{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T17:58:58Z","timestamp":1787162338893,"version":"build-2736575974"},"reference-count":24,"publisher":"ASME International","issue":"4","license":[{"start":{"date-parts":[[2025,2,8]],"date-time":"2025-02-08T00:00:00Z","timestamp":1738972800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Despite the increasing use of inertial measurement units (IMUs) and machine learning techniques for gait analysis, there remains a gap in which feature selection methods are best tailored for gait time series prediction. This study explores the impact of using various feature selection methods on the performance of a random forest (RF) model in predicting lower limb joints kinematics from two IMUs. The primary objectives of this study are as follows: (1) Comparing eight feature selection methods based on their ability to identify more robust feature sets, time efficiency, and impact on RF models' performance, and (2) assessing the performance of RF models using generalized feature sets on a new dataset. Twenty-three typically developed (TD) children (ages 6\u201315) participated in data collection involving optical motion capture (OMC) and IMUs. Joint kinematics were computed using opensim. By employing eight feature selection methods (four filter and four embedded methods), the study identified 30 important features for each target. These selected features were used to develop personalized and generalized RF models to predict lower limbs joints kinematics during gait. This study reveals that various feature selection methods have a minimal impact on the performance of personalized and generalized RF models. However, the RF and mutual information (MI) methods provided slightly lower errors and outliers. MI demonstrated remarkable robustness by consistently identifying the most common features across different participants. ElasticNet emerged as the fastest method. Overall, the study illuminated the robustness of RF models in predicting joint kinematics during gait in children, showcasing consistent performance across various feature selection methods.<\/jats:p>","DOI":"10.1115\/1.4067821","type":"journal-article","created":{"date-parts":[[2025,2,8]],"date-time":"2025-02-08T02:16:26Z","timestamp":1738980986000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":3,"title":["Exploring the Influence of Feature Selection Methods on a Random Forest Model for Gait Time Series Prediction Using Inertial Measurement Units"],"prefix":"10.1115","volume":"147","author":[{"given":"Shima Mohammadi","family":"Moghadam","sequence":"first","affiliation":[{"name":"Auckland Bioengineering Institute, The University of Auckland , 70 Symonds Street, Level 8, Auckland 1010, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5418-5870","authenticated-orcid":false,"given":"Julie","family":"Choisne","sequence":"additional","affiliation":[{"name":"Auckland Bioengineering Institute, The University of Auckland , 70 Symonds Street, Level 8, Auckland 1010, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"33","published-online":{"date-parts":[[2025,2,26]]},"reference":[{"key":"2025022617093838500_bib1","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1097\/00003086-200003000-00023","article-title":"The Effect of Preoperative Gait Analysis on Orthopaedic Decision Making","volume":"372","year":"2000","journal-title":"Clin. Orthop. Relat. Res.\u00ae"},{"issue":"13","key":"2025022617093838500_bib2","doi-asserted-by":"crossref","first-page":"4535","DOI":"10.3390\/s21134535","article-title":"A Comparison of Three Neural Network Approaches for Estimating Joint Angles and Moments From Inertial Measurement Units","volume":"21","year":"2021","journal-title":"Sensors"},{"issue":"1","key":"2025022617093838500_bib3","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1016\/j.gaitpost.2013.08.028","article-title":"An Individual-Specific Gait Pattern Prediction Model Based on Generalized Regression Neural Networks","volume":"39","year":"2014","journal-title":"Gait Posture"},{"issue":"17","key":"2025022617093838500_bib4","doi-asserted-by":"crossref","first-page":"5876","DOI":"10.3390\/s21175876","article-title":"The Use of Synthetic IMU Signals in the Training of Deep Learning Models Significantly Improves the Accuracy of Joint Kinematic Predictions","volume":"21","year":"2021","journal-title":"Sensors"},{"issue":"2","key":"2025022617093838500_bib5","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1002\/cav.2","article-title":"Capturing Human Motion Using Body-Fixed Sensors: Outdoor Measurement and Clinical Applications","volume":"15","year":"2004","journal-title":"Comput. Anim. Virtual Worlds"},{"issue":"22","key":"2025022617093838500_bib6","doi-asserted-by":"crossref","first-page":"28328","DOI":"10.1109\/JSEN.2023.3317366","article-title":"The Effect of IMU Sensor Location, Number of Features, and Window Size on a Random Forest Model's Accuracy in Predicting Joint Kinematics and Kinetics During Gait","volume":"23","year":"2023","journal-title":"IEEE Sens. J."},{"issue":"11","key":"2025022617093838500_bib7","doi-asserted-by":"crossref","first-page":"12380","DOI":"10.1109\/JSEN.2023.3267398","article-title":"Personalised Machine Learning Approach to Estimating Knee Kinematics Using Only Shank-Mounted IMU","volume":"23","year":"2023","journal-title":"IEEE Sens. J."