Rate My Professor Mathias Verbeke

Mathias Verbeke is Professor in Artificial Intelligence for Industry at KU Leuven, serving as Associate Professor in the Faculty of Engineering Technology at the Bruges Campus. He heads the Subdivision M-Group Industrial Artificial Intelligence within the M-Group division and acts as contact person for the Declarative Languages and Artificial Intelligence (DTAI) section at the Bruges Campus. Affiliated with the Department of Computer Science, the STADIUS division at the Department of Electrical Engineering (ESAT), and Leuven.AI, he also contributes to Flanders Make through the DTAI-FET Core Lab. Previously, Verbeke worked as Senior Data Scientist at Sirris, the collective research and innovation centre for the Belgian technological industry, where he conducted industrial research on advanced data analytics and machine learning to develop data-driven products and services for companies across various sectors. He heads the education for the Postgraduate Certificate in Artificial Intelligence in Business and Industry at the Bruges Campus.

Verbeke's research centers on the industrial application of artificial intelligence, with a focus on automated, adaptive, and embedded machine learning techniques to address challenges like data quality issues, contextual sensitivity, and multivariate multimodal data in dynamic, resource-constrained industrial environments. He supervises and co-supervises numerous research projects, including Real-Time Anomaly Detection in the Electromagnetic Environment Using AI, Optimizing EMI Monitoring through Compressed Sensing, CausAICA for Causal Actionable Understanding via AI for Root Cause Analysis, and PerIMPro for closing the product-production loop in injection-molded parts. His key publications include 'Inducing probabilistic relational rules from probabilistic examples' (2015, 115 citations), 'HMM with non-emitting states for Map Matching' (2018, 66 citations), 'A statistical relational learning approach to identifying evidence based medicine categories' (2012, 56 citations), 'Data-driven models with physical interpretability for real-time cavity profile prediction in electrochemical machining processes' (2025, 40 citations), and 'Process mining on machine event logs for profiling abnormal behaviour and root cause analysis' (2020, 25 citations). With 546 citations on Google Scholar, his work impacts fields such as anomaly detection, predictive maintenance, and manufacturing process optimization. Verbeke has 99 publications listed in LIRIAS from 2006 to 2026 and serves on committees such as EUSIPCO 2026.