Iranian Journal of Biomedical Engineering (IJBME)
نشریه علمی مهندسی پزشکی زیستی

Hand Gesture and Movement Recognition based on Electromyogram Signals using Soft Ensembling Feature Selection and Optimized Classifier

Document Type : Full Research Paper

Authors

Khosro Rezaee 1
Fardin Ghaderi 2
Hamed Taheri Gorji 3
Javad Haddadnia 4

1 Assistant Professor, Biomedical Engineering Group, Department of Engineering, Meybod University, Meybod, Iran

2 Instructor, Biomedical Engineering Group, Department of Engineering, Meybod University, Meybod, Iran

3 Ph.D. Student, School of Electrical Engineering and Computer Science, University of North Dakota, Grand Forks, ND 58202 USA

4 Professor, Biomedical Engineering Group, Department of Engineering, Hakim Sabzevari University, Sabzevar, Iran

https://doi.org/10.22041/ijbme.2020.123570.1580
Abstract
In modern prostheses, accurate processing of surface electromyogram (sEMG) signals has a significant effect on optimal muscle control. Although these signals are useful for diagnosing neuromuscular diseases, controlling prosthetic devices and detecting hand movements, non-robustness of EMG signal-based recognition will give rise to various movement disorders. In this paper, we present an optimal approach to classify EMG signals for hand gesture and movement recognition, whose purpose is to be used as an efficient method of diagnosing neuromuscular diseases, determining the type of treatment and physiotherapy. The main assumption of this study is to improve the accuracy of recognition and therefore, we proposed a novel hand gesture and movement recognition model consists of three steps: (1) EMG signal features extraction based on time-frequency domain and fractal dimension features; (2) feature selection by soft ensembling of three procedures in which includes two sample T-tests, entropy and common wrapper feature reduction, and (3) classification based on kernel parameters optimization of SVM classifier by using Gases Brownian Motion Optimization (GBMO) algorithm. Two UC2018 DualMyo and UCI datasets have been considered to evaluate the proposed model. The first dataset is used to classify eight hand gestures and the second dataset is employed for the classification of six types of movement. The experiment results and statistical tests reveal that the designed approach has desirable performance with an average accuracy of above 98% in both datasets. Contrary to similar methods that perform classifications in finite classes with high error rates, the integrated method has satisfactory accuracy, robustness and reliability. Not only the proposed method contributes to the design of prostheses, but also provides effective outcomes for rehabilitation applications and clinical diagnosis processes. 

