ABSTRACT
This work proposes a neural reinforcement learning (NRL) identifier for accurate classification finger movements for typing tasks using forearm Electromyogram (EMG) signals. We first extract four key statistical features from the EMG signals (channel 1 and channel 2) corresponding to seven typing keys. Next, these features are fed to a reinforcement learning based k nearest neighbor neural classifier for identifying the keys using a "trial and error" approach. We use EMG data from typing tasks of ten subjects using two acquisition electrodes: channel 1 and channel 2. In the first part of our work, we attempt to classify typing keys using EMG data corresponding to one subject only. After sufficient learning, NRL classifier achieved an accuracy of 99.01% and 98.29% for channel 1 and channel 2, respectively. In second part of our work, we fed the EMG data of all the ten subjects to the NRL. The NRL is able to achieve a classification accuracy of 92.7%. We also employ a subspace ensemble nearest neighbor approximator yielding a classification accuracy of 94.3% with 5-cross fold validation and 97.1% with 3-cross fold validation. Results show the effectiveness and viability of using NRL for identifying typing movements using forearm EMG signals.
- N. Uchida et al., "EMG Pattern Recognition by Neural Networks for Multi Fingers Control" Engineering in Medicine and Biology Society, 14th Annual International Conference of the IEEE, Oct,29 1992-Nov,1 1992, pp. 1016--1018.Google Scholar
- M. Skurichina et al., "Bagging, Boosting and the Random Subspace Method for Linear Classifiers", Pattern Analysis & Applications, Vol. 5, 2002, pp. 121--135.Google ScholarCross Ref
- R. Sharma, and M. Gopal, "Synergizing Reinforcement Learning and Game Theory - A new direction for Control," ASOC Journal, Elsevier Sciences, vol. 10, issue 3, pp. 675--688, June 2010. Google ScholarDigital Library
- Wiering, M., van Otterlo M., Reinforcement Learning: State-of-the-Art. vol. 12, Adaptation, Learning and Optimization, M. (Eds.), Springer, Berlin, 2012.Google Scholar
- R. Sharma, "Lyapunov theory based Stable Markov Game Fuzzy Control for Non Linear Systems", Engineering Applications of Artificial Intelligence, Elsevier Sciences, vol. 55, pp. 119--127, 2016. Google ScholarDigital Library
- H. Malik and R. Sharma, "EMD and ANN based intelligent fault diagnosis model for Transmission Line", Journal of Intelligent & Fuzzy Systems, vol. 32, pp. 3043--3050, 2017.Google ScholarCross Ref
- K. Ishikawa et al. "Finger Motion Classification Using Surface-electromyogram Signals" 9th IEEE/ACIS International Conference on Computer and Information Science, 18-20 Aug. 2010, pp. 37--42. Google ScholarDigital Library
- Ali H. Al-Timemy et al., "Classification of finger movements for the dexterous hand prosthesis control with surface electromyography" IEEE Journal of Biomedical and Health Informatics, vol. 17, no. 3, May 2013, pp. 608--618.Google ScholarCross Ref
- M.W. Jiang, R.C. Wang, J.Z Wang, D.W. Jin. "A method of Recognizing finger motion using Wavelet transform of surface EMG signal", Proc. IEEE, EMBC, Shanghai, China, Sept, 1--4, 2015.Google Scholar
- S.M.Mane, R.A.Kamblib, F.S.Kazi and N.M. Singh, "Hand Motion Recognition from Single Channel Surface EMG Using Wavelet & Artificial Neural Network", Procedia Computer Science, vol. 49, pp. 58--65, 2015.Google ScholarCross Ref
- S. Sharma, H. Farooq and N. Chahal, "Feature Extraction and Classification of Surface EMG Signals for Robotic Hand Simulation", Communications on Applied Electronics 4(2), pp. 27--31, January 2016.Google ScholarCross Ref
Index Terms
- Neural Reinforcement Learning based Identifier for Typing Keys using Forearm EMG Signals
Recommendations
Real-Time Replication of Arm Movements Using Surface EMG Signals
AbstractIn this paper, a real time application to replicate nine arm movements is proposed. The two important joints that are controlled are wrist and elbow. Electromyogram signals are recorded for four wrist positions and five elbow positions. These ...
Game-based EMG biofeedback system for muscle training in the elderly
i-CREATe '11: Proceedings of the 5th International Conference on Rehabilitation Engineering & Assistive TechnologyThis paper presents a game-based EMG biofeedback system for training the tibialis anterior muscle in elderly persons. The strong tibialis anterior muscle can reduce the risk of loss of balance, which causes fall in the elderly. Therefore, the volunteers ...
Using Forearm Electromyograms to Classify Hand Gestures
BIBM '09: Proceedings of the 2009 IEEE International Conference on Bioinformatics and BiomedicineProsthetic hands of increasing capability and sophistication are being built, but how does the user tell the hand what to do? One method is to use the low-level electrical signals associated with forearm muscle movement, or electrogmyograms (EMGs). This ...
Comments