RESEARCH ON A HAND GESTURE RECOGNITION MODEL TO OPTIMIZE ROBOTIC HAND CONTROL
DOI:
https://doi.org/10.62985/j.huit_ojs.vol26.no2E.412Từ khóa:
Hand gesture recognition, Surface electromyography (sEMG), 1D-CNN, EMG classificationTóm tắt
Achieving accurate and responsive control of robotic hands remains a major challenge in human-machine interaction, particularly for applications requiring high dexterity such as prosthetic control and rehabilitation systems. Surface electromyography (sEMG) offers a non-invasive solution for capturing human motion intent; however, its nonlinear, non-stationary nature and susceptibility to noise significantly degrade recognition performance when using conventional methods. This paper proposes a robust sEMG-based hand gesture recognition framework that integrates systematic signal preprocessing, including noise filtering, normalization, and temporal segmentation, with a hybrid deep learning architecture. The proposed model combines a one-dimensional convolutional neural network (1D-CNN) for effective spatial and time–frequency feature extraction with a long short-term memory (LSTM) network to capture long-term temporal dependencies in multi-channel sEMG signals. Six fundamental hand gestures such as Rock, Paper, Scissors, Pointing, Hand Flexion, and Hand Relaxation are evaluated using a custom annotated sEMG dataset. Experimental results demonstrate that the proposed hybrid 1D-CNN–LSTM model achieves consistently high classification accuracies of 96.0% and 0.96 weighted F1-score, outperforming conventional 1D-CNN-based approaches relying solely on time-domain features. Furthermore, the proposed framework exhibits low computational complexity and strong inter-subject generalization, indicating its suitability for real-time robotic and prosthetic hand control applications.
Tài liệu tham khảo
[1] X. Zhao, J. Huang, J. Zheng, Y. Ma, and H. Tang, "A multimodal-signals-based gesture recognition method for human machine interaction," in 2020 3rd International Conference on Unmanned Systems (ICUS), 2020: IEEE, pp. 494-499. DOI: http://doi.org/10.1109/ICUS50048.2020.9274853
[2] Q. Zhang, T. Pi, R. Liu, and C. Xiong, "Simultaneous and proportional estimation of multijoint kinematics from EMG signals for myocontrol of robotic hands," IEEE/ASME Transactions on Mechatronics, vol. 25, no. 4, pp. 1953-1960, 2020. DOI: http://doi.org/10.1109/TMECH.2020.2999532
[3] D. Yang and H. Liu, "An EMG-based deep learning approach for multi-DOF wrist movement decoding," IEEE Transactions on Industrial Electronics, vol. 69, no. 7, pp. 7099-7108, 2021. DOI: http://doi.org/10.1109/TIE.2021.3097666
[4] N. Tsujiuchi, K. Takayuki, and M. Yoneda, "Manipulation of a robot by EMG signals using linear multiple regression model," in 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)(IEEE Cat. No. 04CH37566), 2004, vol. 2: IEEE, pp. 1991-1996. DOI: http://doi.org/10.1109/IROS.2004.1389690
[5] H.-P. Huang and C.-Y. Chen, "Development of a myoelectric discrimination system for a multi-degree prosthetic hand," in Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No. 99CH36288C), 1999, vol. 3: IEEE, pp. 2392-2397. DOI: http://doi.org/10.1109/ROBOT.1999.770463
[6] C. Xie, Q. Yang, Y. Huang, S. W. Su, T. Xu, and R. Song, "A hybrid arm-hand rehabilitation robot with EMG-based admittance controller," IEEE Transactions on Biomedical Circuits and Systems, vol. 15, no. 6, pp. 1332-1342, 2021. DOI: http://doi.org/10.1109/TBCAS.2021.3130090
