Comparative Study of Methods Based on Pattern Recognition to Identify Hand and Wrist Movements through SEMG Signals

10.21158/23823399.v10.n0.2022.3450
Published 2022-06-22
Artículos científicos

Abstract

One of the channels in human-machine interaction is the use of surface electromyography (SEMG) signals, which, through feature processing and classification techniques, can provide commands to control assistive devices, accessibility, and rehabilitation for people with disabilities. The NinaPro public database was used, which provides SEMG records while a user executes various movements. In total, 10 subjects were evaluated: 5 men and 5 women. The developed algorithm includes preprocessing, feature extraction, and pattern classification stages. The feature extraction stage included the signal's root-mean-square (RMS) calculation. Four classification methods (KNN, NB, LDA, and SVM) were implemented, identifying eight isometric and isotonic hand and wrist movements. The classification percentage was used as an evaluation metric. In addition, a statistical significance analysis is performed to determine differences between classifiers and population groups. The results determined that the best classifier implemented is the SVM, with a classification percentage higher than 90%, finding significant differences between the results of other methods. However, it is observed that men present better results than women, according to the evaluation metric.

Keywords

Authors

References

Doucet, B. M.; Lam, A.; Griffin, L. (2012). Neuromuscular electrical stimulation for skeletal muscle function. The Yale Journal of Biology and Medicine, 85(2), 201-215. Recuperado de https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3375668/

Geethanjali, P. (2016). Myoelectric control of prosthetic hands: State-of-the-art review. Medical Devices, 9, 247-255. DOI: https://doi.org/10.2147/MDER.S91102

Guerrero-Mendez, C. D.; Blanco-Díaz, C. F.; Ruiz-Olaya, A. F. (2021a). How do factors of comfort, concentration, and eye fatigue affect the performance of a BCI system based on SSVEP? Paper presented at 2021 IEEE 2nd International Congress of Biomedical Engineering and Bioengineering (CI-IB&BI). Bogotá, Colombia, 13-15 October. DOI: https://doi.org/10.1109/CIIBBI54220.2021.9626107

Guerrero-Mendez, C. D.; Blanco-Díaz, C. F.; Ruiz-Olaya, A. F. (2021b). Identification of motor imagery tasks using power-based connectivity descriptors from EEG signals. Paper presented at 2021 XXIII Symposium on Image, Signal Processing and Artificial Vision (STSIVA). Popayán, Colombia, 11 de noviembre. DOI: https://doi.org/10.1109/STSIVA53688.2021.9591997

Guerrero-Mendez, C. D.; Ruiz-Olaya, A. F. (2022). Coherence-based connectivity analysis of EEG and EMG signals during reach-to-grasp movement involving two weights. Brain-Computer Interfaces, 9(3), 140-154. DOI: https://doi.org/10.1080/2326263X.2022.2029308

Kandel, E. R.; Schwartz, J. H.; Jessell, T. M.; Siegelbaum, S.; Hudspeth, A. J.; Mack, S. (Eds.). (2000). Principles of neural science (Vol. 4, pp. 1227-1246). New York: McGraw-Hill.

Kim, K. T.; Park, S.; Lim, T. H.; Lee, S. J. (2021). Upper-Limb electromyogram classification of reaching-tograsping tasks based on convolutional neural networks for control of a prosthetic hand. Frontiers in Neuroscience, 15, 733359. DOI: https://doi.org/10.3389/fnins.2021.733359

Leone, F.; Gentile, C.; Cordella, F.; Gruppioni, E.; Guglielmelli, E.; Zollo, L. (2022). A parallel classification strategy to simultaneous control elbow, wrist, and hand movements. Journal of NeuroEngineering and Rehabilitation, 19(1), 1-17. DOI: https://doi.org/10.1186/s12984-022-00982-z

López Delis, A.; Ruiz Olaya, A. F. (2012). Métodos computacionales para el reconocimiento de patrones mioeléctricos en el control de exoesqueletos robóticos: una revisión. Revista Nodo, 3(5), 42-59.

Recuperado de https://revistas.uan.edu.co/index.php/nodo/article/view/350

Merletti, R.; Botter, A.; Troiano, A.; Merlo, E.; Minetto, M. A. (2009). Technology and instrumentation for detection and conditioning of the surface electromyographic signal: State of the art. Clinical Biomechanics, 24(2), 122-134. DOI: https://doi.org/10.1016/j.clinbiomech.2008.08.006

Organización Mundial de la Salud. (OMS). (2011). Informe mundial sobre la discapacidad. Recuperado de https://www.afro.who.int/sites/default/files/2017-06/9789240688230_spa.pdf

Paolanti, M.; Frontoni, E. (2020). Multidisciplinary pattern recognition applications: A review. Computer Science Review, 37, 100276. DOI: https://doi.org/10.1016/j.cosrev.2020.100276

Rajapriya, R.; Rajeswari, K.; Thiruvengadam, S. J. (2021). Deep learning and machine learning techniques to improve hand movement classification in myoelectric control system. Biocybernetics and Biomedical Engineering, 41(2), 554-571. DOI: https://doi.org/10.1016/j.bbe.2021.03.006

Rand, D. (2018). Proprioception deficits in chronic stroke—Upper extremity function and daily living. PLoS ONE, 13(3), e0195043. DOI: https://doi.org/10.1371/journal.pone.0195043

Ruiz-Olaya, A. F.; Quinayas Burgos, C. A.; Londono, L. T. (2019). A low-cost arm robotic platform based on myoelectric control for rehabilitation engineering. Paper presented at 2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON). New York, Estados Unidos, 13 de febrero. DOI: https://doi.org/10.1109/UEMCON47517.2019.8993080

Vigotsky, A. D.; Halperin, I.; Lehman, G. J.; Trajano, G. S.; Vieira, T. M. (2018). Interpreting signal amplitudes in surface electromyography studies in sport and rehabilitation sciences. Frontiers in Physiology, 8, 985. DOI: https://doi.org/10.3389/fphys.2017.00985

Yang, Z.; Jiang, D.; Sun, Y.; Tao, B.; Tong, X.; Jiang, G.; Xu, M.; Yun, J.; Liu, Y.; Chen, B.; Kong, J. (2021). Dynamic gesture recognition using surface EMG signals based on multi-stream residual network. Frontiers in Bioengineering and Biotechnology, 9, 779353. DOI: https://doi.org/10.3389/fbioe.2021.779353

Statistics

Abstract
0
PDF accesses
0

Dimensions

PlumX

Downloads

Download data is not yet available.