STANDARD Project Team

Mr. James Haworth
PhD Candidate

Multi-scale analysis of road network performance

In today’s data rich environment, time and location specific data are collected in huge volumes and are often available in real time and the traditional challenges of data sparsity and lack of computational power have been replaced with fresh challenges in data storage, data mining and knowledge discovery. Traffic data is now collected on the urban road systems of many major cities and if put to good use can provide vital information on road network performance to be used in intelligent transportation systems (ITS). Typical data collected on road systems are traffic flows, journey times and speeds. They may be collected at any temporal (ie, 1min, 5min 15min) or spatial resolution (eg. homogeneously sized road sections, individual road links). If the spatial relationship between data collection points is known then the sensor locations form a network. To effectively model the dynamics of the road network, the sensor network should capture the dynamic nature of the propagation of traffic conditions around it. The aims of this research are twofold; firstly, statistical analysis is used to examine the spatio-temporal autocorrelation structure of London’s road network. Secondly, this structure is integrated into a space-time model using a kernel based approach.


Principal Investigator
Dr. Tao Cheng

Prof. Benjamin Heydecker

Research Fellows
Dr. Ioannis Tsapakis
Dr. Jiaqiu Wang

Research Students
Mr. Berk Anbaroglu
Mr. James Haworth
Mr. Ed Manley
Ms. Garavig Tanaksaranond

Industrial Partners at TfL
Mr. Andy Emmonds
Mr. Jonathan Turner
Mr. Alexandre Santacreu

alt: Research Poster
Sponsored By:     University College London   Transport For London   Engineering and Phyical Research Council