Enhancing EMG Signals for Amputee People with Deep Neural Network and Optimization Algorithms


DOI:
https://doi.org/10.5281/zenodo.15099262Keywords:
EMG signals, deep neural networks, optimization, data preprocessingAbstract
Individuals with amputations often rely on prosthetic limbs to maintain daily functionality; however, over time, the performance of these devices can be compromised by wear, signal degradation, or other technical issues. In this study, we investigate the enhancement of electromyography (EMG) signals to mitigate changes in signal characteristics associated with long-term use by amputees. Our approach employs deep neural networks (DNN) integrated with various optimization algorithms. Data were acquired using an MYO Armband on the right arms of seven volunteers performing repeated fist clenching until muscle fatigue set in. The acquired data were augmented using synthetic data generation techniques and subsequently processed with a DNN that incorporated methods such as Principal Component Analysis (PCA), low variance and high correlation filters, nonlinear convolution layers, ensemble learning, bagging, batch normalization, and optimization algorithms including Stochastic Gradient Descent (SGD), Adagrad, RMSprop, Adam, and Particle Swarm Optimization (PSO). The performance was evaluated using metrics such as accuracy, precision, recall, and F-measure. Without optimization, the precision was 0.76; however, after extensive testing of various algorithmic combinations and synthetic data augmentation, the best configuration achieved a precision of approximately 0.98. These findings demonstrate that, with carefully selected deep learning and optimization strategies, EMG signals can be processed in near real-time, thereby significantly reducing the impact of mobility limitations.
References
Abel, E.W., Zacharia, P.C., Forster, A., Farrow, T.L., 1996. Neural network analysis of the EMG interference pattern. Medical Engineering and Physics, 18(1): 12-17.
Andreas, G., Studer, R.M., de Figueiredo Rui J.P., Moschytz George, S., 1984. A new framework and computer program for quantitative emg signal analysis. IEEE Transactions on Biomedical Engineering, 31(12).
Artemiadis, P.K., Kyriakopoulos, K.J., 2007. EMG-based position and force control of a robot arm: Application to teleoperation and orthosis. IEEE/ASME International Conference on Advanced Intelligent Mechatronics, pp:6.
Bernhardt, P., 2015. MYO Developer Blog. (https://developerblog.myo.com/), (Access Date: 03.01.2025).
Bodruzzaman, M., Devgan, S., Kari, S., 1992. Chaotic classification of electromyographic (EMG) signals via correlation dimension measurement. IEEE Proceedings of South-East Conference, Birmingham, pp. 95-98.
Cichosz, P., 2015. Data Mining Algorithms: Explained Using R. United States: John Wiley & Sons.
Çarkacı, N., 2018. Derin öğrenme uygulamalarında en sık kullanılan hiper parameteler. (https://medium.com/deep-learning-turkiye/derin-ogrenme-uygulama larinda-en-sik-kullanilan-hiper-parametre ler-ece8e9125c4), (Accessed: 05.01.2025).
Daniel, G., William, K.C., 1975. Functional separation of EMG signals via ARMA identification methods for prosthesis control purposes. Conference Proceedings of Systems, Man and Cybernetics International Conference on IEEE, pp. 252-259.
Doerschuk Peter, C., Donald E., Gustafon, A., Willsky, S., 1983. Upper extremity limb function discrimination using EMG signal analysis. Biomedical Engineering, 18-29.
Dwyer, G., Noguchi, Y., Szeto, H.H., 1989. EMG burst waveform recognition procedure. Proceedings of the 1989 Fifteenth Annual Northeast on Bioengineering Conference, 27-28th March, Boston, MA, pp. 235-236.
Edward, A., Clancy Neville H., 1995. Multiple site electromyograph amplitude estimation. IEEE Transactions on Biomedical Engineering, 42(2).
Erin, K., Boru, B., 2018. Real-time control of industrial robot arm with EMG and gyroscope data. Sakarya University Journal of Science, 22(2): 509-515.
Farina, D., Merletti, R., 2000. Comparison of algorithms for estimation of EMG variables during voluntary isometric contractions. Journal of Electro-myography and Kinesiology, 10(5): 337-349.
Fernandez, C., Soria, E., Martin, J.D., Serrano, A.J., 2006. Neural networks for animal science applications: Two case studies. Expert Systems With Applications. 31: 444-450.
Friedman, J.H., 2001. Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5): 1189-1232.
