Change-Point Detection in Time-Series Data by Relative Density-Ratio Estimation

被引：0

作者：

Liu, Song ^{[1
]}

Yamada, Makoto ^{[2
]}

Collier, Nigel ^{[3
]}

Sugiyama, Masashi ^{[1
]}

机构：

[1] Tokyo Inst Technol, 2-12-1 O Okayama, Tokyo 1528552, Japan

[2] Nippon Telegraph & Tel Corp, Commun Sci Lab, Kyoto 6190237, Japan

[3] Natl Inst Informat, Tokyo 1018430, Japan

来源：

STRUCTURAL, SYNTACTIC, AND STATISTICAL PATTERN RECOGNITION | 2012年 / 7626卷

关键词：

change-point detection; distribution comparison; relative density-ratio estimation; kernel methods; time-series data;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：363 / 372

页数：10

共 50 条

[1] Change-point detection in time-series data by relative density-ratio estimation
Liu, Song
Yamada, Makoto
Collier, Nigel
Sugiyama, Masashi
NEURAL NETWORKS, 2013, 43 : 72 - 83
[2] Generalization of change-point detection in time series data based on direct density ratio estimation
Hushchyn, Mikhail
Ustyuzhanin, Andrey
JOURNAL OF COMPUTATIONAL SCIENCE, 2021, 53
[3] Change-point detection in time-series data based on subspace identification
Kawahara, Yoshinobu
Yairi, Takehisa
Machida, Kazuo
ICDM 2007: PROCEEDINGS OF THE SEVENTH IEEE INTERNATIONAL CONFERENCE ON DATA MINING, 2007, : 559 - 564
[4] Change-point detection in multivariate time-series data by Recurrence Plot
1600, World Scientific and Engineering Academy and Society, Ag. Ioannou Theologou 17-23, Zographou, Athens, 15773, Greece (13):
[5] A TEST FOR DETECTING A CHANGE-POINT IN TIME-SERIES
PICARD, D
COMPTES RENDUS DE L ACADEMIE DES SCIENCES SERIE I-MATHEMATIQUE, 1982, 295 (10): : 591 - 594
[6] NON-PARAMETRIC ONLINE CHANGE-POINT DETECTION WITH KERNEL LMS BY RELATIVE DENSITY RATIO ESTIMATION
Bouchikhi, Ikram
Ferrari, Andre
Richard, Cedric
Bourrier, Anthony
Bernot, Marc
2018 IEEE STATISTICAL SIGNAL PROCESSING WORKSHOP (SSP), 2018, : 538 - 542
[7] OPTIMAL CHANGE-POINT ESTIMATION IN TIME SERIES
Chan, Ngai Hang
Ng, Wai Leong
Yau, Chun Yip
Yu, Haihan
ANNALS OF STATISTICS, 2021, 49 (04): : 2336 - 2355
[8] A Novel Method of AOT Evaluation for Change-Point Detection on Synthetic Time-series
Qi, Jin-Peng
Zhu, Ying
Pu, Fang
2018 CHINESE AUTOMATION CONGRESS (CAC), 2018, : 2023 - 2027
[9] A Non-Parametric Approach for Change-Point Detection of Multi-Parameters in Time-Series Data
Hu, Y. M.
Yang, C. X.
Liang, Z. M.
Luo, X. Y.
Huang, Y. X.
Tang, C.
JOURNAL OF ENVIRONMENTAL INFORMATICS, 2023, 42 (01) : 65 - 74
[10] SAR-Based Change Detection over Power line corridors by Relative Density-Ratio Estimation
Xu, Dewei
Yang, Wen
Yin, Xiaoshuang
Liao, Mingsheng
10TH EUROPEAN CONFERENCE ON SYNTHETIC APERTURE RADAR (EUSAR 2014), 2014,

← 1 2 3 4 5 →