On maximum likelihood identification of errors-in-variables models

作者: Giulio Bottegal , Riccardo S. Risuleo , Mohsen Zamani , Brett Ninness , Håkan Hjalmarsson

DOI: 10.1016/J.IFACOL.2017.08.634

关键词: Expectation–maximization algorithmLikelihood functionEstimation theoryAlgorithmMaximum likelihood sequence estimationErrors-in-variables modelsRestricted maximum likelihoodMarginal likelihoodM-estimatorComputer science

摘要: Abstract In this paper, we revisit maximum likelihood methods for identification of errors-in-variables systems. We assume that the system admits a parametric description, and input is stochastic ARMA process. The cost function associated with criterion minimized by introducing new iterative solution scheme based on expectation-maximization method, which proves fast easily implementable. Numerical simulations show effectiveness proposed method.

参考文章(26)
XIAO-LI MENG, DONALD B. RUBIN, Maximum likelihood estimation via the ECM algorithm: A general framework Biometrika. ,vol. 80, pp. 267- 278 ,(1993) , 10.1093/BIOMET/80.2.267
Torsten Söderström, Extending the Frisch scheme for errors‐in‐variables identification to correlated output noise International Journal of Adaptive Control and Signal Processing. ,vol. 22, pp. 55- 73 ,(2008) , 10.1002/ACS.961
Torsten Söderström, Umberto Soverini, Kaushik Mahata, Perspectives on errors-in-variables estimation for dynamic systems Signal Processing. ,vol. 82, pp. 1139- 1154 ,(2002) , 10.1016/S0165-1684(02)00252-9
B. D. O. Anderson, M. Deistler, IDENTIFIABILITY IN DYNAMIC ERRORS‐IN‐VARIABLES MODELS Journal of Time Series Analysis. ,vol. 5, pp. 1- 13 ,(1984) , 10.1111/J.1467-9892.1984.TB00374.X
S. Beghelli, R.P. Guidorzi, U. Soverini, The Frisch scheme in dynamic system identification Automatica. ,vol. 26, pp. 171- 176 ,(1990) , 10.1016/0005-1098(90)90168-H
Stuart Gibson, Brett Ninness, Robust maximum-likelihood estimation of multivariable dynamic systems Automatica. ,vol. 41, pp. 1667- 1682 ,(2005) , 10.1016/J.AUTOMATICA.2005.05.008
Jaafar ALMutawa, Identification of errors-in-variables models using the EM algorithm IFAC Proceedings Volumes. ,vol. 41, pp. 1378- 1383 ,(2008) , 10.3182/20080706-5-KR-1001.00236