Recognition of Hand Gestures Based on EMG Signals with Deep and Double-Deep Q-Networks
Author:
Valdivieso Caraguay Ángel Leonardo1ORCID, Vásconez Juan Pablo2ORCID, Barona López Lorena Isabel1ORCID, Benalcázar Marco E.1ORCID
Affiliation:
1. Artificial Intelligence and Computer Vision Research Lab, Escuela Politécnica Nacional, Quito 170517, Ecuador 2. Faculty of Engineering, Universidad Andres Bello, Santiago, Chile
Abstract
In recent years, hand gesture recognition (HGR) technologies that use electromyography (EMG) signals have been of considerable interest in developing human–machine interfaces. Most state-of-the-art HGR approaches are based mainly on supervised machine learning (ML). However, the use of reinforcement learning (RL) techniques to classify EMGs is still a new and open research topic. Methods based on RL have some advantages such as promising classification performance and online learning from the user’s experience. In this work, we propose a user-specific HGR system based on an RL-based agent that learns to characterize EMG signals from five different hand gestures using Deep Q-network (DQN) and Double-Deep Q-Network (Double-DQN) algorithms. Both methods use a feed-forward artificial neural network (ANN) for the representation of the agent policy. We also performed additional tests by adding a long–short-term memory (LSTM) layer to the ANN to analyze and compare its performance. We performed experiments using training, validation, and test sets from our public dataset, EMG-EPN-612. The final accuracy results demonstrate that the best model was DQN without LSTM, obtaining classification and recognition accuracies of up to 90.37%±10.7% and 82.52%±10.9%, respectively. The results obtained in this work demonstrate that RL methods such as DQN and Double-DQN can obtain promising results for classification and recognition problems based on EMG signals.
Funder
National Polytechnic School
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference47 articles.
1. Jaramillo-Yánez, A., Benalcázar, M.E., and Mena-Maldonado, E. (2020). Real-Time Hand Gesture Recognition Using Surface Electromyography and Machine Learning: A Systematic Literature Review. Sensors, 20. 2. An overview of hand gestures recognition system techniques;Sulaiman;IOP Conference Series: Materials Science and Engineering,2015 3. Romero, R., Cruz, P.J., Vásconez, J.P., Benalcázar, M., Álvarez, R., Barona, L., and Valdivieso, Á.L. (2022, January 7–9). Hand Gesture and Arm Movement Recognition for Multimodal Control of a 3-DOF Helicopter. Proceedings of the International Conference on Robot Intelligence Technology and Applications, Daejeon, Republic of Korea. 4. Chico, A., Cruz, P.J., Vásconez, J.P., Benalcázar, M.E., Álvarez, R., Barona, L., and Valdivieso, Á.L. (2021, January 12–15). Hand Gesture Recognition and Tracking Control for a Virtual UR5 Robot Manipulator. Proceedings of the 2021 IEEE Fifth Ecuador Technical Chapters Meeting (ETCM), Cuenca, Ecuador. 5. Colli Alfaro, J.G., and Trejos, A.L. (2022). User-Independent Hand Gesture Recognition Classification Models Using Sensor Fusion. Sensors, 22.
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|