Feature fusion of electrocardiogram and surface electromyography for estimating the fatigue states during lower limb rehabilitation_Journal of Biomedical Engineering

Authors：

YUAN Yaoyao ¹ ,  CAO Dianguo ¹ , LI Cong ¹ , LIU Chengyu ²

1. College of Engineering, Qufu Normal University, Rizhao, Shandong 276826, P.R.China;
2. School of Instrument Science and Engineering, Southeast University, Nanjing 210096, P.R.China;

Corresponding?author：

CAO Dianguo, Email: caodg@qfnu.edu.cn

Keywords：

lower limbs fatigue estimation; electrocardiogram; surface electromyography; feature fusion; improved particle swarm optimization-support vector machine

DOI：

10.7507/1001-5515.201907053

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

In the process of lower limb rehabilitation training, fatigue estimation is of great significance to improve the accuracy of intention recognition and avoid secondary injury. However, most of the existing methods only consider surface electromyography (sEMG) features but ignore electrocardiogram (ECG) features when performing in fatigue estimation, which leads to the low and unstable recognition efficiency. Aiming at this problem, a method that uses the fusion features of ECG and sEMG signal to estimate the fatigue during lower limb rehabilitation was proposed, and an improved particle swarm optimization-support vector machine classifier (improved PSO-SVM) was proposed and used to identify the fusion feature vector. Finally, the accurate recognition of the three states of relax, transition and fatigue was achieved, and the recognition rates were 98.5%, 93.5%, and 95.5%, respectively. Comparative experiments showed that the average recognition rate of this method was 4.50% higher than that of sEMG features alone, and 13.66% higher than that of the combined features of ECG and sEMG without feature fusion. It is proved that the feature fusion of ECG and sEMG signals in the process of lower limb rehabilitation training can be used for recognizing fatigue more accurately.

Citation： YUAN Yaoyao, CAO Dianguo, LI Cong, LIU Chengyu. Feature fusion of electrocardiogram and surface electromyography for estimating the fatigue states during lower limb rehabilitation. Journal of Biomedical Engineering, 2020, 37(6): 1056-1064. doi: 10.7507/1001-5515.201907053 Copy

