Injury Prevention via sEMG

In this project, we analyzed sEMG measurements of professional athletes. I worked on this project for three years as a Consultant for Machine Learning in Signal Processing at Neurocess

• In Attention-Enhanced Frequency-Split Convolution Block for sEMG Motion Classification: Experiments on Premier League and Ninapro Datasets, we have presented convolutional octave-band zooming-in with depth-kernel attention learning (COZDAL), a versatile deep learning model designed for surface electromyography (sEMG) motion classification.

• In A Novel Framework for Motion-Induced Artefact Cancellation in sEMG: Evaluation on English Premier League and Ninapro Datasets, we have study proposes a framework involving two consecutive models specifically designed to detect Motion-Induced Artifact (MIA) zones in the sEMG stream and to denoise MIA. For the denoising of MIA, a novel convolution block within the U-net Encoder Decoder (UED) is introduced, featuring attention-enhanced kernel and channel selection.

• In sEMG Motion Classification Via Few-Shot Learning With Applications To Sports Science, we have utilised few-shot learning (FSL) techniques to overcome the small dataset problem of sports-related motion classification tasks. The employed methodology uses the knowledge gathered from a large set of tasks to classify unseen tasks with a few data samples.

• We presented our study on ‘Cooperation of Isometric Force Test and EMG for Hamstring Injury Prevention’ at the Isokinetic Conference23 in London.