Deep Learning-Enhanced Internet of Things for Activity Recognition in Post-Stroke Rehabilitation

Jin, Fangpeng; Zou, Mi; Peng, Xiaoyun; Lei, Hua; Ren, Yongjun

doi:10.1109/jbhi.2023.3332735

Cited by 5 publications

(1 citation statement)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jin et al [ 9 ] have demonstrated the efficacy of DRL in improving post-stroke limb function, whereas Majhi and Kashyap [ 10 ] have explored adaptive algorithms for patient-specific therapy adjustments. Furthermore, the work by Wang et al [ 11 ] has been instrumental in showcasing how DRL can optimize engagement levels during robotic-assisted therapy.…”

Section: Literature Reviewmentioning

confidence: 99%

Telehealth-Enabled In-Home Elbow Rehabilitation for Brachial Plexus Injuries Using Deep-Reinforcement-Learning-Assisted Telepresence Robots

Khan,

Altalbe,

Naseer

et al. 2024

Sensors

View full text Add to dashboard Cite

Due to damage to the network of nerves that regulate the muscles and feeling in the shoulder, arm, and forearm, brachial plexus injuries (BPIs) are known to significantly reduce the function and quality of life of affected persons. According to the World Health Organization (WHO), a considerable share of global disability-adjusted life years (DALYs) is attributable to upper limb injuries, including BPIs. Telehealth can improve access concerns for patients with BPIs, particularly in lower-middle-income nations. This study used deep reinforcement learning (DRL)-assisted telepresence robots, specifically the deep deterministic policy gradient (DDPG) algorithm, to provide in-home elbow rehabilitation with elbow flexion exercises for BPI patients. The telepresence robots were used for a six-month deployment period, and DDPG drove the DRL architecture to maximize patient-centric exercises with its robotic arm. Compared to conventional rehabilitation techniques, patients demonstrated an average increase of 4.7% in force exertion and a 5.2% improvement in range of motion (ROM) with the assistance of the telepresence robot arm. According to the findings of this study, telepresence robots are a valuable and practical method for BPI patients’ at-home rehabilitation. This technology paves the way for further research and development in telerehabilitation and can be crucial in addressing broader physical rehabilitation challenges.

show abstract

Section: Literature Reviewmentioning

confidence: 99%