Wavelet Based Machine Learning Technique to Classify the Different Shoulder Movement of Upper Limb Amputee


Article Preview

The wavelet transform is an accurate, efficient and efficacious method to improve the quality of the myoelectric signal. Classification of the signal from upper limb using Surface Electromyogram (SEMG) signal has been the matter of extensive research. Number of methods and algorithms have been described by researchers to classify biomedical signals. The main aim of this paper to extract the different coefficient values from the given SEMG data by using Discrete Wavelet Transform (DWT). Afterward, random forest machine learning algorithm was used to identify the different shoulder movement of an upper limb amputee. The combination of wavelet coefficients and random forest exhibited the best performance with 99.2% accuracy for the classification of different shoulder motions. It was found that the different motion can be identified accurately and provide the fundamental information to develop an efficient prosthetic device.





A. Kaur et al., "Wavelet Based Machine Learning Technique to Classify the Different Shoulder Movement of Upper Limb Amputee", Journal of Biomimetics, Biomaterials and Biomedical Engineering, Vol. 31, pp. 32-43, 2017

Online since:

March 2017




* - Corresponding Author

[1] K. Ziegler-Graham, E. J. MacKenzie, P. L. Ephraim, T. G. Travison, and R. Brookmeyer, Estimating the prevalence of limb loss in the united states: 2005 to 2050, Archives of Physical Medicine and Rehabilitation, 89(2008) 422–429.

DOI: 10.1016/j.apmr.2007.11.005

[2] Kaur A, Agarwal R, Kumar A. Comparison of muscles activity of abled bodied and amputee subjects for around shoulder movement. Biomed Mater Eng. 27 (2016) 29-37.

DOI: 10.3233/bme-161565

[3] R.T. Floyd. The Shoulder Girdle, Manual of Structural Kinesiology, Chapter 4. The McGraw-Hill Companies, (2012).

[4] Soma Hirokazu, Horiuchi Yuse, Gonzalez Jose and Wenwei Yu. Classification of Upper Limb Motions from Around-Shoulder Muscle Activities, Proceeding of IEEE Int. Conf. on Rehabilitation Robotics Rehab Week Zurich. ETH Zurich Science City, Switzerland (2011).

DOI: 10.5772/21763

[5] Min-Hyeok Kang, Jae-Seop, Jun-Hyeok. Jang Differences in Muscle Activities of the Infraspinatus and Posterior Deltoid during Shoulder External Rotation in Open Kinetic Chain and Closed Kinetic Chain Exercises. J Phys Ther Sci. 26 (2014) 895–897.

DOI: 10.1589/jpts.26.895

[6] Robert A. McCabe, Karl F. Orishimo, Malachy P. McHugh, Stephen J. Nicholas. Surface Electromygraphic Analysis of the Lower Trapezius Muscle During Exercises Performed Below Ninety Degrees of Shoulder Elevation in Healthy Subjects. N Am J Sports Phys Ther 2 (2007).

[7] A. Phinyomark1, C. Limsakul, P. Phukpattaranont. Application of Wavelet Analysis in EMG Feature Extraction for Pattern Classification, Measurement Science Review 11 (2011) 45-52.

DOI: 10.2478/v10048-011-0009-y

[8] Phinyomark, A., Hirunviriya, S., Limsakul, C., Phukpattaranont, P. Evaluation of EMG feature extraction for hand movement recognition based on euclidean distance and standard deviation. 7th International Conference on Electrical Engineering/Electronics, Computer, Telecommunica-tions and Information Technology, Chiang Mai, Thailand (2010).

[9] Wang, G., Wang, Z., Chen, W., Zhuang, J. Classification of surface EMG signals using optimal wavelet packet method based on Davies–Bouldin criterion. Med. Biol. Eng. Comput 44 (2006). 865-872.

DOI: 10.1007/s11517-006-0100-y

[10] A. Phinyomark, A. Nuidod, P. Phukpattaranont, C. Limsakul Feature Extraction and Reduction of Wavelet Transform Coefficients for EMG Pattern Classification, Electronics and electrical engg 2 (2012) 27-33.

DOI: 10.5755/j01.eee.122.6.1816

[11] A. B. M. S. U. Doulah, S. A. Fattah, W. -P. Zhu. Wavelet Domain Feature Extraction Scheme Based on Dominant Motor Unit Action Potential of EMG Signal for Neuromuscular Disease Classification, IEEE Transactions On Biomedical Circuits And Systems 8 (2014).

