EMG-Based Hand Gesture Recognition Using Interpretable Deep Learning for Prostheses
##plugins.themes.bootstrap3.article.sidebar##
##plugins.themes.bootstrap3.article.main##
Abstract
This study proposes an EMG-based hand gesture recognition method for adaptive prosthesis applications using interpretable deep learning. The proposed method utilizes EMG (electromyography) signals obtained from arm muscles to identify various hand movements performed by prosthesis users. By using a deep learning architecture, the developed model can classify hand movements with high accuracy. This approach also integrates model interpretability through saliency map visualization techniques, which allows understanding of the key features used by the network to make decisions. EMG datasets collected from several subjects were trained to recognize hand gestures such as gripping, grasping, and waving, and were complemented with signal processing to reduce noise and improve data quality. Evaluation results show that the proposed deep learning model achieves classification accuracy of up to 95%, with a relatively low time-to-decision, making it suitable for prosthesis applications that require fast and accurate responses. The results of this study have the potential to improve prosthesis performance with smoother and more responsive control, as well as provide new insights for the development of biomedical signal-based prosthetic devices.
##plugins.themes.bootstrap3.article.details##
[2] PS Madhusudhan, AG Mamatha, & MSR (2015). "EMG signal classification for prosthetic control using support vector machine." Journal of Electrical Engineering & Technology, vol. 10, no. 4, pp. 1250–1258, Jul. 2015. doi:10.5370/JEET.2015.10.4.1250.
[3] MAZ Alam, AFB Othman, & SAMBH (2020). "A deep learning approach for gesture recognition using EMG signals for prosthetic applications." Journal of Biomedical Science and Engineering, vol. 13, pp. 321-334, Feb. 2020. doi:10.4236/jbise.2020.133022.
[4] LXKDSYZ, "Recognition of Hand Gestures from EMG Signals Using Deep Learning Techniques," IEEE Access, vol. 8, pp. 135765–135776, 2020. doi:10.1109/ACCESS.2020.3010089.
[5] J. Zhang, J. Li, & H. Zhang, "A survey of machine learning-based methods for hand gesture recognition using electromyography," Pattern Recognition Letters, vol. 133, pp. 58-66, Oct. 2020. doi:10.1016/j.patrec.2020.01.014.
[6] F. Jafari, MAST, & HRE, "Real-time EMG classification for prosthetic applications using machine learning algorithms," IEEE Transactions on Biomedical Engineering, vol. 67, no. 7, pp. 1995-2006, Jul. 2020. doi:10.1109/TBME.2019.2969437.
[7] PJFWE, "Deep learning techniques for gesture recognition using EMG signals: A review," Journal of Neuroscience Methods, vol. 276, pp. 58–73, 2017. doi:10.1016/j.jneumeth.2017.06.004.
[8] BMAMKC, "Recent developments in electromyography signal-based hand gesture recognition for prosthetic control," IEEE Transactions on Human-Machine Systems, vol. 49, no. 4, pp. 309–318, Aug. 2019. doi:10.1109/THMS.2019.2903415.
[9] MYMHNY, "A deep learning approach for real-time EMG classification for robotic prosthetics," Journal of Artificial Intelligence in Medicine, vol. 107, pp. 101–114, Oct. 2020. doi:10.1016/j.artmed.2020.101019.
[10] TGPMFA, "Interpretability of deep learning models for medical applications," Nature Machine Intelligence, vol. 2, no. 1, pp. 1–9, 2020. doi:10.1038/s41586-020-2147-1.
[11] HLGMH, "Saliency mapping for neural network interpretability," Journal of Artificial Intelligence Research, vol. 64, pp. 1–19, Apr. 2020. doi:10.1613/jair.1.11932.
[12] GBHDK, "Performance evaluation of deep learning-based EMG signal classification for prosthetic applications," IEEE Transactions on Biomedical Engineering, vol. 66, no. 5, pp. 1242–1253, May 2019. doi:10.1109/TBME.2018.2888907.
[13] FJMTAG, "A real-time prosthesis control system using surface EMG signal classification," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 28, no. 6, pp. 1342–1352, June 2020. doi:10.1109/TNSRE.2020.2976347.
[14] LCACJ, "Prosthetic hand control using electromyographic signals: A review of recent approaches," IEEE Transactions on Biomedical Engineering, vol. 62, no. 12, pp. 2737-2747, Dec. 2015. doi:10.1109/TBME.2015.2448670.
[15] YSSGJ, "Understanding the deep learning approach for hand gesture recognition using EMG signals," IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 50, no. 1, pp. 155–165, Jan. 2020. doi:10.1109/TSMC.2019.2948888.