Fukuda, O., Tsujı, T., Ohtsuka A., Kaneko, M., 1998. EMG-based human-robot ınterface for rehabilitation aid. IEEE International Conference on Robotics and Automation, Proceedings Book, pp. 3492-3497.
Fukuda, O., Tsuji, T., Kaneko, M., 1997. An EMG controlled robotic manipulator using neural networks. 6th IEEE International Workshop on Robot and Human Communication, Proceedings Book, 29 September-1 October, pp.442-447.
Fukuda, O., Tsuji, T., Ohtsuka, A., Kaneko, M., 1998. EMG-based human-robot interface for rehabilitation aid. IEEE International Conference on Robotics and Automation, Proceedings Book, 16-20 May, pp. 3492-3497.
Geoffrey, L.S., 2012. Application of time-varying analysis to diagnostic needle electromyography, Medical Engineering & Physics, 34(2): 249-255.
Goen, A., 2014. Classification of EMG signals for assessment of neuromuscular disorders. International Journal of Electronics and Electrical Engineering, 2(3).
Graupe, D., 1989. EMG Pattern analysis for patient-responsive control of fes in paraplegics for walker-supported walking. IEEE Transactions on Bio-medical Engineering, 36(7): 711-721.
Graupe, D., Kohn, K.H., Basseas, S.P., 1989. Control of electrically-stimulated walk-ing of paraplegics via above- and below-lesion EMG signature identification. IEEE Transactions on Automatic Control, 34(2): 130-138.
Gurbuz, S., 2020. Deep Neural Network Design for Radar Applications. The Institution of Engineering and Technology: Stevenage, UK.
Gut, R., Moschytz George S., 2000. High-precision EMG signal decomposition using communication techniques. IEEE Transactions on Signal Processing, 48(9): 2487-2494.
Gwo-Ching, C., Wen-Juh, K., Jer-Junn, L., Cheng-Kung, C., Jin-Hae-Jeong, P., Sung-Hoon, K., Hee-Chan K., Kwang-Suk, P., 1999. Adaptive EMG-driven communication for the disabled. Proceedings of Engineering in Medicine and Biology, 21st Annual Conference and of the Bio-medical Engineering Society Conference, 13-16 October, Atlanta, GA.
Hefftner, G., Zucchini, W., Jaros, G.G., 1988. The electromyogram (EMG) as a control signal for functional neuromuscular stimulation. I. Autoregressive modeling as a means of EMG signature discrimination. IEEE Transactions on Biomedical Engineering, 35(4): 230-237.
Henneberg, K.A., Plonsey, R., 1993. Boundary element analysis of the directional sensitivity of the concentric EMG electrode. IEEE Transactions on Bio-medical Engineering, 40(7), 621-631.
Hershler, C., Morris M., 1978. An optimality criterion for processing electromyographic (EMG) signals relating to human locomotion. Biomedical Engineering, IEEE Transactions, pp. 413-420.
Hiraiwa, A., Yukio Tokunaga, K.S., 1989. EMG Pattern Analy-sis and Classification by Neural Network. Conference Proceedings of Systems, Man and Cybernetics International Conference on IEEE, pp. 1113-1115.
Hultman, E., Sjöholm, H., 1983. Electromyogram, force and relaxation time during and after continuous electrical stimulation of human skeletal muscle in situ. The Journal of Physiology, 33-40.
Ito, K., Tsuji, T., Kato, A., Ito, M., 1992. An EMG controlled prosthetic forearm in three degrees of freedom using ultrasonic motors. 14th Annual International Conference of the IEEE on Engineering in Medicine and Biology Society, Oct 29-Nov 1, Paris, pp.1487-1488.
Jingdong, Z., Zongwu, X., Li, J., Hegao, C., Hong, L., Hirzinger, G., 2006. EMG control for a five-fingered prosthetic hand based on wavelet trans-form and autoregressive model. Proceedings of the 2006 IEEE International Conference on Mechatronics and Automation, 25-28 June, Luoyang, Henan, pp.1097-1102.
Jun-Uk C., Inhyuk, M., Yun-Jung, L., Shin-Ki, K., Mu-seong, M., 2007. A supervised feature-projection-based real-time EMG pattern recognition for multifunction myoelectric hand control. IEEE/ASME Transactions on-Mechatronics.
Kamen, G., Caldwell Graham E., 1996. Physiology and ınterpretation of the electromyogram. Journal of Clinical Neurophysiology, 13(5): 366-384.
Kang, W.J., Cheng, C.K., Lai, J.S., Shiu, J.R., Kuo, T.S., 1996. A comparative analysis of various EMG pattern recognition methods. Medical Engineering & Physics, 18(5): 390–395.
