[en] Deep neural networks (DNNs) have demonstrated higher performance results when compared to traditional approaches for implementing robust myoelectric control (MEC) systems. However, the delay induced by optimising a MEC remains a concern for real-time applications. As a result, an optimised DNN architecture based on fine-tuned hyperparameters is required. This study investigates the optimal configuration of convolutional neural network (CNN)-based MEC by proposing an effective data segmentation technique and a generalised set of hyperparameters. Firstly, two segmentation strategies (disjoint and overlap) and various segment and overlap sizes were studied to optimise segmentation parameters. Secondly, to address the challenge of optimising the hyperparameters of a DNN-based MEC system, the problem has been abstracted as an optimisation problem, and Bayesian optimisation has been used to solve it. From 20 healthy people, ten surface electromyography (sEMG) grasping movements abstracted from daily life were chosen as the target gesture set. With an ideal segment size of 200 ms and an overlap size of 80%, the results show that the overlap segmentation technique outperforms the disjoint segmentation technique (p-value < 0.05). In comparison to manual (12.76 ± 4.66), grid (0.10 ± 0.03), and random (0.12 ± 0.05) search hyperparameters optimisation strategies, the proposed optimisation technique resulted in a mean classification error rate (CER) of 0.08 ± 0.03 across all subjects. In addition, a generalised CNN architecture with an optimal set of hyperparameters is proposed. When tested separately on all individuals, the single generalised CNN architecture produced an overall CER of 0.09 ± 0.03. This study's significance lies in its contribution to the field of EMG signal processing by demonstrating the superiority of the overlap segmentation technique, optimizing CNN hyperparameters through Bayesian optimization, and offering practical insights for improving prosthetic control and human-computer interfaces.
Disciplines :
Engineering, computing & technology: Multidisciplinary, general & others
Author, co-author :
Ashraf, Hassan ; Université de Liège - ULiège > Département d'aérospatiale et mécanique > Laboratoire des Systèmes Multicorps et Mécatroniques
Waris, Asim; Department of Biomedical Engineering and Sciences, School of Mechanical and Manufacturing Engineering (SMME), National University of Science and Technology (NUST), Islamabad, 44000, Pakistan. asim.waris@smme.nust.edu.pk
Gilani, Syed Omer; Department of Electrical, Computer and Biomedical Engineering, Faculty of Engineering, Abu Dhabi University, Abu Dhabi, United Arab Emirates
Shafiq, Uzma; Department of Biomedical Engineering and Sciences, School of Mechanical and Manufacturing Engineering (SMME), National University of Science and Technology (NUST), Islamabad, 44000, Pakistan
Iqbal, Javaid; Department of Biomedical Engineering and Sciences, School of Mechanical and Manufacturing Engineering (SMME), National University of Science and Technology (NUST), Islamabad, 44000, Pakistan
Kamavuako, Ernest Nlandu; Department of Informatics, King's College London, London, WC2R 2LS, UK
Berrouche, Yaakoub; LIS Laboratory, Department of Electronics, Faculty of Technology, Ferhat Abbas University Setif 1, Setif, Algeria
Bruls, Olivier ; Université de Liège - ULiège > Département d'aérospatiale et mécanique > Laboratoire des Systèmes Multicorps et Mécatroniques
Boutaayamou, Mohamed ; Université de Liège - ULiège > Département d'électricité, électronique et informatique (Institut Montefiore) > Exploitation des signaux et images
Niazi, Imran Khan; New Zealand College of Chiropractic, Auckland, New Zealand
Language :
English
Title :
Optimizing the performance of convolutional neural network for enhanced gesture recognition using sEMG.
Lowery, M. M., Stoykov, N. S. & Kuiken, T. A. Independence of myoelectric control signals examined using a surface EMG model. IEEE Trans. Biomed. Eng. 50(6), 789–793 (2003). DOI: 10.1109/TBME.2003.812152
Waris, A. & Kamavuako, E. N. Effect of threshold values on the combination of EMG time domain features: Surface versus intramuscular EMG. Biomed. Signal Process. Control 45, 267–273 (2018). DOI: 10.1016/j.bspc.2018.05.036
Fu, J., Choudhury, R., Hosseini, S. M., Simpson, R. & Park, J. H. Myoelectric control systems for upper limb wearable robotic exoskeletons and exosuits—A systematic review. Sensors 22(21), 8134 (2022). DOI: 10.3390/s22218134
Asif, A. R. et al. Performance evaluation of convolutional neural network for hand gesture recognition using EMG. Sensors 20(6), 1642 (2020). DOI: 10.3390/s20061642
Frazier, P.I. A tutorial on Bayesian optimisation. Preprint at https://arXiv.org/quant-ph/1807.02811 (2018).