[7] M. Soto-Florido et al., "Identification of Neuromotor Patterns Associated with Hand Rehabilitation Movements from EMG and EEG Signals," in 2025 International Conference On Rehabilitation Robotics (ICORR), 2025: IEEE, pp. 1307-1312. DOI: http://doi.org/10.1109/ICORR66766.2025.11063054
[8] D. K. Singh, A. P. Srivastava, S. Singh, S. Paliwal, A. Singh, and J. Singh, "Machine learning based Development and Evaluation of a Hand Exoskeleton Rehabilitation Robot for Patients with Partial Paralysis," in 2024 2nd International Conference on Disruptive Technologies (ICDT), 2024: IEEE, pp. 418-423. DOI: http://doi.org/10.1109/ICDT61202.2024.10489600
[9] N. Sanwlot, K. V. Raj, G. Udupa, and R. Anand, "Cost-Effective EMG Signal Acquisition for Rehabilitation Robotics using Single-Channel Sensors and Machine Learning," in 2024 2nd International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS), 2024: IEEE, pp. 1603-1609. DOI: http://doi.org/10.1109/ICSSAS64001.2024.10761024
[10] D. Farina et al., "Man/machine interface based on the discharge timings of spinal motor neurons after targeted muscle reinnervation," Nature biomedical engineering, vol. 1, no. 2, p. 0025, 2017. DOI: http://doi.org/10.1038/s41551-016-0025
[11] M. H. Zafar, S. K. R. Moosavi, and F. Sanfilippo, "Federated learning-enhanced edge deep learning model for EMG-based gesture recognition in real-time human-robot interaction," IEEE Sensors Journal, 2025. DOI: http://doi.org/10.1109/JSEN.2025.3529841
[12] A. A. Neacsu, G. Cioroiu, A. Radoi, and C. Burileanu, "Automatic EMG-based hand gesture recognition system using time-domain descriptors and fully-connected neural networks," in 2019 42nd International Conference on Telecommunications and Signal Processing (TSP), 2019: IEEE, pp. 232-235. DOI: http://doi.org/10.1109/TSP.2019.8768831
[13] N. Trivedi, I. Naik, N. Fadia, D. Karia, and N. Ghatte, "Universal Remote using EMG based Gesture Recognition," in 2021 IEEE Bombay Section Signature Conference (IBSSC), 2021: IEEE, pp. 1-5. DOI: http://doi.org/10.1109/IBSSC53889.2021.9673376
[14] P. Kang, S. Jiang, and B. He, "Diffusion-Driven Deep Decoding: Advancing EMG-Based Hand Skill Learning for Environment-Free Human–Robot Interaction," IEEE/ASME Transactions on Mechatronics, 2025. DOI: http://doi.org/10.1109/TMECH.2025.3546753
[15] M. Atzori, M. Cognolato, and H. Müller, "Deep learning with convolutional neural networks applied to electromyography data: A resource for the classification of movements for prosthetic hands," Frontiers in neurorobotics, vol. 10, p. 9, 2016. DOI: http://doi.org/10.3389/fnbot.2016.00009
[16] K. Bakırcıoğlu and N. Özkurt, "Classification of EMG signals using convolution neural network," International Journal of Applied Mathematics Electronics and Computers, vol. 8, no. 4, pp. 115-119, 2020. DOI: http://doi.org/10.18100/ijamec.795227
[17] N. Gehlot, R. Kumar, S. Hans, and P. Nkomozepi, "1D Convolutional Neural Architecture Search for sEMG Hand Gesture Recognition," SN Computer Science, vol. 6, no. 7, p. 789, 2025. DOI: http://doi.org/10.1007/s42979-025-04324-3
[18] M. Coskun, O. Yildirim, Y. Demir, and U. R. Acharya, "Efficient deep neural network model for classification of grasp types using sEMG signals," Journal of ambient intelligence and humanized computing, vol. 13, no. 9, pp. 4437-4450, 2022. DOI: http://doi.org/10.1007/s12652-021-03284-9
