A Bayesian approach for classification of Markov sources

A Bayesian approach for classification of Markov sources whose parameters are not explicitly known is developed and studied. A universal classifier is derived and shown to achieve, within a constant factor, the minimum error probability in a Bayesian sense. The proposed classifier is based on sequential estimation of the parameters of the sources, and it is closely related to earlier proposed universal tests under the Neyman-Pearson criterion. >

[1]  Michael Gutman,et al.  Asymptotically optimal classification for multiple tests with empirically observed statistics , 1989, IEEE Trans. Inf. Theory.

[2]  Neri Merhav,et al.  A Bayesian classification approach with application to speech recognition , 1991, IEEE Trans. Signal Process..

[3]  Jacob Ziv,et al.  On classification with empirically observed statistics and universal data compression , 1988, IEEE Trans. Inf. Theory.

[4]  Raphail E. Krichevsky,et al.  The performance of universal encoding , 1981, IEEE Trans. Inf. Theory.

[5]  Robert B. Ash,et al.  Information Theory , 2020, The SAGE International Encyclopedia of Mass Media and Society.

[6]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[7]  Arthur Nadas,et al.  Optimal solution of a training problem in speech recognition , 1985, IEEE Trans. Acoust. Speech Signal Process..

[8]  S. Qureshi,et al.  Adaptive equalization , 1982, Proceedings of the IEEE.

[9]  Byoung-Seon Choi,et al.  Conditional limit theorems under Markov conditioning , 1987, IEEE Trans. Inf. Theory.

[10]  Frank Thomson Leighton,et al.  Estimating a probability using finite memory , 1986, IEEE Trans. Inf. Theory.