Parameters identification of a time-varying stochastic dynamic systems using Viterbi algorithm

Autor:	Tarik Al-Ani, Yskander Hamam
Rok vydání:	1996
Předmět:	symbols.namesake Noise Mathematical optimization Iterative Viterbi decoding Computer science Stochastic process symbols Forward algorithm Hidden Markov model Viterbi algorithm Algorithm Stochastic programming Soft output Viterbi algorithm
Zdroj:	System Modelling and Optimization ISBN: 9781475766714
DOI:	10.1007/978-0-387-34897-1_69
Popis:	An on-line non-linear parameter identification algorithm is introduced. The system parameters are considered to be time varying. This algorithm is based on Viterbi algorithm applied to finite state models. It allows the identification based on the dynamic continuous output of the system. The algorithm is first applied to first order dynamic systems, then it is extended to a higer order systems. In order to reduce the complexity of the parameters discretisation, these parameters are supposed to be decoupled with respect to noise. Preliminary Simulation results are given.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::0a3a88ffd0809427a62f938d61c78857 https://doi.org/10.1007/978-0-387-34897-1_69 Zobrazit plný text záznamu