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 based on non-parametric divergence estimation between time-series samples from two retrospective segments. Our...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neural networks Jg. 43; S. 72 - 83
Hauptverfasser: Liu, Song, Yamada, Makoto, Collier, Nigel, Sugiyama, Masashi
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Kidlington Elsevier Ltd 01.07.2013
Elsevier
Schlagworte:
Algorithms
Applied sciences
Change-point detection
Computer science; control theory; systems
Data processing. List processing. Character string processing
Distribution comparison
Divergence
Exact sciences and technology
Gene Expression Profiling - methods
Humans
Inference from stochastic processes; time series analysis
Kernel methods
Mathematics
Memory organisation. Data processing
Messages
Models, Statistical
Neural networks
Probability and statistics
Relative density-ratio estimation
Retrospective Studies
Samples
Sciences and techniques of general use
Segments
Software
Specific Gravity
Speech
Statistical analysis
Statistics
Time Factors
Time-series data
Change-point detection
Kernel methods
Time-series data
Distribution comparison
Relative density-ratio estimation
Statistical analysis
Divergence
Event detection
Time series
Non parametric estimation
Social network
Change point
Kernel method
Lying
Human activity
Probability density function
Web site
ISSN:0893-6080, 1879-2782, 1879-2782
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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 based on non-parametric divergence estimation between time-series samples from 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 artificial and real-world datasets including human-activity sensing, speech, and Twitter messages, we demonstrate the usefulness of the proposed method.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0893-6080
1879-2782
1879-2782
DOI:10.1016/j.neunet.2013.01.012