A Bayesian Approach for Classicification of Continuous-Time Markov Sources

A Bayesian approach for classification of Markov source is developed and studied. Each of M sources is described by a continuous-time, discrete-state Markov chain All states and times of transitions between states can be observed perfectly but the transition rate matrices which establish the parameters of the sources are not known a priori. A Bayesian training samples that consist of a member function from each chain. This leads to an iterative computationally simple classification algorithm.