Advancing EMG Finger Movement Classification with Feature Extraction and Machine Learning

Moysar, Rasha; Abdullah, Mohammed Abdulmuttaleb

doi:10.33899/arej.2024.152539.1368

	Advancing EMG Finger Movement Classification with Feature Extraction and Machine Learning
Al-Rafidain Engineering Journal (AREJ)
Volume 30, Issue 1, March 2025, Pages 150-163 PDF (1.07 M)
Document Type: Research Paper
DOI: 10.33899/arej.2024.152539.1368
Authors
Rasha Moysar; Mohammed Abdulmuttaleb Abdullah^*
Computer and Information Engineering Department, College of Electronics Engineering, Ninevah University, Mosul, Iraq
Abstract
In prosthetic finger development using electromyogram (EMG) data, a crucial challenge is accurately recognizing finger movements, thus requiring developed models that process EMG signals, facilitating independent finger gesture classification with high accuracy. To successfully classify an EMG signal, the feature selection should be carefully evaluated. However, many studies on EMG signal classification have employed a feature set that includes several redundant elements. In this study, several combinations of time domain features are employed for EMG signal reduction. In addition, two models of CNN namely: (CNN-1, CNN-2), DFNN, LSTM, and GRU architectures are proposed to provide high accuracy with minimal computational overhead and minimum parameters. Through careful model selection and hyperparameter optimization, the models’ effectiveness was enhanced. The models were evaluated based on accuracy, precision, recall, and F1-score metrics. Among the proposed models, CNN-1 resulted in a good balance in terms of accuracy, computational time, and memory size, with an accuracy of 97.3 in 0.96 minutes with 890.73 KB size of memory. Furthermore, a comparison against earlier work confirmed the efficacy of the approach.
Keywords
Electromyography (EMG); Machine Learning (ML); Convolution Neural Network (CNN); Deep Feedforward Neural Network (DFNN); Long Short-Term Memory (LSTM); Gated Recurrent Units (GRUs)

