Machine learning-based novel approach to classify the shoulder motion of upper limb amputees

Amanpreet, Kaur

doi:10.1016/j.bbe.2019.07.007

Artykuł - szczegóły

Tytuł artykułu

Machine learning-based novel approach to classify the shoulder motion of upper limb amputees

Autorzy

Amanpreet Kaur

Wybrane pełne teksty z tego czasopisma

Identyfikatory

DOI

10.1016/j.bbe.2019.07.007

Warianty tytułu

Języki publikacji

Abstrakty

An upper limb amputation is a traumatic event that can seriously affect the person's capacity to perform regular tasks and can lead individuals to lose their confidence and autonomy. Prosthetic devices can be controlled via the acquisition and processing of electromyogram signal produced at the muscles fiber from the surface of the body with an array of an electrode placed on the residual limb. This paper presents the feasibility of classifying the different shoulder movements from around shoulder muscles of transhumeral amputees. The performance of a classifier is affected by the variation of Surface Electromyography (sEMG) signals due to the different categories of contraction. To avoid this, the wavelet transform and data transformation method are employed for features extraction from sEMG signals. Afterward five different supervised machine learning techniques viz. Support Vector Machines (SVM), Decision Tree (DT), Random Forest (RF), K-Nearest Neighbor (KNN) and Naïve Bayes (NB) are applied to determine the different classifiers accuracy. An effective combination of wavelet and RF achieves the best performance with a total classification accuracy of 98%.

Słowa kluczowe

surface electromyography upper limb amputation support vector machine naïve Bayes random forest decision tree k-nearest neighbor

elektromiografia powierzchniowa amputacja kończyny górnej maszyna wektorów wsparcia las losowy drzewo decyzyjne metoda najbliższych sąsiadów

Wydawca

Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences
Elsevier

Czasopismo

Biocybernetics and Biomedical Engineering

Rocznik

2019

Tom

Vol. 39, no. 3

Strony

857--867

Opis fizyczny

Bibliogr. 65 poz., rys., tab., wykr.

