Navigating Attention-Centric: A Machine Learning Approach to EMG-Based Hand Gesture Recognition for Interactive RC Car

被引：0

作者：

Neamah, Husam A. ^{[1
,2
]}

Khudhair, Mohammed A. ^{[3
,4
]}

Dhaiban, Magd Saeed ^{[5
]}

机构：

[1] Univ Debrecen, Elect Engn & Mechatron Dept, Debrecen, Hungary

[2] Natl Univ Sci & Technol, Coll Engn, Dhi Qar, Iraq

[3] Univ Debrecen, Fac Informat, H-4028 Debrecen, Hungary

[4] Al Imam Univ Coll, Dept Business Management, Balad, Iraq

[5] Univ Debrecen, Elect Engn & Mechatron Dept, Fac Engn, Debrecen, Hungary

来源：

2024 IEEE 21ST INTERNATIONAL POWER ELECTRONICS AND MOTION CONTROL CONFERENCE, PEMC 2024 | 2024年

关键词：

electromyogram signals; gesture recognition; data set; machine-learning; classification learner;

D O I：

10.1109/PEMC61721.2024.10726353

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This research investigates the application of electromyogram (EMG) signals for real-time human-computer interaction through the control of an RC vehicle using hand gestures. By employing a dual-channel EMG sensor, EMG signals associated with four distinct hand gestures were collected from ten participants. These signals were processed to extract both time-domain and frequency-domain features. A classification model was developed using a dataset of signals produced by four different gestures performed with two hands. This model, trained using a Boosted Trees learning algorithm, achieved an accuracy of 84.1% in gesture recognition. The findings highlight the viability of EMG-based interfaces for interactive device control and potential advancements in assistive technology.

引用

页数：6