[19] N. Tsagkas, P. Tsinganos, and A. Skodras, "On the use of deeper CNNs in hand gesture recognition based on sEMG signals," in 2019 10th international conference on information, intelligence, systems and applications (IISA), 2019: IEEE, pp. 1-4. DOI: http://doi.org/10.1109/IISA.2019.8900709
[20] S. Briouza, H. Gritli, N. Khraief, S. Belghith, and D. Singh, "A convolutional neural network-based architecture for EMG signal classification," in 2021 International conference on data analytics for business and industry (ICDABI), 2021: IEEE, pp. 107-112. DOI: http://doi.org/10.1109/ICDABI53623.2021.9655876
[21] S. Bitzer and P. Van Der Smagt, "Learning EMG control of a robotic hand: towards active prostheses," in Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006., 2006: IEEE, pp. 2819-2823. DOI: http://doi.org/10.1109/ROBOT.2006.1642128
[22] M. Khezri and M. Jahed, "Surface electromyogram signal estimation based on wavelet thresholding technique," in 2008 30th annual international conference of the IEEE engineering in medicine and biology society, 2008: IEEE, pp. 4752-4755. DOI: http://doi.org/10.1109/IEMBS.2008.4650275
[23] G. Ouyang, X. Zhu, Z. Ju, and H. Liu, "Dynamical characteristics of surface EMG signals of hand grasps via recurrence plot," IEEE journal of biomedical and health informatics, vol. 18, no. 1, pp. 257-265, 2013. DOI: http://doi.org/10.1109/JBHI.2013.2261311
[24] C. Sapsanis, G. Georgoulas, A. Tzes, and D. Lymberopoulos, "Improving EMG based classification of basic hand movements using EMD," in 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2013: IEEE, pp. 5754-5757. DOI: http://doi.org/10.1109/EMBC.2013.6610858
[25] S. Kim, J. Kim, M. Kim, S. Kim, and J. Park, "Grasping force estimation by sEMG signals and arm posture: tensor decomposition approach," Journal of bionic engineering, vol. 16, no. 3, pp. 455-467, 2019. DOI: http://doi.org/10.1007/s42235-019-0037-0
[26] C. Wu, A. Song, Y. Ling, N. Wang, and L. Tian, "A control strategy with tactile perception feedback for EMG prosthetic hand," Journal of Sensors, vol. 2015, no. 1, p. 869175, 2015. DOI: http://doi.org/10.1155/2015/869175
[27] N. M. Kakoty and S. M. Hazarika, "Recognition of grasp types through principal components of DWT based EMG features," in 2011 IEEE International Conference on Rehabilitation Robotics, 2011: IEEE, pp. 1-6. DOI: http://doi.org/10.1109/ICORR.2011.5975398
[28] X. Tang, Y. Liu, C. Lv, and D. Sun, “Hand Motion Classification Using a Multi-Channel Surface Electromyography Sensor,” Sensors, vol. 12, no. 2, pp. 1130–1147, 2012. DOI: http://doi.org/10.3390/s120201130
[29] S. Taran and V. Bajaj, "Motor imagery tasks-based EEG signals classification using tunable-Q wavelet transform," Neural Computing and Applications, vol. 31, no. 11, pp. 6925-6932, 2019. DOI: http://doi.org/10.1007/s00521-018-3531-0
[30] F. Peng et al., "Gesture recognition by ensemble extreme learning machine based on surface electromyography signals," Frontiers in human neuroscience, vol. 16, p. 911204, 2022. DOI: http://doi.org/10.3389/fnhum.2022.911204
[31] J. Shin, A. S. M. Miah, S. Konnai, I. Takahashi, and K. Hirooka, "Hand gesture recognition using sEMG signals with a multi-stream time-varying feature enhancement approach," Scientific Reports, vol. 14, no. 1, p. 22061, 2024. DOI: http://doi.org/10.1038/s41598-024-72996-7
