Leveraging spatiotemporal correlations with recurrent autoencoders for sensor anomaly detection

The introduction of high- and low-cost Internet of Things (IoT) sensors in air quality monitoring networks, in addition to providing a cost-effective solution for monitoring pollutant levels, also brings with it the challenge of ensuring data reliability. These sensors can present anomalies in the d...

ver descrição completa

Detalhes 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 documento: artigo
Data de publicação:2024
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositório:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglês
OAI Identifier:oai:upcommons.upc.edu:2117/417733
Acesso em linha:https://hdl.handle.net/2117/417733
https://dx.doi.org/10.1109/JIOT.2024.3416525
Access Level:Acceso aberto
Palavra-chave:Air quality
Anomaly detection
Autoencoder
Internet of Things (IoT)
Low-cost sensors (LCSs)
Monitoring stations
Àrees temàtiques de la UPC::Informàtica::Arquitectura de computadors
Descrição
Resumo:The introduction of high- and low-cost Internet of Things (IoT) sensors in air quality monitoring networks, in addition to providing a cost-effective solution for monitoring pollutant levels, also brings with it the challenge of ensuring data reliability. These sensors can present anomalies in the data and identifying them is a challenging task. In this article, we propose a spatiotemporal correlation recurrent autoencoder anomaly detection (STC-RAAD) architecture that unlike the other existing architectures, in addition to the temporal correlation present in the sensor data, also involves information from the neighboring sensors in the monitoring network for better reconstruction. The performance of STC-RAAD is compared with the other methods on two different real data sets, for two categories of anomalies, outperforming the other existing approaches with an average increase of 38% for the detection rate and 36% for the precision.