{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T14:20:14Z","timestamp":1789050014709,"version":"build-2803163510"},"reference-count":50,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:00Z","timestamp":1759881600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Science and Technology Project of Traditional Chinese Medicine in Zhejiang Province","award":["No.2024ZL422"],"award-info":[{"award-number":["No.2024ZL422"]}]},{"DOI":"10.13039\/501100017594","name":"Medical and Health Science and Technology Project of Zhejiang Province","doi-asserted-by":"crossref","award":["NO.2025KY969"],"award-info":[{"award-number":["NO.2025KY969"]}],"id":[{"id":"10.13039\/501100017594","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Ningbo Science Innovation Yongjiang 2035 Key Technological Breakthrough Project","award":["2024Z199"],"award-info":[{"award-number":["2024Z199"]}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"crossref","award":["LQ23F030015"],"award-info":[{"award-number":["LQ23F030015"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key Laboratory of Intelligent Processing Technology for Digital Music (Zhejiang Conservatory of Music), Ministry of Culture and Tourism","award":["2023DMKLC013"],"award-info":[{"award-number":["2023DMKLC013"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025M772894"],"award-info":[{"award-number":["2025M772894"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>The precise recognition of human lower limb movements based on wearable sensors is very important for human-computer interaction. However, the existing methods tend to ignore the dynamic spatial information in the process of executing human lower limb movements, leading to challenges such as reduced decoding accuracy and limited robustness. In this paper, we construct skeleton graph data based on inertial measurement unit (IMU) sensors. Also, a two-branch deep learning model, termed TCNN-MGCHN, is proposed to mine meaningful spatial and temporal feature representations from IMU-based skeleton graph data. Firstly, a temporal convolutional module (consisting of a multi-scale convolutional sub-module and an attention sub-module) is developed to extract temporal feature information with highly discriminative power. Secondly, a multi-scale graph convolutional module and a spatial graph edges\u2019 importance weight assignment method based on body partitioning strategy are proposed to obtain intrinsic spatial feature information between different skeleton nodes. Finally, the fused spatio-temporal features are passed into the classification module to obtain the predicted gait movements and sub-phases. Extensive comparison and ablation studies are conducted on our self-constructed human lower limb movement dataset. The results demonstrate that TCNN-MGCHN delivers superior classification performance compared to the mainstream methods. This study can provide a benchmark for IMU-based human lower limb movement recognition and related deep-learning modeling works.<\/jats:p>","DOI":"10.1371\/journal.pone.0332947","type":"journal-article","created":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T17:38:37Z","timestamp":1759945117000},"page":"e0332947","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":6,"title":["Gait recognition using spatio-temporal representation fusion learning network with IMU-based skeleton graph and body partition strategy"],"prefix":"10.1371","volume":"20","author":[{"given":"Fo","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9057-5778","authenticated-orcid":true,"given":"Qinxu","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanjie","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zukang","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junlong","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8417-4600","authenticated-orcid":true,"given":"Hongsheng","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,10,8]]},"reference":[{"issue":"13","key":"pone.0332947.ref001","doi-asserted-by":"crossref","first-page":"2805","DOI":"10.3390\/electronics12132805","article-title":"Research progress of human\u2013computer interaction technology based on gesture recognition","volume":"12","author":"H Zhou","year":"2023","journal-title":"Electronics"},{"issue":"1","key":"pone.0332947.ref002","doi-asserted-by":"crossref","first-page":"218","DOI":"10.3390\/electronics12010218","article-title":"Human-computer interaction system: a survey of talking-head generation","volume":"12","author":"R Zhen","year":"2023","journal-title":"Electronics"},{"issue":"14","key":"pone.0332947.ref003","doi-asserted-by":"crossref","first-page":"3084","DOI":"10.3390\/electronics12143084","article-title":"RAdam-DA-NLSTM: a nested LSTM-based time series prediction method for human\u2013computer intelligent systems","volume":"12","author":"B