Exploring discriminative features for anomaly detection in public spaces

• Main Authors: NAYAK, Shriguru, MISRA, Archan, JEYARAJAH, Kasthuri, PRASETYO, Philips Kokoh, Ee-peng LIM
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2015
• Subjects: Mobile devices; Multilayers; Sensor fusion; Software; Web 2.0 technologies; Event Detection; Anomaly Detection; Urban Situation Awareness; Indoor Mobility; Twitter Analytics; Databases and Information Systems; Digital Communications and Networking; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/3138; https://ink.library.smu.edu.sg/context/sis_research/article/4138/viewcontent/P_ID_52611_SPIE_2015_LocationBasedAnomaly.pdf
• Institution: Singapore Management University

Context data, collected either from mobile devices or from user-generated social media content, can help identify abnormal behavioural patterns in public spaces (e.g., shopping malls, college campuses or downtown city areas). Spatiotemporal analysis of such data streams provides a compelling new approach towards automatically creating real-time urban situational awareness, especially about events that are unanticipated or that evolve very rapidly. In this work, we use real-life datasets collected via SMU's LiveLabs testbed or via SMU's Palanteer software, to explore various discriminative features (both spatial and temporal - e.g., occupancy volumes, rate of change in topic{specific tweets or probabilistic distribution of group sizes) for such anomaly detection. We show that such feature primitives fit into a future multi-layer sensor fusion framework that can provide valuable insights into mood and activities of crowds in public spaces.