Title :
Outlier Detection on Large-Scale Collective Behaviors
Author :
Zhou, Wenbin ; Yang, Su
Author_Institution :
Coll. of Comput. Sci. & Technol., Fudan Univ., Shanghai, China
Abstract :
Outlier detection on collective behaviors is an interesting and practical problem with the aid of tracking technology and devices such as mobile phones, GPS, and cameras. The aim of outlier detection is to monitor and alarm abnormal collective behaviors of crowd. This study proposes a framework for detecting outliers of collective behaviors. The experiments with toy data and real-world traffic data show that the proposed framework can work satisfactorily.
Keywords :
data mining; security of data; GPS; camera; large-scale collective behavior; mobile phone; outlier detection; tracking device; tracking technology; Companies; Detectors; Eigenvalues and eigenfunctions; Feature extraction; Mobile handsets; Noise; Unemployment; Collective Behaviors; Data Mining; Outlier Detection; Pattern Recognition;
Conference_Titel :
Computational Sciences and Optimization (CSO), 2011 Fourth International Joint Conference on
Conference_Location :
Yunnan
Print_ISBN :
978-1-4244-9712-6
Electronic_ISBN :
978-0-7695-4335-2
DOI :
10.1109/CSO.2011.199
