AI-Based Real-Time Control System using Functional Electrical Stimulation for Central Cord Syndrome

Spinal cord injuries, particularly Central Cord Syndrome (CCS), often result in partial paralysis and impaired motor control. Functional Electrical Stimulation (FES) has been widely used to restore motor function by stimulating paralyzed muscles; however, conventional FES systems operate with fixed stimulation parameters, limiting adaptability and personalization. This paper proposes an AI-based real-time control system that dynamically adjusts stimulation using bio-signals such as electromyography (EMG) and motion data from inertial sensors (IMU, flex sensors). By integrating machine learning algorithms with a closed-loop feedback mechanism, the system can recognize user intent and deliver personalized stimulation patterns for effective rehabilitation. The expected outcome is a compact, wearable prototype that enhances motor recovery, improves rehabilitation efficiency, and establishes a foundation for intelligent, patient-specific neurorehabilitation technologies.