Optimal Segmentation of Random Sequences

Article type: Research Article

Authors: Lipeika, Antanas

Affiliations: Institute of Mathematics and Informatics, Akademijos 4, 2600 Vilnius, Lithuania. E-mail: [email protected]

Abstract: This paper deals with maximum likelihood and least square segmentation of autoregressive random sequences with abruptly changing parameters. Conditional distribution of the observations has been derived. Objective function was modified to the form suitable to apply dynamic programming method for its optimization. Expressions of Bellman functions for this case were obtained. Performance of presented approach is illustrated with simulation examples and segmentation of speech signals examples.

Keywords: optimal segmentation, maximum likelihood, least square, dynamic programming

DOI: 10.3233/INF-2000-11303

Journal: Informatica, vol. 11, no. 3, pp. 243-256, 2000