Pattern-based attention recurrent autoencoder for anomaly detection in air quality sensor networks

Sensor networks play an essential role in today's air quality monitoring platforms. Nevertheless, sensors often malfunction, leading to data anomalies. In this paper, an unsupervised pattern-based attention recurrent autoencoder for anomaly detection (PARAAD) is proposed to detect and locate an...

Descripción completa

Detalles Bibliográficos
Autores: Allka, Xhensilda|||0000-0003-2187-9985, Ferrer Cid, Pau|||0000-0003-2112-8516, Barceló Ordinas, José María|||0000-0002-9738-2425, García Vidal, Jorge|||0000-0001-5969-1182
Tipo de recurso: artículo
Fecha de publicación:2024
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/424136
Acceso en línea:https://hdl.handle.net/2117/424136
https://dx.doi.org/10.1109/TNSE.2024.3454459
Access Level:acceso abierto
Palabra clave:Anomaly detection
Monitoring
Air quality
Atmospheric modeling
Data models
Correlation
Attention mechanisms
Monitoring networks
Internet of Things
Autoencoder
Attention mechanism.
Àrees temàtiques de la UPC::Informàtica::Arquitectura de computadors
Descripción
Sumario:Sensor networks play an essential role in today's air quality monitoring platforms. Nevertheless, sensors often malfunction, leading to data anomalies. In this paper, an unsupervised pattern-based attention recurrent autoencoder for anomaly detection (PARAAD) is proposed to detect and locate anomalies in a network of air quality sensors. The novelty of the proposal lies in the use of temporal patterns, i.e., blocks of data, instead of point values. By looking at temporal patterns and through an attention mechanism, the architecture captures data dependencies in the feature space and latent space, enhancing the model's ability to focus on the most relevant parts. Its performance is evaluated with two categories of anomalies, bias fault and drift anomalies, and compared with baseline models such as a feed-forward autoencoder and a transformer architecture, as well as with models not based on temporal patterns. The results show that PARAAD achieves anomalous sensor detection and localization rates higher than 80%, outperforming existing baseline models in air quality sensor networks for both bias and drift faults.