نشریه علمی مهندسی پزشکی زیستی
Iranian Journal of Biomedical Engineering (IJBME)

تحلیل تاثیر روش بهینه‌سازی و پارامترهای تنظیم کننده‌ی شبکه‌ی عمیق جهت بهبود صحت کلاس‌بندی حرکات انگشتان دست مبتنی بر سیگنال الکترومایوگرام

نوع مقاله : مقاله کامل پژوهشی

نویسندگان

مسعود صاحب‌جمعیان 1
محمدعلی احمدی‌پژوه 2
محمدحسن مرادی 3

1 دانشجوی دکتری، گروه بیوالکتریک، دانشکده‌ی مهندسی پزشکی، دانشگاه صنعتی امیرکبیر، تهران، ایران

2 استادیار، گروه بیوالکتریک، دانشکده‌ی مهندسی پزشکی، دانشگاه صنعتی امیرکبیر، تهران، ایران

3 استاد، گروه بیوالکتریک، دانشکده‌ی مهندسی پزشکی، دانشگاه صنعتی امیرکبیر، تهران، ایران

https://doi.org/10.22041/ijbme.2024.2022213.1884
چکیده
حرکات دست و انگشتان در زندگی روزمره نقش مهمی دارد. ممکن است در اثر بیماری و سوانح به این اندام آسیب وارد شود. در توان‌بخشی انگشتان دست و درمان آسیب­های وارده به آن‌ها، طبقه‌بندی حرکات انگشتان دست و شناسایی وضعیت آن‌ها بسیار حائز اهمیت است. یکی از روش­ها برای ایجاد نگاشت بین سیگنال الکترومایوگرام سطحی و کلاس­های حرکتی انگشتان دست، به کارگیری دانش یادگیری عمیق است. این علم در سال‌های اخیر باعث پیش‌رفت­های چشم­گیری در بسیاری از زمینه­ها شده است. در این مطالعه به ­طبقه­بندی و شناسایی 8 حرکت انگشتان دست بر اساس شبکه­های عصبی عمیق کانولوشنال پرداخته شده است. داده­های مورد نیاز این پژوهش که سیگنال­های الکترومایوگرام سطحی بوده مربوط به پایگاه داده‌ی نیناپرو است. نتایج نشان می­دهد که دقت طبقه‌بندی در برخی از حرکات به 9/98 درصد رسیده است. برخی از تنظیم کننده­ها و بهینه کننده­ها می­توانند بر دقت طبقه­بندی بسیار موثر باشند. با انتخاب صحیح تنظیم کننده­ها از قبیل لایه­ی حذف تصادفی و L2 دقت طبقه‌بندی قابل افزایش است. 

کلیدواژه‌ها

الکترومایوگرام سطحی
شبکه‌ی عصبی کانولوشن
شبکه‌ی عصبی عمیق
طبقه‌بندی
بهینه کننده
تنظیم کننده

موضوعات

عنوان مقاله English

Analysis of the Effect of the Optimization Method and the Regulating Parameters in the Deep Network to Improve the Classification Accuracy of Finger Movements based on Electromyogram Signal

نویسندگان English

Masoud Saheb Jameyan 1
Mohammad Ali Ahmadi Pajouh 2
Mohammad Hassan Moradi 3
1 Ph.D. Student, Bioelectric Group, Biomedical Engineering Department, Amirkabir University of Technology, Tehran, Iran
2 Assistant Professor, Bioelectric Group, Biomedical Engineering Department, Amirkabir University of Technology, Tehran, Iran
3 Professor, Bioelectric Group, Biomedical Engineering Department, Amirkabir University of Technology, Tehran, Iran
چکیده English

Hand and finger movements are crucial for daily activities, and their impairment due to illness or accidents can have a significant impact. In the rehabilitation and treatment of finger injuries, it is vital to classify finger movements and assess their condition accurately. One approach to establishing a connection between the surface electromyogram (EMG) signal and finger movement classes is through the application of deep learning techniques. Deep learning has made remarkable advancements across various domains in recent years, and leveraging its knowledge can be beneficial in this context. In this study, the focus is on classifying and identifying eight different finger movements using deep convolutional neural networks. The researchers utilized EMG signals obtained from the Ninapro database for their analysis. The results indicate that the classification accuracy for certain movements reaches as high as 98.9%. Certain regulators and optimizers have a significant impact on the classification accuracy. By carefully selecting regulators, such as the random removal layer and L2, it is possible to improve the accuracy of the classification.

کلیدواژه‌ها English

Surface Electromyogram
Convolution Neural Network
Deep Neural Network
Classification
Optimizer
Regulator
  1. Merletti, D.Farina, “Surface electro myo graphy: Physiology, engineering and applications”, 1nd ed., New Jersey, John Wiely & Sons, 2016, pp. 440-443.
  2. V. Arteaga, J.C. Castiblanco, I. F. Mondragon, J. D. Colorado, C.A. Rojas, “EMG-driven hand model based on the classification of individual finger movements”, Biomedical Signal Processing and Control, volume 58, no. 101834, 2020. https://doi.org/10.1016/j.bspc.2019.101834.
  3. M. Fajardo, O. Gomez, F. Prieto, “EMG hand gesture classification using handcrafted and deep features, Biomedical Signal Processing and Control”, volume 63, no. 102210, 2021. https://doi.org/10.1016/j.bspc.2020.102210.
  4. S. Miften, M. Diykh, S. Abdulla, S. Siuly, J.H. Green, R.C. Deo, “A new framework for classification of multi-category hand grasps using EMG signals”, Artificial Intelligence in Medicine, vol. 112, 102005, 2021. https:// doi. org/10.1016/j.artmed.2020.102005.
  5. , Narayan. “SEMG signal classification using KNN classifier with FD and TFD features”. Materials Today: Proceedings, vol. 37, no. 2, pp. 3219-3225, 2021. https://doi.org /10.1016/j.matpr. 2020. 09.089. 
  6. , Subasi, S.M., Qaisar. “Surface EMG signal classification using TQWT, Bagging and Boosting for hand movement recognition.” J Ambient Intell Human Comput, vol. 13, pp. 3539-3554, 2022. https://doi.org/10.1007/s1265 2-020-01980-6.
  7. M., Singh, V., Ahlawat, S., Chatterji, A., Kumar. “Comparative analysis of SVM and ANN classifier based on surface EMG signals for elbow movement classification”. Journal of Interdisciplinary Mathematics, vol. 23, no. 1, pp. 153–161. 2020. https://doi.org/0.1080/ 09720502.2020.1721709.
  8. C., Oh, Y.U., Jo. “Classification of hand gestures based on multi-channel EMG by scale average wavelet transform and convolutional neural network”.  Int. J. Control.  Autom. Syst., 19, 1443–1450, 2021. https://doi.org/10.1007 /s12555-019-0802-1.
  9. Wen, Q. Wang, Z. Li, “Human hand movement recognition using infinite hidden Markov model based sEMG classification”, Biomedical Signal Processing and Control, vol. 68, no. 102592, 2021, https://doi.org/10.1016/j. bspc.2021.102592.
  10. K., Karnam, A. C., Turlapaty, S. R., Dubey, B., Gokaraju, “ Classification of sEMG signals of hand gestures based on energy features”, Biomedical Signal Processing and Control, vol. 70, 2021, 102948, https://doi.org/10.1016 /j.bs pc.2021.102948.
  11. , Qi, G., Jiang, G., Li. “Surface EMG hand gesture recognition system based on PCA and GRNN”. Neural Comput & Applic 32, pp. 6343–6351, 2020. https://doi.org/10.1007/ s00 521-019-04142-8.
  12. , Baygin, P.D., Barua, S., Dogan, T., Tuncer, S. Key, U.R., Acharya, K.H., Cheong. “A Hand-Modeled Feature Extraction-Based Learning Network to Detect Grasps Using sEMG Signal”. Sensors, vol.22, pp. 2007, 2022. https://doi.org/10.3390/s22052007.
  13. H., Lee, J.Y., Min, S., Byun. “Electromyo gram Based Classification of Hand and Finger Gestures Using Artificial Neural Networks. Sensors”, vol. 22, no 1, pp. 225, 2021. https://doi.org/10.3390/s22010225.
