Real-Time Chinese Sign Language Gesture Prediction Based on Surface EMG Sensors and Artificial Neural Network
Electronics · 2025-11-09 · 14 (22) · 4374
DOI: 10.3390/electronics14224374 ↗At a glance
Journal article in Electronics, published online on 2025-11-09. Written by Jinrun Cheng and 2 co-authors. Cited 1 times so far (Crossref); 29 references. The full text is freely available (open access, CC BY 4.0).
Abstract (original language)
Sign language recognition aims to capture and classify hand and arm motion signals to enable intuitive communication for individuals with hearing and speech impairments. This study proposes a real-time Chinese Sign Language (CSL) recognition framework that integrates a dual-stage segmentation strategy with a lightweight three-layer artificial neural network to achieve early gesture prediction before completion of motion sequences. The system was evaluated on a 21-class CSL dataset containing several highly similar gestures and achieved an accuracy of 91.5%, with low average inference latency per cycle. Furthermore, training set truncation experiments demonstrate that using only the first 50% of each gesture instance preserves model accuracy while reducing training time by half, thereby enhancing real-time efficiency and practical deployability for embedded or assistive applications.
Cite
APA
Cheng, J., Hu, X., & Yang, K. (2025). Real-Time Chinese Sign Language Gesture Prediction Based on Surface EMG Sensors and Artificial Neural Network. Electronics, 14(22), 4374. https://doi.org/10.3390/electronics14224374
Vancouver
Cheng J, Hu X, Yang K. Real-Time Chinese Sign Language Gesture Prediction Based on Surface EMG Sensors and Artificial Neural Network. Electronics. 2025;14(22):4374. doi:10.3390/electronics14224374
BibTeX
@article{Cheng2025,
author = {Cheng, Jinrun and Hu, Xing and Yang, Kuo},
title = {Real-Time Chinese Sign Language Gesture Prediction Based on Surface EMG Sensors and Artificial Neural Network},
journal = {Electronics},
year = {2025},
volume = {14},
number = {22},
pages = {4374},
doi = {10.3390/electronics14224374}
}
EUVIMED