Title :
Classification of multidimensional observation sequences described by Hidden Markov Models
Author :
Gultyaeva, T.A. ; Kokoreva, V.V.
Author_Institution :
Novosibirsk State Tech. Univ., Novosibirsk, Russia
Abstract :
This article analyses several approaches to classification of multidimensional observation sequences described by Hidden Markov Models. It demonstrates good efficiency of method based on HMM parameter derivatives when competing classes are close in some way.
Keywords :
hidden Markov models; image classification; image sequences; HMM parameter derivatives; hidden Markov models; multidimensional observation sequences; Hidden Markov models; Markov processes; Probability density function; Random processes; Speech recognition; Support vector machine classification; Training; Hidden Markov Models; classification of sequences; derivatives;
Conference_Titel :
Actual Problems of Electronics Instrument Engineering (APEIE), 2014 12th International Conference on
Conference_Location :
Novosibirsk
Print_ISBN :
978-1-4799-6019-4
DOI :
10.1109/APEIE.2014.7040746
