{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T09:37:06Z","timestamp":1786700226271,"version":"build-2736575974"},"reference-count":24,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:00:00Z","timestamp":1786665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Scientific Research Foundation of the Education Department of Anhui Province","award":["2024AH051687"],"award-info":[{"award-number":["2024AH051687"]}]},{"name":"Collaborative Research Project of Huaibei Normal University","award":["2024340609000054"],"award-info":[{"award-number":["2024340609000054"]}]},{"award":["2024340609000054"],"award-info":[{"award-number":["2024340609000054"]}],"id":[{"id":"https:\/\/ror.org\/03ek23472","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Accurate continuous prediction of lower-limb joint angles from surface electromyography (sEMG) remains challenging because of the nonlinear, non-stationary, and subject-specific nature of sEMG signals, which can reduce robustness and lead to degraded prediction accuracy during highly dynamic gait phases. In this study, we propose RTGNet, a dual-branch deep learning framework for lower-limb joint-angle prediction from multichannel sEMG. The method constructs two feature views from the same sEMG stream: recurrence-plot (RP)-based representations for nonlinear texture characterization and time-series sequences for long-term temporal dependency modeling. These views are processed by a convolutional neural network (CNN) with a convolutional block attention module (CBAM) and a bidirectional long short-term memory network (BiLSTM), respectively, and integrated through an adaptive gated fusion mechanism. An enhanced Huber-TopK loss is further employed to emphasize samples with large prediction errors. Experiments on the SIAT-LLMD dataset under an offline cross-subject evaluation setting show that RTGNet achieves a mean absolute error (MAE) of 3.87\u00b0, a root mean square error (RMSE) of 5.25\u00b0, and an R2 of 0.81 during walking, as well as an MAE of 4.53\u00b0, an RMSE of 6.47\u00b0, and an R2 of 0.84 during stair ascent. The proposed framework outperforms temporal-only and RP-based baselines, and ablation results further support the effectiveness of the gated fusion strategy and CBAM attention. Overall, these results suggest that integrating recurrence texture and temporal dynamics is a promising strategy for sEMG-driven joint-angle prediction and provides a useful basis for future exoskeleton control-oriented studies.<\/jats:p>","DOI":"10.3390\/s26165144","type":"journal-article","created":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T09:04:01Z","timestamp":1786698241000},"page":"5144","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RTGNet: A Dual-Branch Network Integrating Recurrent Texture and Temporal Dynamics from sEMG for Lower-Limb Joint Angle Prediction"],"prefix":"10.3390","volume":"26","author":[{"given":"Zhiwei","family":"Hu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Huaibei Normal University, Huaibei 235000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quansheng","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huaibei Normal University, Huaibei 235000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaowei","family":"Su","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huaibei Normal University, Huaibei 235000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7440-1742","authenticated-orcid":false,"given":"Yinggan","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Yanshan University, Qinhuangdao 066004, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonghong","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huaibei Normal University, Huaibei 235000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"143883","DOI":"10.1109\/ACCESS.2024.3414175","article-title":"Deep learning approaches for enhanced lower-limb exoskeleton control: A review","volume":"12","author":"Belal","year":"2024","journal-title":"IEEE Access"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/j.gaitpost.2020.10.026","article-title":"Lower body kinematics estimation from wearable sensors for walking and running: A deep learning approach","volume":"83","author":"Hernandez","year":"2021","journal-title":"Gait Posture"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Coker, J., Chen, H., Schall, M.C., Gallagher, S., and Zabala, M. (2021). EMG and joint angle-based machine learning to predict future joint angles at the knee. Sensors, 21.","DOI":"10.3390\/s21113622"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.gaitpost.2021.06.015","article-title":"Synergy-based knee angle estimation using kinematics of thigh","volume":"89","author":"Liang","year":"2021","journal-title":"Gait Posture"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1038\/s41597-023-02263-3","article-title":"Surface electromyogram, kinematic, and kinetic dataset of lower limb walking for movement intent recognition","volume":"10","author":"Wei","year":"2023","journal-title":"Sci. Data"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"104042","DOI":"10.1016\/j.bspc.2022.104042","article-title":"Feasibility of recurrence quantification analysis (RQA) in quantifying dynamical coordination among muscles","volume":"79","author":"Zhao","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"109692","DOI":"10.1016\/j.jbiomech.2020.109692","article-title":"The effects of fatigue on synergy of selected lower limb muscles during running","volume":"103","author":"Hajiloo","year":"2020","journal-title":"J. Biomech."