Finding Behavior Patterns from Temporal Data using Hidden Markov Model based Unsupervised Classification

Cen Li and Gautam Biswas

Department of Computer Science, Vanderbilt University
Box 1679, Station B,
Nashville, TN 37235

in Proceedings of the ICSC'99 Advances in Intelligent Data Analysis(AIDA'99),
Rochester, NY, June 22-25, 1999.

This paper describes a clustering methodology for temporal data using hidden Markov model (HMM) representation. The proposed method improves upon existing HMM based clustering methods in two ways:

it enables HMMs to dynamically change its model structure to obtain a better fit model for data during clstering process
it provides objective criterion function to automatically select the optimal clustering partition

The algorithm is presented in terms of four nested levels of searches:

the search for the optimal number of clusters in a partition
the search for the optimal structure
the search for the optimal HMM structure for each cluster
the search for the optimal parameter values for each HMM

Preliminary experiments with artifically generated data demonstrate the effectiveness of the proposed methodology.

Full Paper (PDF 180224 bytes).