Abstract
Dual-channel evaluation of surface electromyogram (SEMG) signals acquired from amputee subjects using computational techniques for classification of arm motions is presented in this study. SEMG signals were classified by the neural network (NN) and interpretation was done using statistical techniques to extract the effectiveness of the recorded signals. From the results, it was observed that there exists a calculative difference in amplitude gain across different motions and that SEMG signals have great potential to classify arm motions. The outcomes indicated that the NN algorithm performs significantly better than other algorithms, with a classification rate (CR) of 96.40%. Analysis of variance (ANOVA) presents the results to validate the effectiveness of the recorded data to discriminate SEMG signals. The results are of significant thrust in identifying the operations that can be implemented for classifying upper-limb movements suitable for prostheses’ design.
Research funding: Authors state no funding involved.
Conflict of interest: No potential conflict of interest was reported by the authors.
Informed consent: All the participants read and signed an informed consent prior to the experiment (as described by the World edical Association’s Declaration of Helsinki).
Ethical approval: The research related to human use complies with all the relevant national regulations and institutional policies, was performed in accordance with the tenets of the Helsinki Declaration.
References
[1] Ahsan MR, Ibrahimy MI, Khalif OO. Electromygraphy (EMG) Signal based Hand Gesture Recognition using Artificial Neural Network (ANN). 4th International Conference on Mechatronics (ICOM), Kuala Lumpur, 2011: 1–6.10.1109/ICOM.2011.5937135Search in Google Scholar
[2] Arjunan SP, Kumar DK. Decoding subtle forearm flexions using fractal features of surface electromyogram from single and multiple sensors. J Neuro Eng Rehabil 2010; 7: 1–10.10.1186/1743-0003-7-53Search in Google Scholar PubMed PubMed Central
[3] Balbinot A, Junior SA, Favieiro WG. Decoding arm movements by myoelectric signal and artificial neural networks. Int Control Autom 2013; 4: 87–93.10.4236/ica.2013.41012Search in Google Scholar
[4] Castro F, Claudia M. Linear discriminating analysis versus Artificial Neural network as classifiers for elbow angular position recognition purposes. Proceedings of the International Conference on Bio-inspired Systems and Signal Processing, 351–355: 2012.Search in Google Scholar
[5] Hariharan M, Fook YC, Sindhu R, Ilias B, Yaacob S. A comparative study of wavelet families for classification of wrist motions. Comp Electr 2012; 38: 1798–1807.10.1016/j.compeleceng.2012.08.009Search in Google Scholar
[6] Herle S, Man S, lazea G, Raica P. Myoelectric controls strategies for a human upper limb prosthesis. Control Eng Appl Inf 2012; 14: 58–66.Search in Google Scholar
[7] Hincapie GJ, Kirsch FR. Feasibility of EMG based neural network controller for an upper extremity neuroprosthesis. IEEE Trans Neural Syst Rehabil Eng 2009; 17: 80–90.10.1109/TNSRE.2008.2010480Search in Google Scholar PubMed PubMed Central
[8] Itou T, Terao M, Nagata J, Yoshida M. Mouse cursor control system using EMG. In: EMBS, 23rd Annual International Conference of the IEEE 2001; 2: 1368–1369.10.1109/IEMBS.2001.1020453Search in Google Scholar
[9] Jung K, Kim JW. EMG Pattern Classification using Spectral Estimation and Neural network. SICE Annual Conference, Kagawa University 2007: 1108–1111.Search in Google Scholar
[10] Kwon S, Kim J. Real-time upper limb motion estimation from surface electromyography and joint angular velocities using an artificial neural network for human–machine cooperation. IEEE Trans Inform Technol Biomed 2011; 15: 522–530.10.1109/TITB.2011.2151869Search in Google Scholar PubMed
[11] Li Y, Guo Z, Wang K. A BP neural network based method for upper limb motion intensity evaluation. International Conference on Cloud Computing and Big Data 2013: 171–176.10.1109/CLOUDCOM-ASIA.2013.12Search in Google Scholar
[12] Mehtani P, Archita P. Pattern Classification using Artificial Neural Networks. B.Tech theses, Submitted at the department of computer science and engineering, Rourkela 2010: 1–40.Search in Google Scholar
[13] Micera S. Control of hand prostheses using peripheral information. IEEE Rev Biomed Eng 2010; 3: 48–68.10.1109/RBME.2010.2085429Search in Google Scholar PubMed
[14] Parsaei H, Nezhad JF, Stashuk WD, Wright HA. Validating motor unit firing patters extracted by EMG signal decomposition. Med Biol Eng Comput 2011; 49: 649–658.10.1007/s11517-010-0703-1Search in Google Scholar PubMed
[15] Sharma T, Veer K. Wavelet based feature extraction of electromyogram signal for denoising. IJARCSEE 2014; 3: 2623–2627.Search in Google Scholar
[16] Sharma T, Veer K. Design and optimization of neural classifier to identify around shoulder motions. Optik 2016; 127: 3564–3568.10.1016/j.ijleo.2016.01.007Search in Google Scholar
[17] Sobahi NM. Denoising of EMG signals based on wavelet transform. Ain Trans Eng 2011; 1: 17–23.Search in Google Scholar
[18] Veer K. Interpretation of surface electromyograms to characterize arm movement. Instrum Sci Technol 2014; 42: 513–521.10.1080/10739149.2014.913178Search in Google Scholar
[19] Veer K. Experimental study and characterization of SEMG signals for upper limbs. Fluct Noise Lett 2015; 14: 150028 (1–18).10.1142/S0219477515500285Search in Google Scholar
[20] Veer K. A technique for classification and decomposition of muscle signal for control of myoelectric prostheses based on wavelet statistical classifier. Measurement 2015; 60: 283–291.10.1016/j.measurement.2014.10.023Search in Google Scholar
[21] Veer K, Agarwal R. Wavelet and short-time Fourier transform comparison-based analysis of myoelectric signals. J Appl Stat 2015; 42: 1591–1601.10.1080/02664763.2014.1001728Search in Google Scholar
[22] Veer K, Agarwal R, Kumar A. Processing and interpretation of surface electromyogram signal to design prosthetic device. Robotica 2014; 34: 1486–1494.10.1017/S0263574714002409Search in Google Scholar
©2018 Walter de Gruyter GmbH, Berlin/Boston