Abstract—In this paper, a limb rehabilitation system based on the integration of Augmented Reality (AR) and Artificial Intelligence (AI) technology, which is called RAA, is introduced. By creating rehabilitation exercises on a physical system with a crank and pedal mechanism with an AR interface, the RAA enhances the patient’s incentive to exercise. Therefore, the efficacy of practice is increased. In addition, the AI platform serves as a medical assistant for patients by suggesting practicing courses according to Fuzzy logic. Furthermore, using the Perceptron network and Microsoft Kinect, the RAA can assess and correct a patient’s exercise posture, thereby decreasing reliance on physiotherapists. Training data is stored by the system during exercise, which is a critical parameter for analyzing and assessing recovery. Two experimental processes (n = 20) were conducted to assess the efficacy of the RAA, yielding promising results.

Index Terms—stroke, hemiparesis, rehabilitation, augmented reality, artificial intelligence

Cite: Nguyen Anh Quoc, Nguyen Vo Tam Toan, Tran The Luc, and Nguyen Truong Thinh, "A Limb Rehabilitation Training System Based on Augmented Reality and Artificial Intelligence," International Journal of Mechanical Engineering and Robotics Research, Vol. 11, No. 6, pp. 445-451, June 2022. DOI: 10.18178/ijmerr.11.6.445-451 

Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.