Islam, M. R., Massicotte, D., Nougarou, F., Massicotte, P. et Zhu, W. P. (2020, July 20-24). S-Convnet: A shallow convolutional neural network architecture for neuromuscular activity recognition using instantaneous high-density surface EMG images. Dans 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, Canada DOI 10.1109/EMBC44109.2020.9175266.
Prévisualisation |
PDF
Télécharger (411kB) | Prévisualisation |
Résumé
The recent progress in recognizing low-resolution instantaneous high-density surface electromyography (HD-sEMG) images opens up new avenues for the development of more fluid and natural muscle-computer interfaces. However, the existing approaches employed a very large deep convolutional neural network (ConvNet) architecture and complex training schemes for HD-sEMG image recognition, which requires learning of ˃5.63 million(M) training parameters only during fine-tuning and pre-trained on a very large-scale labeled HD-sEMG training dataset, as a result, it makes high-end resource-bounded and computationally expensive. To overcome this problem, we propose S-ConvNet models, a simple yet efficient framework for learning instantaneous HD-sEMG images from scratch using random-initialization. Without using any pre-trained models, our proposed S-ConvNet demonstrate very competitive recognition accuracy to the more complex state of the art, while reducing learning parameters to only ≈ 2M and using ≈ 12 × smaller dataset. The experimental results proved that the proposed S-ConvNet is highly effective for learning discriminative features for instantaneous HD-sEMG image recognition, especially in the data and high-end resource-constrained scenarios.
Type de document: | Document issu d'une conférence ou d'un atelier |
---|---|
Mots-clés libres: | Neuromuscular activity recognition Shallow convolutional neural networks Feature learning HD-sEMG Gesture recognition Muscle-computer interface Deep neural networks |
Date de dépôt: | 09 mai 2022 18:12 |
Dernière modification: | 09 mai 2022 18:12 |
URI: | https://depot-e.uqtr.ca/id/eprint/10133 |
Actions (administrateurs uniquement)
Éditer la notice |