An EM algorithm for batch Markovian arrival processes and its comparison to a simpler estimation procedure

DOI10.1023/A:1020981005544zbMath1088.62511OpenAlexW2172003598MaRDI QIDQ1872048

Lothar Breuer

Publication date: 4 May 2003

Published in: Annals of Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1023/a:1020981005544

zbMATH Keywords

EM algorithmmaximum likelihood estimationhidden Markov modelsMarkovian Arrival Process

Mathematics Subject Classification ID

Markov processes: estimation; hidden Markov models (62M05)

Related Items

An EM algorithm for continuous-time bivariate Markov chains ⋮ An \textit{EM} algorithm for the model fitting of Markovian binary trees ⋮ Parameter estimation of discrete multivariate phase-type distributions ⋮ Fitting correlated arrival and service times and related queueing performance ⋮ Transient and stationary losses in a finite-buffer queue with batch arrivals ⋮ QBD Markov chains on binomial-like trees and its application to multilevel feedback queues ⋮ Analysis of a single server queue with interdependence of arrival and service processes -- a semi-Markov approach ⋮ Analysis of an aggregate loss model in a Markov renewal regime ⋮ A Multi-Server Retrial Queueing Model with Poisson Signals ⋮ Compact Markov-modulated models for multiclass trace fitting ⋮ Fitting procedure for the two-state batch Markov modulated Poisson process ⋮ An EM algorithm for platoon arrival processes in discrete time ⋮ Filtering and the EM-Algorithm for the Markovian Arrival Process ⋮ Threshold policies for controlled retrial queues with heterogeneous servers ⋮ Recursive filters for partially observable finite Markov chains ⋮ Risk processes analyzed as fluid queues ⋮ Parallelization of EM-Algorithms for Markovian Arrival Processes ⋮ Fitting bivariate losses with phase-type distributions