Keywords

Electromyogram
Hand Gesture
Hand Movement
Fractal Dimension
Soft Ensembling
Optimal Classifier
[1]   T. Tuncer, S. Dogan, A. Subasi, “Surface EMG signal classification using ternary pattern and discrete wavelet transform based feature extraction for hand movement recognition”, Biomed. Signal Process. Control, Vol. 58, pp. 101872, 2020.
[2]   Z. Zhang, F. Sup, “Activity recognition of the torso based on surface electromyography for exoskeleton control”, Biomed. Signal Process. Control, vol. 10, pp. 281–288, 2014.
[3]   R. Merletti, S. Muceli, “Surface EMG detection in space and time: Best practices”, Journal of Electromyography and Kinesiology, vol. 49, pp. 102363, 2019.
[4]   Akhtar et al., “A Low-Cost Open-Source Compliant Hand for Enabling Sensorimotor Control for People with Transradial Amputations”, Conf Proc IEEE Eng Med Biol Soc, 2017.
[5]   I. Hussain, G. Spagnoletti, G. Salvietti, D. Prattichizzo, “Toward wearable supernumerary robotic fingers to compensate missing grasping abilities in hemiparetic upper limb”, Int. J. Robot. Res., vol. 36, no. 13–14, pp. 1414-1436, Dec. 2017.
[6]   D. Blana, T. Kyriacou, J. M. Lambrecht, E. K. Chadwick, “Feasibility of using combined EMG and kinematic signals for prosthesis control: a simulation study using a virtual reality environment”, Journal of ElectroMYOgraphy and Kinesiology, vol. 29, pp. 21-27, 2016.
[7]    Y. Nam et al., “GOM-Face: GKP EOG and EMG-Based Multimodal Interface With Application to Humanoid Robot Control”, IEEE Transactions on Biomedical Engineering, vol. 61, no. 2, pp. 453-462, 2014.
[8]    S Lo, S Q. Xie, “Exoskeleton robots for upper-limb rehabilitation: State of the art and future prospects”, Medical Engineering & Physics, vol. 34, no. 3, pp. 261-268, 2012.
[9]   N. Wang, K. Lao, X. Zhang, “Design and Myoelectric Control of an Anthropomorphic Prosthetic Hand”, Journal of Bionic Engineering, vol. 14, pp. 47-59, 2017.
[10]L. Bi, A. G. Feleke, C. Guan, “A review on emg-based motor intention prediction of continuous human upper limb motion for humanrobot collaboration”, Biomed Signal Proces., vol. 51, pp. 113-127, 2019.
[11]S., Pancholi, A. M. Joshi, “Portable EMG data acquisition module for upper limb prosthesis application”, IEEE Sensors J., vol. 18, no. 8, pp. 3436-3443, Apr. 2018.
[12]G. Jang, J. Kim, S. Lee, Y. Choi, “EMG-based continuous control scheme with simple classifier for electric-powered wheelchair”, IEEE Trans. Ind. Electron., vol. 63, no. 6, pp. 3695-3705, Jun. 2016.
[13]A.S. Kundu, O. Mazumder, P.K. Lenka, S. Bhaumik, “Hand Gesture Recognition Based Omnidirectional Wheelchair Control Using IMU and EMG Sensors”, Journal of Intelligent and Robotic Systems, vol. 91, pp. 529-541, 2018.
[14]I. M. Skavhaug, K. R. Lyons, A. Nemchuk, S. D. Muroff, S. S. Joshi, “Learning to modulate the partial powers of a single sEMG power spectrum through a novel human-computer interface”, Human Movement Science, vol. 47, pp. 60-69, June 2016.
[15]M.R. Al-Mulla, F. Sepulveda, M. Colley, “Evolved pseudo-wavelet function to optimally decompose SEMG for automated classification of localized muscle fatigue”, Medical Engineering &Physics, vol. 33, no. 4, pp. 411-417, May 2011.
[16]R. H. Chowdhury, M. B. I. Reaz, M. A. B. M. Ali, A. A. A. Bakar, K. Chellappan, T. G. Chang, “Surface electromyography signal processing and classification techniques”, Sensors (Basel Switzerland), vol. 13, no. 9, pp. 12431-12466, 2013.
[17]N. Thakur, L. Mathew, “sEMG Signal Classification Using Ensemble Learning Classification Approach and DWT”, 2018 International Conference on Current Trends towards Converging Technologies (ICCTCT), pp. 1-4, 2018.
[18]C. Sapsanis, A. Tzes, G. Georgoulas, UCI Machine Learning Repository. http://archive.ics.uci.edu/ml
[19]Y Y. Ruangpaisarn, S. Jaiyen, “SEMG signal classification using SMO algorithm and singular value decomposition”, Envisioning the Trend of Computer Information and Engineering ICITEE 2015, pp. 46-50, 2015.
[20]C. Sravani, V. Bajaj, S. Taran, A. Sengur, “Flexible analytic wavelet transform based features for physical action identification using sEMG signals”, IRBM, vol. 41, no. 1, pp. 18-22, 2020.
[21]D. Dheeru, E. Karra Taniskidou, UCI Machine Learning Repository. http://archive.ics.uci.edu/ml.
[22]G. R. Naik, S. E. Selvan, S. P. Arjunan, A. Acharyya, D. K. Kumar, A. Ramanujam, H. T. Nguyen, “An ica-ebm-based semg classifier for recognizing lower limb movements in individuals with and without knee pathology”, IEEE Transactions on Neural Systems and Rehabi
Iranian Journal of Biomedical Engineering (IJBME)
Volume 14, Issue 3
Autumn 2020
Pages 195-208

  • Receive Date 25 April 2021

Home

Contact Us