{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T16:36:57Z","timestamp":1787330217925,"version":"build-2736575974"},"reference-count":36,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T00:00:00Z","timestamp":1787270400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In recent years, advances in exoskeleton technology have increased the demand for human motion classification in terms of both movement diversity and recognition accuracy, making the effective classification of more complex asymmetric movements increasingly important. This study integrated surface electromyography (sEMG) and inertial measurement unit (IMU) signals and employed mutual information (MI) and muscle symmetry features (MSF) to analyze the characteristic differences between symmetrical muscles in both legs during asymmetric movements, with the aim of improving the accuracy of asymmetric motion classification. sEMG and IMU signals were collected from six movements, including three asymmetric postures: asymmetrical stance, single-knee kneeled position, and crouching advance. The acquired signals were processed through energy envelope analysis, active segment extraction, empirical mode decomposition (EMD), feature extraction, MI extraction, and MSF extraction. The relevance based on weight feature selection (RWFS) combined with conditional mutual information (CMI) method was then applied to reduce feature dimensionality, prioritize features with significant fluctuations, and preserve key characteristics. Finally, the CNN-LSTM-Attention algorithm was used for classification. Experimental results showed that fusing sEMG and IMU signals achieved 96.30% accuracy in lower limb motion recognition. The proposed method improves asymmetric movement classification and may provide a potential basis for exoskeleton motion classification in special environments.<\/jats:p>","DOI":"10.3390\/s26165314","type":"journal-article","created":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T15:51:05Z","timestamp":1787327465000},"page":"5314","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Lower Limb Motion Classification of Actions in Confined Environments Based on Multi-Source Signal Fusion and Muscle Symmetry Features"],"prefix":"10.3390","volume":"26","author":[{"given":"Dingzhe","family":"Li","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering, Nanjing University of Science and Technology, No. 200, Xiaolingwei, Nanjing 210094, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5493-3699","authenticated-orcid":false,"given":"Xiaorong","family":"Guan","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Nanjing University of Science and Technology, No. 200, Xiaolingwei, Nanjing 210094, China"},{"name":"Hangzhou Zhiyuan Research Institute Co., Ltd., No. 188 Yunzhan Road, Hangzhou 310000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Nanjing University of Science and Technology, No. 200, Xiaolingwei, Nanjing 210094, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3640-1491","authenticated-orcid":false,"given":"Changlong","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Nanjing University of Science and Technology, No. 200, Xiaolingwei, Nanjing 210094, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"He","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Nanjing University of Science and Technology, No. 200, Xiaolingwei, Nanjing 210094, China"},{"name":"Hangzhou Zhiyuan Research Institute Co., Ltd., No. 188 Yunzhan Road, Hangzhou 310000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiwang","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Nanjing University of Science and Technology, No. 200, Xiaolingwei, Nanjing 210094, China"},{"name":"Hangzhou Zhiyuan Research Institute Co., Ltd., No. 188 Yunzhan Road, Hangzhou 310000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Air Force Hospital of Eastern Theater Command, Nanjing 210002, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"104293","DOI":"10.1016\/j.apergo.2024.104293","article-title":"Effectiveness of a Passive Military Exoskeleton in Off-Loading Weight during Static and Dynamic Load Carriage: A Randomised Cross-Over Study","volume":"119","author":"Kong","year":"2024","journal-title":"Appl. Ergon."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1007\/978-3-030-98260-7_29","article-title":"Current State and Design Recommendations of Exoskeletons of Lower Limbs in Military Applications","volume":"Volume 13207","author":"Mazal","year":"2022","journal-title":"Modelling and Simulation for Autonomous Systems"},{"key":"ref_3","first-page":"14537","article-title":"Design and Evaluation of Wearable Exoskeleton to Augment Load Carrying Capacity for Ground Force Soldiers","volume":"7","author":"Seid","year":"2017","journal-title":"Int. J. Eng. Sci. Comput."