Research on Deep Learning Based Denoising and Classification of Electromyographic Signals

Yicheng Yu

doi:10.54254/2755-2721/2025.BJ25436

Applied and Computational EngineeringOpen access

Research on Deep Learning Based Denoising and Classification of Electromyographic Signals

Research Article

Open Access

Research on Deep Learning Based Denoising and Classification of Electromyographic Signals

Yicheng Yu ^1*

¹ Department of Information Engineering, Minzu University of China, Beijing, China

^*Corresponding author: 23011961@muc.edu.cn

Published on 24 July 2025

ACE Vol.177

ISSN (Print): 2755-273X

ISSN (Online): 2755-2721

ISBN (Print): 978-1-80590-241-6

ISBN (Online): 978-1-80590-242-3

Download Cover

Abstract

Electromyography (EMG) signals, as important bioelectric signals reflecting human muscle activity, have broad application prospects in fields such as human-computer interaction, prosthetic control, and motion recognition. However, electromyographic signals themselves are susceptible to noise interference such as motion artifacts and power interference, and traditional filtering methods are difficult to effectively distinguish signals from complex background noise. Meanwhile, traditional feature engineering relies on manual experience, which limits the model's generalization ability and real-time processing performance. In response to the above issues, this article proposes an end-to-end electromyographic signal processing method based on Convolutional Neural Network (CNN), which is used to simultaneously achieve signal denoising and motion pattern recognition. Firstly, the original electromyographic signal is segmented using a sliding window method and standardized; Subsequently, the processed data is input into a CNN model consisting of multiple layers of convolution and pooling structures, which automatically extracts time-domain features and completes classification. During the model training phase, the introduction of cross entropy loss function and Adam optimization algorithm improves the convergence speed and classification accuracy of the model. We used an open-source surface Electromyographic (sEMG) dataset on the PhysioNet platform for validation and compared its performance with traditional support vector machine (SVM) methods. The experimental results show that the proposed method is significantly better than traditional methods in key indicators such as accuracy and F1 score, and has better robustness and real-time performance. This study demonstrates the potential of deep learning in electromyographic signal processing, providing technical support for future intelligent prosthetic control and high-precision human-machine interaction systems.

Keywords:

EMG signal, deep learning, convolutional neural network, signal denoising, pattern recognition

View PDF

References

[1]. Farina D, Merletti R, Enoka R M. The extraction of neural strategies from the surface EMG [J]. Journal of applied physiology, 2004, 96(4): 1486-1495.

[2]. Khushaba R N, Kodagoda S, Takruri M, et al. Toward improved control of prosthetic fingers using surface electromyogram (EMG) signals [J]. Expert Systems with Applications, 2012, 39(12): 10731-10738.

[3]. Fratini A, Cesarelli M, Bifulco P, et al. Relevance of motion artifact in electromyography recordings during vibration treatment [J]. Journal of Electromyography and Kinesiology, 2009, 19(4): 710-718.

[4]. Christiano L J, Fitzgerald T J. The band pass filter [J]. International economic review, 2003, 44(2): 435-465.

[5]. Davenport Jr W B. Signal‐to‐Noise Ratios in Band‐Pass Limiters [J]. Journal of Applied Physics, 1953, 24(6): 720-727.

[6]. Rehman N, Mandic D P. Multivariate empirical mode decomposition [J]. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2010, 466(2117): 1291-1302.

[7]. Toledo-Pérez D C, Rodríguez-Reséndiz J, Gómez-Loenzo R A, et al. Support vector machine-based EMG signal classification techniques: A review [J]. Applied Sciences, 2019, 9(20): 4402.

[8]. Paul Y, Goyal V, Jaswal R A. Comparative analysis between SVM & KNN classifier for EMG signal classification on elementary time domain features [C]//2017 4th international conference on signal processing, computing and control (ISPCC). IEEE, 2017: 169-175.

[9]. Chua L O. CNN: A vision of complexity [J]. International Journal of Bifurcation and Chaos, 1997, 7(10): 2219-2425.

[10]. Disselhorst-Klug C, Schmitz-Rode T, Rau G. Surface electromyography and muscle force: Limits in sEMG–force relationship and new approaches for applications [J]. Clinical biomechanics, 2009, 24(3): 225-235.

[11]. Yacouby R, Axman D. Probabilistic extension of precision, recall, and f1 score for more thorough evaluation of classification models [C]//Proceedings of the first workshop on evaluation and comparison of NLP systems. 2020: 79-91.

[12]. Scalo J. The IMF revisited: a case for variations [J]. arXiv preprint astro-ph/9712317, 1997.

[13]. Griffin D, Lim J. Signal estimation from modified short-time Fourier transform [J]. IEEE Transactions on acoustics, speech, and signal processing, 1984, 32(2): 236-243.

[14]. Rahimi A, Benatti S, Kanerva P, et al. Hyperdimensional biosignal processing: A case study for EMG-based hand gesture recognition [C]//2016 IEEE International Conference on Rebooting Computing (ICRC). IEEE, 2016: 1-8.

[15]. Chen L, Fu J, Wu Y, et al. Hand gesture recognition using compact CNN via surface electromyography signals [J]. Sensors, 2020, 20(3): 672.