Towards Smarter Cities via Urban Computing
Principal Supervisor: Dr. Cheng Long
Second Supervisor: Dr. Jun Hong
+ Project Description
Big and heterogeneous data is being generated by a diversity of sources in urban spaces, such as sensors, devices, vehicles, buildings, and humans. This massive data together with the advances in computing technology have provided us with unprecedented opportunities to tackle the big challenges that cities face, e.g., traffic, energy, health care, pollution, efficiency, etc. The idea is to improve urban systems and qualities of city lives through a process of data acquisition, integration, analysis and visualization, which is referred as urban computing. Recently, quite a few research projects have been proposed on urban computing, but the technologies that have been developed are far from being mature, and there are still a lot of issues in this area that are unexplored. This project is to develop techniques for two aspects of urban computing, namely data management and data mining/analysis.
Data management. Urban data is usually of big size, in heterogeneous forms, and from different sources, which makes it a challenging problem to integrate, index, and query the data. For example, different kinds of index structures have been proposed to manage different types of data individually, whereas the hybrid index that can simultaneously manage multiple types of data (e.g., spatial, temporal and social media) is yet to be studied. The hybrid index provides a foundation that enables an efficient and effective integration of multiple heterogeneous data sources.
Data mining/analysis. It is not surprising that various kinds of knowledge that reflect different aspects of a city can be mined from the urban data. Recently years, researchers have been working on mining many different kinds of knowledge from urban data, such as, people’s movement patterns, traffic patterns, pollution patterns, etc. Yet, there are more types of knowledge that have not been explored. For example, inferring tourism statistics from users’ geosocial footprint data which could be acquired from Twitter, Instagram and Flicker, is a very promising idea but no existing studies have been done for it yet.
+ How to Apply
Applicants should apply electronically through the Queen’s online application portal at: https://dap.qub.ac.uk/portal/
+ Contact Details
|Supervisor Name:||Dr. Cheng Long|
Queens University of Belfast
+44 (0)28 9097 4783