IoT-Based Smart Ankle-Foot Orthosis for Patients with Gait Imbalance

This research aims to transform the conventional Ankle-Foot Orthosis (AFO), a specialized medical brace, into a smart device by integrating Internet of Things (IoT) technologies. The smart AFO device incorporates sensors, including a surface electromyogram (sEMG) and an Inertial Measurement Unit (IMU). The sEMG sensor is employed to measure muscle activity, while the IMU sensor captures gait movements. The collected data is subsequently transmitted via a wireless network, first to the fog layer and finally to the cloud server. To facilitate predictive decision-making, the collected data underwent a comprehensive analysis. The analysis was carried out using a variety of machine learning algorithms, providing valuable insights. This process laid the foundation for employing predictive machine learning techniques to compare patient gait data with that of healthy individuals, resulting in the development of an accuracy metric. This metric effectively assesses the Smart AFO's capacity to predict the degree of improvement achieved by the patient. Among the tested models, the Long Short-Term Memory (LSTM) exhibited the highest accuracy rate, achieving an impressive 95.02% accuracy. To ensure the reliability of the results, the most accurate outcome is cross-checked by the doctor using a separate device. Upon the doctor's approval, the comprehensive report is securely transmitted to the patient's device, facilitating efficient communication between healthcare professionals and patients. This technology-driven approach enhances the monitoring and analysis of AFO usage, enabling personalized treatment plans and optimizing the overall patient experience.