This research paper aims to advance the clinical applicability of Force Myography (FMG) technology, particularly for the benefit of individuals with disabilities. FMG is employed to map muscle deformation resulting from gesture recognition, utilizing force-sensing resistors mounted on a flexible band wrapped around a person's area of effect to detect muscle stiffness. Even residual limbs with minimal muscle tissue can facilitate effective human-machine interfaces for appropriate actions using FMG.

Machine learning algorithms play a critical role in providing highly accurate results. Despite significant progress in precision over the past two decades, there remains a substantial gap between laboratory testing and clinical trials. This paper seeks to address this disparity by exploring methods for enhancing FMG performance outside of controlled laboratory environments, thereby improving its potential for real-world applications and positively impacting the lives of disabled individuals.

Index Terms- Disabled, Force-Sensing-Resistors, FMG, Gesture recognitions, Machine Learning