Kermani, M.Z., Tehran, Iran., Badie, K., 1989. An intelligent strategy for motion interpretation in an EMG-controlled prosthesis. International Conference of the IEEE Engineering in Engineering in Medicine and Biology Society, 9-12 November, 5: 1682-1683.
Kreifeldt John, G., 1971. Signal versus noise characteristics of filtered EMG used as a control source. Biomedical Engineering, IEEE Transactions, 16-22.
Kurt, F., 2018. Evrişimli sinir ağlarında hiper parametrelerin etkisinin incelenmesi Yüksek Lisans Tezi, Hacettepe Üniversitesi, Fen Bilimleri Enstitüsü. Ankara, Türkiye.
Kutlu, H., 2018. Biyoistatistik temelli bilimsel araştırmalarda derin öğrenme uygulamaları. Yüksek Lisans Tezi, Yakındoğu Üniversitesi, Sağlık Bilimleri Enstitüsü, Lefkoşa, Kıbrıs.
Lee, S., Sankai, Y., 2002. Power assist control for walking aid with HAL-3 based on EMG and impedance adjustment around knee joint. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2: 1499-1504.
Li, P., 2017. Optimization algorithms for deep learning. department of systems engineering and engineering management.
Li-Zhi, L., Yi-Li, T., Hsin-Han, C., 2018. EMG-based control scheme with svm classifier for assistive robot arm. International Automatic Control Conference (CACS), pp.1-5.
Maksutov, R., 2018. Deep study of a not very deep neural network. part 3b: choosing an optimizer. (https://medium.com/@maksu tov.rn/deep-study-of-a-not-very-deep-neura l-network-part-3b-choosing-an-optimizer-de8965aaf1ff), (Accessed: 05.01.2025).
Manabe, H., Zhang, Z, 2004. Multi-stream HMM for EMG-based speech recognition. 26th Annual International Conference of the IEEE engineering in Medi-cine and Biology Society, San Francisco, pp.4389-4392.
Matt, F., Somesh, J., Thomas, R., 2015. Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures. In ACM SIGSAC Conference on Computer and Communications Security.
Mesin, L., Farina, D., 2005. A model for surface EMG generation in volume conductors with spherical inhomogeneities. IEEE Transactions of Biomedical Engineering, 52(12): 1984-1993.
Moradi, M., Hashtrudi-Zaad, K., Mountjoy, K., and Morin, E., 2008. An EMG-based force control system for prosthetic arms. Canadian Conference on Electrical and Computer Engineering, pp.1737-1742.
Morita, S., Kondo, T., Ito, K., 2001. Estimation of forearm movement from EMG signal and application to prosthetic hand control. Proceedings of IEEE International Conference on Robotics and Automation, pp.3692-3697.
Nikolic, Z.M., Popovic, D.B., Stein, R.B., Kenwell, Z., 1994. Instrumentation for ENG and EMG recordings in FES systems. IEEE Transactions on Biomedical Engineering, 41(7): 706.
Nishikawa, D., Wenwei, Yu., Yokoi, H., Kakazu, Y., 1999. EMG prosthetic hand controller using real-time learning method. Proceedings of IEEE International Conference on Systems, Man, and Cybernetics, 12-15 October, Tokyo, pp.153-158.
Nishikawa, D., Wenwei, Yu., Yokoi, H., Kakazu, Y., 1999. EMG prosthetic hand controller discriminating ten motions using real-time learning method. Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, Kyongju, pp.1592-1597.
Okut, H., 2018. Machine learning methods for big data and genomic selection: r application. Workshop Material, International Agricultural Congress, 8 May, Van, Turkey.
Okut, H., Gianola, D., Rosa, G.J.M., Weigel, K.A., 2011. Prediction of body mass index in mice using dense molecular markers and a regularized neural network. Genetics Research, 93(3): 189-201.
Ouyang, G., Zhu, X., Ju, Z., Liu, H., 2013. Dynamical characteristics of surface EMG signals of hand grasps via recurrence plot. IEEE Journal of Biomedical and Health Informatics, 257-265.
Paiss, Omry., Inbar, G.F., 1987. Autoregressive modeling of surface EMG and ıts spectrum with application to fatigue. IEEE Transactions on Biomedical Engineering, 34(10): 761-770.
Paul, G.M., Fan, Cao., Torah, R., Kai, Yang., Beeby, S., Tudor, J., 2014. A smart textile based facial EMG and EOG computer ınterface. Sensors Journal, 14(2): 393-400.
