A Practical Case of Learning Muscle Fatigue Based on a sEMG Signal Using Bitalino Kit

Abstract

This paper explores the use of technology in teaching biosignal processing, specifically focusing on the flipped classroom model and the BITalino kit. The flipped classroom allows students to learn at their own pace before coming to class, while the BITalino kit provides an affordable and versatile platform for acquiring and analyzing biosignals like electromyography (EMG). The paper details a case study where students used the BITalino kit to classify EMG signals as fatigue and non-fatigue. The methodology involved acquiring EMG signals from the quadriceps muscles during an incremental exercise test, followed by signal processing, feature extraction, and machine learning classification. The study demonstrates the effectiveness of the flipped classroom and BITalino kit in enhancing student learning and engagement with biosignal processing. The developed machine learning model achieved an accuracy of 90% in classifying muscle fatigue, highlighting its potential for applications in sports science, rehabilitation, and ergonomics. The paper concludes by emphasizing the importance of integrating new technologies into engineering education to create immersive learning experiences and equip students with the necessary skills for the evolving demands of the industry. © 2024 Latin American and Caribbean Consortium of Engineering Institutions. All rights reserved.