A Novel Lightweight Human Activity Recognition Method Via L-CTCN
Sensors · 2023
DOI: 10.3390/s23249681 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Xue Ding und 5 weiteren Autor:innen. Beteiligte Einrichtung: Mobile and Terminal Technology Research Department, China Telecom Research Institute, Beijing 100876, China. Hauptthemen laut MEDLINE: Internet of Things, Labor, Obstetric. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Sciences Foundation of China.
Abstract (Originalsprache)
Wi-Fi-based human activity recognition has attracted significant attention. Deep learning methods are widely used to achieve feature representation and activity sensing. While more learnable parameters in the neural networks model lead to richer feature extraction, it results in significant resource consumption, rendering the model unsuitable for lightweight Internet of Things (IoT) devices. Furthermore, the sensing performance heavily relies on the quality and quantity of data, which is a time-consuming and labor-intensive task. Therefore, there is a need to explore methods that reduce the dependence on the quality and quantity of the dataset while ensuring recognition performance and decreasing model complexity to adapt to ubiquitous lightweight IoT devices. In this paper, we propose a novel Lightweight-Complex Temporal Convolution Network (L-CTCN) for human activity recognition. Specifically, this approach effectively combines complex convolution with a Temporal Convolution Network (TCN). Complex convolution can extract richer information from limited raw complex data, reducing the reliance on the quality and quantity of training samples. Based on the designed TCN framework with 1D convolution and residual blocks, the proposed model can achieve lightweight human activity recognition. Extensive experiments verify the effectiveness of the proposed method. We can achieve an average recognition accuracy of 96.6% with only 0.17 M parameter size. This method performs well under conditions of low sampling rates and a low number of subcarriers and samples.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Mobile and Terminal Technology Research Department, China Telecom Research Institute, Beijing 100876, China.
- School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 102209, China.
Förderung
- National Natural Sciences Foundation of China
Zitieren
APA
Ding, X., Li, Z., Yu, J., Xie, W., Li, X., & Jiang, T. (2023). A Novel Lightweight Human Activity Recognition Method Via L-CTCN. Sensors. https://doi.org/10.3390/s23249681
Vancouver
Ding X, Li Z, Yu J, Xie W, Li X, Jiang T. A Novel Lightweight Human Activity Recognition Method Via L-CTCN. Sensors. 2023. doi:10.3390/s23249681
BibTeX
@article{Ding2023,
author = {Ding, Xue and Li, Zhiwei and Yu, Jinyang and Xie, Weiliang and Li, Xiao and Jiang, Ting},
title = {A Novel Lightweight Human Activity Recognition Method Via L-CTCN},
journal = {Sensors},
year = {2023},
doi = {10.3390/s23249681}
}
EUVIMED