Twórcy

autor

Amanpreet Kaur

dr.apkaur@gmail.com, aman.preet@thapar.edu

Thapar Institute of Engg and Technology, Patiala, India

Bibliografia

[1] Kim YC, Park CI, Kim DY, Kim TS, Shin JC. Statistical analysis of amputations and trends in Korea. Prosthet Orthot Int 1996;20(2):88–95. http://dx.doi.org/10.3109/03093649609164424.
[2] Geng Y, Zhou P, Li G. Toward attenuating the impact of arm positions on electromyography pattern-recognition based motion classification in transradial amputees. J Neuroeng Rehabil 2012;9(1):74. http://dx.doi.org/10.1186/1743-0003-9-74.
[3] DaSalla C, Kim J, Koike Y. Robot Control Using Electromyography (EMG) Signals of the Wrist. Appl Bionics Biomech 2015;2(2):97–102. http://dx.doi.org/10.1155/2005/952754.
[4] You K-J, Rhee K-W, Shin H-C. Finger motion decoding using EMG signals corresponding various arm postures. Exp Neurobiol 2011;19(1):54. http://dx.doi.org/10.5607/en.2010.19.1.54.
[5] Shi WT, Lyu ZJ, Tang ST, Chia TL, Yang CY. A bionic hand controlled by hand gesture recognition based on surface EMG signals: A preliminary study. Biocybern Biomed Eng 2018;38(1):126–35. http://dx.doi.org/10.1016/j.bbe.2017.11.001.
[6] Leija-Salas L, Gutiérrez-Martínez J, Vera-Hernández A, Toledo-Peral CL, Mercado-Gutiérrez JA, Martín-Vignon- Whaley AI. sEMG Signal Acquisition Strategy towards Hand FES Control. J Healthc Eng 2018;2018:1–11. http://dx.doi.org/10.1155/2018/2350834.
[7] Guglielmelli E, Ranieri F, Zollo L, Davalli A, Romeo RA, Di Pino G, Di Lazzaro V. Control of Prosthetic Hands via the Peripheral Nervous System. Funct Neurol 2016;10(April):1– 17. http://dx.doi.org/10.3389/fnins.2016.00116.
[8] Englehart K, Hudgins B, Parker PA, Stevenson M. Classification of the Myoeletric Signal using Time- Frequency Based Representations. Med Eng Phys 1999;21:431–8.
[9] Rojas-Martínez M, Mañanas MA, Alonso JF. High-density surface EMG maps from upper-arm and forearm muscles. J Neuroeng Rehabil 2012;9(1):1–17. http://dx.doi.org/10.1186/1743-0003-9-85.
[10] Phinyomark A, Quaine F, Charbonnier S, Serviere C, Tarpin- Bernard F, Laurillau Y. EMG feature evaluation for improving myoelectric pattern recognition robustness. Expert Syst Appl 2013;40(12):4832–40. http://dx.doi.org/10.1016/j.eswa.2013.02.023.
[11] Guo S, Pang M, Gao B, Hirata H, Ishihara H. Comparison of sEMG-based feature extraction and motion classification methods for upper-limb movement. Sensors (Switzerland) 2015;15(4):9022–38. http://dx.doi.org/10.3390/s150409022.
[12] Karabulut D, Ortes F, Arslan YZ, Adli MA. Comparative evaluation of EMG signal features for myoelectric controlled human arm prosthetics. Biocybern Biomed Eng 2017;37 (2):326–35. http://dx.doi.org/10.1016/j.bbe.2017.03.001.
[13] Hussain MS, Reaz MBI, Yasin FM, Ibrahimy MI. Electromyography Signal Analysis Using Wavelet Transform and Higher Order Statistics to Determine Muscle Contraction. Expert Systems 2009;26(1):35–48.
[14] Hariharan M, Fook CY, Sindhu R, Ilias B, Yacoob S. A comparative study of wavelet families for classification of wrist motions. Comp Electr Eng Arch 2012;38(6):1798–807.
[15] Narayan Y, Mathew L, Chatterji S. sEMG signal classification using Discrete Wavelet Transform and Decision Tree classifier. Int J Control Theory Appl 2017;10(6):511–7.
[16] Ngui WK, Leong MS, Hee LM, Abdelrhman AM. Wavelet Analysis: Mother Wavelet Selection Methods. Appl Mech Mater 2013;393(January):953–8. http://dx.doi.org/10.4028/www.scientific.net/AMM.393.953.
[17] Uyar M, Yildirim S, Gencoglu MT. An effective wavelet-based feature extraction method for classification of power quality disturbance signals. Electr Pow Syst Res 2008;78 (10):1747–55. http://dx.doi.org/10.1016/j.epsr.2008.03.002.
[18] Zhang X, Wang Y, Han RPS. Wavelet Transform Theory and its Application in EMG Signal Processing. In Proceedings of FSKD 2010 7th International Conference on Fuzzy Systems and Knowledge Discovery; 2010. p. 2234–8.
[19] Myoelectric P, Hudgins B, Control PM, Hargrove LJ, Li G, Member S, et al. Principal Components Analysis Preprocessing for Improved Classification Accuracies in pattern-recognition-based myoelectric control. EEE Trans Biomed Eng 2009;56:1407–14. http://dx.doi.org/10.1109/TBME.2008.2008171.
