gauss process state-space model trained in a laboratory cannot accurately simulate a nonlinear system in a non-laboratory environment. To solve this problem, a novel Gauss process state-space model optimization algorithm is proposed by combining the expectation–maximization algorithm with the Gauss process Rauch–Tung–Striebel smoother algorithm, that is, the EM-GP-RTSS algorithm. First, a theoretical formulation of the Gauss process state-space model is proposed, which is not found in previous references. Second, a Gauss process state-space model optimization framework with the expectation–maximization algorithm is proposed. In the expectation–maximization algorithm, the unknown system state is considered as the lost data, and the maximization of measurement likelihood function is transformed into that of a conditional expectation function. Then, the Gauss process–assumed density filter algorithm and the Gauss process Rauch–Tung–Striebel smoother algorithm are proposed with the Gauss process state-space model defined in this article, in order to calculate the smoothed distribution in the conditional expectation function. Finally, the Monte Carlo numerical integral method is used to obtain the approximate expression of the conditional expectation function. The simulation results demonstrate that the Gauss process state-space model optimized by the EM-GP-RTSS can simulate the system in the non-laboratory environment better than the Gauss process state-space model trained in the laboratory, and can reach or exceed the estimation accuracy of the traditional state-space model.
format Article
id doaj-art-4daffa64ab5c41be8153583fc34887d3
institution OA Journals
issn 1550-1477
language English
publishDate 2019-07-01
publisher Wiley
record_format Article
series International Journal of Distributed Sensor Networks
spelling doaj-art-4daffa64ab5c41be8153583fc34887d32025-08-20T02:38:43ZengWileyInternational Journal of Distributed Sensor Networks1550-14772019-07-011510.1177/1550147719862217Gauss process state-space model optimization algorithm with expectation maximizationHongqiang Liu0Haiyan Yang1Tao Zhang2Bo Pan3PLA Air Force Aviation University, Changchun, P.R. ChinaAir Force Engineering University, Xi’an, P.R. ChinaAir Force Engineering University, Xi’an, P.R. ChinaAir Force Engineering University, Xi’an, P.R. ChinaA Gauss process state-space model trained in a laboratory cannot accurately simulate a nonlinear system in a non-laboratory environment. To solve this problem, a novel Gauss process state-space model optimization algorithm is proposed by combining the expectation–maximization algorithm with the Gauss process Rauch–Tung–Striebel smoother algorithm, that is, the EM-GP-RTSS algorithm. First, a theoretical formulation of the Gauss process state-space model is proposed, which is not found in previous references. Second, a Gauss process state-space model optimization framework with the expectation–maximization algorithm is proposed. In the expectation–maximization algorithm, the unknown system state is considered as the lost data, and the maximization of measurement likelihood function is transformed into that of a conditional expectation function. Then, the Gauss process–assumed density filter algorithm and the Gauss process Rauch–Tung–Striebel smoother algorithm are proposed with the Gauss process state-space model defined in this article, in order to calculate the smoothed distribution in the conditional expectation function. Finally, the Monte Carlo numerical integral method is used to obtain the approximate expression of the conditional expectation function. The simulation results demonstrate that the Gauss process state-space model optimized by the EM-GP-RTSS can simulate the system in the non-laboratory environment better than the Gauss process state-space model trained in the laboratory, and can reach or exceed the estimation accuracy of the traditional state-space model.https://doi.org/10.1177/1550147719862217
spellingShingle Hongqiang Liu
Haiyan Yang
Tao Zhang
Bo Pan
Gauss process state-space model optimization algorithm with expectation maximization
International Journal of Distributed Sensor Networks
title Gauss process state-space model optimization algorithm with expectation maximization
title_full Gauss process state-space model optimization algorithm with expectation maximization
title_fullStr Gauss process state-space model optimization algorithm with expectation maximization
title_full_unstemmed Gauss process state-space model optimization algorithm with expectation maximization
title_short Gauss process state-space model optimization algorithm with expectation maximization
title_sort gauss process state space model optimization algorithm with expectation maximization
url https://doi.org/10.1177/1550147719862217
work_keys_str_mv AT hongqiangliu gaussprocessstatespacemodeloptimizationalgorithmwithexpectationmaximization
AT haiyanyang gaussprocessstatespacemodeloptimizationalgorithmwithexpectationmaximization
AT taozhang gaussprocessstatespacemodeloptimizationalgorithmwithexpectationmaximization
AT bopan gaussprocessstatespacemodeloptimizationalgorithmwithexpectationmaximization