Privacy-Enhanced Intelligent Lower Limb Rehabilitation System

Abstract

Rehabilitation for a person appears as a fundamental process to restore function and prevent new injuries. However, traditional rehabilitation programs often lack personalization and real-time feedback, limiting their effectiveness. Additionally, privacy concerns often make data sharing and collaboration between researchers and healthcare providers complex, slowing the development of new and improved rehabilitation methods. This work proposes a privacy-enhanced intelligent lower limb rehabilitation system that leverages machine learning and real-time operating systems to provide patients with personalized rehabilitation programs, and feedback about their correct, incorrect, or compensated movements. Regarding data privacy, a security analysis will be necessary to incorporate it. Expected results include substantial improvement in the rehabilitation process. This approach mitigates the risk of re-injury by promptly addressing incorrect, faulty, or compensated movement patterns. From a broader perspective, this research intends to significantly contribute to advancing rehabilitation strategies, benefiting people at different levels and skills.