Marginalized Viterbi Algorithm for Hierarchical Hidden Markov Models

URI http://harp.lib.hiroshima-u.ac.jp/hiroshima-cu/metadata/12386
File
Title
Marginalized Viterbi Algorithm for Hierarchical Hidden Markov Models
Author
氏名 HAYASHI Akira
ヨミ ハヤシ アキラ
別名 林 朗
氏名 IWATA Kazunori
ヨミ イワタ カズノリ
別名 岩田 一貴
氏名 SUEMATSU Nobuo
ヨミ スエマツ ノブオ
別名 末松  伸朗
Subject
Time series data
Hierarchical HMM
Finding the most likely state sequence
Generalized Viterbi algorithm
Marginalized Viterbi algorithm
Abstract

The generalized Viterbi algorithm, a direct extension of the Viterbi algorithm for hidden Markov models (HMMs), has been used to find the most likely state sequence for hierarchical HMMs. However, the generalized Viterbi algorithm finds the most likely whole level state sequence rather than the most likely upper level state sequence. In this paper, we propose a marginalized Viterbi algorithm, which finds the most likely upper level state sequence by marginalizing lower level state sequences. We show experimentally that the marginalized Viterbi algorithm is more accurate than the generalized Viterbi algorithm in terms of upper level state sequence estimation.

Description Peer Reviewed
Journal Title
Pattern Recognition
Volume
46
Issue
12
Spage
3452
Epage
3459
Published Date
2013-12
Publisher
Elsevier
ISSN
00313203
NCID
AA00770025
AA11948832
DOI
10.1016/j.patcog.2013.06.001
Language
eng
NIIType
Journal Article
Text Version
著者版
Rights
@ 2013 Published by Elsevier Ltd.
This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/
Relation URL
Old URI
Set
hiroshima-cu