Methodology for muscle identification in gesture recognition using machine learning methods
DOI:
https://doi.org/10.35366/113828Keywords:
electromyography,, human-machine interface, machine learning, principal component analysis, support vector machine, K nearest neighborsAbstract
Human-Machine-Interfaces (HMIs) can use surface electromyography (sEMG) signals to control equipment that assists disabled people in their activities of daily living (ADLs). The use of sEMG signals in HMIs is currently the subject of extensive research. However, some drawbacks of previous research are that weight loads that directly impact sEMG signals, movement velocities, electrode positioning, and a criterion for selecting sEMG features are not considered for the best performance in HMI. Therefore, the article’s main contribution is the presentation of a methodology that allows identifying the muscles and features that have the most significant contribution in sEMG-based gesture recognition, considering electrode positioning and avoiding compensatory movements. The article highlights how load weights affect sEMG signals and how principal component analysis determines the best sEMG features for gesture classification. We compared seventeen machine learning classifier models for classifying four upper limb movements based on decision trees, support vector machines, k-Nearest Neighbors, and ensembled methods classifier models. The results show that the signal square integral and Mean Frequency features of sEMG make it possible for classifiers to get an accuracy of above 90%.
References
Ivanov AV, Skripnik T. Human-machine interface with motion capture system for prosthetic control”, 2019 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus), Saint Petersburg and Moscow, Russia, 2019, pp. 235-239, doi: 10.1109/EIConRus.2019.8657282.
Wu Y, Jiang D, Liu X, Bayford R, Demosthenous A. A Human-machine interface using electrical impedance tomography for hand prosthesis control. IEEE Trans Biomed Circuits Syst. 2018; 12 (6): 1322-1333. doi: 10.1109/TBCAS.2018.2878395.
Ai Q, Liu Q, Meng W, Xie SQ. Chapter 2-state-of-the-art. In: Ai Q, Liu Q, Meng W, Xie SQ, eds. Advanced rehabilitative technology. academic press; 2018, pp. 11-32. doi: https://doi.org/10.1016/B978-0-12-814597-5.00002-3.
Sinyukov DA, Troy KL, Bowers MP, Padir T. 13 - Wheelchairs and Other Mobility Assistance. In: Popovic MB, ed. Biomechatronics. Academic Press; 2019: 373-417. doi: https://doi.org/10.1016/B978-0-12-812939-5.00013-6.
Zhang Z, Yang K, Qian J, Zhang L. Real-time surface EMG pattern recognition for hand gestures based on an artificial neural network. Sensors (Basel). 2019; 19 (14): 3170. doi: 10.3390/s19143170.
Rose CG, Pezent E, Kann CK, Deshpande AD, O’Malley MK. Assessing wrist movement with robotic devices. IEEE transactions on neural systems and rehabilitation engineering. 2018; 26 (8): 1585-1595. doi: 10.1109/TNSRE.2018.2853143.
Mahdavi FA, Ahmad SA. Surface electromyography feature extraction based on wavelet transform. International Journal of Integrated Engineering. 2013; 4 (3): 1-7.
Said S, Boulkaibet I, Sheikh M, Karar AS, Alkork S, Nait-ali A. Machine-Learning-Based Muscle Control of a 3D-Printed Bionic Arm. Sensors. 2020; 20 (11): 3144. doi: 10.3390/s20113144.
Shaw L, Bagha S. Online emg signal analysis for diagnosis of neuromuscular diseases by using PCA and PNN. Int J Eng Sci. 2012; 4 (10): 4453-4459.
Alam MS, Arefin AS. Real-time classification of multi-channel forearm EMG to recognize hand movements using effective feature combination and LDA classifier. Bangladesh Journal of Medical Physics. 2018; 10 (1): 25-39. doi: 10.3329/bjmp.v10i1.39148.
She H, Zhu J, Tian Y, Wang Y, Yokoi H, Huang Q. SEMG feature extraction based on stockwell transform improves hand movement recognition accuracy. Sensors (Basel). 2019; 19 (20): 4457. doi: 10.3390/s19204457.
Daud WMBW, Yahya AB, Horng CS, Sulaima MF, Sudirman R. Features extraction of electromyography signals in time domain on biceps brachii muscle. International Journal of Modeling and Optimization. 2013; 3 (6): 515-519. doi: 10.7763/ijmo.2013.v3.332.
Phinyomark A, Phukpattaranont P, Limsakul C. Feature reduction and selection for EMG signal classification. Expert Syst Appl. 2012; 39: 7420-7431.
Chu JU, Lee YJ. Conjugate-prior-penalized learning of Gaussian mixture models for multifunction myoelectric hand control. IEEE Trans Neural Syst Rehabil Eng. 2009; 17 (3): 287-297. doi: 10.1109/ tnsre.2009.2015177.
