Furkejuvvon:
| Váldodahkkit: | , , , , , , , , , , , , |
|---|---|
| Materiálatiipa: | Recurso digital |
| Giella: | |
| Almmustuhtton: |
Zenodo
2026
|
| Liŋkkat: | https://doi.org/10.5281/zenodo.19762545 |
| Fáddágilkorat: |
Lasit fáddágilkoriid
Eai fáddágilkorat, Lasit vuosttaš fáddágilkora!
|
Sisdoallologahallan:
- <p>Abstract Knee osteoarthritis (KOA) is a chronic degenerative joint disorder that significantly affects mobility, independence, and quality of life, especially in aging populations. Traditional rehabilitation approaches rely on periodic physiotherapy sessions, which often lack continuous monitoring, objective assessment, and real-time corrective feedback. In recent years, advancements in artificial intelligence (AI), wearable sensor technology, and smart biomedical engineering have enabled the development of intelligent rehabilitation systems such as smart knee braces. These systems integrate inertial measurement units (IMUs), electromyography (EMG), and pressure sensors with machine learning and deep learning algorithms to enable real-time detection and correction of abnormal joint movements. The AI-driven smart knee brace continuously analyses- biomechanical data, identifies movement deviations, and provides immediate feedback to improve exercise accuracy and rehabilitation outcomes. This article explores the development, architecture, and clinical application of AI-based systems for real-time knee movement monitoring in osteoarthritis rehabilitation. It also highlights sensor fusion techniques, AI model integration, and future directions in personalized digital rehabilitation. The findings suggest that smart knee braces significantly enhance rehabilitation efficiency, improve patient adherence, and support remote healthcare delivery, marking a shift toward intelligent, data-driven orthopaedic care systems. Keywords: Knee Osteoarthritis, Artificial Intelligence, Smart Knee Brace, Rehabilitation, Wearable Sensors, Machine Learning, Real-Time Motion Detection, Sensor Fusion, Deep Learning.</p>