Liu","year":"2023","journal-title":"Electronics"},{"issue":"2","key":"pone.0332947.ref004","doi-asserted-by":"crossref","first-page":"349","DOI":"10.3390\/s24020349","article-title":"Hand gesture recognition using FSK radar sensors","volume":"24","author":"K Yang","year":"2024","journal-title":"Sensors (Basel)"},{"issue":"4","key":"pone.0332947.ref005","doi-asserted-by":"crossref","first-page":"934","DOI":"10.3390\/electronics12040934","article-title":"Human\u2013computer interaction and participation in software crowdsourcing","volume":"12","author":"HU Khan","year":"2023","journal-title":"Electronics"},{"issue":"3","key":"pone.0332947.ref006","doi-asserted-by":"crossref","first-page":"1579","DOI":"10.1109\/LRA.2023.3234813","article-title":"Lower limb exoskeleton - energy optimization of bipedal walking with energy recycling - modeling and simulation","volume":"8","author":"H Lee","year":"2023","journal-title":"IEEE Robot Autom Lett"},{"issue":"2","key":"pone.0332947.ref007","doi-asserted-by":"crossref","first-page":"1092","DOI":"10.1109\/JSEN.2021.3131582","article-title":"Wearable gait recognition systems based on MEMS pressure and inertial sensors: a review","volume":"22","author":"W Li","year":"2022","journal-title":"IEEE Sensors J"},{"issue":"1","key":"pone.0332947.ref008","doi-asserted-by":"crossref","first-page":"1","DOI":"10.23736\/S1973-9087.21.06846-5","article-title":"Efficacy of robotic exoskeleton for gait rehabilitation in patients with subacute stroke: a systematic review","volume":"58","author":"D Calafiore","year":"2022","journal-title":"Eur J Phys Rehabil Med"},{"issue":"23","key":"pone.0332947.ref009","doi-asserted-by":"crossref","first-page":"26470","DOI":"10.1109\/JSEN.2021.3119658","article-title":"Recent advances in quantitative gait analysis using wearable sensors: a review","volume":"21","author":"Y Hutabarat","year":"2021","journal-title":"IEEE Sensors J"},{"issue":"10","key":"pone.0332947.ref010","doi-asserted-by":"crossref","first-page":"3325","DOI":"10.3390\/s21103325","article-title":"Evaluating the accuracy of virtual reality trackers for computing spatiotemporal gait parameters","volume":"21","author":"M Guaitolini","year":"2021","journal-title":"Sensors (Basel)"},{"key":"pone.0332947.ref011","doi-asserted-by":"crossref","first-page":"105486","DOI":"10.1016\/j.cmpb.2020.105486","article-title":"Accurate recognition of lower limb ambulation mode based on surface electromyography and motion data using machine learning","volume":"193","author":"B Zhou","year":"2020","journal-title":"Comput Methods Programs Biomed"},{"key":"pone.0332947.ref012","doi-asserted-by":"crossref","first-page":"104096","DOI":"10.1016\/j.bspc.2022.104096","article-title":"Electromyography-controlled lower extremity exoskeleton to provide wearers flexibility in walking","volume":"79","author":"W Chen","year":"2023","journal-title":"Biomedical Signal Processing and Control"},{"issue":"2","key":"pone.0332947.ref013","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1109\/TBME.2021.3102009","article-title":"Wearables-only analysis of muscle and joint mechanics: an EMG-driven approach","volume":"69","author":"RD Gurchiek","year":"2022","journal-title":"IEEE Trans Biomed Eng"},{"key":"pone.0332947.ref014","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.patcog.2016.05.019","article-title":"RGB-D-based action recognition datasets: a survey","volume":"60","author":"J Zhang","year":"2016","journal-title":"Pattern Recognition"},{"issue":"5","key":"pone.0332947.ref015","doi-asserted-by":"crossref","first-page":"1758","DOI":"10.1109\/JBHI.2020.3024925","article-title":"Spatiotemporal gait measurement with a side-view depth sensor using human joint proposals","volume":"25","author":"A Hynes","year":"2021","journal-title":"IEEE J Biomed Health Inform"},{"key":"pone.0332947.ref016","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"K Simonyan","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"10","key":"pone.0332947.ref017","doi-asserted-by":"crossref","first-page":"6649","DOI":"10.1109\/TPAMI.2021.3092833","article-title":"A self-supervised gait encoding approach with locality-awareness for 3D skeleton based person re-identification","volume":"44","author":"H Rao","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"pone.0332947.ref018","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1007670802811","article-title":"Technical note: Naive Bayes for regression","volume":"41","author":"E Frank","year":"2000","journal-title":"Machine Learning"},{"issue":"10","key":"pone.0332947.ref019","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1038\/nbt1004-1315","article-title":"What is a hidden Markov model?","volume":"22","author":"SR Eddy","year":"2004","journal-title":"Nat Biotechnol"},{"issue":"1","key":"pone.0332947.ref020","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1007413323501","article-title":"Decision