[20] Veer K. A technique for classification and decomposition of muscle signal for control of myoelectric prostheses based on wavelet statistical classifier. Measurement 2015;60:283–91. http://dx.doi.org/10.1016/j.measurement.2014.10.023.
[21] Reaz MBI, Hussain MS, Mohd-Yasin F. Techniques of EMG Signal Analysis: Detection, Processing, Classification and Applications. Biol Proced Online 2006;8(1):11–35.
[22] Lolure A. Wavelet Transform Based EMG Feature Extraction and Evaluation Using Scatter Graphs;(May) 2015;1273–7. http://dx.doi.org/10.1109/IIC.2015.7150944.
[23] Subasi A. Classification of EMG signals using combined features and soft computing techniques. Appl Soft Comput J 2012;12(8):2188–98. http://dx.doi.org/10.1016/j.asoc.2012.03.035.
[24] Andrade AO, Mattioli Fernando ER, Lamounier Edgard A, Cardoso Alexandre, Soares Alcimar B. Classification of EMG signals using artificial neural networks for virtual hand prosthesis control. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2011. pp. 7354–7.
[25] Blanaa D, Kyriacou T, Lambrecht Joris M, Chadwicka Edward K. Feasibility of using combined EMG and kinematic signals for prosthesis control: A simulation study using a virtual reality environment. J Electromyogr Kinesiol 2016;21–7.
[26] Elektrik FK, Teknikal U, Tunggal D. Application of Spectrogram and Discrete Wavelet Transform for Emg Pattern. Journal of Theoretical and Applied Information Technology 2018;96(10):3036–47.
[27] Wu X, Kumar V, Ross QJ, Ghosh J, Yang Q, Motoda H, Steinberg D, et al. Top 10 algorithms in data mining. Knowledge and Information Systems 2008;14. http://dx.doi.org/10.1007/s10115-007-0114-2.
[28] Gokgoz E, Subasi A. Comparison of decision tree algorithms for EMG signal classification using DWT. Biomedical Signal Processing and Control 2015;18:138–44. http://dx.doi.org/10.1016/j.bspc.2014.12.005.
[29] Abdullah AA, Subasi A, Qaisar SM. Surface EMG Signal Classification by Using WPD and Ensemble Tree Classifiers. In IFMBE Proceedings; 2017. p. 475–81. http://dx.doi.org/10.1007/978-981-10-4166-2_73.
[30] Gaudet G, Raison M, Achiche S. Classification of Upper limb phantom movements in transhumeral amputees using electromyographic and kinematic features. Eng Appl Artif Intel 2018;68(November 2017):153–64. http://dx.doi.org/10.1016/j.engappai.2017.10.017.
[31] Gini G, Rivela D, Frigo CA, Belluco P, Scannella A, Pavan EE. Analysis and comparison of features and algorithms to classify shoulder movements from sEMG signals. IEEE Sens J 2018;1. http://dx.doi.org/10.1109/jsen.2018.2813434.
[32] Li X, Samuel OW, Zhang X, Wang H, Fang P, Li G. A motion-classification strategy based on sEMG-EEG signal combination for upper-limb amputees. J Neuroeng Rehabil 2017;14(1):2. http://dx.doi.org/10.1186/s12984-016-0212-z.
[33] Cook CE, Décary S. Braz J Phys Ther 2019;22(2). http://dx.doi.org/10.1016/j.bjpt.2019.01.010.
[34] Minning S, Eliot CA, Uhl TL, Malone TR. EMG analysis of shoulder muscle fatigue during resisted isometric shoulder elevation. J Electromyog Kinesiol 2007;17(2):153–9. http://dx.doi.org/10.1016/j.jelekin.2006.01.008.
[35] Jochumsen M, Waris A, Kamavuako EN. The effect of arm position on classification of hand gestures with intramuscular EMG. Biomed Signal Process Control 2018;43:1–8. http://dx.doi.org/10.1016/j.bspc.2018.02.013.
[36] Kaur A, Agarwal R, Kumar A. Adaptive threshold method for peak detection of surface electromyography signal from around shoulder muscles. J Appl Stat 2017;44:1–13. http://dx.doi.org/10.1080/02664763.2017.1293624.
[37] Phinyomark A, Limsakul C, Phukpattaranont P. Application of Wavelet Analysis in EMG Feature Extraction for Pattern Classification. Meas Sci Rev 2011;11(2):45–52. http://dx.doi.org/10.2478/v10048-011-0009-y.
[38] Kaur A, Agarwal R, Kumar A. Comparison of muscles activity of abled bodied and amputee subjects for around shoulder movement. Bio-Medical Materials and Engineering 2016;27(5):29–37. http://dx.doi.org/10.3233/BME-161565.
