Classification of EMG Signal for Health Screening Task for Musculoskeletal Disorder
Keywords:Electromyography, Spectrogram, Machine learning classifier, Mean root mean square voltage.
Electromyography signal analysis and classification method for Health Screening ProgramÂ for Social Security Organisation (SOCSO) Malaysia is the first time applied using time-frequency distribution (TFD). This paper presents the classification of EMG signals for health screening task for musculoskeletal disorder. A time-frequency method, i.e spectrogram is employed to obtain the data of time and frequency information of the EMG signal. Four machine learning classifier of k-Nearest Neighbor (k-NN), Linear Discriminant Analysis (LDA), NaÃ¯ve Bayes (NB) and Support Vector Machine (SVM) are implemented to EMG signal. Three out of six tasks (axial rotational task, kneeling reach and kneeling to standing back reach) which focused on the upper limb was performed using Multi Sensor Management ConsensysPRO and functional range on motion (FROM). From the experiment, SVM classifier is outperformed others using the purposed extracted features from spectrogram which is more than 80% except NB with 73.33%. The finding of the study concludes that SVM is suitable to classify EMG signal and can help rehabilitation center to diagnose their patients.
 Daneshmandi, H., Choobineh, A. R., Ghaem, H., Alhamd, M., & Fakherpour, A. (2017). The effect of musculoskeletal problems on fatigue and productivity of office personnel: a cross-sectional study. Journal of preventive medicine and hygiene, 58(3), pp. 252-258.
 Zawawi, T. T., Abdullah, A. R., Jopri, M. H., Sutikno, T., Saad, N. M., & Sudirman, R. (2018). A Review of Electromyography Signal Analysis Techniques for Musculoskeletal Disorders,11(3), pp. 1136-1146.
 Too. Jingwei, A.R Abdullah, Norhashimah Mohd Saad, N. Ali, And T.N.S Tengku Zawawi (2018). Application of Spectrogram and Discrete Wavelet Transform For EMG Pattern Recognition. Journal of Theoretical & Applied Information Technology, 96(10), pp. 3036-3047.
 Buckley, P. (2016). Work-related Musculoskeletal Disorder (WRMSDs) Statistics, Great Britain 2016. Health and Safety Executive (HSE), pp. 1-20.
 Nazmi, N., Abdul Rahman, M., Yamamoto, S. I., Ahmad, S., Zamzuri, H., & Mazlan, S. (2016). A review of classification techniques of EMG signals during isotonic and isometric contractions. Sensors, 16(8), 1304.
 Ruchika, Shalini Dhingra. (2013). An explanatory study of the parameters to be measured from emg signal, International Journal of Engineering and Computer Science , 2(1), pp.207â€“213.
 Y. Ning and Y. Zhang, (2017). A new approach for multi-channel surface EMG signal simulation, Biomedical Engineering Letters, 7(1), pp. 45â€“53.
 Kiguchi, Kazuo, and Yoshiaki Hayashi, (2012). Estimation of joint torque for a myoelectric arm by genetic programming based on EMG signals, In World Automation Congress (WAC), pp. 1-4. IEEE.
 S. Thongpanja, A. Phinyomark, F. Quaine, Y. Laurillau, C. Limsakul, and P. Phukpattaranont, (2016). Probability Density Functions of Stationary Surface EMG Signals in Noisy Environments, IEEE Transactions on Instrumentation and Measurement, 65(7), pp. 1547â€“1557.
 R. H. Chowdhury, M. B. I. Reaz, M. A. B. M. Ali, A. A. A. Bakar, K. Chellappan, and T. G. Chang,(2013). Surface electromyography signal processing and classification techniques, Sensors, 13(9), pp. 12431â€“12466.
 Zhang, Xu, and Ping Zhou, (2012). High-density myoelectric pattern recognition toward improved stroke rehabilitation, IEEE Transactions on Biomedical Engineering, 59(6), pp.1649-1657.
 Kakoty, Nayan M., and Shyamanta M. Hazarika, (2011). Recognition of grasp types through principal components of dwt based emg features, In 2011 IEEE International Conference on Rehabilitation Robotics (ICORR), pp. 1-6. IEEE
 D. Joshi, B. H. Nakamura, and M. E. Hahn, (2015). High energy spectrogram with integrated prior knowledge for EMG-based locomotion classification, Medical Engineering and Physics, 37(5), pp. 518â€“524.