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.medengphy.2018.04.003","article-title":"Evaluation of matrix factorisation approaches for muscle synergy extraction","volume":"57","author":"Ebied","year":"2018","journal-title":"Med. Eng. Phys."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"107848","DOI":"10.1016\/j.cmpb.2023.107848","article-title":"Adaptive neuro-fuzzy inference system model driven by the non-negative matrix factorization-extracted muscle synergy patterns to estimate lower limb joint movements","volume":"242","author":"Xu","year":"2023","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"101968","DOI":"10.1016\/j.bspc.2020.101968","article-title":"Continuous angular position estimation of human ankle during unconstrained locomotion","volume":"60","author":"Gupta","year":"2020","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"117340","DOI":"10.1016\/j.eswa.2022.117340","article-title":"Continuous and simultaneous estimation of lower limb multi-joint angles from sEMG signals based on stacked convolutional and LSTM models","volume":"203","author":"Lu","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"107761","DOI":"10.1016\/j.engappai.2023.107761","article-title":"Interpretable dual-branch EMGNet: A transfer learning-based network for inter-subject lower limb motion intention recognition","volume":"130","author":"Zhang","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.aej.2024.09.116","article-title":"A multimodal multistream multilevel fusion network for finger joint angle estimation with hybrid sEMG and FMG sensing","volume":"110","author":"Chen","year":"2025","journal-title":"Alex. Eng. J."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Sharifi-Renani, M., Mahoor, M.H., and Clary, C.W. (2023). BioMAT: An open-source biomechanics multi-activity transformer for joint kinematic predictions using wearable sensors. Sensors, 23.","DOI":"10.3390\/s23135778"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Han, Y., Tao, Q., and Zhang, X. (2025). Multijoint continuous motion estimation for human lower limb based on surface electromyography. Sensors, 25.","DOI":"10.3390\/s25030719"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"S8","DOI":"10.1016\/j.gaitpost.2023.07.297","article-title":"Co-activation in time-frequency domain among EMG signals from several muscles during walking","volume":"105","author":"Borzelli","year":"2023","journal-title":"Gait Posture"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Han, X., Chen, H., Cheng, X., and Zhao, P. (2025). Continuous estimation of sEMG-based upper-limb joint angles in the time\u2013frequency domain using a scale temporal\u2013channel cross-encoder. Actuators, 14.","DOI":"10.3390\/act14080378"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"20299","DOI":"10.1007\/s00521-025-11456-3","article-title":"Improvement in the classification of EMG signals through a convolutional neural network","volume":"37","year":"2025","journal-title":"Neural Comput. Appl."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"102854","DOI":"10.1016\/j.bspc.2021.102854","article-title":"Analysis of epileptic seizures based on EEG using recurrence plot images and deep learning","volume":"69","author":"Shankar","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","article-title":"CBAM: Convolutional block attention module","volume":"Volume 11211","author":"Woo","year":"2018","journal-title":"Computer Vision\u2013ECCV 2018"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Liu, X., Peng, H., Zheng, N., Yang, Y., Hu, H., and Yuan, Y. (2023, January 17\u201324). EfficientViT: Memory efficient vision transformer with cascaded group attention. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Wang, A., Chen, H., Lin, Z., Han, J., and Ding, G. (2024, January 17\u201321). RepViT: Revisiting mobile CNN from ViT perspective. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01506"},{"key":"ref_23","unstructured":"Vasu, P.K.A., Gabriel, J., Zhu, J., Tuzel, O., and Ranjan, A. (2023, January 1\u20136). FastViT: A Fast Hybrid Vision Transformer Using Structural Reparameterization. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5144\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T09:08:21Z","timestamp":1786698501000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5144"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,14]]},"references-count":24,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26165144"],"URL":"https:\/\/doi.org\/10.3390\/s26165144","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,14]]}}}