PhD oral Exam - Taiwo Olubunmi Adetiloye, Concordia Institute for Information Systems Engineering
When studying for a doctoral degree (PhD), candidates submit a thesis that provides a critical review of the current state of knowledge of the thesis subject as well as the student’s own contributions to the subject. The distinguishing criterion of doctoral graduate research is a significant and original contribution to knowledge.
Once accepted, the candidate presents the thesis orally. This oral exam is open to the public.
Traffic congestion is a widely occurring phenomenon caused by increased use of vehicles on roads resulting in slower speeds, longer delays, and increased vehicular queueing in traffic. Every year, over a thousand hours are spent in traffic congestion leading to great cost and time losses. In this thesis, we propose a multi-data multi-method approach for predicting traffic congestion on urban motorway networks. The first approach models traffic congestion on urban motorway networks using data mining techniques. For this, we used freely available data on traffic for UK cities. Two categories of models are proposed namely neural networks, and random forest classifiers. The neural network models include the back propagation neural network, neuro-fuzzy, and deep belief network. The second approach models real-world traffic congestion using agent-based simulation. Vehicle agents cruising on single lane are studied with regards to the onset of rush hour, the presence of traffic signalization and the passage of an emergency vehicle. These include the visualization as well as dynamic event analysis of the traffic flow and delay time using the data obtained during the simulation experiment. The third approach analyzes traffic congestion using social media data analysis. Twitter traffic delay tweets are analyzed using sentiment analysis and cluster classification for traffic flow prediction. For this, we mined tweets related to the UK traffic delay. Lastly, results emanating from the various models are fused using Extended Kalman Filter and Mamdani fuzzy rule based inferencing system for final traffic congestion prediction.
Our research study can assist academia and industry in intelligent route planning, better monitoring and mitigation of traffic congestion on urban motorways by traffic management systems, reduction of traffic delays, waiting times, air pollution and noise in cities. In particular, to help the road vehicle drivers to find an optimal route so as to avoid congested traffic route; and the first responders to know the root cause of traffic congestion in the shortest possible time; as well as assist the traffic managers to design better road traffic infrastructure.