<p><strong>Motion classification with surface electromyog-</strong><br> <strong>raphy (sEMG) has been studied for practical applications</strong><br> <strong>in prosthesis limb control and human-machine interaction. Recent studies have shown that feature learning with deep neural networks (DNN) reaches considerable accuracy in motion classification tasks. However, DNNs require large datasets for acceptable performance and fail for tasks with few data samples available for training. Professional athlete training includes hundreds of exercises, and coupled with privacy and confidentiality issues acquiring a large dataset for all the exercises is not feasible. As a result, state-of-the-art DNN architectures are unsuitable for real-life sports applications. We utilise 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. The FSL approach with a siamese network and triplet loss reached the best performance with a median F1-score of</strong> 72.01%<strong>,</strong> 76%<strong>, and</strong> 79% <strong>for 1, 5 and 10 shot datasets that include an unseen set of tasks, respectively. In contrast, DNN with transfer learning (TF) reached</strong> 49.27%<strong>,</strong> 51.58%<strong>, and</strong> 67.66% <strong>for the same set of tasks, respectively.</strong></p>

<p><strong>Motion classification with surface electromyog-</strong><br> <strong>raphy (sEMG) has been studied for practical applications</strong><br> <strong>in prosthesis limb control and human-machine interaction. Recent studies have shown that feature learning with deep neural networks (DNN) reaches considerable accuracy in motion classification tasks. However, DNNs require large datasets for acceptable performance and fail for tasks with few data samples available for training. Professional athlete training includes hundreds of exercises, and coupled with privacy and confidentiality issues acquiring a large dataset for all the exercises is not feasible. As a result, state-of-the-art DNN architectures are unsuitable for real-life sports applications. We utilise 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. The FSL approach with a siamese network and triplet loss reached the best performance with a median F1-score of</strong> 72.01%<strong>,</strong> 76%<strong>, and</strong> 79% <strong>for 1, 5 and 10 shot datasets that include an unseen set of tasks, respectively. In contrast, DNN with transfer learning (TF) reached</strong> 49.27%<strong>,</strong> 51.58%<strong>, and</strong> 67.66% <strong>for the same set of tasks, respectively.</strong></p>