Extraction of Hierarchical Behavior Patterns Using a Non-parametric Bayesian Approach

Extraction of complex temporal patterns, such as human behaviors, from time series data is a challenging yet important problem. The double articulation analyzer has been previously proposed by Taniguchi et al. to discover a hierarchical structure that leads to complex temporal patterns. It segments time series into hierarchical state subsequences, with the higher level and the lower level analogous to words and phonemes, respectively. The double articulation analyzer approximates the sequences in the lower level by linear functions. However, it is not suitable to model real behaviors since such a linear function is too simple to represent their non-linearity even after the segmentation. Thus, we propose a new method that models the lower segments by fitting autoregressive functions that allows for more complex dynamics, and discovers a hierarchical structure based on these dynamics. To achieve this goal, we propose a method that integrates the beta process-autoregressive hidden Markov model and the double articulation by nested Pitman-Yor language model. Our results showed that the proposed method extracted temporal patterns in both low and high levels from synthesized datasets and a motion capture dataset with smaller errors than those of the double articulation analyzer.