Zia ur Rehman, M. et al. Multiday EMG-based classification of hand motions with deep learning techniques. Sensors 18(8), 2497 (2018). DOI: 10.3390/s18082497
Ashraf, H. et al. Determination of optimum segmentation schemes for pattern recognition-based myoelectric control: A multi-dataset investigation. IEEE Access 8, 90862–90877 (2020). DOI: 10.1109/ACCESS.2020.2994829
Hu, R., Chen, X., Zhang, H., Zhang, X. & Chen, X. A novel myoelectric control scheme supporting synchronous gesture recognition and muscle force estimation. IEEE Trans. Neural Syst. Rehabil. Eng. 30, 1127–1137 (2022). DOI: 10.1109/TNSRE.2022.3166764
Wahid, M. F., Tafreshi, R. & Langari, R. A multi-window majority voting strategy to improve hand gesture recognition accuracies using electromyography signal. IEEE Trans. Neural Syst. Rehabil. Eng. 28(2), 427–436 (2019). DOI: 10.1109/TNSRE.2019.2961706
Oskoei, M. A. & Hu, H. Support vector machine-based classification scheme for myoelectric control applied to upper limb. IEEE Trans. Biomed. Eng. 55(8), 1956–1965 (2008). DOI: 10.1109/TBME.2008.919734
Côté-Allard, U. et al. A transferable adaptive domain adversarial neural network for virtual reality augmented EMG-based gesture recognition. IEEE Trans. Neural Syst. Rehabil. Eng. 29, 546–555 (2021). DOI: 10.1109/TNSRE.2021.3059741
Rahimian, E. et al. Fs-hgr: Few-shot learning for hand gesture recognition via electromyography. IEEE Trans. Neural Syst. Rehabil. Eng. 29, 1004–1015 (2021). DOI: 10.1109/TNSRE.2021.3077413
Chen, X., Li, Y., Hu, R., Zhang, X. & Chen, X. Hand gesture recognition based on surface electromyography using convolutional neural network with transfer learning method. IEEE J. Biomed. Health Inform. 25(4), 1292–1304 (2020). DOI: 10.1109/JBHI.2020.3009383
Chen, L., Fu, J., Wu, Y., Li, H. & Zheng, B. Hand gesture recognition using compact CNN via surface electromyography signals. Sensors 20(3), 672 (2020). DOI: 10.3390/s20030672
Triwiyanto, T., Pawana, I. P. A. & Purnomo, M. H. An improved performance of deep learning based on convolution neural network to classify the hand motion by evaluating hyper parameter. IEEE Trans. Neural Syst. Rehabil. Eng. 28(7), 1678–1688 (2020). DOI: 10.1109/TNSRE.2020.2999505
Gadekallu, T. R. et al. Hand gesture classification using a novel CNN-crow search algorithm. Complex Intell. Syst. 7(4), 1855–1868 (2021). DOI: 10.1007/s40747-021-00324-x
Snoek, J., Larochelle, H. and Adams, R.P. Practical bayesian optimisation of machine learning algorithms. Adv. Neural Inform. Process. Syst. 25, (2012).
Lei, B. et al. Bayesian optimisation with adaptive surrogate models for automated experimental design. npj Computat. Mater. 7(1), 1–12 (2021).
McIntire, M., Ratner, D. & Ermon, S. Sparse Gaussian Processes for Bayesian Optimization (UAI, 2016).
Berk, J., Nguyen, V., Gupta, S., Rana, S. & Venkatesh, S. Exploration enhanced expected improvement for Bayesian optimisation. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases (eds Berlingerio, M. et al.) 621–637 (Springer, 2018).
Ortiz-Catalan, M., Brånemark, R. & Håkansson, B. BioPatRec: A modular research platform for the control of artificial limbs based on pattern recognition algorithms. Sour. Code Biol. Med. 8(1), 1–18 (2013).
Hudgins, B., Parker, P. & Scott, R. N. A new strategy for multifunction myoelectric control. IEEE Trans. Biomed. Eng. 40(1), 82–94 (1993). DOI: 10.1109/10.204774
Albawi, S., Mohammed, T. A. & Al-Zawi, S. Understanding of a convolutional neural network. In 2017 International Conference on Engineering and Technology (ICET) (eds Albawi, S. et al.) 1–6 (IEEE, 2017).
Moreira, M. & Fiesler, E. Neural Networks with Adaptive Learning Rate and Momentum Terms (No. REP_WORK) (IDIAP, 1995).
Ozaki, Y., Tanigaki, Y., Watanabe, S., Nomura, M. & Onishi, M. Multiobjective tree-structured Parzen estimator. J. Artif. Intell. Res. 73, 1209–1250 (2022). DOI: 10.1613/jair.1.13188
