- PhD / DPhil (University of Hull)
Koorosh Aslansefat is an Assistant Professor of Computer Science and a member of the Dependable Intelligent System Group (DEIS) in the University of Hull. He received M.Sc. degree in control engineering from Shahid Beheshti University, Tehran, Iran, in 2014. He got a fellowship with Grant No. 723764 for the EU H2020 project entitled: GO0D MAN (aGent Oriented Zero Defect Multi-stage mANufacturing) from 2016 to 2018. In 2018, he got a Studentship Award from EDF Energy R&D UK to do a PhD at the University of Hull and have an industrial collaboration with EDF Energy for a project entitled: DREAM (Data-driven Reliability-centred Evolutionary Automated Maintenance for Offshore Wind Farms). In his PhD career, he managed to get the IET Leslie H. Paddle Award for being an Outstanding Researcher for his work on Real-time dependability evaluation and the DREAM project.
In 2021, he became a Research Associate and as a named researcher got a fellowship with Grant No. 101017258 for another EU H2020 project entitled: (SESAME) Safe MultiRobot Systems. In this position, he managed to get an Post-Doctoral Enrichment Award from the Alan Turing Institute for his innovative research on the safety evaluation of machine learning known as SafeML. Koorosh Aslansefat is internationally renowned for innovative research on the engineering of dependable systems that includes real-time dependability analysis of complex systems and safety assurance of machine learning algorithms. His main research interests are in artificial intelligence safety and explainability, Markov modelling, performance assessment, optimization, stochastic modelling, and runtime dependability evaluation.
Explaining black boxes with a SMILE: Statistical Model-agnostic Interpretability with Local Explanations
Aslansefat, K., Hashemian, M., Walker, M., Akram, M. N., Sorokos, I., & Papadopoulos, Y. (2023). Explaining black boxes with a SMILE: Statistical Model-agnostic Interpretability with Local Explanations. IEEE Software, https://doi.org/10.1109/ms.2023.3321282
Towards Improving Confidence in Autonomous Vehicle Software: A Study on Traffic Sign Recognition Systems
Aslansefat, K., Kabir, S., Abdullatif, A., Vasudevan Nair, V., & Papadopoulos, Y. (in press). Towards Improving Confidence in Autonomous Vehicle Software: A Study on Traffic Sign Recognition Systems. Computer,
SafeML: Safety Monitoring of Machine Learning Classifiers Through Statistical Difference Measures
Aslansefat, K., Sorokos, I., Whiting, D., Tavakoli Kolagari, R., & Papadopoulos, Y. (2020). SafeML: Safety Monitoring of Machine Learning Classifiers Through Statistical Difference Measures. Lecture notes in computer science, 12297, 197-211. https://doi.org/10.1007/978-3-030-58920-2_13
A Hybrid Modular Approach for Dynamic Fault Tree Analysis
Kabir, S., Aslansefat, K., Sorokos, I., Papadopoulos, Y., & Konur, S. (2020). A Hybrid Modular Approach for Dynamic Fault Tree Analysis. IEEE Access, 8, 97175-97188. https://doi.org/10.1109/ACCESS.2020.2996643
A runtime safety analysis concept for open adaptive systems
Kabir, S., Sorokos, I., Aslansefat, K., Papadopoulos, Y., Gheraibia, Y., Reich, J., …Wei, R. (2019). A runtime safety analysis concept for open adaptive systems. Lecture notes in computer science, 11842, 332-346. https://doi.org/10.1007/978-3-030-32872-6_22
• Artificial Intelligence Safety and Explainability
• Performance Assessment
• Data-driven Fault Detection, Diagnosis, and Prognosis
• Dependability Evaluation and Improvement
• Optimization and Evolutionary Algorithms
• Probabilistic Modelling (In particular Markov Modelling)
• Offshore Wind Turbines
• Safety Evaluation of Multi-Robot Systems
The Alan Turing Institute - Post-Doctoral Enrichment Awards
The Alan Turing Institute
1 March 2022
SafeML: Exploring techniques for safety monitoring of machine learning classifiers.
SafeDrones: Reliability/Safety Modelling and Evaluation of Multicopters (Multi-rotor Drones) and Electric powered Vertical TakeOff and Landing (eVTOL) Aircrafts.