Spatial-Temporal Graph Attention Fuser for Calibration in IoT Air Pollution Monitoring Systems

TL;DR

This paper introduces a graph attention network-based method to improve calibration accuracy of low-cost IoT air pollution sensors in uncontrolled environments, addressing a key challenge in environmental monitoring.

Contribution

It presents a novel graph neural network approach specifically designed for sensor data fusion and calibration in IoT air quality monitoring systems.

Findings

Significant improvement in sensor calibration accuracy

Effective data fusion from sensor arrays

Validated on real-world IoT air pollution data

Abstract

The use of Internet of Things (IoT) sensors for air pollution monitoring has significantly increased, resulting in the deployment of low-cost sensors. Despite this advancement, accurately calibrating these sensors in uncontrolled environmental conditions remains a challenge. To address this, we propose a novel approach that leverages graph neural networks, specifically the graph attention network module, to enhance the calibration process by fusing data from sensor arrays. Through our experiments, we demonstrate the effectiveness of our approach in significantly improving the calibration accuracy of sensors in IoT air pollution monitoring platforms.