Change-Point Detection in Time-Series Data by Relative Density-Ratio Estimation
The objective of change-point detection is to discover abrupt property changes lying behind time-series data. In this paper, we present a novel statistical change-point detection algorithm that is based on non-parametric divergence estimation between two retrospective segments. Our method uses the relative Pearson divergence as a divergence measure, and it is accurately and efficiently estimated by a method of direct density-ratio estimation. Through experiments on real-world human-activity sensing, speech, and Twitter datasets, we demonstrate the usefulness of the proposed method.
Keywordschange-point detection distribution comparison relative density-ratio estimation kernel methods time-series data
- 1.Basseville, M., Nikiforov, I.V.: Detection of Abrupt Changes: Theory and Application. Prentice-Hall, Inc., Upper Saddle River (1993)Google Scholar
- 5.Kawahara, Y., Yairi, T., Machida, K.: Change-point detection in time-series data based on subspace identification. In: Proceedings of the 7th IEEE International Conference on Data Mining, pp. 559–564 (2007)Google Scholar
- 11.Yamada, M., Suzuki, T., Kanamori, T., Hachiya, H., Sugiyama, M.: Relative density-ratio estimation for robust distribution comparison. Advances in Neural Information Processing Systems 24, 594–602 (2011)Google Scholar
- 13.Csiszár, I.: Information-type measures of difference of probability distributions and indirect observation. Studia Scientiarum Mathematicarum Hungarica 2, 229–318 (1967)Google Scholar
- 14.Liu, S., Yamada, M., Collier, N., Sugiyama, M.: Change-point detection in time-series data by relative density-ratio estimation. arXiv 1203.0453 (2012)Google Scholar