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1705","DOI":"10.3390\/s140101705","article-title":"Wearable Gait Measurement System with an Instrumented Cane for Exoskeleton Control","volume":"14","author":"Hassan","year":"2014","journal-title":"Sensors"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"107765","DOI":"10.1016\/j.measurement.2020.107765","article-title":"Parameter Identification and Adaptive Compliant Control of Rehabilitation Exoskeleton Based on Multiple Sensors","volume":"159","author":"Chen","year":"2020","journal-title":"Measurement"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"035017","DOI":"10.1088\/1361-665X\/abdc04","article-title":"Smart Wearable Monitoring System Based on Multi-Type Sensors for Motion Recognition","volume":"30","author":"Yang","year":"2021","journal-title":"Smart Mater. Struct."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1109\/TBME.2008.2003293","article-title":"A Strategy for Identifying Locomotion Modes Using Surface Electromyography","volume":"56","author":"Huang","year":"2009","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Dehzangi, O., Taherisadr, M., and ChangalVala, R. (2017). IMU-Based Gait Recognition Using Convolutional Neural Networks and Multi-Sensor Fusion. Sensors, 17.","DOI":"10.3390\/s17122735"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"189","DOI":"10.4028\/www.scientific.net\/AMR.60-61.189","article-title":"Towards Multi-Classification of Human Motions Using Micro IMU and SVM Training Process","volume":"60\u201361","author":"Shi","year":"2009","journal-title":"Adv. Mater. Res."},{"key":"ref_10","first-page":"37","article-title":"Human Motion Attitude Recognition Method Based on Machine Learning","volume":"30","author":"Deng","year":"2022","journal-title":"J. Chin. Inert. Technol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"103198","DOI":"10.1016\/j.bspc.2021.103198","article-title":"Recognition of Lower Limb Movements Using Empirical Mode Decomposition and k-Nearest Neighbor Entropy Estimator with Surface Electromyogram Signals","volume":"71","author":"Wei","year":"2022","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"53986","DOI":"10.1109\/ACCESS.2024.3388044","article-title":"Exoskeleton Recognition of Human Movement Intent Based on Surface Electromyographic Signals: Review","volume":"12","author":"Lu","year":"2024","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Hayashi, Y., and Kiguchi, K. (2015, January 7\u201311). A Study of Features of EEG Signals during Upper-Limb Motion. Proceedings of the 2015 IEEE International Conference on Advanced Intelligent Mechatronics (AIM), Busan, Republic of Korea.","DOI":"10.1109\/AIM.2015.7222660"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"991","DOI":"10.1007\/s12652-021-03351-1","article-title":"Bio-Signal Based Motion Control System Using Deep Learning Models: A Deep Learning Approach for Motion Classification Using EEG and EMG Signal Fusion","volume":"14","author":"Aly","year":"2023","journal-title":"J. Ambient Intell. Humaniz. Comput."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"V\u00e1sconez, J.P., Barona L\u00f3pez, L.I., Valdivieso Caraguay, \u00c1.L., and Benalc\u00e1zar, M.E. (2022). Hand Gesture Recognition Using EMG-IMU Signals and Deep Q-Networks. Sensors, 22.","DOI":"10.3390\/s22249613"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1007\/s10846-017-0725-0","article-title":"Hand Gesture Recognition Based Omnidirectional Wheelchair Control Using IMU and EMG Sensors","volume":"91","author":"Kundu","year":"2018","journal-title":"J. Intell. Robot. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"38242","DOI":"10.1038\/s41598-025-22103-1","article-title":"Deep Learning for Motion Classification in Ankle Exoskeletons Using Surface EMG and IMU Signals","volume":"15","author":"Mallah","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"e39902","DOI":"10.1097\/MD.0000000000039902","article-title":"The Effect of Squats on Muscle Activity in Standing, Kneeling, and Half-Kneeling Positions: A Cross-Sectional Study","volume":"103","author":"Jeong","year":"2024","journal-title":"Medicine"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"132534","DOI":"10.1016\/j.neucom.2025.132534","article-title":"A Survey on Feature Selection Techniques for Biomedical Data: Methods and Applications","volume":"670","author":"Chen","year":"2026","journal-title":"Neurocomputing"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1109\/TSMCA.2008.2007977","article-title":"Gait Feature Subset Selection by Mutual Information","volume":"39","author":"Guo","year":"2009","journal-title":"IEEE Trans. Syst. Man Cybern. A Syst. Hum."