Electromyography pattern-recognition based prosthetic limb control using various machine learning techniques. (4th July 2022)

• Record Type: Journal Article
• Authors: Ghildiyal, Sushil; Mani, Geetha; Nersisson, Ruban
• Is Part Of: Journal of medical engineering & technology. Volume 46:Number 5(2022)
• Page Start: 370
• Page End: 377
• Publication Date: 2022-07-04
• Subjects: Electromyography -- machine learning -- prosthetic limb -- servomotors; Biomedical engineering -- Periodicals; Medical technology -- Periodicals; 610.28
• DOI: 10.1080/03091902.2022.2062064
• Languages: English
• ISSNs: 0309-1902

Abstract

Abstract: People who have lost their limbs to amputation and neurological disorders confront this loss every morning. As per the literature review, nearly 30% of the Indian population suffered from upper extremity amputation. As a coping-up measure, a force-controlled prosthetic limb has been developed to improve their self-reliance, quality of lifestyle and mental strength. The current prosthetic limb operation is done by residual muscle contraction, which contributes to the activation of the sensor and the motor. But there are some cons, the amputee does not know how much pressure needs to be exerted for holding various objects. Also, the amputee still has to undergo the surgical procedure. However, this paper proposes a way to predict the force which is needed to regulate the voltage for the servomotors using different Machine Learning (ML) regression approaches. Support Vector Regressor (SVR), Linear Regression and Random Forest models have been used to predict that force requirement. After comparing the results, the Random Forest model gave a highly accurate prediction of the force needed to control the voltage for the DC servomotors