URBAN EVENTS MINING FROM SPATIOTEMPORAL BIG DATA

PhD Thesis Proposal Defence


Title: "URBAN EVENTS MINING FROM SPATIOTEMPORAL BIG DATA"

by

Mr. Mingyang ZHANG


Abstract:

Urban events are the sets of real-world occurrences in urban space associated 
with specific topics. Discovering, understanding, and forecasting various types 
of urban events are important to facilitate smart-city applications and benefit 
people’s urban life. In recent years, mobile devices and sensors widely located 
in cities collect large amounts of data produced in urban space, which form a 
large-scale, cross-domain, and multi-view data ecosystem. The collected data, 
termed urban big data, provide an unprecedented opportunity to discover and 
analyze urban events. In this thesis proposal, we develop data-driven 
methodologies for urban events mining. We present three of our works on urban 
anomaly detection, urban location representation learning, and road network 
traffic prediction respectively.

Detecting abnormal urban events such as unusual crowd flows at an early stage 
is important to minimize the adverse effects. In the first work, we introduce 
an urban dynamic decomposition method to detect urban anomalies. We propose a 
neural network model to estimate normal urban dynamics using spatiotemporal 
features and detect abnormal events via residual analysis. We validate the 
effectiveness of the proposed method with both synthetic and real-world event 
datasets.

Regions are usually considered as the minimal spatial units for urban event 
analysis. In the second work, we focus on learning an embedding space from 
urban big data for urban regions. We propose to construct multi-view relations 
among urban regions and learn urban region embeddings through a multi-view 
joint learning model. Experiments on real-world datasets prove the 
effectiveness of the learned embeddings on downstream applications including 
predicting long-term regional event statistics such as crime rates.

As a special type of urban event, traffic congestions have been a great concern 
in metropolises. Traffic prediction is a crucial task for congestion diagnosis 
and control. In the third work, we propose a traffic prediction model called 
Adaptive Spatiotemporal Convolutional Network, which models complicated 
spatiotemporal traffic dependencies adaptively with awareness of the real-time 
traffic conditions. Experiments on real-world traffic datasets from California 
and Beijing demonstrate the proposed model outperforms the state-of-the-art.

In the end, we conclude this thesis proposal with future research directions 
and challenges related to data-driven urban events analysis.


Date:			Wednesday, 16 February 2022

Time:                  	4:00pm - 6:00pm

Zoom Meeting: 
https://hkust.zoom.us/j/99617868046?pwd=YWpsNEM5M1JmR3lZbDJyd21uYXF6QT09

Committee Members:	Prof. Pan Hui (Supervisor, EMIA)
  			Prof. Dik-Lun Lee (Chairperson)
 			Prof. Raymond Wong
 			Prof. Nevin Zhang


**** ALL are Welcome ****