Michael Pritchard

Michael Pritchard is a Postgraduate Research scholar at the College of Engineering and Physical Sciences. His research focuses on multimodal biosignal fusion, particularly integrating electromyography (EMG) and electroencephalography (EEG) for upper-limb gesture classification and robotic prosthesis control. He explores machine learning techniques, including GPT-2-driven data augmentation and dynamic fusion strategies, to enhance classification accuracy in biomedical applications.

His academic work includes a doctoral thesis titled Multimodal EMG-EEG Biosignal Fusion in Upper-Limb Gesture Classification, supervised by Dr. Helen Goldingay and Dr. Felipe Campelo. Research interests span biosignal processing, human-machine interaction, and real-time systems. Notable contributions include leveraging synthetic data and automated machine learning to improve prosthesis control systems.

Michael’s publications address challenges in neural engineering, emphasizing practical applications in robotics and clinical settings. His work bridges theoretical data science with applied biomedical engineering, aiming to advance assistive technologies through innovative signal processing methodologies.