Electromyographic (EMG) signal classification paves the road for many human-machine interface applications where EMG sensors capture muscle activity for further processing and application. In this work, the performance of several machine learning algorithms is tested, including Decision Trees, Random Forests (RF), K-Nearest Neighbors (KNN), Extreme Gradient Boosting (XGBoost), Long Short-Term Memory (LSTM), and Convolutional Neural Network-Long Short Term Memory (CNN- LSTM). These models are evaluated and compared using EMG data collected from approximately 30 subjects performing six distinct gestures. In addition, a hybrid CNN-LSTM model is proposed to achieve an accurate yet low-cost EMG classification. Moreover, the performance of these algorithms is compared on both Central Processing Unit (CPU) and Graphics Processing Unit (GPU) platforms in terms of accuracy, training/testing time, and hardware utilization. Results show that the RF algorithm gives the best performance with an accuracy of 98.16%. On the other hand, the decision tree algorithm gives a trade-off between the accuracy and computational efficiency, with 95.46% accuracy, and approximately 17.6 times faster compared to RF, making it more suitable for real-time applications and limited resources environments. On the other hand, deep learning models acquired noticeably higher computational time compared to classical algorithms. This research demonstrates the importance of selecting a suitable classification algorithm and hardware platform to achieve an efficient EMG classification.

[1] Abbaspour S., Naber A., Catalan M., GholamHosseini H., and Linden M., “Real-Time and Offline Evaluation of Myoelectric Pattern Recognition for the Decoding of Hand Movements,” Sensors, vol. 21, no. 16, pp. 1-17, 2021. https://doi.org/10.3390/s21165677

[2] Blockeel H., Devos L., Frenay B., Nanfack G., and Nijssen S., “Decision Trees: from Efficient Prediction to Responsible AI,” Frontiers in Artificial Intelligence, vol. 6, pp. 1-17, 2023. https://doi.org/10.3389/frai.2023.1124553

[3] Eddy E., Campbell E., Bateman S., and Scheme E., “Big Data in Myoelectric Control: Large Multi-User Models Enable Robust Zero-Shot EMG-based Discrete Gesture Recognition,” Frontiers in Bioengineering and Biotechnology, vol. 12, pp. 1-24, 2024. https://doi.org/10.3389/fbioe.2024.1463377

[4] Ersin C. and Yaz M., “Comparison of KNN and Random Forest Algorithms in Classifying EMG Signal,” Avrupa Bilim ve Teknoloji Dergisi, vol. 51, pp. 209-216, 2023. https://doi.org/10.31590/ejosat.1285176

[5] Espinoza D. and Velasco L., “Comparison of EMG Signal Classification Algorithms for the Control of an Upper Limb Prosthesis Prototype,” in Proceedings of the 17th International Conference Electrical Engineering, Computing Science and Automatic Control, Mexico City, pp. 1-4, 2020. https://doi.org/10.1109/CCE50788.2020.9299208

[6] Fleming A., Stafford N., Huang S., Hu X., and et al., “Myoelectric Control of Robotic Lower Limb Prostheses: A Review of Electromyography Interfaces, Control Paradigms, Challenges and Future Directions,” Journal of Neural Engineering, vol. 18, no. 4, pp. 1741-2552, 2021. https://doi.org/10.1088/1741-2552/ac1176

[7] Ghosh S., “Comparing Regular Random Forest Model with Weighted Random Forest Model for Classification Problem,” International Journal of Statistics and Applications, vol. 14, no. 1, pp. 7- 12, 2024. DOI:10.5923/j.statistics.20241401.02

[8] Huang D. and Chen B., “Surface EMG Decoding for Hand Gestures Based on Spectrogram and CNN-LSTM,” in Proceedings of the 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, Xi’an, pp. 123-126, 2019. https://doi.org/10.1109/CCHI.2019.8901936

