Inferring Unusual Crowd Events from Mobile Phone Call Detail Records
The pervasiveness and availability of mobile phone data offer the opportunity of discovering usable knowledge about crowd behavior in urban environments. Cities can leverage such knowledge to provide better services (e.g., public transport planning, optim
- PDF / 1,636,783 Bytes
- 19 Pages / 439.37 x 666.142 pts Page_size
- 55 Downloads / 198 Views
Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, USA {ydong1,nchawla}@nd.edu 2 IBM Research, Mulhuddart, Ireland {fabiopin,yiannisg,zubairn,fcalabre}@ie.ibm.com Abstract. The pervasiveness and availability of mobile phone data offer the opportunity of discovering usable knowledge about crowd behavior in urban environments. Cities can leverage such knowledge to provide better services (e.g., public transport planning, optimized resource allocation) and safer environment. Call Detail Record (CDR) data represents a practical data source to detect and monitor unusual events considering the high level of mobile phone penetration, compared with GPS equipped and open devices. In this paper, we propose a methodology that is able to detect unusual events from CDR data, which typically has low accuracy in terms of space and time resolution. Moreover, we introduce a concept of unusual event that involves a large amount of people who expose an unusual mobility behavior. Our careful consideration of the issues that come from coarse-grained CDR data ultimately leads to a completely general framework that can detect unusual crowd events from CDR data effectively and efficiently. Through extensive experiments on real-world CDR data for a large city in Africa, we demonstrate that our method can detect unusual events with 16% higher recall and over 10× higher precision, compared to state-of-the-art methods. We implement a visual analytics prototype system to help end users analyze detected unusual crowd events to best suit different application scenarios. To the best of our knowledge, this is the first work on the detection of unusual events from CDR data with considerations of its temporal and spatial sparseness and distinction between user unusual activities and daily routines.
1
Introduction
The ubiquity of mobile devices offers an unprecedented opportunity to analyze the trajectories of movement objects in an urban environment, which can We wish to thank the Orange D4D Challenge (http://www.d4d.orange.com) organizers for releasing the data we used for testing our algorithms. Research was sponsored in part by the Army Research Laboratory under Cooperative Agreement Number W911NF-09-2-0053 and the U.S. Air Force Office of Scientific Research (AFOSR) and the Defense Advanced Research Projects Agency (DARPA) grant #FA9550-121-0405. c Springer International Publishing Switzerland 2015 A. Appice et al. (Eds.): ECML PKDD 2015, Part II, LNAI 9285, pp. 474–492, 2015. DOI: 10.1007/978-3-319-23525-7 29
Inferring Unusual Crowd Events from Mobile Phone Call Detail Records
475
have a significant effect on city planning, crowd management, and emergency response [4]. The big data generated from mobile devices, thus, provides a new powerful social microscope, which may help us to understand human mobility and discover the hidden principles that characterize the trajectories defining human movement patterns. Cities can leverage the results of the analytics to better provide and plan services for citizens as well a
Data Loading...
