Mining Taxi Trajectory Data for Emerging Location-based Services

PhD Thesis Proposal Defence


Title: "Mining Taxi Trajectory Data for Emerging Location-based Services"

by

Mr. Ye DING


Abstract:

As one type of public transportation, taxis perform an important part in our 
daily life. By equipping global positioning system (GPS) devices on taxis in 
recent years, it is possible for a taxi to act like a mobile sensor, and gather 
large amount of location tracking trajectory data. Leveraging such information 
enables us to discover various knowledge that are difficult to identify 
intuitively, for the use of location-based services (LBS). In this thesis, we 
study the applications based on the analysis of taxi trajectories, including 
inferring the types of road segments and recommending the passenger-hunting 
routes for taxis. In consideration of the large size and the complexity of 
trajectories, we also study the storage and query processing via the use of 
diverse replicas in distributed systems. These applications benefit not only 
the taxi drivers themselves, but also the passengers and the government. Unlike 
other public transportations and vehicles, taxis have their own unique 
characteristics. Due to the low-density, sparsity, and uncertainty of taxi 
trajectories, knowledge discovery from taxi trajectories faces many challenges. 
In this thesis, we will discuss the important challenges and research issues of 
each aspect, and compare the differences between our methods and the 
state-of-the-art.


Date:			Thursday, 27 March 2014

Time:                   3:00pm - 5:00pm

Venue:                  Room 5505
                         lifts 25/26

Committee Members:	Prof. Lionel Ni (Supervisor)
 			Dr. Raymond Wong (Chairperson)
 			Dr. Pan Hui
 			Dr. Ke Yi


**** ALL are Welcome ****