Priddy, K.L., Keller, P.E., 2005. Artificial neural network: An Introduction, 1st. Ed., Spie Press, Washington.
Reucher, H., Silny, J., Rau, G., 1987. Spatial filtering of noninvasivemultielec-trode EMG: Part II-filter performance in theory and modeling. IEEE Transactions on Biomedical Engineering, 34(2): 106-113.
Ruder, S., 2016. An overview of gradient descent optimization algorithms. (http://adsabs.harvard.edu/abs/2016arXiv160904747R), (Accessed: 05.01.2025).
Sammut, C., Webb, G.I., 2015. Encyclopedia of machine learning and data mining, Springer.
Sang-Hui, P., Seok P., 1998. EMG pattern recognition based on artificial ıntelligence techniques. IEEE Transactions On Rehabilitation Engineering, 6(4).
Saridis George N., Thomas, P., 1982. EMG pattern analysis and classification for a prosthetic arm. Biomedical Engineering, IEEE Transactions, 6: 403-412.
Sharma, A., 2017. Understanding activation functions in neural networks. (https://medium.com/the-theory-of-everyt hing/understanding-activation-functions-in-neural-networks-9491262884e0), (Accessed: 05.01.2025).
Shin, L., Jia-Jin, J., Chen Te-Son, K., 1996. Real-time implementation of electromyogram pattern recognition as a control command of man-machine interface. Medical Engineering and Physics, 18(7): 529-535.
Song, S., Chaudhuri K., Sarwate, A.D., 2013. Stochastic gradient descent with differentially private updates. IEEE Global Conference on Signal and Information Processing, Austin, pp. 245-248.
Stefan Karlsson, J., Karin, R., Christer G., Andreas, H., Nils Ö., 1887. Signal processing of the surface electromyogram to gain insight into neuromuscular physiology. Medical Engineering and Physics, Elsevier.
Studer, R.M., de Figueiredo Rui J.P., Moschytz George S., 1984. An algorithm for sequential signal estimation and system ıdentification for emg signals. IEEE Transactions on Biomedical Engineering, 31(3): 285-295.
Su, H., Nelder, J.A., Spence, R., Ismail, M., 1994. Generalized linear models for empirical performance modeling in circuit design. Proceedings of APCCAS'94-Asia Pacific Conference on Circuits and Systems.
Şengöz, N., 2017. Yapay sinir ağları. (http://www.derinogrenme.com/author/nilgunsengoz/), (Accessed: 08.01.2025).
Tsuji, T., Shigeyoshi, H., Kaneko, M., 2000. Bio-mimetic impedance control of an EMG-controlled prosthetic hand. Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, 31 October – 5 November, Takamatsu, pp.377-382.
Vuckovic, M., Sijiang, D., 2002. Classification of prehensile EMG patterns with simplified fuzzy ARTMAP networks. Proceedings of the 2002 International Joint Conference on Neural Networks, 12-17 May, Honolulu, HI. pp.2539-2544.
Winter, D.A., Yack, H.J., 1987. EMG profiles during normal human walking: stride-to-stride and inter-subject variability. Electroencephalography and Clinical Neurophysiology, 67: 402-411.
Xiaowen, Z., Yupu, Y., Xiaoming, X., Ming Z., 2002. Wavelet-based neuro-fuzzy classification for EMG control. IEEE 2002 International Conference on Communications, Circuits, and Systems and West Sino Expositions, 29 June- 1 July, pp.1087-1089.
Yitong, Z., Chellappa, R., Bekey, G., 1986. Estimation of intramuscular EMG signals from surface EMG signal analysis. Acoustics, Speech, and Signal Pro-cessing, IEEE International Conference on ICASSP, pp.1805-1808.
Zahedi, E., Farahani, H., 1995. Graphical simulation of artificial hand motion with fuzzy EMG pattern recognition. 14th Conference of the Biomedical Engineering Society of India an International Meeting.
Zardoshti-Kermani, M., Badie, K., Hashemi, R.M., 1995. EMG feature evaluation for movement control of upper extremity prostheses. IEEE Transactions on Rehabilitation Engineering, 3(4): 324-333.
Zennaro, D., Wellig, P., Koch, V.M., Moschytz George, S., Laubli, T., 2003. A software package for the decomposition of long-term multichannel EMG signals using wavelet coefficients. IEEE Transactions on Biomedical Engineering, 50(1): 58-69.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 The copyright of the published article belongs to its author.

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.