Training Hidden Markov Model Structure with Genetic Algorithm for Human Motion Pattern Classification

Author

Manabe, Shuhei ; Hatanaka, Toshiharu ; Uosaki, Katsuji ; Tabuchi, Noriyuki ; Matsuo, Tomoyuki ; Hashizume, Ken

Author_Institution

Dept. of Inf. & Phys. Sci., Osaka Univ.

fYear

2006

Firstpage

618

Lastpage

622

Abstract

Physical exercise classification method by hidden Markov model (HMM) is considered in this study. The aim of this study is to discuss the availability of HMM based motion modeling in order to compare human skills. In this paper, a preprocessing technique for observed human motion by self-organizing map (SOM) to label a motion characteristic is proposed. Then, HMM construction method by using genetic algorithm (GA) with Baum-Welch algorithm, modified crossover and mutation is introduced. Simulation studies are carried out for bat swing motions. It is shown that the proposed approach has an ability to recognize bat swing motions

Keywords

genetic algorithms; hidden Markov models; pattern classification; self-organising feature maps; Baum-Welch algorithm; bat swing motion; genetic algorithm; hidden Markov model; human motion pattern classification; self-organizing map; Biological system modeling; Conference management; Genetic algorithms; Hidden Markov models; Humans; Information management; Management training; Pattern classification; Pattern recognition; Stochastic processes; Hidden markov model; bayesian information criterion; genetic algorithm; self-organizing map;

fLanguage

English

Publisher

ieee

Conference_Titel

SICE-ICASE, 2006. International Joint Conference

Conference_Location

Busan

Print_ISBN

89-950038-4-7

Electronic_ISBN

89-950038-5-5

Type

conf

DOI

10.1109/SICE.2006.315709

Filename

4108905