Rehabilitation monitoring and assessment: a comparative analysis of feature engineering and machine learning algorithms on the UI-PRMD and KIMORE benchmark datasets

Rehabilitation is crucial for individuals recovering from injuries or illnesses. It combines medical knowledge, therapy, and technology to improve health and independence. However, a global shortage of physiotherapists makes it challenging to provide adequate rehabilitation services. Current rehabil...

Full description

Saved in:
Bibliographic Details
Main Authors: Moamen Zaher, Amr S. Ghoneim, Laila Abdelhamid, Ayman Atia
Format: Article
Language:English
Published: Taylor & Francis Group 2025-01-01
Series:Journal of Information and Telecommunication
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/24751839.2025.2454053
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832540902128615424
author Moamen Zaher
Amr S. Ghoneim
Laila Abdelhamid
Ayman Atia
author_facet Moamen Zaher
Amr S. Ghoneim
Laila Abdelhamid
Ayman Atia
author_sort Moamen Zaher
collection DOAJ
description Rehabilitation is crucial for individuals recovering from injuries or illnesses. It combines medical knowledge, therapy, and technology to improve health and independence. However, a global shortage of physiotherapists makes it challenging to provide adequate rehabilitation services. Current rehabilitation research often lacks advanced computational techniques to automate exercise assessment, relying heavily on time-consuming and costly in-person sessions. This study uses computer vision and classical machine learning (ML) to monitor and evaluate physical rehabilitation exercises using skeletal data. It compares five feature extraction approaches, six feature ranking techniques, and thirteen ML algorithms to identify the most influential features for accurate exercise classification using benchmark datasets (UI-PRMD and KIMORE). The performances of feature ranking algorithms–X2, ReliefF, Gini Decrease, FCBF, Information Gain, and Information Gain Ratio–were examined alongside ML algorithms such as SVMs, RFs, KNN, LDA, and lightGBM, amongst others. ReliefF with an Extra-Tree demonstrated superior performance (classification accuracy of 99.94%) compared to state-of-the-art studies on the UI-PRMD (a 4.4% improvement). However, FCBF, alongside an Extra-Tree, demonstrated robust performance across diverse datasets, achieving 99.64% on UIPRMD (the second-best result) and 81.85% on KIMORE (the highest accuracy reported compared to state-of-the-art studies). FCBF attained robust results together with the various classifiers, averaging 92.65%.
format Article
id doaj-art-7e216dd0376a42d88e2614af283d2766
institution Kabale University
issn 2475-1839
2475-1847
language English
publishDate 2025-01-01
publisher Taylor & Francis Group
record_format Article
series Journal of Information and Telecommunication
spelling doaj-art-7e216dd0376a42d88e2614af283d27662025-02-04T12:48:38ZengTaylor & Francis GroupJournal of Information and Telecommunication2475-18392475-18472025-01-0112110.1080/24751839.2025.2454053Rehabilitation monitoring and assessment: a comparative analysis of feature engineering and machine learning algorithms on the UI-PRMD and KIMORE benchmark datasetsMoamen Zaher0Amr S. Ghoneim1Laila Abdelhamid2Ayman Atia3Software Engineering Prog. Faculty of Computing and Artificial Intelligence, Helwan University, Cairo, EgyptComputer Science Dept. Faculty of Computing and Artificial Intelligence, Helwan University, Cairo, EgyptInformation System Dept. Faculty of Computing and Artificial Intelligence, Helwan University, Cairo, EgyptFaculty of Computer Science, October University for Modern Sciences and Arts (MSA), Giza, EgyptRehabilitation is crucial for individuals recovering from injuries or illnesses. It combines medical knowledge, therapy, and technology to improve health and independence. However, a global shortage of physiotherapists makes it challenging to provide adequate rehabilitation services. Current rehabilitation research often lacks advanced computational techniques to automate exercise assessment, relying heavily on time-consuming and costly in-person sessions. This study uses computer vision and classical machine learning (ML) to monitor and evaluate physical rehabilitation exercises using skeletal data. It compares five feature extraction approaches, six feature ranking techniques, and thirteen ML algorithms to identify the most influential features for accurate exercise classification using benchmark datasets (UI-PRMD and KIMORE). The performances of feature ranking algorithms–X2, ReliefF, Gini Decrease, FCBF, Information Gain, and Information Gain Ratio–were examined alongside ML algorithms such as SVMs, RFs, KNN, LDA, and lightGBM, amongst others. ReliefF with an Extra-Tree demonstrated superior performance (classification accuracy of 99.94%) compared to state-of-the-art studies on the UI-PRMD (a 4.4% improvement). However, FCBF, alongside an Extra-Tree, demonstrated robust performance across diverse datasets, achieving 99.64% on UIPRMD (the second-best result) and 81.85% on KIMORE (the highest accuracy reported compared to state-of-the-art studies). FCBF attained robust results together with the various classifiers, averaging 92.65%.https://www.tandfonline.com/doi/10.1080/24751839.2025.2454053Exercise classificationFeature RankingKinectPhysical RehabilitationMachine Learning
spellingShingle Moamen Zaher
Amr S. Ghoneim
Laila Abdelhamid
Ayman Atia
Rehabilitation monitoring and assessment: a comparative analysis of feature engineering and machine learning algorithms on the UI-PRMD and KIMORE benchmark datasets
Journal of Information and Telecommunication
Exercise classification
Feature Ranking
Kinect
Physical Rehabilitation
Machine Learning
title Rehabilitation monitoring and assessment: a comparative analysis of feature engineering and machine learning algorithms on the UI-PRMD and KIMORE benchmark datasets
title_full Rehabilitation monitoring and assessment: a comparative analysis of feature engineering and machine learning algorithms on the UI-PRMD and KIMORE benchmark datasets
title_fullStr Rehabilitation monitoring and assessment: a comparative analysis of feature engineering and machine learning algorithms on the UI-PRMD and KIMORE benchmark datasets
title_full_unstemmed Rehabilitation monitoring and assessment: a comparative analysis of feature engineering and machine learning algorithms on the UI-PRMD and KIMORE benchmark datasets
title_short Rehabilitation monitoring and assessment: a comparative analysis of feature engineering and machine learning algorithms on the UI-PRMD and KIMORE benchmark datasets
title_sort rehabilitation monitoring and assessment a comparative analysis of feature engineering and machine learning algorithms on the ui prmd and kimore benchmark datasets
topic Exercise classification
Feature Ranking
Kinect
Physical Rehabilitation
Machine Learning
url https://www.tandfonline.com/doi/10.1080/24751839.2025.2454053
work_keys_str_mv AT moamenzaher rehabilitationmonitoringandassessmentacomparativeanalysisoffeatureengineeringandmachinelearningalgorithmsontheuiprmdandkimorebenchmarkdatasets
AT amrsghoneim rehabilitationmonitoringandassessmentacomparativeanalysisoffeatureengineeringandmachinelearningalgorithmsontheuiprmdandkimorebenchmarkdatasets
AT lailaabdelhamid rehabilitationmonitoringandassessmentacomparativeanalysisoffeatureengineeringandmachinelearningalgorithmsontheuiprmdandkimorebenchmarkdatasets
AT aymanatia rehabilitationmonitoringandassessmentacomparativeanalysisoffeatureengineeringandmachinelearningalgorithmsontheuiprmdandkimorebenchmarkdatasets