Dr Shadi S. Basurra
Senior Lecturer
School of Computing and Digital Technology - CDT
- Email:
- Shadi.basurra@bcu.ac.uk
- Phone:
- +44 (0) 121 331 5438
Shadi Basurra received his BSc (Hons) degree in Computer Science from Exeter University, the UK, and MSc in Distributed Systems and Networks from Kent University at Canterbury, UK. He obtained his Ph.D. from the University of Bath in collaboration with Bristol University. After completing his Ph.D., Shadi worked at Sony Corporation developing Goal Decision Systems, he then moved on to work as a Research Fellow at the Zero Carbon Lab - Birmingham City University. He recently joined the Computer Science Centre as a Senior Lecturer in Software Engineering at Birmingham City University.
He was awarded The Yemen President National Science Prize (2010), Best Presentation at Meeting of Minds – Bath 2012 and MEX Scholarship 2013, (Toshiba ltd, Great Western Research and Yemen gov. for Ph.D. scholarship 2009) and various academic funding grants. He has had extensive experience in dynamic modelling and simulation of buildings; software development of predictive control algorithms.
He worked solidly on theoretical and technical aspects of networking and mobile computing. He has designed adaptive communication protocols that combined distance vector and link-state routing protocols for wireless mobile ad hoc networks in order to increase performance efficiency and energy saving. He was the co-investigator and technical lead for BCU work packages in the nationally recognized project Retrofit Plus. Retrofit Plus project secured a £1.2 million external fund from Innovate UK for scaling up retrofit of the nation’s homes. Shadi research interests include simulation and emulation of networks (vehicular, mesh and sensor ad hoc network), game theory, multi-agent systems, multi-objective optimisation, model calibration and dynamic simulation of zero-carbon design and retrofit of buildings.
His recent research is related to Edge Computing, in particular, the use of the lightweight machine and deep learning techniques that allow the learning and inference to occur on devices with limited resources, e.g. IoT devices, to aid rapid decision-making whilst maintaining the highest possible accuracy in Classification and Regression Analysis. He has published a number of peer-reviewed scientific publications in international conferences, journals, and has taught postgraduate and undergraduate courses in software engineering and networking.