sEMG biceps and triceps effort signals classification using 1D-CNN convolution

Authors

  • Sofiane Tchoketch Kebir
  • Fouaz Berrhail

DOI:

https://doi.org/10.54021/seesv5n1-111

Keywords:

deep learning, 1D-CNN, wavelet scattering transform, sEMG biceps signals effort classification, sEMG triceps signals effort classification

Abstract

In this paper, we present a system for acquiring and classifying surface physiological muscles signals (sEMG) for the biceps and triceps muscles during movement or work, as normal or aggressive effort in order to control and command the aid prostheses to intervene only during aggressive efforts. Thus, the main objective of our work is to developing and improving the performance of the hand prostheses for daily life tasks for elderly persons or for persons who have hand muscle failure. Our contribution consists of detecting and classifying physiological signals of biceps and triceps muscles hand as normal and aggressive efforts, for that we proposed a technique based on a 1D Convolutional Neural Network (CNN-1D) using the Wavelet Scattering Transform as the sEMG feature extraction technique. Our methodology is carried out in two steps: the first step is crucial to build a database for deep learning network for sEMG signals classification based on fifty-five volunteers spanning various ages and genders. The second step achieves the sEMG signals effort classification as normal or aggressive efforts based on the classification network produced based on sEMG signal sequences treated by the WST. The obtained results for the training and validation sets indicate perfect performance of the proposed technique, with an accuracy, precision, sensitivity, and specificity of 100% for the training process, and 99.3%, 98.6%, 100% and 98.7% for the accuracy, precision, sensibility and specificity respectively. It is important to note that while perfect metrics on the training and the test set might suggest excellent model learning.

References

PASSINGHAM, R. E. The frontal lobes and voluntary action. OUP Oxford, 1995. v. 21.

LATASH, M. L. The control and perception of antagonist muscle action. Experimental Brain Research, v. 241, n. 1, p. 1–12, 2023.

PHINYOMARK, A.; Campbell, E.; Scheme, E. Surface electromyography (emg) signal processing, classification, and practical considerations. Biomedical Signal Processing: Advances in Theory, Algorithms and Applications, p. 3–29, 2020.

JAIN, R.; GARG, V. K. Review of emg signal classification approaches based on various feature domains. Matter: International Journal of Science and Technology, v. 6, n. 3, p. 123–143, 2021.

DHUMAL, S.; SHARMA, P. Emg pattern recognition: A systematic review. In: International Conference on Information Systems and Management Science, p. 120–130, Springer, 2021.

LIU, Y.; ZHANG, Q.; CHEN, W. Massive-scale complicated human action recognition: Theory and applications. Future Generation Computer Systems, v. 125, p. 806–811, 2021.

RANI, G. J.; HASHMI, M.; F.; GUPTA, A. Surface electromyography and artificial intelligence for human activity recognition-a systematic review on methods, emerging trends applications, challenges, and future implementation. IEEE Access, 2023.

NAZMUN, N.; Rahman, A.; AHAD, M. A. Deep learning based surface emg hand gesture classification for low-cost myoelectric prosthetic hand. In: 2020 Joint 9th International Conference on Informatics, Electronics & Vision (ICIEV) and 2020 4th International Conference on Imaging, Vision & Pattern Recognition (icIVPR), IEEE, p. 1–8, 2020.

Ozdemir, M. A.; Kisa, D. H.; Guren, O.; Onan, A.; Akan, A. Emg based hand gesture recognition using deep learning. In: 2020 Medical Technologies Congress (TIPTEKNO), p. 1–4, IEEE, 2020.

WANG, M.; ZHAO, C.; BARR, A.; FAN, H.; YU, S.; KAPELLUSCH, J.; ADAMSON, C. H. Hand posture and force estimation using surface electromyography and an artificial neural network. Human Factors, v. 65, n. 3, p. 382–402, 2023.

ZANGHIERI, M. sEMG-based hand gesture recognition with deep learning, 2023.

LI, J.; WEI, L.; WEN, Y.; LIU, X.; WANG, H. An approach to continuous hand movement recognition using semg based on features fusion. The Visual Computer, v. 39, n. 5, p. 2065–2079, 2023.

MONK, S. Raspberry pi cookbook. O’Reilly Media, Inc., 2022.

WU, Y.-D.; RUAN, S.-J.; LEE, Y.-H. An ultra-low power surface emg sensor for wearable biometric and medical applications. Biosensors, v. 11, n. 11, p. 411, 2021.

MALLAT, S. Group invariant scattering. Communications on Pure and APPLIED Mathematics, v. 65, n. 10, p. 1331–1398, 2012.

Sundararajan, D. Discrete wavelet transform: a signal processing approach. John Wiley & Sons, 2016.

ZHANG, D.; ZHANG, D. Wavelet transform. Fundamentals of image data mining: Analysis, Features, Classification and Retrieval, p. 35–44, 2019.

GUO, T.; ZHANG, T.; LIM, E.; LOPEZ-BENITEZ, M.; MA, F.; YU, L. A review of wavelet analysis and its applications: Challenges and opportunities. IEEE Access, v. 10, p. 58869–58903, 2022.

HEIL, C. E.; WALNUT, D. F. Continuous and discrete wavelet transforms. SIAM review, v. 31, n. 4, p. 628–666, 1989.

RIOUL, O.; DUHAMEL, P. Fast algorithms for discrete and continuous wavelet transforms. IEEE transactions on information theory, v. 38, n. 2, p. 569–586, 1992.

Zou, X.; Xue, J.; Li, X.; Chan, C. P. Y.; Li, Z., Li, P.; Yang, Z.; Lai, K. W. C. High-fidelity semg signals recorded by an on-skin electrode based on agnws for hand gesture classification using machine learning. ACS Applied Materials & Interfaces, v. 15, n. 15, p. 19374–19383, 2023.

XIONG, B.; CHEN, W.; NIU, Y., GAN, Z.; MAO, G.; XU, Y. A global and local feature fused cnn architecture for the semg-based hand gesture recognition. Computers in Biology and Medicine, v. 166, p. 107497, 2023.

FARRUKH, M.; QURESHI, MUSHTAQ, Z.; REHMAN, M. Z. U.; KAMAVUAKO, E. N. E2cnn: An efficient concatenated cnn for classification of surface emg extracted from upper limb. IEEE Sensors Journal, v. 23, n. 8, p. 8989–8996, 2023.

XU, Z.; YU, J.; XIANG, W.; ZHU, S.; HUSSAIN, M.; LIU, B.; LI. J. A novel se-cnn attention architecture for semg-based hand gesture recognition. CMES-Computer Modeling in Engineering & Sciences, v. 134, n. 1, p. 157–177, 2023.

KANG, S.; KIM, H.; PARK, C.; SIM, Y.; LEE, S.; JUNG, Y. semg-based hand gesture recognition using binarized neural network. Sensors, v. 23, n. 3, p. 1436, 2023.

KEBIR, S. T.; MEKAOUI, S.; BOUHEDDA, M. A fully automatic methodology for mri brain tumour detection and segmentation. The Imaging Science Journal, v. 67, n. 1, p. 42–62, 2019.

Downloads

Published

2024-05-27

How to Cite

Kebir, S. T., & Berrhail, F. (2024). sEMG biceps and triceps effort signals classification using 1D-CNN convolution. STUDIES IN ENGINEERING AND EXACT SCIENCES, 5(1), 2232–2253. https://doi.org/10.54021/seesv5n1-111