 Jopri, M. H., A. R. Abdullah, M. Manap, T. Sutikno, and M. R. Ab Ghani, (2018). Harmonic Contribution Analysis of Electric Arc Furnace by Using Spectrogram, Bulletin of Electrical Engineering and Informatics, 7(2), pp. 236-243.
 M. B. I. Reaz, M. S. Hussain, and F. Mohd-Yasin, (2006). Techniques of EMG signal analysis: detection, processing, classification and applications, Biol. Proced. Online, 8(1), pp. 11â€“35.
 Tengku Nor Shuhada Tengku Zawawi, Abdul Rahim Abdullah, Isa Halim, Ezreen Farina Shair, and Saleha Mohamad Salleh, (2016). Application of spectrogram in analysing electromyography (EMG) signals of manual lifting, ARPN Journal of Engineering and Applied Sciences, 22(5), pp. 3603-3609.
 Andreotti, A., A. Bracale, P. Caramia, and G. Carpinelli, (2009) Adaptive Prony method for the calculation of power-quality indices in the presence of nonstationary disturbance waveforms, IEEE Transactions on Power Delivery, 24(2), pp. 874-883.
 Kotsiantis, Sotiris B., I. Zaharakis, and P. Pintelas,(2007). Supervised machine learning: A review of classification techniques, Emerging artificial intelligence applications in computer engineering,160, pp. 3-24.
 Tripathy, Abinash, Ankit Agrawal, and Santanu Kumar Rath, (2015). Classification of sentimental reviews using machine learning techniques, Procedia Computer Science, 57, pp. 821-829, 2015.
 NQ Zainal Abidin et al, (2012) Leakage current analysis on polymeric surface condition using time-frequency distribution. In: 2012 IEEE International Power Engineering and Optimization Conference (PEOCO) Melaka,Malaysia,. IEEE. pp. 171â€“175, 2012.
 Maillo, Jesus, Sergio RamÃrez, Isaac Triguero, and Francisco Herrera, (2016). kNN-IS: An Iterative Spark-based design of the k-Nearest Neighbors classifier for big data, Knowledge-Based Systems,117, pp. 3-15.
 Deng, Zhenyun, Xiaoshu Zhu, Debo Cheng, Ming Zong, and Shichao Zhang, (2016) Efficient kNN classification algorithm for big data. Neurocomputing, 195, pp. 143-148.
 G.Venugopal, M. Navaneethakrishna, and S. Ramakrishnan, (2014). Extraction and analysis of multiple time window features associated with muscle fatigue conditions using sEMG signalsâ€, Expert Systems with Applications, 41(6), pp. 2652â€“2659.
 Khan, Salabat, Muhammad Hussain, Hatim Aboalsamh, and George Bebis,(2017). A comparison of different Gabor feature extraction approaches for mass classification in mammography, Multimedia Tools and Applications, 76(1) , pp. 33-57.
 P. Bermejo, J. A. GÃ¡mez, and J. M. Puerta, (2014). Speeding up incremental wrapper feature subset selection with Naive Bayes classifier, Knowledge-Based Systems, 55, pp. 140â€“147.
 Wang, Lipo, ed. (2005). Support vector machines: theory and applications. Springer Science & Business Media, 177.
 J. Yousefi and A. Hamilton-Wright, Characterizing EMG data using machine- learning tools (2014), Computers Biology and Medicine, 51, pp. 1â€“13.
 H. Xu and G. Chen, (2013). An intelligent fault identification method of rolling bearings based on LSSVM optimized by improved PSO, Mechanical Systems and Signal Processing, 35(1), pp. 167â€“ 175.
 A.-C. Tsai, J.-J. Luh, and T.-T. Lin, (2015). A novel STFT-ranking feature of multi-channel EMG for motion pattern recognition, Expert Systems with Applications, 42(7), pp. 3327â€“3341.
 Gao, Vance, Fred Turek, and Martha Vitaterna, (2016). Multiple classifier systems for automatic sleep scoring in mice, Journal of neuroscience methods, 264, pp. 33-39.
 Wang, Hua, and Yanchun Zhang, (2016). Detection of motor imagery EEG signals employing NaÃ¯ve Bayes based learning process, Measurement, 86, pp. 148-158.
 Harris, Terry, (2015). Credit scoring using the clustered support vector machine,â€ Expert Systems with Applications,42(2), pp. 741-750.