An Incremental Change Detection Test Based on Density Difference Estimation

doi:10.1109/TSMC.2017.2682502

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 深度强化学习

	An Incremental Change Detection Test Based on Density Difference Estimation
	Bu, Li1,2 ; Zhao, Dongbin1,2 ; Alippi, Cesare 3,4
刊名	IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
	2017-10-01
卷号	49 期号:10 页码:2714-2726
关键词	Change Detection Incremental Computing Incremental Least Squares Density Difference Change Detection Method (Lsdd-inc) Probability Density Function (Pdf)-free
DOI	10.1109/TSMC.2017.2682502
文献子类	Article
英文摘要	We propose incremental least squares density difference (LSDD) change detection method, an incremental test to detect changes in stationarity based on the difference between the unknown prechange and the post-change probability density functions (pdfs). The method is computationally light and, hence, adequate to process continuous datastreams, as those emerging from the Internet of Things and the big data framework. The incremental change detection test operates on two nonoverlapping data windows to estimate the LSDD between the two pdfs. We construct a theoretical framework that shows how the distribution of LSDD values follows a linear combination of chi(2) distributions and provides thresholds to control false positive rates. The proposed test can operate online, with needed estimates and thresholds computed incrementally as fresh samples come. Comprehensive experiments validate the effectiveness of the test both in detecting abrupt and drift types of changes.
WOS关键词	STATISTICAL PROCESS-CONTROL ; CLASSIFIERS ; SHIFTS ; MODEL
WOS研究方向	Automation & Control Systems ; Computer Science
语种	英语
WOS记录号	WOS:000411098200009
资助机构	National Natural Science Foundation of China(61573353 ; 61533017 ; 61603382)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/14329]
专题	复杂系统管理与控制国家重点实验室_深度强化学习
通讯作者	Zhao, Dongbin
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 3.Politecn Milan, I-20133 Milan, Italy 4.Univ Svizzera Italiana, CH-6904 Lugano, Switzerland
推荐引用方式 GB/T 7714	Bu, Li,Zhao, Dongbin,Alippi, Cesare. An Incremental Change Detection Test Based on Density Difference Estimation[J]. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,2017,49(10):2714-2726.
APA	Bu, Li,Zhao, Dongbin,&Alippi, Cesare.(2017).An Incremental Change Detection Test Based on Density Difference Estimation.IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,49(10),2714-2726.
MLA	Bu, Li,et al."An Incremental Change Detection Test Based on Density Difference Estimation".IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 49.10(2017):2714-2726.