Inferring Unusual Crowd Events from Mobile Phone Call Detail Records

Abstract

The pervasiveness and availability of mobile phone data offer the opportunity of discovering usable knowledge about crowd behaviors in urban environments. Cities can leverage such knowledge in order to provide better services (e.g., public transport planning, optimized resource allocation) and safer cities. 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 provide a methodology that is able to detect unusual events from CDR data that 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 times higher precision, compared to stateof-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.

Advances in Crowd Analysis for Urban Applications Through Urban Event Detection

“…Thus the raw CDR data has space and time sparseness. Different techniques have been reported in the literature to identify user location and trajectory accurately which eventually reduces the space-time sparsity of the data [5], [49], [70].…”

“…To identify user's location, Dong et al defined that each user belongs to a cylindrical cluster with a certain existence probability [5]. Gonzalez et al considered the users to be concentrated at the centroid of the cell area [32].…”

“…Devices enabled with pervasive computing technologies, such as, smart cards [1], [2], wearable devices [3], Radio-Frequency (RF) communication devices (RFCD) (e.g., mobile phones [4], [5], [6], Bluetooth [7], [8], [9], [10], Wireless Fidelity (WiFi) [11], [12], [13], RadioFrequency ID (RFID), and Global Positioning System (GPS) [14], [15], [16]), Optical-Wireless communication (OWC) (e.g., infrared or IR devices) [17], video surveillance [18], [19], [20], in conjunction with social media [21], [22], [23] and different event websites are part and parcel of our daily lives. Recent studies report that the above mentioned ubiquitous technologies can also be employed as sensors to collect data on human activities from the urban space and are uploaded to distributed / centralized databases.…”

Can multimodal sensing detect and localize transient events?

“…CDR data have also been used to detect unusual urban events (e.g., elections, emergency events, etc. 16,17 ). Previous works on anomaly detection in transportation have looked at varied aspects of the problem including the detection of and finding the root causes of the anomalies.…”

Urban event detection with big data of taxi OD trips: A time series decomposition approach

“…Recently, there has been an increasing interest in exploring both the temporal and spatial dimensions in social media data to extract and understand events at different spatial-temporal scales (Chen & Roy, 2009;Dong, Mavroeidis, et al, 2015;Rattenbury, Good, & Naaman, 2007). Mobile phone data have also been widely used in urban activity monitoring (Calabrese et al, 2010;Ratti, Frenchman, Pulselli, & Williams, 2006), event detection (Candia et al, 2008;Dong, Pinelli, et al, 2015;Traag, Browet, Calabrese, & Morlot, 2011), population density mapping (Deville et al, 2014), and tourism management (Ahas, Aasa, Mark, Pae, & Kull, 2007;Ahas, Silm, Järv, Saluveer, & Tiru, 2010). A more complete review on mobile phone data analysis can be found in Calabrese, Blondel, and Ferrari (2014).…”