Classification of 52 Hand Postures and Movements Using the LDA and LS-SVM Classifiers Applicable to Myoelectric Hand Prostheses

Nazemi, Afarin; Maleki, Ali

doi:10.22041/ijbme.2014.14707

Document Type : Technical note

Authors

Afarin Nazemi ¹
Ali Maleki ²

¹ M.Sc Student, Biomedical Engineering Department, Semnan University, Semnan, Iran

² Assisstant Professor, Biomedical Engineering Department, Semnan University, Semnan, Iran

10.22041/ijbme.2014.14707

Abstract

Classification of distal limb movements based on surface electromyography (sEMG) of proximal muscles is an important issue in the control of myoelectric hand prosthesis. In most of previous studies, classification of a limited number of hand motions is investigated. In this paper, we have used NINAPRO database containing kinematics and sEMG of upper limbs while performing 52 finger, hand and wrist movements. We evaluated performance of LDA and LS-SVM with RBF kernel classifiers using different combination of features. First by windowing the signal with two different methods, the major part of the signal was selected and eight various temporal features (MAV, IAV, RMS, WL, E, ER1, ER2, CC) were extracted. Then performance of each classifier with single, double and multiple combinations of features was evaluated. For LDA classifier, the best average classification accuracy of 84.23% was achived for first windowing method and MAV (or IAV)+CC features, The corresponding accuracy for LS-SVM classifier with second windowing method and IAV+MAV+RMS+WL features, was 85.19%.

Keywords

Main Subjects

References

[1] L. R. Hochberg, M. D. Serruya, G. M. Friehs, J. A. Mukand, M. Saleh, A. H. Caplan, A. Branner, D. Chen, R. D. Penn, J. P. Donoghue, “Neuronal ensemble control of prosthetic devices by a human with tetraplegia” Nature 442, 164-171, 2006.

[2] T. Kuiken, P. Marasco, B. Lock, R. Harden, J. Dewald, “Redirection of cutaneous sensation from the hand to the chest skin of human amputees with targeted reinnervation” Proc Nat Acad Sci USA 104 (50), 20061–20066, 2007.

[3] B. Peerdeman, D. Boere, H. Witteveen, R. Huis, H. H, S. Stramigioli, H. Rietman, P. Veltink, S. Misra, ”Myoelectric forearm prostheses: State of the art from a user-centered perspective” JRRD 2011.

[4] P. Shenoy, K. J. Miller, B. Crawford, R. N. Rao, “Online electromyographic control of a robotic prosthesis” IEEE Trans Biomed Eng 55 (3), 1128–35, 2008.

[5] L. Hargrove, Y. Losier, B. Lock, K. Englehart, B. Hudgins, "A real-time pattern recognition based myoelectric control usability study implemented in a virtual environment" Conf Proc IEEE Eng Med Biol Soc 4842–45, 2007.

[6] J. W. Sensinger, B. A. Lock, T. A. Kuiken, “Adaptive pattern recognition of myoelectric signals: Exploration of conceptual framework and practical algorithms” IEEE Trans Neural Syst Rehabil Eng 17 (3), 270–78, 2009.

[7] R. Zhou, X. Liu, G. Li, “Myoelectric signal feature performance in classifying motion classes in transradial amputees” Proceedings of the Congress of the International Society of Electrophysiology and Kinesiology (ISEK) 2010.

[8] G. Li, A. Schultz, T. Kuiken, “Quantifying pattern recognition based myoelectric control of multifunctional transradial prostheses” IEEE Trans Neural Syst Rehabil Eng 18 (2), 185–192, 2010.

[9] ا. صائب منفرد، ک. ستاره‌دان، "طبقه‌بندی سیگنال الکترومایوگرام (EMG) حاصل از حرکات مختلف دست توسط ماشین‌‌های بردار حمایتی (SVM)" یازدهمین کنفرانس سالانه انجمن کامپیوتر ایران، 1384.

[10] M. A. Oskoei, H. Hu, “Support vector machine-based classiﬁcation scheme for myoelectric control applied to upper limb” IEEE Trans Biomed Eng 55 (8), 1956–1965, 2008.

[11] Z. Yan, X. You, J. Chen, X. Ye, “Motion classification of EMG signals based on wavelet packet transform and LS-SVMs ensemble" Transaction on Tianjin University and Springer verlag 2009.

[12] I. Kuzborskij, A. Gijsberts, B. Caputo, “On the Challenge of Classifying 52 Hand Movements from Surface Electromyography” Proceedings of Annual International Conference on IEEE-EMBC 4931-4937, 2012.

[13] M. Atzori, A. Gijsberts, et al. “NINAPRO project first milestone: Set up of the database” Institute of Business Information Systems, University of Applied Sciences Western Switzerland, Sierre, Switzerland, Tech Rep, available at:

http://publications.hevs.ch, 2012.

[14] Otto Bock HealthCare Products GmbH, 13E200 Electrode Myobock, Retrieved 15/10/2013 from: http://www.ottobock.com/ .

[15] M. Zecca, S. Micera, M. C. Carrozza, and P. Dario, “Control of Multifunctional Prosthetic Hands by Processing the Electromyographic Signal” Critical Reviews™ in Biomedical Engineering 2002.

[16] A. Phinyomark, P. Phukpattaranont, C. Limsakul, “Feature reduction and selection for EMG signal classification” Expert Systems with Applications 39, 7420-7431, 2011.

[17] X. Tang, Y. Liu, C. Lv, D. Sun, “Hand Motion Classification Using a Multi-Channel Surface Electromyography” Sensors 12 (2), 1130-1147, 2012.

[18] J. A. K. Suykens, T. V. Gestel, J. De Brabanter, D. B. De Moor, E. J. Vandewalle, “Least Squares Support Vector Machines” World Scientific Singapore (ISBN 981-238-151-1), Retrieved 28/12/2012 from:

http://books.google.com/, 2002.

[19] G. Li, “Electromyography Pattern-Recognition-Based Control of Powered Multifunctional Upper-Limb Prostheses” Advances in Applied Electromyography Joseph Mizrahi (Ed) ISBN 978-953-307-382-8, InTech, Available at:

http://www.intechopen.com, 2011.

[20] Least Square Support Vector Machines MATLAB/C Toolbox, retrieved 11/1/2012 from:

http://www.esat.kuleuven.be/ .

Iranian Journal of Biomedical Engineering

Classification of 52 Hand Postures and Movements Using the LDA and LS-SVM Classifiers Applicable to Myoelectric Hand Prostheses

References

References

Volume 8, Issue 4 - Serial Number 4
February 2015
Pages 411-420

Classification of 52 Hand Postures and Movements Using the LDA and LS-SVM Classifiers Applicable to Myoelectric Hand Prostheses

References

References

Volume 8, Issue 4 - Serial Number 4February 2015Pages 411-420

Volume 8, Issue 4 - Serial Number 4
February 2015
Pages 411-420