[39] Stegeman DF, Hermens HJ. Standards for suface electromyography : The European project Surface EMG for non-invasive assessment of muscles; 2007.
[40] Williams JM. Surface Electromyography with in Equine Performance Analysis 2014.
[41] Hosseini K, Gholam H. Wavelet analysis of surface electromyography signals. 26th Annual International Conference of the IEEE on Engineering in Medicine and Biology Society. 2004. pp. 3832–5.
[42] Moshou D, Hostens I, Papaioannou G, Ramon H. Wavelets and Self-organising Maps in Electromyogram (EMG) Analysis. Proceedings of ESIT 2000 European Symposium on Intelligent Techniques; 2000. p. 186–91.
[43] Zhang QJ, Luo ZZ. Wavelet De-noising of Electromyography. Proceedings of ICMA 2006 IEEE International Conference on Mechatronics and Automation; 2006. p. 1553–8.
[44] Phinyomark A, Limsakul C, Phukpattaranont P. EMG Feature Extraction for Tolerance of White Gaussian Noise. Proceedings of I-SEEC 2008 International Workshop and Symposium Science Technology; 2008. p. 178–83.
[45] Megahed AI, Moussa AM, Elrefaie HB, Marghany YM. Selection of a suitable mother wavelet for analyzing power system fault transients. IEEE Power and Energy Society 2008 General Meeting: Conversion and Delivery of Electrical Energy in the 21st Century, PES. 2008. pp. 1–7. http://dx.doi.org/10.1109/PES.2008.4596367.
[46] Rekhi NS, Arora AS, Singh S, Singh D. Multi-Class SVM Classification of Surface EMG Signal for Upper Limb Function. 3rd International Conference on Bioinformatics and Biomedical Engineering. 2009. pp. 1–4. http://dx.doi.org/10.1109/ICBBE.2009.5163093.
[47] Meena P, Bansal M. Classification of EMG Signals using SVM-kNN. Ijarece 2016;5(6):1718–24.
[48] Camelia L. Strategies for Dealing with Real world Classification Problems; 2010.
[49] Kumar R, Das RR, Mishra VN, Dwivedi R. A radial basis function neural network classifier for the discrimination of individual odor using responses of thick-film tin-oxide sensors. IEEE Sens J 2009;9(10):1254–61. http://dx.doi.org/10.1109/JSEN.2009.2030072.
[50] Nayak MS. Transformed cluster analysis: An approach to the identification of gases/odors using integrated gas sensor array. Sens Actuators 1993;12:103–10.
[51] AlOmari F, Liu G. Analysis of Extracted Forearm sEMG Signal Using LDA, QDA, K-NN Classification Algorithms. Open Autom Contr Syst J 2014;6(1):108–16. http://dx.doi.org/10.2174/1874444301406010108.
[53] Côté-Allard U, Fall CL, Drouin A, Campeau-Lecours A, Gosselin C, Glette K, Gosselin B. Deep Learning for Electromyographic Hand Gesture Signal Classification Using Transfer Learning; 2018;1–18, https://doi.org/ 1801.07756.
[55] Dwi A, Falih I, W, A. D., Sumpeno S. Classification of EMG Signals from forearm Muscles As Automatic Control Using Naive Bayes. Int Semin Intell Technol Its Appl Classif 2017;346–51.
[56] Foster KR, Koprowski R, Skufca JD. Machine learning, medical diagnosis, and biomedical engineering research - commentary. Biomed Eng Online 2014;13(1):94. http://dx.doi.org/10.1186/1475-925X-13-94.
[57] Keller, F. (n.d.). Naive Bayes Classifiers, 1–22.
[58] Moin, A., Zhou, A., Benatti, S., Rahimi, A., Alexandrov, G., Menon, A., Rabaey, J. M. (n.d.). Adaptive EMG-based hand gesture recognition using hyperdimensional computing.
[59] Moise, I., Pournaras, E., Helbing, D., Moise, I., Pournaras, E., & Helbing, D. (n.d.). K-Nearest Neighbour Classifier Supervised data mining Classification Decision Trees.
[62] Sutton O. Introduction to k Nearest Neighbour Classification and Condensed Nearest Neighbour Data Reduction The k Nearest Neighbours Algorithm; 2012;1–10.
[63] Universit L, Curie M, Bo PVI, Cedex P, Yu B. Analysis of a Random Forests Model, 13. 2012. p. 1063–95.
[65] Phinyomark A, Phukpattaranont P, Limsakul C. The Usefulness of Wavelet Transform to Reduce Noise in the SEMG Signal. EMG methods for evaluating muscle and nerve function. 2012. pp. 107–32. https://doi.org/10.5772/ 25757.

Uwagi

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).

W opisie bibliogr. brak poz. nr 52, 54, 60, 61, 64

Typ dokumentu

Bibliografia

Identyfikator YADDA

bwmeta1.element.baztech-34165d4f-34b8-4279-be43-41e4363fa171