Online detection of anomaly behaviors based on multidimensional trajectories

doi:10.1016/j.inffus.2019.12.009

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	Online detection of anomaly behaviors based on multidimensional trajectories
	Pan, Xinlong 1,2; Wang, Haipeng 1; Cheng, Xueqi 2; Peng, Xuan 1; He, You 1
刊名	INFORMATION FUSION
	2020-06-01
卷号	58 页码:40-51
关键词	Anomaly behavior Multidimensional Online detection Trajectory
ISSN号	1566-2535
DOI	10.1016/j.inffus.2019.12.009
英文摘要	In the surveillance domain, timely detection of anomaly behaviors is very important and is a great challenge to human operators due to information overload, fatigue and inattention. Many anomaly detection algorithms based on trajectories have been proposed for this problem. However, these algorithms generally have problems such as complex parameter setting, unfaithful statistical model, not well-calibrated false alarm rate, poor ability of online learning and sequential anomaly detection, etc. The theory of conformal prediction was introduced to solve these problems by constructing the sequential Hausdorff nearest neighbor conformal anomaly detector. Yet, it only considers position information of the targets and is not sensitive to velocity and course anomaly behaviors. And the run times are increasing as the increase of the data size, which is not appropriate for early warning surveillance application. In order to solve these problems, sequential multi-factor Hausdorff nearest neighbor conformal anomaly detector (SMFHNN-CAD) and sequential multi-factor Hausdorff nearest neighbor inductive conformal anomaly detector (SMFHNN-ICAD) based on multidimensional trajectories are proposed in this paper. Experiments in both simulated military scenario and realistic civilian scenario show the presented algorithm has a good performance to online detect anomaly behaviors and would have a wide prospect in early warning surveillance systems.
资助项目	National Natural Science Foundation of China[91538201] ; National Natural Science Foundation of China[61531020] ; National Natural Science Foundation of China[61790554] ; National Natural Science Foundation of China[61671157] ; Outstanding Youth Innovation Team Program of University in Shandong Province[2019KJN031] ; China Postdoctoral Science Foundation
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000516799200004
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/14548]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Pan, Xinlong; Wang, Haipeng
作者单位	1.Naval Aviat Univ, Inst Informat Fus, Yantai 264001, Shandong, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, CAS Key Lab Network Data Sci & Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Pan, Xinlong,Wang, Haipeng,Cheng, Xueqi,et al. Online detection of anomaly behaviors based on multidimensional trajectories[J]. INFORMATION FUSION,2020,58:40-51.
APA	Pan, Xinlong,Wang, Haipeng,Cheng, Xueqi,Peng, Xuan,&He, You.(2020).Online detection of anomaly behaviors based on multidimensional trajectories.INFORMATION FUSION,58,40-51.
MLA	Pan, Xinlong,et al."Online detection of anomaly behaviors based on multidimensional trajectories".INFORMATION FUSION 58(2020):40-51.