TY - JOUR
T1 - Improving patient rehabilitation performance in exercise games using collaborative filtering approach
AU - Ismail, Waidah
AU - Al-Hadi, Ismail Ahmed Al Qasem
AU - Grosan, Crina
AU - Hendradi, Rimuljo
N1 - Funding Information:
Thank you to Directior Dr. Hafez bin Hussain, who helped in carrying out the research at Pusat Rehabilitation Perkeso Sdn Bhd.
Publisher Copyright:
© 2021 Ismail et al. All Rights Reserved.
PY - 2021
Y1 - 2021
N2 - Background: Virtual reality is utilised in exergames to help patients with disabilities improve on the movement of their limbs. Exergame settings, such as the game difficulty, play important roles in the rehabilitation outcome. Similarly, suboptimal exergames' settings may adversely affect the accuracy of the results obtained. As such, the improvement in patients' movement performances falls below the desired expectations. In this paper, a recommender system is incorporated to suggest the most preferred movement setting for each patient, based on the movement history of the patient. Method: The proposed recommender system (ResComS) suggests the most suitable setting necessary to optimally improve patients' rehabilitation performances. In the course of developing the recommender system, three methods are proposed and compared: ReComS (K-nearest neighbours and collaborative filtering algorithms), ReComS+ (k-means, K-nearest neighbours, and collaborative filtering algorithms) and ReComS++ (bacterial foraging optimisation, k-means, K-nearest neighbours, and collaborative filtering algorithms). The experimental datasets are collected using the Medical Interactive Recovery Assistant (MIRA) software platform. Result: Experimental results, validated by the patients' exergame performances, reveal that the ReComS++ approach predicts the best exergame settings for patients with 85.76% accuracy.
AB - Background: Virtual reality is utilised in exergames to help patients with disabilities improve on the movement of their limbs. Exergame settings, such as the game difficulty, play important roles in the rehabilitation outcome. Similarly, suboptimal exergames' settings may adversely affect the accuracy of the results obtained. As such, the improvement in patients' movement performances falls below the desired expectations. In this paper, a recommender system is incorporated to suggest the most preferred movement setting for each patient, based on the movement history of the patient. Method: The proposed recommender system (ResComS) suggests the most suitable setting necessary to optimally improve patients' rehabilitation performances. In the course of developing the recommender system, three methods are proposed and compared: ReComS (K-nearest neighbours and collaborative filtering algorithms), ReComS+ (k-means, K-nearest neighbours, and collaborative filtering algorithms) and ReComS++ (bacterial foraging optimisation, k-means, K-nearest neighbours, and collaborative filtering algorithms). The experimental datasets are collected using the Medical Interactive Recovery Assistant (MIRA) software platform. Result: Experimental results, validated by the patients' exergame performances, reveal that the ReComS++ approach predicts the best exergame settings for patients with 85.76% accuracy.
KW - Artificial Intelligence
KW - Collaborative filtering
KW - Data Mining and Machine Learning
KW - Exercise games
KW - Optimization Theory and Computation
KW - Rehabilitation
UR - http://www.scopus.com/inward/record.url?scp=85112666313&partnerID=8YFLogxK
U2 - 10.7717/PEERJ-CS.599
DO - 10.7717/PEERJ-CS.599
M3 - Article
AN - SCOPUS:85112666313
SN - 2376-5992
VL - 7
SP - 1
EP - 29
JO - PeerJ Computer Science
JF - PeerJ Computer Science
ER -