Surface electromyography (sEMG) signals play an essential role in disease diagnosis and rehabilitation. This study applied a powerful machine learning algorithm called extreme gradient boosting (XGBoost) to classify sEMG signals acquired from muscles around the knee for distinguishing patients with knee osteoarthritis (KOA) from healthy subjects. First, to improve data quality, we preprocessed the data via interpolation and normalization. Next, to ensure the description integrity of model input, we extracted nine time-domain features based on the statistical characteristics of sEMG signals over time. Finally, we classified the samples using XGBoost and cross-validation (CV) and compared the results to those produced by the support vector machine (SVM) and the deep neural network (DNN). Experimental results illustrate that the presented method effectively improves classification performance. Moreover, compared with the SVM and the DNN, XGBoost has higher accuracy and better classification performance, which indicates its advantages in the classification of patients with KOA based on sEMG signals.

1. [1] M. Simamora, G. V. Simanjuntak, and H. Syapitri, “Knee flexion extension and strengthening (FELS) exercise to pain intensity in knee osteoarthritis patients,” Indonesian Nursing J. of Education and Clinic, Vol.2, No.2, doi: 10.24990/injec.v2i2.43, 2018.
2. [2] Y. Li, N. Xu, and Q. Lyu, “Construction of a knee osteoarthritis diagnostic system based on X-ray image processing,” Cluster Computing, Vol.22, pp. 15533-15540, 2019.
3. [3] M. C. Wick, M. Kastlunger, and R. J. Weiss, “Clinical imaging assessments of knee osteoarthritis in the elderly: a mini-review,” Gerontology, Vol.60, No.5, pp. 386-394, 2014.
4. [4] B. Klasny, C. Albreche, I. Haase, and B. Swoboda, “Outcome of inpatient rehabilitation following total knee replacement using HSS-Score,” Z. Orthop. Ihre Grenzgeb., Vol.140, No.1, pp. 37-41, 2002.
5. [5] N. Ohmori, C. Murasawa, J. Aizawa, H. Momose, Y. Koyama, H. Kurita, H. Yoshida, and M. Kamijo, “Noise reduction in swallowing muscle activity measurement based on mixture Gaussian distribution model,” J. Adv. Comput. Intell. Intell. Inform., Vol.21, No.1, pp. 109-118, 2017.
6. [6] N. Duan, L. Liu, X. Yu, Q. Li, and S. Yeh, “Classification of multichannel surface-electromyography signals based on convolutional neural networks,” J. of Industrial Information Integration, Vol.15, pp. 201-206, 2019.
7. [7] N. Yogendra, M. Lini, and S. Chatterji, “sEMG signal classification with novel feature extraction using different machine learning approaches,” J. of Intelligent and Fuzzy Systems, Vol.35, No.5, pp. 5099-5109, 2018.
8. [8] M. Tavakoli, C. Benussi, P. A. Lopes, L. B. Osorio, and A. T. d. Almeida, “Robust hand gesture recognition with a double channel surface EMG wearable armband and SVM classifier,” Biomedical Signal Processing and Control, Vol.46, pp. 121-130, 2018.
9. [9] A. D. Bellingegni, E. Gruppioni, G. Colazzo, A. Davalli, R. Sacchetti, E. Guglielmelli, and L. Zollo, “NLR, MLP, SVM, and LDA: a comparative analysis on EMG data from people with trans-radial amputation,” J. of Neuroengineering and Rehabilitation, Vol.14, Article No.82, 2017.
10. [10] A. K. Mukhopadhyay and S. Samui, “An experimental study on upper limb position invariant EMG signal classification based on deep neural network,” Biomedical Signal Processing and Control, Vol.55, Article No.101669, 2020.
11. [11] A. Bakiya, K. Kamalanand, V. Rajinikanth, R. S. Nayak, and S. Kadry, “Deep neural network assisted diagnosis of time-frequency transformed electromyograms,” Multimedia Tools and Applications, Vol.79, pp. 11051-11067, 2020.
12. [12] Y. Bian and X. Xie, “Generative chemistry: drug discovery with deep learning generative models,” J. of Molecular Modeling, Vol.27, Article No.71, 2021.
13. [13] J. Snoek, H. Larochelle, and R. P. Adams, “Practical Bayesian Optimization of Machine Learning Algorithms,” Advances in Neural Information Processing Systems (NIPS), Vol.25, pp. 2951-2959, 2012.
14. [14] Y. Liu, H. Wang, Y. Fei, Y. Liu, L. Shen, Z. Zhuang, and X. Zhang, “Research on the prediction of green plum acidity based on improved XGBoost,” Sensors, Vol.21, No.3, Article No.930, 2021.
15. [15] C. Wang and J. Guo, “A data-driven framework for learners cognitive load detection using ECG-PPG physiological feature fusion and XGBoost classification,” Procedia Computer Science, Vol.147, pp. 338-348, 2019.
16. [16] S. Samui, A. K. Mukhopadhyay, P. K. Ghadge, and G. Kumar, “Extreme Gradient Boosting for Limb Position Invariant Myoelectric Pattern Recognition,” IEEE Int. Symp. on Smart Electronic Systems (iSES), pp. 81-85, 2020.
17. [17] J. Zhao, J. She, D. Wang, and F. Wang, “Patient classification based on sEMG signals using extreme gradient boosting algorithm,” The 7th Int. Workshop on Advanced Computational Intelligence and Intelligent Informatics (IWACIII), Article No.T1-1-6, 2021.
18. [18] X. Jin, D. Zhang, J. Zhang, and Y. Feng, “Study of multirate sampled acquisition of lightning current waveform based on short-time Fourier transform,” J. Adv. Comput. Intell. Intell. Inform., Vol.21, No.1, pp. 159-165, 2017.
19. [19] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” Proc. of the 22nd ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, pp. 785-794, 2016.
20. [20] J. Wei and H. Chen, “Determining the number of factors in approximate factor models by twice K-fold cross validation,” Economics Letters, Vol.191, Article No.109149, 2020.