Paper
18 October 2024 Unsupervised anomaly detection algorithm for sensor data streams based on GAT-GAN
Yuhang Su, Jun Ma, Jinyu Fan, Bohang Chen
Author Affiliations +
Proceedings Volume 13277, Sixth International Conference on Wireless Communications and Smart Grid (ICWCSG 2024); 132770N (2024) https://doi.org/10.1117/12.3049532
Event: 2024 6th International Conference on Wireless Communications and Smart Grid, 2024, Sipsongpanna, China
Abstract
Detecting data flow anomalies within Wireless Sensor Networks (WSNs) and reaching the server can promptly identify faults and issue maintenance alerts, thereby ensuring safe and reliable operation of the system. However existing methods can utilize single variables in data streams to perform most anomaly detection tasks, they often ignore the correlation between variables, resulting in reduced detection performance. Therefore, our approach constructs a generative adversarial network model based on Graph Attention Network (GAT) and employs a dual autoencoding structure in both the generator and discriminator to learn the latent representation of the entire time series. The results of ablation experiments and comparison experiments on two real datasets with baseline models show that GAT-GAN outperforms the former in detecting data anomalies
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Yuhang Su, Jun Ma, Jinyu Fan, and Bohang Chen "Unsupervised anomaly detection algorithm for sensor data streams based on GAT-GAN", Proc. SPIE 13277, Sixth International Conference on Wireless Communications and Smart Grid (ICWCSG 2024), 132770N (18 October 2024); https://doi.org/10.1117/12.3049532
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Data modeling

Education and training

Performance modeling

Gallium nitride

Sensor networks

Sensors

Detection and tracking algorithms

Back to Top