tree induction based on efficient tree restructuring","volume":"29","author":"PE Utgoff","year":"1997","journal-title":"Machine Learning"},{"issue":"4","key":"pone.0332947.ref021","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/5254.708428","article-title":"Support vector machines","volume":"13","author":"MA Hearst","year":"1998","journal-title":"IEEE Intell Syst Their Appl"},{"key":"pone.0332947.ref022","doi-asserted-by":"crossref","first-page":"923164","DOI":"10.3389\/fnbot.2022.923164","article-title":"Comparison of machine learning and deep learning-based methods for locomotion mode recognition using a single inertial measurement unit","volume":"16","author":"HTT Vu","year":"2022","journal-title":"Front Neurorobot"},{"key":"pone.0332947.ref023","article-title":"Very deep convolutional networks for large-scale image recognition","author":"K Simonyan","year":"2014","journal-title":"arXiv preprint"},{"issue":"2","key":"pone.0332947.ref024","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding structure in time","volume":"14","author":"JL Elman","year":"1990","journal-title":"Cognitive Science"},{"issue":"3","key":"pone.0332947.ref025","doi-asserted-by":"crossref","first-page":"478","DOI":"10.3390\/s17030478","article-title":"Wearable device-based gait recognition using angle embedded gait dynamic images and a convolutional neural network","volume":"17","author":"Y Zhao","year":"2017","journal-title":"Sensors (Basel)"},{"key":"pone.0332947.ref026","first-page":"1874","article-title":"Gait-based frailty assessment using image representation of IMU signals and deep CNN","volume":"2021","author":"MZ Arshad","year":"2021","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"pone.0332947.ref027","doi-asserted-by":"crossref","first-page":"104272","DOI":"10.1016\/j.bspc.2022.104272","article-title":"Gait phases recognition based on lower limb sEMG signals using LDA-PSO-LSTM algorithm","volume":"80","author":"S Cai","year":"2023","journal-title":"Biomedical Signal Processing and Control"},{"issue":"17","key":"pone.0332947.ref028","doi-asserted-by":"crossref","first-page":"16952","DOI":"10.1109\/JSEN.2022.3175823","article-title":"Gait pattern identification and phase estimation in continuous multilocomotion mode based on inertial measurement units","volume":"22","author":"X Zhang","year":"2022","journal-title":"IEEE Sensors J"},{"issue":"5","key":"pone.0332947.ref029","doi-asserted-by":"crossref","first-page":"1059","DOI":"10.1007\/s42235-021-00083-y","article-title":"A novel gait pattern recognition method based on LSTM-CNN for lower limb exoskeleton","volume":"18","author":"C Chen","year":"2021","journal-title":"J Bionic Eng"},{"key":"pone.0332947.ref030","doi-asserted-by":"crossref","first-page":"117306","DOI":"10.1016\/j.eswa.2022.117306","article-title":"Real-time walking gait terrain classification from foot-mounted inertial measurement unit using convolutional long short-term memory neural network","volume":"203","author":"R Moura Coelho","year":"2022","journal-title":"Expert Systems with Applications"},{"issue":"8","key":"pone.0332947.ref031","doi-asserted-by":"crossref","first-page":"9618","DOI":"10.1109\/TITS.2023.3348517","article-title":"EEG-based driver fatigue detection using spatio-temporal fusion network with brain region partitioning strategy","volume":"25","author":"F Hu","year":"2024","journal-title":"IEEE Trans Intell Transport Syst"},{"key":"pone.0332947.ref032","unstructured":"Niepert M, Ahmed M, Kutzkov K. Learning convolutional neural networks for graphs. In: International Conference on Machine Learning. PMLR; 2016. p. 2014\u20132023."},{"issue":"1","key":"pone.0332947.ref033","article-title":"Spatial temporal graph convolutional networks for skeleton-based action recognition","volume":"32","author":"S Yan","year":"2018","journal-title":"AAAI"},{"issue":"5","key":"pone.0332947.ref034","doi-asserted-by":"crossref","first-page":"3497","DOI":"10.1109\/TII.2020.3020694","article-title":"Fatigue detection with covariance manifolds of electroencephalography in transportation industry","volume":"17","author":"X Zhang","year":"2021","journal-title":"IEEE Trans Ind Inf"},{"key":"pone.0332947.ref035","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.neucom.2019.06.081","article-title":"An adaptive and on-line IMU-based locomotion activity classification method using a triplet Markov model","volume":"362","author":"H Li","year":"2019","journal-title":"Neurocomputing"},{"issue":"10","key":"pone.0332947.ref036","doi-asserted-by":"crossref","first-page":"8397","DOI":"10.1109\/TPAMI.2025.3576283","article-title":"OpenGait: a comprehensive benchmark study for gait recognition toward better practicality","volume":"47","author":"C Fan","year":"2025","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"17","key":"pone.0332947.ref037","doi-asserted-by":"crossref","first-page":"5574","DOI":"10.3390\/s24175574","article-title":"A lightweight pathological gait recognition approach based on a new gait template in side-view and improved attention mechanism","volume":"24","author":"C Li","year":"2024","journal-title":"Sensors (Basel)"},{"key":"pone.0332947.ref038","doi-asserted-by":"crossref","unstructured":"Fu Y, Meng S, Hou S, Hu X, Huang Y. GPGait: generalized pose-based gait recognition. