Date of Award


Degree Name

Master of Science


Computer Science

First Advisor

Dr. Elise de Doncker

Second Advisor

Dr. Robert Trenary

Third Advisor

Dr. John Kapenga


Machine learning, time-series, activity recognition, Hidden Markov Models, structure diversity

Access Setting

Masters Thesis-Abstract Only

Restricted to Campus until



Time series often feature structure that is known a priori and easily described using natural language terms such as repetitive, symmetric, seasonal, and self-similar. However, the typical conjugate priors used in Bayesian analysis do not capture such complex phenomena well. As a result of this mismatch, known structure is modeled poorly or completely ignored. Focusing on time series with repetitive structure, this thesis proposes to overcome this problem by reducing rather than in- creasing the capacity of a well know time series model, the Hidden Markov Model. Through a careful choice in the way model capacity is reduced the model is forced to use its latent variables in an interpretable way which accurately reflects known structure. In addition to increased modeling performance, the lower capacity model admits reduced complexity inference and parameter estimation procedures. Experimental results are presented demonstrating the effectiveness of this approach in both supervised and unsupervised learning contexts.