pmSensing: A Participatory Sensing Network for Predictive Monitoring of Particulate Matter

TL;DR

This paper introduces pmSensing, a low-cost participatory sensing network utilizing IoT devices and LSTM-RNN for accurate air quality monitoring and prediction of particulate matter.

Contribution

It develops a novel low-cost IoT-based sensor network for air quality monitoring and demonstrates its predictive capabilities using LSTM-RNN models.

Findings

Sensor data closely matches high-cost meteorological stations

LSTM-RNN achieves high accuracy in particulate matter prediction

System enables affordable air quality monitoring solutions

Abstract

This work presents a proposal for a wireless sensor network for participatory sensing, with IoT sensing devices developed especially for monitoring and predicting air quality, as alternatives of high cost meteorological stations. The system, called pmSensing, aims to measure particulate material. A validation is done by comparing the data collected by the prototype with data from stations. The comparison shows that the results are close, which can enable low-cost solutions to the problem. The system still presents a predictive analysis using recurrent neural networks, in this case the LSTM-RNN, where the predictions presented high accuracy in relation to the real data.