Research on multi-scale convolutional neural network hand muscle strength prediction model improved based on convolutional attention module_Journal of Biomedical Engineering

Authors：

 DU Yihao , SUN Mengyu , LI Jingjin , WANG Xiaoran , CAO Tianfu

Key Laboratory of Intelligent Rehabilitation and Neuroregulation of Hebei Province, School of Electrical Engineering, Key Laboratory of Intelligent Control and Neural Information Processing, Ministry of Education, Yanshan University, Qinhuangdao, Hebei 066000, P. R. China;

Corresponding author：

DU Yihao, Email: duyihao@126.com

Keywords：

Muscle strength prediction; Convolutional block attention module; Multi-scale convolutional neural network; Hand force; Ablation experiment

DOI：

10.7507/1001-5515.202406054

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

In order to realize the quantitative assessment of muscle strength in hand function rehabilitation and then formulate scientific and effective rehabilitation training strategies, this paper constructs a multi-scale convolutional neural network (MSCNN) - convolutional block attention module (CBAM) - bidirectional long short-term memory network (BiLSTM) muscle strength prediction model to fully explore the spatial and temporal features of the data and simultaneously suppress useless features, and finally achieve the improvement of the accuracy of the muscle strength prediction model. To verify the effectiveness of the model proposed in this paper, the model in this paper is compared with traditional models such as support vector machine (SVM), random forest (RF), convolutional neural network (CNN), CNN - squeeze excitation network (SENet), MSCNN-CBAM and MSCNN-BiLSTM, and the effect of muscle strength prediction by each model is investigated when the hand force application changes from 40% of the maximum voluntary contraction force (MVC) to 60% of the MVC. The research results show that as the hand force application increases, the effect of the muscle strength prediction model becomes worse. Then the ablation experiment is used to analyze the influence degree of each module on the muscle strength prediction result, and it is found that the CBAM module plays a key role in the model. Therefore, by using the model in this article, the accuracy of muscle strength prediction can be effectively improved, and the characteristics and laws of hand muscle activities can be deeply understood, providing assistance for further exploring the mechanism of hand functions.

