Adaptation in symbolic dynamic systems for pattern classification

Author

Yicheng Wen ; Mukherjee, Kingshuk ; Ray, Avik

Author_Institution

Pennsylvania State Univ., University Park, PA, USA

fYear

2012

fDate

27-29 June 2012

Firstpage

697

Lastpage

702

Abstract

This paper addresses the problem of pattern classification in the symbolic dynamic domain, where the patterns of interest are represented by probabilistic finite state automata (PFSA) with possibly dissimilar algebraic structures. A combination of Dirichlet and multinomial distributions is used to model the uncertainties due to the finite length approximation of symbol strings. The classifier algorithm follows the structure of a Bayes model and has been validated on a simulation test bed.

Keywords

Bayes methods; approximation theory; finite state machines; pattern classification; string matching; Bayes model; Dirichlet distributions; PFSA; dissimilar algebraic structures; finite length approximation; multinomial distributions; pattern classification; patterns of interest; probabilistic finite state automata; symbol strings; symbolic dynamic systems; Manganese; Nickel; Silicon; Testing; Time series analysis; Training; Vectors; Probabilistic Finite State Automata; Statistical Pattern Classification; Symbolic Dynamics;

fLanguage

English

Publisher

ieee

Conference_Titel

American Control Conference (ACC), 2012

Conference_Location

Montreal, QC

ISSN

0743-1619

Print_ISBN

978-1-4577-1095-7

Electronic_ISBN

0743-1619

Type

conf

DOI

10.1109/ACC.2012.6314678

Filename

6314678