Introduction to the concept of structural HMM: application to mining customers´ preferences in automotive design

Author

Bouchaffra, D. ; Tan, J.

Author_Institution

Dept. of Comput. Sci. & Eng., Oakland Univ., Rochester, MI, USA

Volume

2

fYear

2004

fDate

23-26 Aug. 2004

Firstpage

493

Abstract

We have introduced in this paper the concept of structural hidden Markov models (SHMM). This new paradigm adds the syntactical (or structural) component to the traditional HMM. SHMM introduce relationships between the visible observations of a sequence. These observations are related because they are viewed as evidences of a same conclusion in a rule of inference. We have applied this novel concept to predict customer´s preferences for automotive designs. SHMM has outperformed both the k-nearest neighbors and the neural network classifiers with an additional 12% increase in accuracy.

Keywords

automotive engineering; data mining; design; hidden Markov models; pattern classification; production engineering computing; automotive design; customer preference mining; structural HMM; structural hidden Markov models; syntactical component; Amino acids; Application software; Automotive engineering; Character generation; Hidden Markov models; Humans; Pattern recognition; Proteins; Sequences; Statistics;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on

ISSN

1051-4651

Print_ISBN

0-7695-2128-2

Type

conf

DOI

10.1109/ICPR.2004.1334274

Filename

1334274