JOINT MODELING OF MULTIPLE TIME SERIES VIA THE BETA PROCESS WITH APPLICATION TO MOTION CAPTURE SEGMENTATION

被引：69

作者：

Fox, Emily B. ^{[1
]}

Hughes, Michael C. ^{[2
]}

Sudderth, Erik B. ^{[2
]}

Jordan, Michael I. ^{[3
,4
]}

机构：

[1] Univ Washington, Dept Stat, Seattle, WA 98195 USA

[2] Brown Univ, Dept Comp Sci, Providence, RI 02912 USA

[3] Univ Calif Berkeley, Dept Stat, Berkeley, CA 94720 USA

[4] Univ Calif Berkeley, Dept EECS, Berkeley, CA 94720 USA

来源：

ANNALS OF APPLIED STATISTICS | 2014年 / 8卷 / 03期

关键词：

Bayesian nonparametrics; beta process; hidden Markov models; motion capture; multiple time series; HIDDEN MARKOV-MODELS; CHAIN MONTE-CARLO; PROCESS MIXTURE MODEL; DIRICHLET PROCESSES; GIBBS SAMPLER;

D O I：

10.1214/14-AOAS742

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

We propose a Bayesian nonparametric approach to the problem of jointly modeling multiple related time series. Our model discovers a latent set of dynamical behaviors shared among the sequences, and segments each time series into regions defined by a subset of these behaviors. Using a beta process prior, the size of the behavior set and the sharing pattern are both inferred from data. We develop Markov chain Monte Carlo (MCMC) methods based on the Indian buffet process representation of the predictive distribution of the beta process. Our MCMC inference algorithm efficiently adds and removes behaviors via novel split-merge moves as well as data-driven birth and death proposals, avoiding the need to consider a truncated model. We demonstrate promising results on unsupervised segmentation of human motion capture data.

引用

页码：1281 / 1313

页数：33

共 49 条

[1] Aligning gene expression time series with time warping algorithms [J].