},{"key":"2025022617093838500_bib8","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1016\/j.bspc.2017.10.002","article-title":"Surface EMG Based Continuous Estimation of Human Lower Limb Joint Angles by Using Deep Belief Networks","volume":"40","year":"2018","journal-title":"Biomed. Signal Process. Control"},{"issue":"15","key":"2025022617093838500_bib9","doi-asserted-by":"crossref","first-page":"5143","DOI":"10.3390\/s21155143","article-title":"Remote Patient Monitoring With Wearable Sensors Following Knee Arthroplasty","volume":"21","year":"2021","journal-title":"Sensors"},{"key":"2025022617093838500_bib10","unstructured":"Zarshenas, H., 2022, \u201cEMG-Informed Estimation of Human Walking Dynamics for Assistive Robots,\u201d Ph.D. thesis, ResearchSpace@Auckland, The University of Auckland, Auckland, New Zealand.https:\/\/hdl.handle.net\/2292\/61854"},{"issue":"1","key":"2025022617093838500_bib11","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","year":"2001","journal-title":"Mach. Learn."},{"issue":"21","key":"2025022617093838500_bib12","doi-asserted-by":"crossref","first-page":"3711","DOI":"10.1093\/bioinformatics\/bty373","article-title":"The Revival of the Gini Importance?","volume":"34","year":"2018","journal-title":"Bioinformatics"},{"key":"2025022617093838500_bib13","volume-title":"An Introduction to Statistical Learning","year":"2013"},{"key":"2025022617093838500_bib14","doi-asserted-by":"crossref","first-page":"1372669","DOI":"10.3389\/fbioe.2024.1372669","article-title":"3D Gait Analysis in Children: Feasibility of Predicting Joint Kinematics and Kinetics With Personalized Machine Learning Models and Inertial Measurement Units","volume":"12","year":"2024","journal-title":"Front. Bioeng. Biotechnol."},{"issue":"11","key":"2025022617093838500_bib15","doi-asserted-by":"crossref","first-page":"1940","DOI":"10.1109\/TBME.2007.901024","article-title":"OpenSim: Open-Source Software to Create and Analyze Dynamic Simulations of Movement","volume":"54","year":"2007","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"2025022617093838500_bib16","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.neucom.2018.03.067","article-title":"Time Series Feature Extraction on Basis of Scalable Hypothesis Tests (Tsfresh\u2014A Python Package)","volume":"307","year":"2018","journal-title":"Neurocomputing"},{"issue":"3\/4","key":"2025022617093838500_bib17","doi-asserted-by":"crossref","first-page":"441","DOI":"10.2307\/1422689","article-title":"The Proof and Measurement of Association Between Two Things","volume":"100","year":"1987","journal-title":"Am. J. Psychol."},{"issue":"1\u20132","key":"2025022617093838500_bib18","first-page":"81","article-title":"A New Measure of Rank Correlation","volume":"30","year":"1938","journal-title":"Biometrika"},{"issue":"14","key":"2025022617093838500_bib19","doi-asserted-by":"crossref","first-page":"6371","DOI":"10.1016\/j.eswa.2014.04.019","article-title":"MIFS-ND: A Mutual Information-Based Feature Selection Method","volume":"41","year":"2014","journal-title":"Expert Syst. Appl."},{"key":"2025022617093838500_bib20","volume-title":"Elements of Information Theory","year":"1999"},{"key":"2025022617093838500_bib21","first-page":"296","article-title":"An Adaptation of Relief for Attribute Estimation in Regression","volume-title":"ICML'97","year":"1997"},{"issue":"12","key":"2025022617093838500_bib22","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.3390\/f10121073","article-title":"Influence of Variable Selection and Forest Type on Forest Aboveground Biomass Estimation Using Machine Learning Algorithms","volume":"10","year":"2019","journal-title":"Forests"},{"issue":"1","key":"2025022617093838500_bib23","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression Shrinkage and Selection Via the Lasso","volume":"58","year":"1996","journal-title":"J. R. Stat. Soc. Ser. B: Stat. Methodol."},{"issue":"2","key":"2025022617093838500_bib24","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and Variable Selection Via the Elastic Net","volume":"67","year":"2005","journal-title":"J. R. Stat. Soc. Ser. B: Stat. Methodol."}],"container-title":["Journal of Biomechanical Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/asmedigitalcollection.asme.org\/biomechanical\/article-pdf\/147\/4\/044502\/7436960\/bio_147_04_044502.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/asmedigitalcollection.asme.org\/biomechanical\/article-pdf\/147\/4\/044502\/7436960\/bio_147_04_044502.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T12:09:54Z","timestamp":1740571794000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/biomechanical\/article\/147\/4\/044502\/1212582\/Exploring-the-Influence-of-Feature-Selection"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,26]]},"references-count":24,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4067821","relation":{},"ISSN":["0148-0731","1528-8951"],"issn-type":[{"value":"0148-0731","type":"print"},{"value":"1528-8951","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,26]]},"article-number":"044502"}}