1.	彭亮, 侯增廣, 王晨, 等. 康復輔助機器人及其物理人機交互方法. 自動化學報, 2018, 44(11): 2000-2010.
2.	崔立軍, 鮑勇, 陳昕, 等. 中國康復臨床實踐指南的質量評價. 中國循證醫學雜志, 2019, 19(6): 723-728.
3.	Li W F, Hu X Y, Gravina R, et al. A neuro-fuzzy fatigue-tracking and classification system for wheelchair users. IEEE Access, 2017, 5: 19420-19431.
4.	Shahmoradi S, Zare A, Behzadipour S. Fatigue status recognition in a post-stroke rehabilitation exercise with sEMG signal//24th National Iranian Conference on Biomedical Engineering/2nd International Iranian Conference on Biomedical Engineering (ICBME). Tehran: IEEE, 2017: 162-166.
5.	謝平, 劉歡, 王磊磊, 等. 基于腦肌電反饋的虛擬康復訓練系統設計. 儀器儀表學報, 2018, 39(1): 250-257.
6.	于亞萍, 孫立寧, 張峰峰, 等. 基于小波變換的多特征融合sEMG模式識別. 傳感技術學報, 2016, 29(4): 512-518.
7.	徐國政, 宋愛國, 高翔, 等. 基于焦慮情緒與混雜控制的機器人輔助臨床康復實驗. 儀器儀表學報, 2017, 38(10): 2364-2372.
8.	Mei Z N, Gu X, Chen W, et al. Automatic atrial fibrillation detection based on heart rate variability and spectral features. IEEE Access, 2018, 6: 53566-53575.
9.	Berkaya S K, Uysal A K, Gunal E S, et al. A survey on ECG analysis. Biomed Signal Process Control, 2018, 43: 216-235.
10.	Zhang Z Q, Ji L Y, Huang Z P, et al. Adaptive information fusion for human upper limb movement estimation. IEEE Trans Syst Man Cybern, 2012, 42(5): 1100-1108.
11.	Zhao L N, Liu C Y, Wei S S, et al. Enhancing detection accuracy for clinical heart failure utilizing pulse transit time variability and machine learning. IEEE Access, 2019, 7: 17716-17724.
12.	Aly H I, Youssef S, Fathy C. Hybrid brain computer interface for movement control of upper limb prostheses//International Conference on Biomedical Engineering and Applications (ICBEA). Funchal: IEEE, 2018: 86-91.
13.	Baumgartner C, Koren J P, Rothmayer M. Automatic computer-based detection of epileptic seizures. Front Neurol, 2018, 9: 1-9.
14.	Astorino T A, Allen R P, Roberson D W, et al. Attenuated RPE and leg pain in response to short-term high-intensity interval training. Physiol Behav, 2012, 105(2): 402-407.
15.	Cui C K, Blan G B, Hou Z G, et al. A multimodal framework based on integration of cortical and muscular activities for decoding human intentions about lower limb motions. IEEE Trans Biomed Circuits Syst, 2017, 11(4): 889-899.
16.	任斌斌, 譚海燕, 馬成群, 等. 基于白噪聲分離的集合經驗模態分解心電信號去噪方法研究. 生物醫學工程學雜志, 2016, 33(2): 221-226.
17.	Kuthe C D, Uddanwadiker R V, Ramteke A A. Surface electromyography based method for computing muscle strength and fatigue of biceps brachii muscle and its clinical implementation. Inform Med Unlocked, 2018, 12: 34-43.
18.	Liu J K, Yin L Y, He C G, et al. Multiscale autoregressive model-based electrocardiogram identification method. IEEE Access, 2018, 6: 18251-18263.
19.	李昕, 蔡二娟, 田彥秀, 等. 一種改進腦電特征提取算法及其在情感識別中的應用. 生物醫學工程學雜志, 2017, 34(4): 510-528.
20.	Amin S U, Alsulaiman M, Muhammad G, et al. Deep learning for EEG motor imagery classification based on multi-layer CNNs feature fusion. Future Gener Comput Syst, 2019, 101: 542-554.
21.	Melgani F, Bazi Y. Classification of electro-cardiogram signals with support vector machines and particle swarm optimization. IEEE Trans Inform Technol Biomed, 2008, 12(5): 667-677.
22.	Liu C Y, Zhang X Y, Zhao L N, et al. Signal quality assessment and lightweight QRS detection for wearable ECG SmartVest system. IEEE Internet of Things J, 2019, 6(2): 1363-1374.
23.	Zhan Y F, Yao H X, Liu Y, et al. Network-based statistic show aberrant functional connectivity in Alzheimer’s disease. IEEE J Sel Top Signal Process, 2016, 10(7): 1182-1188.
24.	Wu Q, Mao J F, Wei C F, et al. Hybrid BF-PSO and fuzzy support vector machine for diagnosis of fatigue status using EMG signal features. Neurocomputing, 2015, 173(3): 483-500.
25.	Karthick P A, Ghosh D M, Ramakrishnan S. Surface electromyography based muscle fatigue detection using high-resolution time-frequency methods and machine learning algorithms. Comput Meth Prog Bio, 2018, 154: 45-56.

