A model based appraoch to sequence clustering
There is a more recent version of this eprint available. Click here to view it.
We present a Hidden Markov Model-based approach to cluster sequences. This problem is adressed in term of learning Hidden Markov Models (HMM) structure from data. Using a top-down approach, we iteratively simplify an initial HMM that consists in a mixture of as many left-right HMMs as training sequences. Our approach allows to learn, in an unsupervised manner, the cluster models that best represent training data. We provide experimental results on two different application fields, on-line handwriting signals and hypermedia navigation patterns.
Available Versions of this Item