1.	Becker C J, Sucharew H, Robinson D, et al. Impact of poverty on stroke recurrence: a population-based study. Neurology, 2024, 102(11): e209423.
2.	Nam H K, Chang S J, Kim C B, et al. The association between social support, metabolic syndrome, and incidence of cardio-cerebrovascular diseases in older adults: the ARIRANG study. Yonsei Med J, 2024, 65(6): 363-370.
3.	Moore R T, Piitz M A, Singh N, et al. The independence of impairments in proprioception and visuomotor adaptation after stroke. J Neuroeng Rehabil, 2024, 21(1): 81.
4.	Liu F, Chen C, Hong W, et al. Selectively disrupted sensorimotor circuits in chronic stroke with hand dysfunction. CNS Neurosci Ther, 2022, 28(5): 677-689.
5.	Min S B, Hyun J L. Effect of different pelvic-drop exercises on hip muscles activity in patients with gluteus medius weakness. Isokinetics and Exercise Science, 2023, 31(4): 275-281.
6.	栗志铃. 基于sEMG信号和UE4引擎的手部康复训练系统的设计与实现. 合肥: 合肥工业大学, 2022.
7.	李丽惠. 不同运动干预方式对孤独症儿童运动能力的影响研究. 南昌: 江西师范大学, 2023.
8.	Yoshikawa T, Sasaki K I, Adachi H, et al. Weakened grip strength over 40 years in a community-dwelling cohort in Tanushimaru, Japan. Kurume Med J, 2023, 68(3.4): 191-200.
9.	Walker S, Avela J, Wikgren J, et al. Aging and strength training influence knee extensor intermuscular coherence during low- and high-force isometric contractions. Front Physiol, 2019, 9: 1933.
10.	Langhorne P, Bernhardt J, Kwakkel G. Stroke rehabilitation. Lancet, 2011, 377(9778): 1693-1702.
11.	Kan S, Ding M, Wang Z, et al. Design and research of eight-link rehabilitation training robot based on single degree of freedomitle. Journal of Mechanical Science and Technology, 2024, 38(4): 2029-2040.
12.	于玲. 加强康复训练对脑外伤患者康复效果的影响研究. 中国实用医药, 2021, 16(14): 186-189.
13.	Nasri H, Ghotbeddin Z, Rahimi K, et al. The effects of MEPaL on oxidative stress and motor function in the rats affected by prenatal hypoxia. Brain Behav, 2024, 14(6): e3539.
14.	邹琳. 基于表面肌电信号的下肢肌力预测研究. 武汉: 武汉理工大学, 2015.
15.	Hayashi K, Chuang C C D, Chang N J T, et al. Functioning free muscle transplantation to restore finger movement for sequalae of volkmann ischemic contracture. Hand Clin, 2024, 40(2): 269-281.
16.	张开拓. 上肢肘关节肌力预测与肌肉疲劳算法量化评价方法研究. 乌鲁木齐: 新疆大学, 2020.
17.	王成焘, 王冬梅, 白雪岭, 等. “中国力学虚拟人”研究及应用. 生命科学, 2010, 22(12): 1235-1240.
18.	Huang C, Chen X, Cao S, et al. An isometric muscle force estimation framework based on a high-density surface EMG array and an NMF algorithm. J Neural Eng, 2017, 14(4): 046005.
19.	Yang X, Yan J, Chen Z, et al. A proportional pattern recognition control scheme for wearable A-mode ultrasound sensing. IEEE Transactions on Industrial Electronics, 2020, 67(1): 800-808.
20.	Michela B, Martin H, Lukas L. Double machine learning for sample selection models. Journal of Business & Economic Statistics, 2024, 42(3): 958-969.
21.	Markco M, Kannan S. Texture-driven super-resolution of ultrasound images using optimized deep learning model. The Imaging Science Journal, 2024, 72(5): 643-656.
22.	Amir F, Alireza N. Classifying random variables based on support vector machine and a neural network scheme. Journal of Experimental & Theoretical Artificial Intelligence, 2024, 36(5): 679-702.
23.	Yin X, Müller F, Laguna A F, et al. Deep random forest with ferroelectric analog content addressable memory. Sci Adv, 2024, 10(23): eadk8471.
24.	Yin L, Mo N. Fractional-order transfer Q-learning based on modal decomposition and convolutional neural networks for voltage control of smart grids. Advanced Engineering Informatics, 2024, 62(Part A): 102602.
25.	Liu Y, Zhang X, Chen G, et al. Deterministic wave prediction model for irregular long-crested waves with recurrent neural network. Journal of Ocean Engineering and Science, 2024, 9(3): 251-263.
26.	夏伟. 基于A型超声与表面肌电信号融合的人机接口研究. 上海: 上海交通大学, 2019.
27.	Li Z, Liu F, Yang W, et al. A survey of convolutional neural networks: analysis, applications, and prospects. IEEE Trans Neural Netw Learn Syst, 2022, 33(12): 6999-7019.
28.	程镕杰, 杨耘, 李龙威, 等. 基于深度可分离卷积的轻量化残差网络高光谱影像分类. 光学学报, 2023, 43(12): 311-320.
29.	Hajimiri M, Talebi H A, Zareinejad M. Force tracking impedance control of robot-tissue interaction with a hunt-crosseley model//2016 4th International Conference on Control, Instrumentation, and Automation (ICCIA). Qazvin, Iran: IEEE, 2016: 142-147.
30.	Li X, Zhou S, Wang F, et al. An improved sparrow search algorithm and CNN-BiLSTM neural network for predicting sea level height. Sci Rep, 2024, 14(1): 4560.
31.	Mai N, Myers S, Shen S, et al. Dose dense doxorubicin plus cyclophosphamide in a modified KEYNOTE522 regimen for triple negative breast cancer. NPJ Breast Cancer, 2024, 10(1): 39.

