Sagittal-Plane Knee Flexion Moment Estimation Using a Lightweight Deep Learning Framework Based on Sequential Surface EMG Feature Frames
Sensors · 18.04.2026 · 26 (8) · 2500
DOI: 10.3390/s26082500 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 18.04.2026. Verfasst von Yuanzhi Zhuo und 3 weiteren Autor:innen. Beteiligte Einrichtung: Biomedical Engineering Department, School of Engineering, STEM College, RMIT University, Melbourne, VIC 3000, Australia. Hauptthemen laut MEDLINE: Knee Joint, Electromyography, Deep Learning, Range of Motion, Articular. Die Arbeit nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Knee joint moment is an important biomechanical parameter for sports assessment, rehabilitation monitoring, and human–machine interaction. However, direct measurement is often restricted to laboratory-based settings. Surface electromyography (sEMG) offers a non-invasive alternative for indirect joint moment estimation, but many existing deep learning models remain too computationally demanding for potential wearable edge deployment. To address this gap, this study proposes Topo2DCNN-LSTM, a lightweight two-dimensional (2D) convolutional neural network model, designed for sagittal-plane knee flexion moment estimation. The model used a feature-based sequential representation, transforming raw sEMG signals into compact Root Mean Square (RMS) feature frames. The input was processed by a lightweight 2D convolutional neural network (CNN) encoder and paired with long short-term memory (LSTM) units. The model was trained on a public walking dataset of healthy subjects with synchronized sEMG and joint kinetics at two treadmill speeds. When compared with selected deep learning baselines, the quantized model achieved a mean RMS Error of 0.088 ± 0.020 Nm/kg at 1.2 m/s and 0.114 ± 0.034 Nm/kg at 1.8 m/s. On a SparkFun Thing Plus–SAMD51, it achieved an average inference latency of 28 ms using 71,316 bytes of random-access memory (RAM) and 257,172 bytes of flash. These results support its use as a proof of concept for personalized unilateral knee moment estimation with isolated on-device inference feasibility under resource-constrained and limited walking conditions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Biomedical Engineering Department, School of Engineering, STEM College, RMIT University, Melbourne, VIC 3000, Australia.
- School of Health and Biomedical Science, RMIT University, Bundoora, VIC 3082, Australia.
- Mechanical, Manufacturing and Mechatronic Engineering Department, School of Engineering, STEM College, RMIT University, Melbourne, VIC 3000, Australia.
ORCID-Profile: Yuanzhi Zhuo, Adrian Pranata, Chi-Tsun Cheng, Toh Yen Pang
Zitieren
APA
Zhuo, Y., Pranata, A., Cheng, C. T., & Pang, T. Y. (2026). Sagittal-Plane Knee Flexion Moment Estimation Using a Lightweight Deep Learning Framework Based on Sequential Surface EMG Feature Frames. Sensors, 26(8), 2500. https://doi.org/10.3390/s26082500
Vancouver
Zhuo Y, Pranata A, Cheng CT, Pang TY. Sagittal-Plane Knee Flexion Moment Estimation Using a Lightweight Deep Learning Framework Based on Sequential Surface EMG Feature Frames. Sensors. 2026;26(8):2500. doi:10.3390/s26082500
BibTeX
@article{Zhuo2026,
author = {Zhuo, Yuanzhi and Pranata, Adrian and Cheng, Chi-Tsun and Pang, Toh Yen},
title = {Sagittal-Plane Knee Flexion Moment Estimation Using a Lightweight Deep Learning Framework Based on Sequential Surface EMG Feature Frames},
journal = {Sensors},
year = {2026},
volume = {26},
number = {8},
pages = {2500},
doi = {10.3390/s26082500}
}
EUVIMED