  14. Ma, Y. Liu, “Continuous estimation of knee joint angle based on surface electromyography using a Long Short-Term Memory neural network and time-advanced feature,” Sensors, vol. 20, no. 17, Sept. 2020, https://doi.org/10.3390/s20174966.
  15. Atzori, M. Cognolato, H. Müller, “Deep learning with convolutional neural networks applied to electromyography data: A resource for the classification of movements for prosthetic hands,” Front. Neurorobot. Vol. 10, Sept. 2016, https://doi.org/10.3389/fnbot.2016. 00009.
  16. Geng, Y. Du, W. Jin, W. Wei, Y. Hu, J. Li, Gesture recognition by instantaneous surface EMG images, Sci. Rep., vol. 6, no. 1, 2016. https://doi.org/10.1038/srep36571.
  17. Du, W. Jin, W. Wei, Y. Hu, W. Geng. Surface EMG-Based Inter-Session Gesture Recognition Enhanced by Deep Domain Adaptation. Sensors. 2017; 17, 3, pp: 458. https://doi.org/10.3390/s17030458.
  18. , Ding, C., Yang, Z., Tian, C., Yi, Y., Fu, F., Jiang, “sEMG-Based Gesture Recognition with Convolution Neural Networks”. Sustainability 2018, 10, 1865. https://doi.org/10.3390/su1006 1865.
  19. , Shen, K., Gu, X.-R., Chen, M., Yang , R.-C., Wang, “Movements Classification of Multi-Channel sEMG Based on CNN and Stacking Ensemble Learning,” in IEEE Access, vol. 7, pp. 137489-137500, 2019, https://doi.org/ 10. 1109/ACCESS.2019.2941977.
  20. , Kan, D., Yang, L., Cao, H., Shu, Y., Li, W., Yao, X., Zhang, “A Novel PSO-Based Optimized Lightweight Convolution Neural Network for Movements Recognizing from Multichannel Surface Electromyogram”, Complexity, vol. 2020, Article ID 6642463, 15 pages, 2020. https://doi.org/10.1155/ 2020/ 66 42463.
  21. Asif, A. Waris, SO. Gilani, M. Jamil, H. Ashraf, M. Shafique, IK. Niazi, Performance Evaluation of Convolutional Neural Network for Hand Gesture Recognition Using EMG. Sensors. 2020; 20, 6, pp. 1642. https://doi.org/ 10.3390/s20061642.
  22. , Qi, X., W., Chen, J., Liu, J., Zhang, J., Wang, sEMG-based recognition of composite motion with convolutional neural network, Sensors and Actuators A: Physical, Volume 311, 2020, 112046, ISSN 0924-4247, https://d oi.org/ 10.1016/j.sna.2020.112046.
  23. Chen, Y. Li, R. Hu, X. Zhang and X. Chen, "Hand Gesture Recognition based on Surface Electromyography using Convolutional Neural Network with Transfer Learning Method," in IEEE Journal of Biomedical and Health Informatics, vol. 25, no. 4, pp. 1292-1304, April 2021, https://doi.org/10.1109/JBHI. 2020 3009383.
  24. Chen, J. Fu, Y. Wu, H. Li, B. Zheng. Hand Gesture Recognition Using Compact CNN via Surface Electromyography Signals. Sensors. 2020; 20,3, pp.672.https://doi.org/10.3390/s200 30672.
  25. , Kim, S., Stapornchaisit, M., Miyakoshi, N., Yoshimura, Y., Koike. “The Effect of ICA and Non-negative Matrix Factorization Analysis for EMG Signals Recorded From Multi-Channel EMG Sensors”. Front. Neurosci. 14:600804. 2020. https://doi.org/10.3389/fnins.2020 .600 804.
  26. Nasri, S. Orts-Escolano, F. Gomez-Donoso, M. Cazorla, “Inferring static hand poses from a low-cost non-intrusive sEMG sensor,” Sensors, vol. 19, no. 2, pp. 371, Jan. 2019, https://doi .org /10.3390/s19020371.
