Congestion management and prediction

Objectives:

The research aims to reduce traffic congestion & improve the throughput of key roadways. It aims to use cutting

edge crowdsourcing, cloud and cyber-physicals ystems as well as wireless sensor network technologies & data

mining techniques to improve our commute to work time (when the roadways are most stressed). The

contribution of this work is to include accurate real-time traffic prediction using a hybrid exponential smoothing

and neural-nets-based approaches and traffic flows forecasting using swarm intelligence. Among the work in this

area also include Congestion issues, impact and global view, congestion management through collective intelligence

and crowd sourcing, Logistics issues in InfrastructureStrategies, Planning and Policy, Intelligent Logistics Infrastructure

Design and Development, Intelligent strategy for planning and design (including ports, Air orSea), Intelligent strategy

for planning and design of highway, overpass, road, rail and freight corridors. The research also includes urban and

regional development model through data mining for the specific characteristics of road user background and

travelling behaviour and enablement of the study on road user demographic background and how this has affected

the local industry and urban regional business development, including the prediction of population growth, and its

impact on localbu siness and services in 5, 10 or 25 years’ time.

Description of Work:

This project involves design and development of algorithms, knowledge, information analysis techniques, good

mathematical knowledge as well as possible numerical modelling.