RTGNet: A Dual-Branch Network Integrating Recurrent Texture and Temporal Dynamics from sEMG for Lower-Limb Joint Angle Prediction
Sensors · 14.08.2026 · 26 (16) · 5144
DOI: 10.3390/s26165144 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 14.08.2026. Verfasst von Zhiwei Hu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Huaibei Normal University, Huaibei 235000, China. Hauptthemen laut MEDLINE: Electromyography, Lower Extremity, Joints. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Scientific Research Foundation of Education Department of Anhui Province, Beijing Zhongheng Wei-Tech Electronics Co., Ltd., the Collaborative Research Project of Huaibei Normal University.
Abstract (Originalsprache)
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°, a root mean square error (RMSE) of 5.25°, and an R2 of 0.81 during walking, as well as an MAE of 4.53°, an RMSE of 6.47°, 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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer Science and Technology, Huaibei Normal University, Huaibei 235000, China.
- School of Electrical Engineering, Yanshan University, Qinhuangdao 066004, China.
ORCID-Profile: Quansheng Xu, Yinggan Tang
Förderung
- Scientific Research Foundation of Education Department of Anhui Province
- Beijing Zhongheng Wei-Tech Electronics Co., Ltd.
- the Collaborative Research Project of Huaibei Normal University
- Scientific Research Foundation of the Education Department of Anhui Province
- Collaborative Research Project of Huaibei Normal University
Zitieren
APA
Hu, Z., Xu, Q., Su, S., Tang, Y., & Xu, Y. (2026). RTGNet: A Dual-Branch Network Integrating Recurrent Texture and Temporal Dynamics from sEMG for Lower-Limb Joint Angle Prediction. Sensors, 26(16), 5144. https://doi.org/10.3390/s26165144
Vancouver
Hu Z, Xu Q, Su S, Tang Y, Xu Y. RTGNet: A Dual-Branch Network Integrating Recurrent Texture and Temporal Dynamics from sEMG for Lower-Limb Joint Angle Prediction. Sensors. 2026;26(16):5144. doi:10.3390/s26165144
BibTeX
@article{Hu2026,
author = {Hu, Zhiwei and Xu, Quansheng and Su, Shaowei and Tang, Yinggan and Xu, Yonghong},
title = {RTGNet: A Dual-Branch Network Integrating Recurrent Texture and Temporal Dynamics from sEMG for Lower-Limb Joint Angle Prediction},
journal = {Sensors},
year = {2026},
volume = {26},
number = {16},
pages = {5144},
doi = {10.3390/s26165144}
}
EUVIMED