Real-Time Prediction for Fine-Grained Air Quality Monitoring System with Asynchronous Sensing

TL;DR

This paper introduces a novel asynchronous sensing-based approach for real-time, fine-grained air quality prediction in urban areas, leveraging a correlation graph to model sparse data and spatial-temporal relations.

Contribution

The paper presents a new method that effectively predicts air quality using sparse, asynchronous sensor data and a correlation graph model, improving real-time monitoring accuracy.

Findings

The proposed method outperforms existing approaches on collected dataset.

Asynchronous sensing with correlation graph enhances prediction accuracy.

The system demonstrates effective real-time fine-grained air quality monitoring.

Abstract

Due to the significant air pollution problem, monitoring and prediction for air quality have become increasingly necessary. To provide real-time fine-grained air quality monitoring and prediction in urban areas, we have established our own Internet-of-Things-based sensing system in Peking University. Due to the energy constraint of the sensors, it is preferred that the sensors wake up alternatively in an asynchronous pattern, which leads to a sparse sensing dataset. In this paper, we propose a novel approach to predict the real-time fine-grained air quality based on asynchronous sensing. The sparse dataset and the spatial-temporal-meteorological relations are modeled into the correlation graph, in which way the prediction procedures are carefully designed. The advantage of the proposed solution over existing ones is evaluated over the dataset collected by our air quality monitoring system.