RTGNet: A Dual-Branch Network Integrating Recurrent Texture and Temporal Dynamics from sEMG for Lower-Limb Joint Angle Prediction
Zhiwei Hu, Quansheng Xu, Shaowei Su, Yinggan Tang, Yonghong Xu · 2026
Read RTGNet: A Dual-Branch Network Integrating Recurrent Texture and Temporal Dynamics from sEMG for Lower-Limb Joint Angle Prediction by Zhiwei Hu, Quansheng Xu, Shaowei Su, Yinggan Tang, Yonghong Xu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13517106.txt.
Description
Zhiwei Hu, Quansheng Xu, Shaowei Su, Yinggan Tang, and Yonghong Xu predict leg joint angles from muscle electrical signals with a two-branch neural network, in a two thousand twenty-six biomedical engineering paper. Surface electromyography is nonlinear and person-specific, making continuous angle prediction stubborn.
RTGNet reads the same signal twice: as recurrence plots capturing nonlinear texture, processed by an attention-equipped convolutional network, and as raw sequences modeled by a bidirectional memory network. A gated fusion merges the views, and a custom loss emphasizes the worst errors. On a public dataset it beat single-view baselines in walking and stair climbing. The authors target exoskeleton control applications.
Catalog record
| CREATOR | Zhiwei Hu, Quansheng Xu, Shaowei Su, Yinggan Tang, Yonghong Xu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 34 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |