Speaker: Weiyao Meng, Data Scientist (KTP Associate), Nottingham University, UK
Date: 10 June 2024
Time: 9:00 - 10:00am (London Time, UTC+1)
Weiyao Meng is a Data Scientist (KTP Associate) at Nottingham University Business School, specialising in applying data science techniques to address challenges in sustainable food systems. Before taking on her role in the Knowledge Transfer Partnership (KTP) in 2024, Weiyao served as a Teaching Associate in the School of Computer Science at the University of Nottingham, where she completed her PhD in 2023. Her main research interests include machine learning into automated algorithm design, and data-driven decision-making for critical sustainability challenges, particularly for sectors such as Transportation and Food. She has also served as a reviewer for leading journals including IEEE Transactions on Evolutionary Computation, Engineering Applications of Artificial Intelligence, and Journal of the Operational Research Society. She is also a member of the IEEE Task Force on Automated Algorithm Design, Configuration and Selection and the IEEE Task Force on Evolutionary Scheduling and Combinatorial Optimisation at the IEEE Computational Intelligence Society.
Designing effective search algorithms for solving Combinatorial Optimisation Problems (COPs) presents a challenge for researchers due to the time-consuming experiments and experience required in decision-making. Automated algorithm design removes the heavy reliance on human experts and allows the exploration of new algorithm designs. This talk delves into the integration of machine learning techniques into the automated design of local search-based meta-heuristics, a main theme of my PhD research. I will discuss the key studies conducted during my PhD, focusing on the utilisation of machine learning techniques ranging from rule mining to classification, and sharing insights gained from the investigation at the intersection of machine learning and combinatorial optimisation. The proposed methodology is evaluated using the vehicle routing problem with time windows as a testbed.
The Webinar went very successful, with 60+ participants.
The slides of the Webinar can be found here.
Back to the Webinar Series