[9] Jabbari M., Khushaba R., and Nazarpour K., “EMG-Based Hand Gesture Classification with Long Short-Term Memory Deep Recurrent Neural Networks,” in Proceedings of the 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Montreal, pp. 3302-3305, 2020. https://doi.org/10.1109/EMBC44109.2020.9175279

[10] Karnam N., Dubey S., Turlapaty A., and Gokaraju B., “EMGHandNet: A Hybrid CNN and Bi-LSTM Architecture for Hand Activity Classification Using Surface EMG Signals,” Biocybernetics and Biomedical Engineering, vol. 42, pp. 325-340, 2022. https://doi.org/10.1016/j.bbe.2022.02.005

[11] Khan M., Khan H., Muneeb M., Abbasi Z., and et al., “Supervised Machine Learning-based Fast Machine and Deep Learning Model for EMG Signal Classification: A New Performance ... 323 Hand Gesture Recognition and Classification Using Electromyography (EMG) Signals,” in Proceedings of the International Conference on Applied and Engineering Mathematics, Taxila, pp. 1-6, 2021. https://doi.org/10.1109/ICAEM53552.2021.9547 148

[12] Kok C., Ho C., Tan F., and Koh Y., “Machine Learning-based Feature Extraction and Classification of EMG Signals for Intuitive Prosthetic Control,” Applied Sciences, vol. 14, no. 13, pp. 1-29, 2024. https://doi.org/10.3390/app14135784

[13] Krilova N., Kastalskiy I., Kazantsev V., Makarov V., and Lobov S., EMG Data for Gestures, UCI Machine Learning Repository, https://doi.org/10.24432/C5ZP5C, Last Visited, 2025.

[14] Krstinic D., Braovic M., Seric L., and Stulic D., “Multi-Label Classifier Performance Evaluation with Confusion Matrix,” Computer Science and Information Technology, vol. 10, no. 8, pp. 1-14, 2020. https://csitcp.org/abstract/10/108csit01

[15] Kundu B. and Naidu D., “Classification and Feature Extraction of Different Hand Movements from EMG Signal Using Machine Learning-based Algorithms,” in Proceedings of the International Conference on Electrical, Communication, and Computer Engineering, Kuala Lumpur, pp. 1-66, 2021. https://doi.org/10.1109/ICECCE52056.2021.9514 134

[16] Lee K., Min J., and Byun S., “Electromyogram- based Classification of Hand and Finger Gestures Using Artificial Neural Networks,” Sensors, vol. 22, no. 1, pp. 1-20, 2021. https://doi.org/10.3390/s22010225

[17] Liu Y., Breceda A., Karoly P., Grayden D., and et al., “Brain Model State Space Reconstruction Using an LSTM Neural Network,” Journal of Neural Engineering, vol. 20, no. 3, pp. 1-14, 2023. DOI: 10.1088/1741-2552/acd871

[18] Lopez J., Aviles M., Perez D., Socarras I., and Resendiz J., “Electromyography Signals in Embedded Systems: A Review of Processing and Classification Techniques,” Biomimetics, vol. 10, no. 3, pp. 1-25, 2025. https://doi.org/10.3390/biomimetics10030166

[19] Lopez L., Ferri F., Zea J., Caraguay A., and Benalcazar M., “CNN-LSTM and Post- Processing for EMG-based Hand Gesture Recognition,” Intelligent Systems with Applications, vol. 22, pp. 1-12, 2024. https://doi.org/10.1016/j.iswa.2024.200352

[20] Maged A., Elshaboury N., and Akanbi L., “Data- Driven Prediction of Construction and Demolition Waste Generation Using Limited Datasets in Developing Countries: An Optimized Extreme Gradient Boosting Approach,” Environment, Development and Sustainability, vol. 27, pp. 26865-26889, 2024. https://doi.org/10.1007/s10668-024-04814-z

[21] Omar S., Kimwele M., Olowolayemo A., and Kaburu D., “Enhancing EEG Signals Classification Using LSTM-CNN Architecture,” Engineering Reports, vol. 6, no. 9, pp. 1-23, 2023. https://doi.org/10.1002/eng2.12827