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Ju, Z., Ouyang, G., and Liu, H. (2013, January 16\u201319). EMG-EMG Correlation Analysis for Human Hand Movements. Proceedings of the 2013 IEEE Workshop on Robotic Intelligence in Informationally Structured Space (RiiSS), Singapore.","DOI":"10.1109\/RiiSS.2013.6607927"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"102292","DOI":"10.1016\/j.bspc.2020.102292","article-title":"Effect of the sEMG Electrode (Re)placement and Feature Set Size on the Hand Movement Recognition","volume":"64","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Azhiri, R.B., Esmaeili, M., and Nourani, M. (2021, January 9\u201312). Real-Time EMG Signal Classification via Recurrent Neural Networks. Proceedings of the 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Houston, TX, USA.","DOI":"10.1109\/BIBM52615.2021.9669872"},{"key":"ref_24","first-page":"986","article-title":"KNN Model-Based Approach in Classification","volume":"Volume 2888","author":"Meersman","year":"2003","journal-title":"On the Move to Meaningful Internet Systems 2003: CoopIS, DOA, and ODBASE"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1526","DOI":"10.1109\/JBHI.2018.2864335","article-title":"Multiday Evaluation of Techniques for EMG-Based Classification of Hand Motions","volume":"23","author":"Waris","year":"2019","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1007\/s42235-022-00280-3","article-title":"sEMG-Based Lower Limb Motion Prediction Using CNN-LSTM with Improved PCA Optimization Algorithm","volume":"20","author":"Zhu","year":"2023","journal-title":"J. Bionic Eng."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhang, J., Ye, L., and Lai, Y. (2023). Stock Price Prediction Using CNN-BiLSTM-Attention Model. Mathematics, 11.","DOI":"10.3390\/math11091985"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"101833","DOI":"10.1016\/j.apr.2023.101833","article-title":"Deep Learning Methods for Atmospheric PM2.5 Prediction: A Comparative Study of Transformer and CNN-LSTM-Attention","volume":"14","author":"Cui","year":"2023","journal-title":"Atmos. Pollut. Res."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Borr\u00e9, A., Seman, L.O., Camponogara, E., Stefenon, S.F., Mariani, V.C., and Coelho, L.S. (2023). Machine Fault Detection Using a Hybrid CNN-LSTM Attention-Based Model. Sensors, 23.","DOI":"10.3390\/s23094512"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"e2532","DOI":"10.7717\/peerj-cs.2532","article-title":"Enhanced Detection of Accounting Fraud Using a CNN-LSTM-Attention Model Optimized by Sparrow Search","volume":"10","author":"Wu","year":"2024","journal-title":"PeerJ Comput. Sci."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"012139","DOI":"10.1088\/1742-6596\/1883\/1\/012139","article-title":"LSTM-CNN Network for Human Activity Recognition Using WiFi CSI Data","volume":"1883","author":"Shang","year":"2021","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_32","first-page":"1","article-title":"The WOA-CNN-LSTM-Attention Model for Predicting GNSS Water Vapor","volume":"62","author":"Yan","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Liu, J., Wei, B., Cai, M., and Xu, Y. (2021, January 17\u201319). Dynamic Gesture Recognition Based on CNN-LSTM-Attention. Proceedings of the 2021 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC), Xi\u2019an, China.","DOI":"10.1109\/ICSPCC52875.2021.9565034"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"106219","DOI":"10.1016\/j.bspc.2024.106219","article-title":"An Alternative EMG Normalization Method: Heterogeneous Recurrence Quantification Analysis of Isometric Maximum Voluntary Contraction Movements","volume":"93","author":"Avdan","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Wang, F., Fan, Z., Shi, K., and Wu, H. (2020, January 27\u201329). Human Upper Limb Movement Recognition Based on Kernel Principal Component Analysis and Support Vector Machines. Proceedings of the 2020 39th Chinese Control Conference (CCC), Shenyang, China.","DOI":"10.23919\/CCC50068.2020.9188747"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1016\/j.ins.2022.02.024","article-title":"Feature-Specific Mutual Information Variation for Multi-Label Feature Selection","volume":"593","author":"Hu","year":"2022","journal-title":"Inf. Sci."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5314\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T15:52:54Z","timestamp":1787327574000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5314"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,21]]},"references-count":36,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26165314"],"URL":"https:\/\/doi.org\/10.3390\/s26165314","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,21]]}}}