Feature Extraction Evaluation of Various Machine Learning Methods for Finger Movement Classification using Double Myo Armband

Khairul Anam (Dept. of Electrical Engineering, Faculty of Engineering, University of Jember, Kalimantan Street No. 37, Sumbersari, Krajan Timur, Sumbersari, Sumbersari District, Jember Regency, East Java 68121, Indonesia)
Harun Ismail (Dept. of Electrical and Computer, Engineering, National Taiwan University of Science and Technology, No. 43, Section 4, Keelung Rd, Da’an District, Taipei City, Taiwan 106, Taiwan)
Faruq Sandi Hanggara (Dept. of Electrical Engineering, Faculty of Engineering, University of Jember, Kalimantan Street No. 37, Sumbersari, Krajan Timur, Sumbersari, Sumbersari District, Jember Regency, East Java 68121, Indonesia)
Cries Avian (Dept. of Electrical and Computer, Engineering, National Taiwan University of Science and Technology, No. 43, Section 4, Keelung Rd, Da’an District, Taipei City, Taiwan 106, Taiwan)
Safri Nahela (Center for Development of Advanced Science and Technology, University of Jember, Kalimantan Street No. 37, Sumbersari, Krajan Timur, Sumbersari, Sumbersari District, Jember Regency, East Java 68121, Indonesia)
Muchamad Arif Hana Sasono (Dept. of Electrical Engineering, Faculty of Engineering, University of Jember, Kalimantan Street No. 37, Sumbersari, Krajan Timur, Sumbersari, Sumbersari District, Jember Regency, East Java 68121, Indonesia)

Journal of Engineering and Technological Sciences
Vol. 55 No. 5 (2023)

The deployment of electromyography (EMG) signals attracts many researchers since it can be used in decoding finger movements for exoskeleton robotics, prosthetics hand, and powered wheelchair. However, decoding any movement is a challenging task. The success of EMG signals' use lies in the appropriate choice of feature extraction and classification model, especially in the feature extraction process. Therefore, this study evaluates an eight-feature extraction evaluation on various machine learnings such as the Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Decision Tree (DT), Naïve Bayes (NB), and Quadratic Discriminant Analysis (QDA). The dataset from four intact subjects is used to classify twelve finger movements. Through 5 cross-validations, the result shows that almost all feature extractions combined with SVM outperform other combinations of features and classifiers. Mean Absolute Value (MAV) as a feature and SVM as a classifier highlight the best combination with an accuracy of 94.01%.