Learning and Optimisation
Focus:
The group aims to explore new methods and algorithms for collaborative learning and optimization to achieve synergistic effects. We also seek to promote seamless integration of learning and optimization techniques with real-time systems, cyber-physical systems, robotics, as well as process control and automation.
Our methodological research concerns: metaheuristics for learning, data driven learning in optimization, real-time and continuous learning, distributed learning, data reduction and feature mining, as well as reasoning under uncertainty.
We are also actively engaged in practical applications, to apply the new developed methods and algorithms to solve challenging problems in industrial and medical domains. The interesting application areas include (yet are not limited to) the following:
- Machine learning and optimization in power devices and power systems
- Real-time process monitoring (both in industry and health care) and anomaly detection
- Smart and resillient digital twins for distributed systems
- Cyber attack identification and mitigation
Ensemble-Based Self-Supervised Meta-Learning for Anomaly Detection in Power Systems (Jul 2026) Sarala Mohan, Pawel M Stano, James Ottewill, Ning Xiong Journal of IEEE Access (IEEE-Access2026)
DAT (Dec 2024) Ali Asghar Sharifi, Ali Zoljodi , Masoud Daneshtalab Sensors (MDPI Sensors)
TrajectoryNAS (Sep 2024) Ali Asghar Sharifi, Ali Zoljodi , Masoud Daneshtalab Sensors (SENSC9)
Contrastive Learning for Lane Detection via cross-similarity (Sep 2024) Ali Zoljodi , Sadegh Abadijou , Mina Alibeigi , Masoud Daneshtalab Pattern Recognition (PR)
XES3MaP: Explainable Risks Identified from Ensembled Stacked Self-Supervised Models to Augment Predictive Maintenance (Jun 2024) Sarala Mohan, Ning Xiong IEEE Conference on Artificial Intelligence (CAI2024)
Smart data driven decision trees ensemble methodology for imbalanced big data (May 2024) Diego Garcia-Gil, Salvador García, Ning Xiong, Francisco Herrera Cognitive Computation (CCP24)
