Urban Anomaly Analytics: Description, Detection, and Prediction

PhD Qualifying Examination


Title: "Urban Anomaly Analytics: Description, Detection, and Prediction"

by

Mr. Mingyang ZHANG


Abstract:

Urban abnormal events such as traffic incidents and unexpected crowds pose a 
significant threat to social order and public safety. Alerting abnormal events 
in their early stages or even predicting the happening of such events are of 
great value for emergency handling and anomaly controlling. In recent years, 
with the fast development of mobile smart devices and ubiquitous sensing 
techniques, a large amount of data are continuously produced in cities. 
Encouraged by the wide access to urban big data, data-driven urban anomaly 
analysis frameworks that utilize urban big data and machine learning algorithms 
to detect and predict urban abnormal events have been forming. In this survey, 
we make a comprehensive review of the state-of-the-art research on urban 
anomaly analytics. We start by illustrating the underlying logic and the common 
framework of data-driven urban anomaly analyzing. We then give an overview of 
four main types of urban abnormal events, i.e., traffic anomaly, unexpected 
crowds, environment anomaly, and individual anomaly. Next, we summarize various 
types of urban datasets obtained from diverse devices, i.e., trajectory, trip 
records, CDRs, urban sensors, event records, environment data, social media, 
surveillance cameras. Subsequently, we present a comprehensive taxonomy of 
issues on detecting and predicting techniques for urban abnormal events. 
Finally, we discuss potential research directions from aspects of data 
challenges and applications.


Date:			Thursday, 2 July 2020

Time:                  	10:00am - 12:00noon

Zoom meeting:           https://hkust.zoom.us/j/93945862681

Committee Members:	Dr. Pan Hui (Supervisor)
 			Prof. Tin-Yau Kwok (Chairperson)
 			Dr. Xiaojuan Ma
 			Dr. Brian Mak


**** ALL are Welcome ****