1. 彭亮, 侯增廣, 王晨, 等. 康復輔助機器人及其物理人機交互方法. 自動化學報, 2018, 44(11): 2000-2010.
2. 崔立軍, 鮑勇, 陳昕, 等. 中國康復臨床實踐指南的質量評價. 中國循證醫學雜志, 2019, 19(6): 723-728.
3. Li W F, Hu X Y, Gravina R, et al. A neuro-fuzzy fatigue-tracking and classification system for wheelchair users. IEEE Access, 2017, 5: 19420-19431.
4. Shahmoradi S, Zare A, Behzadipour S. Fatigue status recognition in a post-stroke rehabilitation exercise with sEMG signal//24th National Iranian Conference on Biomedical Engineering/2nd International Iranian Conference on Biomedical Engineering (ICBME). Tehran: IEEE, 2017: 162-166.
5. 謝平, 劉歡, 王磊磊, 等. 基于腦肌電反饋的虛擬康復訓練系統設計. 儀器儀表學報, 2018, 39(1): 250-257.
6. 于亞萍, 孫立寧, 張峰峰, 等. 基于小波變換的多特征融合sEMG模式識別. 傳感技術學報, 2016, 29(4): 512-518.
7. 徐國政, 宋愛國, 高翔, 等. 基于焦慮情緒與混雜控制的機器人輔助臨床康復實驗. 儀器儀表學報, 2017, 38(10): 2364-2372.
8. Mei Z N, Gu X, Chen W, et al. Automatic atrial fibrillation detection based on heart rate variability and spectral features. IEEE Access, 2018, 6: 53566-53575.
9. Berkaya S K, Uysal A K, Gunal E S, et al. A survey on ECG analysis. Biomed Signal Process Control, 2018, 43: 216-235.
10. Zhang Z Q, Ji L Y, Huang Z P, et al. Adaptive information fusion for human upper limb movement estimation. IEEE Trans Syst Man Cybern, 2012, 42(5): 1100-1108.
11. Zhao L N, Liu C Y, Wei S S, et al. Enhancing detection accuracy for clinical heart failure utilizing pulse transit time variability and machine learning. IEEE Access, 2019, 7: 17716-17724.
12. Aly H I, Youssef S, Fathy C. Hybrid brain computer interface for movement control of upper limb prostheses//International Conference on Biomedical Engineering and Applications (ICBEA). Funchal: IEEE, 2018: 86-91.
13. Baumgartner C, Koren J P, Rothmayer M. Automatic computer-based detection of epileptic seizures. Front Neurol, 2018, 9: 1-9.
14. Astorino T A, Allen R P, Roberson D W, et al. Attenuated RPE and leg pain in response to short-term high-intensity interval training. Physiol Behav, 2012, 105(2): 402-407.
15. Cui C K, Blan G B, Hou Z G, et al. A multimodal framework based on integration of cortical and muscular activities for decoding human intentions about lower limb motions. IEEE Trans Biomed Circuits Syst, 2017, 11(4): 889-899.
16. 任斌斌, 譚海燕, 馬成群, 等. 基于白噪聲分離的集合經驗模態分解心電信號去噪方法研究. 生物醫學工程學雜志, 2016, 33(2): 221-226.
17. Kuthe C D, Uddanwadiker R V, Ramteke A A. Surface electromyography based method for computing muscle strength and fatigue of biceps brachii muscle and its clinical implementation. Inform Med Unlocked, 2018, 12: 34-43.
18. Liu J K, Yin L Y, He C G, et al. Multiscale autoregressive model-based electrocardiogram identification method. IEEE Access, 2018, 6: 18251-18263.
19. 李昕, 蔡二娟, 田彥秀, 等. 一種改進腦電特征提取算法及其在情感識別中的應用. 生物醫學工程學雜志, 2017, 34(4): 510-528.
20. Amin S U, Alsulaiman M, Muhammad G, et al. Deep learning for EEG motor imagery classification based on multi-layer CNNs feature fusion. Future Gener Comput Syst, 2019, 101: 542-554.
21. Melgani F, Bazi Y. Classification of electro-cardiogram signals with support vector machines and particle swarm optimization. IEEE Trans Inform Technol Biomed, 2008, 12(5): 667-677.
22. Liu C Y, Zhang X Y, Zhao L N, et al. Signal quality assessment and lightweight QRS detection for wearable ECG SmartVest system. IEEE Internet of Things J, 2019, 6(2): 1363-1374.
23. Zhan Y F, Yao H X, Liu Y, et al. Network-based statistic show aberrant functional connectivity in Alzheimer’s disease. IEEE J Sel Top Signal Process, 2016, 10(7): 1182-1188.
24. Wu Q, Mao J F, Wei C F, et al. Hybrid BF-PSO and fuzzy support vector machine for diagnosis of fatigue status using EMG signal features. Neurocomputing, 2015, 173(3): 483-500.
25. Karthick P A, Ghosh D M, Ramakrishnan S. Surface electromyography based muscle fatigue detection using high-resolution time-frequency methods and machine learning algorithms. Comput Meth Prog Bio, 2018, 154: 45-56.

Previous Article
Design of functional array electrode stimulation system with surface electromyography feedback
Next Article
A bionic cerebellar motion control model and its application in arm control

Journal of Biomedical Engineering

Feature fusion of electrocardiogram and surface electromyography for estimating the fatigue states during lower limb rehabilitation

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content