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). 2023. p. 19538\u201347. https:\/\/doi.org\/10.1109\/iccv51070.2023.01795","DOI":"10.1109\/ICCV51070.2023.01795"},{"issue":"8","key":"pone.0332947.ref039","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.3390\/s25082337","article-title":"GaitRGA: gait recognition based on relation-aware global attention","volume":"25","author":"J Liu","year":"2025","journal-title":"Sensors (Basel)"},{"key":"pone.0332947.ref040","article-title":"Very deep convolutional networks for large-scale image recognition","author":"K Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"pone.0332947.ref041","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1016\/j.compbiolchem.2004.09.006","article-title":"Comparing two K-category assignments by a K-category correlation coefficient","volume":"28","author":"J Gorodkin","year":"2004","journal-title":"Comput Biol Chem"},{"key":"pone.0332947.ref042","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/j.future.2017.11.029","article-title":"A robust human activity recognition system using smartphone sensors and deep learning","volume":"81","author":"MM Hassan","year":"2018","journal-title":"Future Generation Computer Systems"},{"issue":"6","key":"pone.0332947.ref043","doi-asserted-by":"crossref","first-page":"1330","DOI":"10.1109\/TBME.2017.2750139","article-title":"A phase variable approach for IMU-based locomotion activity recognition","volume":"65","author":"HL Bartlett","year":"2018","journal-title":"IEEE Trans Biomed Eng"},{"issue":"11","key":"pone.0332947.ref044","doi-asserted-by":"crossref","first-page":"3136","DOI":"10.1109\/TBME.2019.2900863","article-title":"The classification of minor gait alterations using wearable sensors and deep learning","volume":"66","author":"A Turner","year":"2019","journal-title":"IEEE Trans Biomed Eng"},{"key":"pone.0332947.ref045","doi-asserted-by":"crossref","first-page":"191542","DOI":"10.1109\/ACCESS.2020.3030086","article-title":"Human pose estimation-based real-time gait analysis using convolutional neural network","volume":"8","author":"A Rohan","year":"2020","journal-title":"IEEE Access"},{"key":"pone.0332947.ref046","doi-asserted-by":"crossref","first-page":"102279","DOI":"10.1016\/j.bspc.2020.102279","article-title":"Evaluation of classification performance in human lower limb jump phases of signal correlation information and LSTM models","volume":"64","author":"Y Lu","year":"2021","journal-title":"Biomedical Signal Processing and Control"},{"issue":"13","key":"pone.0332947.ref047","doi-asserted-by":"crossref","first-page":"5905","DOI":"10.3390\/s23135905","article-title":"A novel gait phase recognition method based on DPF-LSTM-CNN using wearable inertial sensors","volume":"23","author":"K Liu","year":"2023","journal-title":"Sensors (Basel)"},{"issue":"9","key":"pone.0332947.ref048","doi-asserted-by":"crossref","first-page":"6029","DOI":"10.1109\/LRA.2023.3303787","article-title":"Gait phase detection based on LSTM-CRF for stair ambulation","volume":"8","author":"H Wei","year":"2023","journal-title":"IEEE Robot Autom Lett"},{"issue":"22","key":"pone.0332947.ref049","doi-asserted-by":"crossref","first-page":"10721","DOI":"10.3390\/app142210721","article-title":"Multi-model gait-based KAM prediction system using LSTM-RNN and wearable devices","volume":"14","author":"D Jung","year":"2024","journal-title":"Applied Sciences"},{"issue":"4","key":"pone.0332947.ref050","doi-asserted-by":"crossref","first-page":"1276","DOI":"10.3390\/s24041276","article-title":"Bi-directional long short-term memory-based gait phase recognition method robust to directional variations in subject\u2019s gait progression using wearable inertial sensor","volume":"24","author":"H Jeon","year":"2024","journal-title":"Sensors (Basel)"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0332947","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T17:38:48Z","timestamp":1759945128000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0332947"}},"subtitle":[],"editor":[{"given":"Andrea","family":"Tigrini","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,10,8]]},"references-count":50,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10,8]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0332947","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,8]]}}}