1. Becker C J, Sucharew H, Robinson D, et al. Impact of poverty on stroke recurrence: a population-based study. Neurology, 2024, 102(11): e209423.
2. Nam H K, Chang S J, Kim C B, et al. The association between social support, metabolic syndrome, and incidence of cardio-cerebrovascular diseases in older adults: the ARIRANG study. Yonsei Med J, 2024, 65(6): 363-370.
3. Moore R T, Piitz M A, Singh N, et al. The independence of impairments in proprioception and visuomotor adaptation after stroke. J Neuroeng Rehabil, 2024, 21(1): 81.
4. Liu F, Chen C, Hong W, et al. Selectively disrupted sensorimotor circuits in chronic stroke with hand dysfunction. CNS Neurosci Ther, 2022, 28(5): 677-689.
5. Min S B, Hyun J L. Effect of different pelvic-drop exercises on hip muscles activity in patients with gluteus medius weakness. Isokinetics and Exercise Science, 2023, 31(4): 275-281.
6. 栗志铃. 基于sEMG信号和UE4引擎的手部康复训练系统的设计与实现. 合肥: 合肥工业大学, 2022.
7. 李丽惠. 不同运动干预方式对孤独症儿童运动能力的影响研究. 南昌: 江西师范大学, 2023.
8. Yoshikawa T, Sasaki K I, Adachi H, et al. Weakened grip strength over 40 years in a community-dwelling cohort in Tanushimaru, Japan. Kurume Med J, 2023, 68(3.4): 191-200.
9. Walker S, Avela J, Wikgren J, et al. Aging and strength training influence knee extensor intermuscular coherence during low- and high-force isometric contractions. Front Physiol, 2019, 9: 1933.
10. Langhorne P, Bernhardt J, Kwakkel G. Stroke rehabilitation. Lancet, 2011, 377(9778): 1693-1702.
11. Kan S, Ding M, Wang Z, et al. Design and research of eight-link rehabilitation training robot based on single degree of freedomitle. Journal of Mechanical Science and Technology, 2024, 38(4): 2029-2040.
12. 于玲. 加强康复训练对脑外伤患者康复效果的影响研究. 中国实用医药, 2021, 16(14): 186-189.
13. Nasri H, Ghotbeddin Z, Rahimi K, et al. The effects of MEPaL on oxidative stress and motor function in the rats affected by prenatal hypoxia. Brain Behav, 2024, 14(6): e3539.
14. 邹琳. 基于表面肌电信号的下肢肌力预测研究. 武汉: 武汉理工大学, 2015.
15. Hayashi K, Chuang C C D, Chang N J T, et al. Functioning free muscle transplantation to restore finger movement for sequalae of volkmann ischemic contracture. Hand Clin, 2024, 40(2): 269-281.
16. 张开拓. 上肢肘关节肌力预测与肌肉疲劳算法量化评价方法研究. 乌鲁木齐: 新疆大学, 2020.
17. 王成焘, 王冬梅, 白雪岭, 等. “中国力学虚拟人”研究及应用. 生命科学, 2010, 22(12): 1235-1240.
18. Huang C, Chen X, Cao S, et al. An isometric muscle force estimation framework based on a high-density surface EMG array and an NMF algorithm. J Neural Eng, 2017, 14(4): 046005.
19. Yang X, Yan J, Chen Z, et al. A proportional pattern recognition control scheme for wearable A-mode ultrasound sensing. IEEE Transactions on Industrial Electronics, 2020, 67(1): 800-808.
20. Michela B, Martin H, Lukas L. Double machine learning for sample selection models. Journal of Business & Economic Statistics, 2024, 42(3): 958-969.
21. Markco M, Kannan S. Texture-driven super-resolution of ultrasound images using optimized deep learning model. The Imaging Science Journal, 2024, 72(5): 643-656.
22. Amir F, Alireza N. Classifying random variables based on support vector machine and a neural network scheme. Journal of Experimental & Theoretical Artificial Intelligence, 2024, 36(5): 679-702.
23. Yin X, Müller F, Laguna A F, et al. Deep random forest with ferroelectric analog content addressable memory. Sci Adv, 2024, 10(23): eadk8471.
24. Yin L, Mo N. Fractional-order transfer Q-learning based on modal decomposition and convolutional neural networks for voltage control of smart grids. Advanced Engineering Informatics, 2024, 62(Part A): 102602.
25. Liu Y, Zhang X, Chen G, et al. Deterministic wave prediction model for irregular long-crested waves with recurrent neural network. Journal of Ocean Engineering and Science, 2024, 9(3): 251-263.
26. 夏伟. 基于A型超声与表面肌电信号融合的人机接口研究. 上海: 上海交通大学, 2019.
27. Li Z, Liu F, Yang W, et al. A survey of convolutional neural networks: analysis, applications, and prospects. IEEE Trans Neural Netw Learn Syst, 2022, 33(12): 6999-7019.
28. 程镕杰, 杨耘, 李龙威, 等. 基于深度可分离卷积的轻量化残差网络高光谱影像分类. 光学学报, 2023, 43(12): 311-320.
29. Hajimiri M, Talebi H A, Zareinejad M. Force tracking impedance control of robot-tissue interaction with a hunt-crosseley model//2016 4th International Conference on Control, Instrumentation, and Automation (ICCIA). Qazvin, Iran: IEEE, 2016: 142-147.
30. Li X, Zhou S, Wang F, et al. An improved sparrow search algorithm and CNN-BiLSTM neural network for predicting sea level height. Sci Rep, 2024, 14(1): 4560.
31. Mai N, Myers S, Shen S, et al. Dose dense doxorubicin plus cyclophosphamide in a modified KEYNOTE522 regimen for triple negative breast cancer. NPJ Breast Cancer, 2024, 10(1): 39.

Journal of Biomedical Engineering

Latest ArticlesResearch on multi-scale convolutional neural network hand muscle strength prediction model improved based on convolutional attention module

Abstract Full text Figures/Tables Video References Cited by

Format

Content