DOI: 10.1109/tbcas.2014.2309252

[12] Kaur A, Agarwal R, Kumar A. A Combined Statistical and Time-Frequency Approach to the Analysis of Electromyography Signals. Advances in Metrology (2014) 19-21.

[13] Englehart, K., Hudgins, B., Parker, P.A. A wavelet-based continuous classification scheme for multifunction myoelectric control, IEEE Trans. Biomed. Eng. 48 (2001) 302-311.

DOI: 10.1109/10.914793

[14] Gokgoz E, Subasi A. Comparison of decision tree algorithms for EMG signal classification using DWT. Biomedical Signal Processing and Control 18 2015)138-144.

DOI: 10.1016/j.bspc.2014.12.005

[15] Shuxiang G, Muye Pang, Baofeng Gao, Hideyuki H, Hidenori, I. Comparison of sEMG-Based Feature Extraction and Motion Classification Methods for Upper-Limb Movement. Sensors 15 (2015) 9022-9031.

DOI: 10.3390/s150409022

[16] Fadlalla A. An experimental investigation of the impact of aggregation on the performance of data mining with logistic regression. Journal of Information & Management 42 (2005)695-707.

DOI: 10.1016/j.im.2004.04.005

[17] Marijana ZS, Sanja P, N Sarlija. A Comparison of Machine Learning Methods in a High-Dimensional Classification Problem. Business Systems Research 5 (2014) 82-96.

DOI: 10.2478/bsrj-2014-0021

[18] Raez M.B.I., Hussain M.S., Mohd-Yasin, F. Techniques of EMG signal analysis: detection, processing, classification and applications. Bio Proced Online 8 (2006) 12-35.

DOI: 10.1251/bpo115

[19] Farzaneh Akhavan Mahdavi, Siti Anom Ahmad, Mohd Hamiruce Marhaban, and Mohammad-R. Akbarzadeh, The Utility of Wavelet Transform in Surface Electromyography Feature Extraction A Comparative Study of Different MotherWavelets, Measurement Science Review 12 (2012).

[20] M. S. Hussain1, Md. Mamun, Effectiveness of the Wavelet Transform on the Surface EMG to Understand the Muscle Fatigue during Walk, School of Electrical and Information Engineering, University of Sydney, NSW Australia (2006) 28-33.

DOI: 10.2478/v10048-012-0005-x

[21] Walker, J. A Primer on Wavelets and Their Scientific Applications. Chapman & Hall. (1999).

[22] González Jose, Horiuchi Yuse, and Wenwei Yu, Classification of Upper Limb Motions from Around-Shoulder Muscle Activities: Hand Biofeedback, The Open Medical Informatics Journal 4 (2010) 74-80.

DOI: 10.2174/1874431101004010074

[23] Horiuchi Yuse, González Jose. A study on classification of upper limb motions from around- shoulder muscle activities. Proceeding of ICORR, IEEE International Conference on Rehabilitation Robotics (2009) 311-16.

DOI: 10.1109/icorr.2009.5209477

[24] Merletti, R, Standards for Reporting EMG Data. Journal of Electromyography and Kinesiology, 1999 III-IV.

[25] Butterworth, S, On the Theory of Filter Amplifiers. Wireless Engineer (also called Experimental Wireless and the Wireless Engineer 7 (1930) 536–541.

[26] Phinyomark, A., C. Limsakul, and P. Phukpattaranont, Optimal wavelet functions in wavelet denoising for multifunction myoelectric control. ECTI Transactions on Electrical Eng., Electronics, and Communications. -ECTI 8 (2010) 43-52.

DOI: 10.1109/ecticon.2009.5137236

[27] 1M.S. Hussain and 2Md. Mamun, Wavelet Denoising and Surface Electromyography Analysis, School of Electrical and Information Engineering, University of Sydney (2006) 2372-2374.

[28] Mitchell, T.M. Machine Learning, McGraw-Hill, (1997).

[29] Qi,Y. Random forest for bioinformatics, Ensemble Machine Learning Methods and Applications 2012. pp.307-323.

[30] Breiman L. Random forests. Mach. Learn. 2001, pp.5-32.

[31] Smola A, Vishwanathan SVN. Introduction to Machine Learning; Cambridge university press.

[32] Ballantyne BT, O'Hare SJ, Paschall JL, et al. Electromyographic activity of selected shoulder muscles in commonly used therapeutic exercises. Phys Ther. 73 (1993) 668–677.

DOI: 10.1093/ptj/73.10.668

Fetching data from Crossref.
This may take some time to load.