Yoshikawa M, Mikawa M, Tanaka K. A myoelectric interface for robotic hand control using support vector machine. In: 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems. San Diego, CA, USA, 2007, 2723-2728. doi: 10.1109/IROS.2007.4399301.
Kurzynski M, Zolnierek A, Wolczowski A. Control of bio-prosthetic hand via sequential recognition of EMG signals using rough sets theory. Advances in Intelligent and Soft Computing. 2009; 57: 455-462. doi: 10.1007/978-3-540-93905-4_54.
Atzori M, Gijsberts A, Castellini C, et al. Electromyography data for non-invasive naturally-controlled robotic hand
prostheses. Sci Data. 2014; 1: 140053. doi: 10.1038/sdata.2014.53.
McDonald CG, Sullivan JL, Dennis TA, O’Malley MK. A Myoelectric control interface for upper-limb robotic rehabilitation following spinal cord injury. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2020; 28 (4): 978-987. doi: 10.1109/TNSRE.2020.2979743.
Sun H, Zhang X, Zhao Y, Zhang Y, Zhong X, Fan Z. A novel feature optimization for wearable human-computerinterfaces using surface electromyography sensors. Sensors (Basel). 2018; 18 (3): 869. doi: 10.3390/s18030869.
Aziz S, Khan MU, Aamir F, Javid MA. Electromyography (EMG) data-driven load classification using empirical mode decomposition and feature analysis. undefined. 2019 International Conference on Frontiers of Information Technology (FIT), Islamabad, Pakistan, [Published online December 1], 2019, 272-277. doi: 10.1109/FIT47737.2019.00058.
Li W, Shi P, Yu H. Gesture recognition using surface electromyography and deep learning for prostheses hand: state-of-the-art, challenges, and future. Front Neurosci. 2021; 15: 621885. doi: 10.3389/FNINS.2021.621885/BIBTEX.
Von Werder SCFA, Disselhorst-Klug C. The role of biceps brachii and brachioradialis for the control of elbow flexion
and extension movements. J Electromyogr Kinesiol. 2016; 28: 67-75. doi: 10.1016/j.jelekin.2016.03.004.
Stegeman D, Hermens H. Standards for surface electromyography: the European project Surface EMG for non-invasive assessment of muscles (SENIAM). 2007; 1.
Perotto A, Delagi EF. Anatomical guide for the electromyographer: the limbs and trunk. Charles C Thomas; 2005. Available in: https://books.google.com.mx/books?id=uwos8W4HiQ8C
Point N. Baseline Upper Body (25). 29 March. Published 2016. Available in: https://v20.wiki.optitrack.com/index. php?title=Baseline_Upper_Body_(25)
Seth A, Hicks JL, Uchida TK, et al. OpenSim: Simulating musculoskeletal dynamics and neuromuscular control to study human and animal movement. PLoS Comput Biol. 2018; 14 (7): e1006223. doi: 10.1371/journal.pcbi.1006223.
González-Mendoza A, Lopéz-Gutierrez R, Pérez-SanPablo AI, et al. Upper limb musculoskeletal modeling
for human-exoskeleton interaction. In: 2019 16th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE). 2019, 1-5. doi: 10.1109/ICEEE.2019.8884537.
Phinyomark A, Hirunviriya S, Limsakul C, Phukpattaranont P. Evaluation of EMG feature extraction for hand movement recognition based on Euclidean distance andstandard deviation. In: ECTI-CON2010: The 2010 ECTI International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, Chiang Mai, Thailand, 2010, 856-886.
Kaczmarek P, Mańkowski T, Tomczyński J. putEMG-A Surface electromyography hand gesture recognition dataset. Sensors (Basel). 2019; 19 (16): 3548. doi: 10.3390/s19163548.
MATLAB. version 9.12.0.1927505 (R2022a). Published online 2022. 31. Powers DMW, Ailab. Evaluation: from precision, recall and F-measure to ROC, Informedness Markedness & correlation. Journal of Machine Learning Technologies.
; 2 (December): 37-63. http://www.bioinfo.in/contents.php?id=51
Braza DW, Yacub Martin JN. Upper limb amputation. essentials of physical medicine and rehabilitation: musculoskeletal disorders, pain, and rehabilitation. Published online August 8, 2023: 651-657. doi: 10.1016/B978-0-323-54947-9.00119-X.
Liu Y, Li C, Jiang D, et al. Wrist angle prediction under different loads based on GA-ELM neural network and surface electromyography. Concurr Comput. 2022; 34 (3): e6574. doi: 10.1002/CPE.6574
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Instituto Nacional de Rehabilitación Luis Guillermo Ibarra Ibarra
This work is licensed under a Creative Commons Attribution 4.0 International License.
© Instituto Nacional de Rehabilitación Luis Guillermo Ibarra Ibarra under a Creative Commons Attribution 4.0 International (CC BY 4.0) license which allows to reproduce and modify the content if appropiate recognition to the original source is given.
