Exploration of Characterization and Classification Techniques for Movement Identification from EMG Signals: Preliminary Results
Today, human-computer interfaces are increasingly more often used and become necessary for human daily activities. Among some remarkable applications, we find: Wireless-computer controlling through hand movement, wheelchair directing/guiding with finger motions, and rehabilitation. Such applications are possible from the analysis of electromyographic (EMG) signals. Despite some research works have addressed this issue, the movement classification through EMG signals is still an open challenging issue to the scientific community -especially, because the controller performance depends not only on classifier but other aspects, namely: used features, movements to be classified, the considered feature-selection methods, and collected data. In this work, we propose an exploratory work on the characterization and classification techniques to identifying movements through EMG signals. We compare the performance of three classifiers (KNN, Parzen-density-based classifier and ANN) using spectral (Wavelets) and time-domain-based (statistical and morphological descriptors) features. Also, a methodology for movement selection is proposed. Results are comparable with those reported in literature, reaching classification errors of 5.18% (KNN), 14.7407% (ANN) and 5.17% (Parzen-density-based classifier).
KeywordsClassification EMG signals Movements selection Wavelet
This work is supported by the “Smart Data Analysis Systems - SDAS” group (http://sdas-group.com), as well as the “Grupo de Investigación en Ingeniería Eléctrica y Electrónica - GIIEE” from Universidad de Nariño. Also, the authors acknowledge to the research project supported by Agreement No. 095 November 20th, 2014 by VIPRI from Universidad de Nariño.
- 2.Aguiar, L.F., Bó, A.P.: Hand gestures recognition using electromyography for bilateral upper limb rehabilitation. In: 2017 IEEE Life Sciences Conference (LSC), pp. 63–66. IEEE (2017)Google Scholar
- 3.Halaki, M., Ginn, K.: Normalization of EMG signals: to normalize or not to normalize and what to normalize to? (2012)Google Scholar
- 5.Podrug, E., Subasi, A.: Surface EMG pattern recognition by using DWT feature extraction and SVM classifier. In: The 1st Conference of Medical and Biological Engineering in Bosnia and Herzegovina (CMBEBIH 2015), 13–15 March 2015 (2015)Google Scholar
- 8.Krishna, V.A., Thomas, P.: Classification of emg signals using spectral features extracted from dominant motor unit action potential. Int. J. Eng. Adv. Technol. 4(5), 196–200 (2015)Google Scholar
- 10.Kira, K., Rendell, L.A.: A practical approach to feature selection. In: Machine Learning Proceedings 1992, pp. 249–256. Elsevier (1992)Google Scholar
- 11.Romo, H., Realpe, J., Jojoa, P., Cauca, U.: Surface EMG signals analysis and its applications in hand prosthesis control. Rev. Av. en Sistemas e Informática 4(1), 127–136 (2007)Google Scholar
- 12.Shin, S., Tafreshi, R., Langari, R.: A performance comparison of hand motion EMG classification. In: 2014 Middle East Conference on Biomedical Engineering (MECBME), pp. 353–356. IEEE (2014)Google Scholar
- 14.Arozi, M., Putri, F.T., Ariyanto, M., Caesarendra, W., Widyotriatmo, A., Setiawan, J.D., et al.: Electromyography (EMG) signal recognition using combined discrete wavelet transform based on artificial neural network (ANN). In: International Conference of Industrial, Mechanical, Electrical, and Chemical Engineering (ICIMECE), pp. 95–99. IEEE (2016)Google Scholar
- 16.Kurzynski, M., Wolczowski, A.: Hetero- and homogeneous multiclassifier systems based on competence measure applied to the recognition of hand grasping movements. In: Piętka, E., Kawa, J., Wieclawek, W. (eds.) Information Technologies in Biomedicine. AISC, vol. 4, pp. 163–174. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-06596-0_15CrossRefGoogle Scholar