Random forest-based simultaneous and proportional myoelectric control system for finger movements

Khairul Anam; Dwiretno Istiyadi Swasono; Agus Triono; Aris Z Muttaqin; Faruq S Hanggara

doi:10.1080/10255842.2023.2165068

Random forest-based simultaneous and proportional myoelectric control system for finger movements

Comput Methods Biomech Biomed Engin. 2023 Oct-Dec;26(16):2057-2069. doi: 10.1080/10255842.2023.2165068. Epub 2023 Jan 17.

Authors

Khairul Anam^{1

2

3}, Dwiretno Istiyadi Swasono⁴, Agus Triono⁵, Aris Z Muttaqin⁵, Faruq S Hanggara²

Affiliations

¹ Department of Electrical Engineering, University of Jember, Jember, Indonesia.
² Intelligent System and Robotics Laboratory, CDAST, University of Jember, Jember, Indonesia.
³ Artificial Intelligence for Industrial Agriculture Research Group, University of Jember, Jember, Indonesia.
⁴ Department, of Computer Science, University of Jember, Jember, Indonesia.
⁵ Department, of Mechanical Engineering, University of Jember, Jember, Indonesia.

PMID: 36649195
DOI: 10.1080/10255842.2023.2165068

Abstract

A classification scheme for myoelectric control systems (MCS) cannot mimic complex hand movements. This paper presents simultaneous and proportional MCS by estimating the angles of fourteen finger joints using time-domain feature extraction and random forest. The experimental results show that the best feature was the root mean square (RMS). Furthermore, the random forest attained an average coefficient of determination (R2) of 0.85 compared to other regressors which perform below 0.75. The ANOVA tests indicated that the performance of the proposed system was significantly different. Therefore, the proposed system will be the best option for real-time MCS applications in the future.

Keywords: Myoelectric control system; prosthesis; random forest.

MeSH terms

Electromyography / methods
Fingers*
Hand
Random Forest*
Upper Extremity