Self-Attention-Based Deep Convolution LSTM Framework for Sensor-Based Badminton Activity Recognition
Sensors · 10.10.2023 · 23 (20) · 8373
DOI: 10.3390/s23208373 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 10.10.2023. Verfasst von Jingyang Deng und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematical Sciences and LMAM, Peking University, Beijing 100871, China. Hauptthemen laut MEDLINE: Artificial Intelligence, Neural Networks, Computer. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China.
Abstract (Originalsprache)
Sensor-based human activity recognition aims to classify human activities or behaviors according to the data from wearable or embedded sensors, leading to a new direction in the field of Artificial Intelligence. When the activities become high-level and sophisticated, such as in the multiple technical skills of playing badminton, it is usually a challenging task due to the difficulty of feature extraction from the sensor data. As a kind of end-to-end approach, deep neural networks have the capacity of automatic feature learning and extracting. However, most current studies on sensor-based badminton activity recognition adopt CNN-based architectures, which lack the ability of capturing temporal information and global signal comprehension. To overcome these shortcomings, we propose a deep learning framework which combines the convolutional layers, LSTM structure, and self-attention mechanism together. Specifically, this framework can automatically extract the local features of the sensor signals in time domain, take the LSTM structure for processing the badminton activity data, and focus attention on the information that is essential to the badminton activity recognition task. It is demonstrated by the experimental results on an actual badminton single sensor dataset that our proposed framework has obtained a badminton activity recognition (37 classes) accuracy of 97.83%, which outperforms the existing methods, and also has the advantages of lower training time and faster convergence.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Mathematical Sciences and LMAM, Peking University, Beijing 100871, China.
ORCID-Profile: Jinwen Ma
Förderung
- National Key Research and Development Program of China
Zitieren
APA
Deng, J., Zhang, S., & Ma, J. (2023). Self-Attention-Based Deep Convolution LSTM Framework for Sensor-Based Badminton Activity Recognition. Sensors, 23(20), 8373. https://doi.org/10.3390/s23208373
Vancouver
Deng J, Zhang S, Ma J. Self-Attention-Based Deep Convolution LSTM Framework for Sensor-Based Badminton Activity Recognition. Sensors. 2023;23(20):8373. doi:10.3390/s23208373
BibTeX
@article{Deng2023,
author = {Deng, Jingyang and Zhang, Shuyi and Ma, Jinwen},
title = {Self-Attention-Based Deep Convolution LSTM Framework for Sensor-Based Badminton Activity Recognition},
journal = {Sensors},
year = {2023},
volume = {23},
number = {20},
pages = {8373},
doi = {10.3390/s23208373}
}
EUVIMED