References
[1] C. Tepe and M. Erdim, "Classification of emg finger data acquired with myo armband," in 2020 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), 2020: IEEE, pp. 1-4.doi: 10.1109/HORA49412.2020.9152850 [2] A. Subasi, E. Yaman, Y. Somaily, H. A. Alynabawi, F. Alobaidi, and S. Altheibani, "Automated EMG signal classification for diagnosis of neuromuscular disorders using DWT and bagging," Procedia Computer Science, vol. 140, pp. 230-237, 2018.doi.org/10.1016/j.procs.2018.10.333 [3] G. Jia, H.-K. Lam, J. Liao, and R. Wang, "Classification of electromyographic hand gesture signals using machine learning techniques," Neurocomputing, vol. 401, pp. 236-248, 2020.doi.org/10.1016/j.neucom.2020.03.009 [4] Z. Taghizadeh, S. Rashidi, and A. Shalbaf, "Finger movements classification based on fractional fourier transform coefficients extracted from surface emg signals," Biomedical Signal Processing and Control, vol. 68, p. 102573, 2021.doi.org/10.1016/j.bspc.2021.102573 [5] E. Gokgoz and A. Subasi, "Comparison of decision tree algorithms for EMG signal classification using DWT," Biomedical signal processing and control, vol. 18, pp. 138-144, 2015.doi.org/10.1016/j.bspc.2014.12.005 [6] A. Phinyomark, P. Phukpattaranont, and C. Limsakul, "Feature reduction and selection for EMG signal classification," Expert systems with applications, vol. 39, no. 8, pp. 7420-7431, 2012.doi.org/10.1016/j.eswa.2012.01.102 [7] M. Jabbari, R. N. Khushaba, and K. Nazarpour, "EMG-based hand gesture classification with long short-term memory deep recurrent neural networks," in 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2020: IEEE, pp. 3302-3305. doi: 10.1109/EMBC44109.2020.9175279 [8] Z. Li, J. Zuo, Z. Han, X. Han, C. Sun, and Z. Wang, "Intelligent classification of multi-gesture EMG signals based on LSTM," in 2020 International Conference on Artificial Intelligence and Electromechanical Automation (AIEA), 2020: IEEE, pp. 62-65. doi: 10.1109/AIEA51086.2020.00020 [9] M. Aviles, J. M. Alvarez-Alvarado, J.-B. Robles-Ocampo, P. Y. Sevilla-Camacho, and J. Rodríguez-Reséndiz, "Optimizing RNNs for EMG Signal Classification: A Novel Strategy Using Grey Wolf Optimization," Bioengineering, vol. 11, no. 1, p. 77, 2024.doi.org/10.3390/bioengineering11010077 [10] C. K. Bhattachargee, N. Sikder, M. T. Hasan, and A.-A. Nahid, "Finger movement classification based on statistical and frequency features extracted from surface EMG signals," in 2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2), 2019: IEEE, pp. 1-4. doi: 10.1109/IC4ME247184.2019.9036671 [11] A. Subasi and E. Yaman, "EMG signal classification using discrete wavelet transform and rotation forest," in CMBEBIH 2019: Proceedings of the International Conference on Medical and Biological Engineering, 16 18 May 2019, Banja Luka, Bosnia and Herzegovina, 2020: Springer, pp. 29-35.doi.org/10.1007/978-3-030-17971-7_5 [12] C. Millar, N. Siddique, and E. Kerr, "LSTMclassification of sEMG signals for individual finger movements using low cost wearable sensor," in 2020 International Symposium on Community-centric Systems (CcS), 2020: IEEE, pp. 1-8. doi: 10.1109/CcS49175.2020.9231515 [13] A. Subasi, "Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders," Computers in biology and medicine, vol. 43, no. 5, pp. 576-586, 2013.doi.org/10.1016/j.compbiomed.2013.01.020 [14] M. Simão, P. Neto, and O. Gibaru, "EMG-based online classification of gestures with recurrent neural networks," Pattern Recognition Letters, vol. 128, pp. 45-51, 2019.doi.org/10.1016/j.patrec.2019.07.021 [15] D. Huang and B. Chen, "Surface EMG decoding for hand gestures based on spectrogram and CNN-LSTM," in 2019 2nd China Symposium on Cognitive Computing and Hybrid Intelligence (CCHI), 2019: IEEE, pp. 123-126.doi: 10.1109/CCHI.2019.8901936 [16] V. B. Srinivasan, M. Islam, W. Zhang, and H. Ren, "Finger movement classification from myoelectricsignals using convolutional neural networks," in 2018 IEEE international conference on robotics and biomimetics (ROBIO), 2018: IEEE, pp. 1070-1075.doi: 10.1109/ROBIO.2018.8664807 [17] N. Naseer, F. Ali, S. Ahmed, S. Iftikhar, R. A. Khan, and H. Nazeer, "EMG based control of individual fingers of robotic hand," in 2018 International Conference on Sustainable Information Engineering and Technology (SIET), 2018: IEEE, pp. 6-9. doi: 10.1109/SIET.2018.8693177 [18] S. Krishnan, R. Akash, D. Kumar, R. Jain, K. M. M. Rathai, and S. Patil, "Finger movement pattern recognition from surface EMG signals using machine learning algorithms," in ICTMI 2017: Proceedings of the International Conference on Translational Medicine and Imaging, 2019: Springer, pp. 75-89. doi.org/10.1007/978-981-13-1477-3_7 [19] M. Fındık, Ş. Yılmaz, and M. Koseoglu, "Random forest classification of finger movements using electromyogram (emg) signals," in 2020 IEEE SENSORS, 2020: IEEE, pp. 1-4. doi: 10.1109/SENSORS47125.2020.9278619 [20] M. V. Arteaga, J. C. Castiblanco, I. F. Mondragon, J. D. Colorado, and C. Alvarado-Rojas, "EMG-driven hand model based on the classification of individual finger movements," Biomedical Signal Processing and Control, vol. 58, p. 101834, 2020.doi.org/10.1016/j.bspc.2019.101834 [21] K. H. Lee, J. Y. Min, and S. Byun, "Electromyogram-based classification of hand and finger gestures usingartificial neural networks," Sensors, vol. 22, no. 1, p. 225, 2021.doi.org/10.3390/s22010225 [22] C. Tepe and M. Erdim, "Classification of surface electromyography and gyroscopic signals of finger gestures acquired by Myo armband using machine learning methods," Biomedical Signal Processing and Control, vol. 75, p. 103588, 2022.doi.org/10.1016/j.bspc.2022.103588 [23] G. Kumar, S. S. Yadav, and V. Pal, "Machine learning-based framework to predict finger movement for prosthetic hand," IEEE Sensors Letters, vol. 6, no. 6, pp. 1-4, 2022.doi: 10.1109/LSENS.2022.3147518 [24] A. Sultana, F. Ahmed, and M. S. Alam, "A systematic review on surface electromyography-based classification system for identifying hand and finger movements," Healthcare Analytics, vol. 3, p. 100126, 2023.doi.org/10.1016/j.health.2022.100126 [25] A. Sultana, M. T. I. Opu, F. Ahmed, and M. S. Alam, "A novel machine learning algorithm for finger movement classification from surface electromyogram signals using welch power estimation," Healthcare Analytics, vol. 5, p. 100296,2024.doi.org/10.1016/j.health.2023.100296 [26] N. M. Esa, A. M. Zain, and M. Bahari, "Electromyography (EMG) based classification of finger movements using SVM," International Journal of Innovative Computing, vol. 8, no. 3, 2018.doi.org/10.11113/ijic.v8n3.181 [27] J. Kobylarz, J. J. Bird, D. R. Faria, E. P. Ribeiro, and A. Ekárt, "Thumbs up, thumbs down: non-verbal human-robot interaction through real-time EMG classification via inductive and supervised transductive transfer learning," Journal of Ambient Intelligence and Humanized Computing, vol. 11, pp. 6021-6031, 2020. doi.org/10.1007/s12652-020-01852-z [28]…….https://www.kaggle.com/datasets/nccvector/electromyography-emg-dataset [29]…….https://www.dreamstime.com/royalty-free-stock-photos-woman-hand-scissors-gesture-image28257308 [30] R. Jain and V. K. Garg, "EMG Signal Feature Extraction, Normalization and Classification for Pain and Normal Muscles Using Genetic Algorithm and Support Vector Machine," Revue d'Intelligence Artificielle, vol. 34, no. 5, 2020.doi:10.18280/ria.340517 [31] H. O. Farag et al., "Electromyography Signal Classification using Convolution Neural Network Architecture for Bionic Arm High Level Control," in 2021 16th International Conference on Computer Engineering and Systems (ICCES), 2021: IEEE, pp. 1-6.doi: 10.1109/ICCES54031.2021.9686171 [32] R. Jain and V. K. Garg, "EMG classification using nature-inspired computing and neural architecture," in 2021 9th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions)(ICRITO), 2021: IEEE, pp. 1-5. doi: 10.1109/ICRITO51393.2021.9596077 [33] T. M. Bittibssi, M. A. Genedy, and S. A. Maged, "sEMG pattern recognition based on recurrent neural network," Biomedical Signal Processing and Control, vol. 70, p. 103048, 2021.doi: 10.1109/HORA49412.2020.9152850
Statistics Article View: 502 PDF Download: 127