Dr Martin Wonders

Assistant Professor

School: Computer Science

Martin is a senior lecturer in the department of computer and information sciences and teaches computer vision, applied programming, machine learning, Artificial Intelligent and Robotics. Martin's doctoral thesis on Activity Recognition in monitored environments using utility meter disaggregation, focused on the use of machine learning to both disaggregate signals from utility meters, and use these signals to infer the activity of the occupants.

Martins current research interests focus on Machine and Deep learning using data from a variety of sources including images and video as well as internal and external environmental sensor data from buildings. The latter of which is being applied to energy load demand forecasting for a local architectural company - European Regional Development Fund (ERDF).

Email Martin

Key Publications

Please visit the Pure Research Information Portal for further information
A Cloud-Based Framework for Creating Scalable Machine Learning Models Predicting Building Energy Consumption from Digital Twin Data, Mahamedi, E., Suliman, A., Wonders, M. 23 Apr 2025, In: Architecture
Measuring Flow: Refining Research Protocols that integrate Physiological and Psychological Approaches, Wonders, M., Hodgson, D., Whitton, N. 14 Feb 2025, In: Human Behavior and Emerging Technologies
A reinforcing transfer learning approach to predict buildings energy performance, Mahamedi, E., Wonders, M., Gerami seresht, N., Woo, W., Kassem, M. 9 Jan 2024, In: Construction Innovation
Digital Twin and Building Performance: A Review and Proposed Framework, Mahamedi, E., Wonders, M., Kassem, M., Woo, W., Greenwood, D. 5 Sep 2022, Proceedings of the 38th Annual ARCOM Conference, 5-7 September 2022, Glasgow, UK, London, Association of Researchers in Construction Management (ARCOM)
Towards Sparse Rule Base Generation for Fuzzy Rule Interpolation, Tan, Y., Li, J., Wonders, M., Chao, F., Shum, H., Yang, L. 25 Jul 2016, WCCI 2016 - IEEE World Congress on Computational Intelligence
Training with synthesised data for disaggregated event classification at the water meter, Wonders, M., Ghassemlooy, Z., Hossain, A. 1 Jan 2016, In: Expert Systems with Applications