  27. , Simão, P., Neto, O., Gibaru, “EMG-based online classification of gestures with recurrent neural networks”, Pattern Recognition Letters, vol. 128, 2019, pp. 45-51, https://doi.org/10. 1016/j.patrec.20 19.07.021.
  28. http://ninaweb.hevs.ch/
  29. J. Jarque-Bou, M. Atzori, H. Müller, “A large calibrated database of hand movements and grasps kinematics,” Sci. Data, vol. 7, no. 12, Jan. 2020, https://doi.org/10.1038/s41597-019-0349-2.
  30. Atzori, A. Gijsberts, C. Castellini, B. Caputo, A.G.M. Hager, S.  Elsig, Electromyo graphy data for non-invasive naturally-controlled robotic hand prostheses, Scientific Data, 2014, 1, 1.https://doi.org/10.1038/sdata. 2014.53.
  31. , LeCun, L.D., Jackel, L., Bottou, A., Brunot, C., Cortes, J.S., Denker. ‘‘Comparison of learning algorithms for hand written digit recognition.’’ In international conference on artificial neural networks (Paris), 53–60, 1995.
  32. , Englehart, B., Hudgins, P.A., Parker, M. Stevenson. Classification of the myoelectric signal using time-frequency based representations. Med. Eng. Phys. Vol.21, pp. 431–438, 1999. https://doi.org/10.1016/s1350-4533 (99) 00066-1.
  33. Géron, Aurélien. Hands-on machine Learning with scikit-learn, keras, and TensorFlow. Sebastopol, CA: O'Reilly Media. (2019).
  34. Alzubaidi, J. Zhang, AJ. Humaidi. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data 8:53, 2021.
  35. Agnes, F. Sagayaraj A survey of optimization techniques for deep learning networks, Int J Res Eng Appl Manag (IJREAM) 5:2, 2019.
  36. Ruder, SM. Park, KB. Sim, KB (2017), An overview of gradient descent optimization algorithms, arXiv: 1609.04747v2.
  37. Wilson, R. Roelofs, M. Stern, N. Srebro, B. Recht. The marginal value of adaptive gradient methods in machine learning, in Advances in Neural Information Processing Systems. 2017.
  38. Reyad, A. Sarhan, M. Arafa. “A modified Adam algorithm for deep neural network optimization”. Neural Comput & Applic 35, 17095–17112, 2023. https://doi.org/10.1007 / s00521-023-08568-z.
  39. , Jabir N., Falih. “Dropout, a basic and effective regularization method for a deep learning model: A case study. Indonesian Journal of Electrical Engineering and Computer Science”. 2021 Nov; vol.24, no. 2, pp. 1009-16.
  40. Balasubramanian, K. Ramyadevi, R. Geetha, Deep transfer learning based real time face mask detection system with computer vision. Multimed Tools Appl, 2023. https://doi.org/10.1007/s11042-023-16192-1.
  41. Shiliang, C. Zehui, Han Z, Z. Jing. A survey of optimization methods from a machine learning perspective, Supported by NSFC Project 61370175 and Shanghai Sailing Program 17YF1404600, 2019.
  42. Zhai, B., Jelfs, R. Chan, C. Tin. “Self-recalibrating surface EMG pattern recognition for neuroprosthesis control based on Convolutional Neural Network,” Frontiers in Neuroscience, 2017, 11, 379. https://doi.org/10. 3389/fnins.2017.00379.
  43. Hirt, H. Seyhan, M. Wagner, R. Zumhasch, “Hand and Wrist Anatomy and Biomechanics, A Comprehensive Guide,” 3nd ed., Germany, Thieme, 2017, pp. 75-80.
نشریه علمی مهندسی پزشکی زیستی
دوره 17، شماره 3
پاییز 1402
صفحه 235-247

  • تاریخ دریافت 16 بهمن 1402
  • تاریخ بازنگری 06 تیر 1403
  • تاریخ پذیرش 11 تیر 1403

صفحه اصلی

تماس با ما