[22] Ossaba A., Tigreros J., Tejada J., Pena A., and et al., “LSTM Recurrent Neural Network for Hand Gesture Recognition Using EMG Signals,” Applied Sciences, vol. 12, no. 19, pp. 1-21, 2022. https://www.mdpi.com/2076-3417/12/19/9700#

[23] Ozdemir M., Kisa D., Guren O., and Akan A., “Hand Gesture Classification Using Time- Frequency Images and Transfer Learning Based on CNN,” Biomedical Signal Processing and Control, vol. 77, pp. 103787, 2022. https://doi.org/10.1016/j.bspc.2022.103787

[24] Priyanka. and Kumar D., “Decision Tree Classifier: A Detailed Survey,” International Journal of Information and Decision Sciences, vol. 12, no. 3, pp. 246-269, 2020. https://doi.org/10.1504/IJIDS.2020.108141

[25] Rajapriya R., Rajeswari K., and Thiruvengadam S., “Deep Learning and Machine Learning Techniques to Improve Hand Movement Classification in Myoelectric Control System,” Biocybernetics and Biomedical Engineering, vol. 41, no. 2, pp. 554-571, 2021. https://doi.org/10.1016/j.bbe.2021.03.006

[26] Rodrigues C., Fernandez M., Megia A., Comino N., and et al., “Comparison of Intramuscular and Surface Electromyography Recordings Towards the Control of Wearable Robots for Incomplete Spinal Cord Injury Rehabilitation,” in Proceedings of the 8th IEEE RAS/EMBSs International Conference for Biomedical Robotics and Biomechatronics, New York, pp. 564-569, 2020. DOI: 10.1109/BioRob49111.2020.9224361

[27] Saurav Z., Mitu M., Ritu N., Hasan M., and et al., “A New Method for Learning Decision Tree Classifier,” in Proceedings of the IEEE International Conference Electrical, Computer and Communication Engineering, Chittagong, pp. 1-6, 2023. https://doi.org/10.1109/ECCE57851.2023.101015 57

[28] Senagi K. and Jouandeau N., “Parallel Construction of Random Forest on GPU,” Journal of Supercomputing, vol. 78, no. 8, pp. 10480- 10500, 2022. https://doi.org/10.1007/s11227-021- 04290-6

[29] Wahid F., Tafreshi R., Al-Sowaidi M., and Langari R., “Subject-Independent Hand Gesture Recognition Using Normalization and Machine Learning Algorithms,” Journal of Computational 324 The International Arab Journal of Information Technology, Vol. 23, No. 2, March 2026 Science, vol. 27, pp. 69-76, 2018. https://doi.org/10.1016/j.jocs.2018.04.019

[30] Waris A., Niazi I., Jamil M., Englehart K., and et al., “Multiday Evaluation of Techniques for EMG- based Classification of Hand Motios,” IEEE Journal of Biomedical and Health Informatics, vol. 23, no. 4, pp. 1526-1534, 2019. https://doi.org/10.1109/JBHI.2018.2864335

[31] Wen W., Shi J., He B., Li Q., and Cui B., “ThunderGBM: Fast GBDTs and Random Forests on GPUs,” Journal of Machine Learning Research, vol. 21, no. 108, pp. 1-5, 2020. https://www.jmlr.org/papers/v21/19-095.html

[32] Yuan B., Hu D., Gu S., Xiao S., and Song F., “The Global Burden of Traumatic Amputation in 204 Countries and Territories,” Frontiers in Public Health, vol. 11, pp. 1-15, 2023. https://doi.org/10.3389/fpubh.2023.1258853

[33] Zhao J., She J., Wang D., and Wang F., “Patient Classification Based on sEMG Signals Using Extreme Gradient Boosting Algorithm,” in Proceedings of the 7th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, Beijing, pp. 1-5, 2021. https://iwaciii2021.bit.edu.cn/docs/2021- 12/bf17766b3bd04ef98dc5faf3706d14ce.pdf