Dr Quddus obtained a PhD from Imperial College London in 2006 where he was working as a research assistant for five years on a number of research projects. He received an MEng degree in Civil Engineering from the National University of Singapore in 2001 and a BSc degree in Civil Engineering from BUET (Bangladesh University of Engineering and Technology) in 1998. He joined Loughborough University as a Lecturer in Transport Studies in 2006,  promoted to Senior Lecturer in 2010 and awarded a personal Chair in "Intelligent Transport Systems" in August 2013. Prof Quddus has conducted cutting-edge research leading to innovative, influential and transformative outcomes in the areas of transport modelling and simulation, safety analysis and connected and autonomous vehicles. His seminal papers on map-matching algorithms have been very influential and highly cited by researchers world-wide and implemented by ITS industry.

Broad interests and expertise

• Connected and Autonomous Vehicles (CAVs)
• Artificial Intelligence (AI)
• Intelligent Transport Systems (ITS)
• Statistical Modelling of Transport Data
• Transport Risk and Safety Analysis
• Traffic Microsimulation

Professional affiliations 

• Fellow of Higher Education Academy
• Committee Member of Geographic Information Science and Applications (ABJ60) - Transportation Research Board (Washington D.C., USA)
• Committee Member of Safety Data, Analysis and Evaluation (ANB20) - Transportation Research Board (Washington D.C., USA)
• Executive Committe Member (2008 - 2011) - Universities' Transport Studies Group (UTSG), UK
• Visiting Professor (2016 – date): Tongji University, Shanghai, P.R. China.

Research interests

• Map Matching Integrity for Autonomous Vehicles (AVs)
• Simulation of Connected and Autonomous Vehicles (CAVs)
• Computational Intelligence Techniques: Bayesian Network, Deep learning & Fuzzy logic
• Statistical Modelling of Transport Data
• Spatial Econometrics using Bayesian Inferences and GIS
• Crash prediction models

Research project

(1)   Real-time crash prediction for proactive traffic management

Real-time crash prediction is a key element of a proactive traffic management system. The most challenging aspect of real-time crash prediction relates to the data imbalance problem arising from the rarity of traffic crashes. Existing studies focused on case-control designs to build approximately balanced samples in developing such models without considering the entire population. A serious limitation of this design involves a biased sample selection that may lead to inaccurate models and even erroneous conclusions. Additionally, previous research uses shallow machine learning methods, which have been under-performing while applying to highly imbalanced large data. This study, therefore, structures the full dataset and adopts a novel Deep Learning methodology - Deep Neural Network (DNN) for the model development. Historical crash data and traffic data from Shanghai Urban Expressway System were combined to build the full dataset that include all crash and non-crash related traffic conditions. The full dataset was then divided into a training dataset and a test dataset: the training dataset was utilized to develop DNN models and the test dataset was used to evaluate the performance of the models by utilizing several evaluation criteria. The results indicated that the DNN technique has powerful identification ability in real-time crash prediction: the area under the Receiver Operating Characteristics (ROC) curve could reach around 0.96 and it can identify and have potential to decrease 90% - 91% of crashes at the cost of a 10% false alarm rate. This is because DNN techniques are capable of extracting high-level, complex abstractions (e.g. non-linear patterns) from massive volumes of data through a deeply hierarchical learning process.

Methods: Deep Neural Network (DNN)

(2)   CAV Simulation

Recent technological advancements bring the Connected and Autonomous Vehicles (CAVs) era closer to reality. CAVs have the potential to vastly improve road safety by taking the human driver out of the driving task. However, the evaluation of their safety impacts has been a major challenge due to the lack of real-world CAV exposure data. Studies that attempt to simulate CAVs by using either a single or integrating multiple simulation platforms have limitations, and in most cases, consider a small element of a network (e.g. a junction) and do not perform safety evaluations due to inherent complexity. This paper addresses this problem by developing a decision-making CAV control algorithm in the simulation software VISSIM, using its External Driver Model Application Programming Interface. More specifically, the developed CAV control algorithm allows a CAV, for the first time, to have longitudinal and lateral control, scan adjacent vehicles, identify nearby CAVs and make decisions based on a ruleset associated with motorway traffic operations. A motorway corridor within M1 in England is designed in VISSIM and employed to implement the CAV control algorithm. Five simulation models are created, one for each weekday. The baseline models (i.e. CAV market penetration: 0%) are calibrated and validated using real-world minute-level inductive loop detector data and also data collected from a radar-equipped vehicle. The safety evaluation of the proposed algorithm is conducted using the Surrogate Safety Assessment Model (SSAM). The results show that CAVs bring about compelling benefit to road safety as traffic conflicts significantly reduce even at relatively low market penetration rates. Specifically, estimated traffic conflicts were reduced by 12-47%, 50-80%, 82-92% and 90-94% for 25%, 50%, 75% and 100% CAV penetration rates respectively. CAVs also ensure efficient traffic flow and reduce delays on busier days.

Methods: Traffic microsimulation – VISSIM, data from instrumented vehicles, statistical analysis

• Associate Editor – Transportation Research Part C: Emerging Technologies (since 2013)
• Associate Editor - Journal of Intelligent Transportation Systems: Technology, Panning and Operations (2010 – 2013)
• Guest Editor - Journal of Journal of Intelligent Transportation Systems: Technology, Planning and Operations
• Member of Editorial Boards - Accident Analysis and Prevention; Analytic Methods in Accident Research
• Paper reviews for: IEEE Transactions on Intelligent Transportation Systems, Transportation Research A: Policy and Practice, Transportation Research C: Emerging Technologies, Transportation Research D, Transportation Research Record, International Journal of Geographic Information Science, Accident Analysis and Prevention
• Proposal reviews for: EPSRC, US National Science Foundation (NSF), Academy of Finland, Dutch Organisation for Scientific Research (NWO)

Shortest path and vehicle trajectory aided map-matching for low frequency GPS data, Transportation Research Part C: Emerging Technologies, 55, pp.328-339, ISSN: 1879-2359. DOI: 10.1016/j.trc.2015.02.017.

Real-time motion planning methods for autonomous on-road driving: State-of-the-art and future research directions, Transportation Research Part C: Emerging Technologies, 60, pp.416-442, ISSN: 0968-090X. DOI: 10.1016/j.trc.2015.09.011.

A New Methodology for Collision Risk Assessment of Autonomous Vehicles. In Transportation Research Board 96th Annual Meeting, Washington D.C.

Impact of combined alignments on lane departure: A simulator study for mountainous freeways, Transportation Research Part C: Emerging Technologies, 86, pp.346-359, ISSN: 1879-2359. DOI: 10.1016/j.trc.2017.11.010.

View all / Visit the CBE Repository page