Deviation Prediction and Correction on Low-Cost Atmospheric Pressure Sensors using a Machine-Learning Algorithm

Tiago de Araújo, Lígia Silva, Adriano Moreira

Abstract

Atmospheric pressure sensors are important devices for several applications, including environment monitoring and indoor positioning tracking systems. This paper proposes a method to enhance the quality of data obtained from low-cost atmospheric pressure sensors using a machine learning algorithm to predict the error behaviour. By using the extremely Randomized Trees algorithm, a model was trained with a reference sensor data for temperature and humidity and with all low-cost sensor datasets that were co-located into an artificial climatic chamber that simulated different climatic situations. Fifteen low-cost environmental sensor units, composed by five different models, were considered. They measure – together – temperature, relative humidity and atmospheric pressure. In the evaluation, three categories of output metrics were considered: raw; trained by the independent sensor data; and trained by the low-cost sensor data. The model trained by the reference sensor was able to reduce the Mean Absolute Error (MAE) between atmospheric pressure sensor pairs by up to 67%, while the same ensemble trained with all low-cost data was able to reduce the MAE by up to 98%. These results suggest that low-cost environmental sensors can be a good asset if their data are properly processed.

Paper Citation

in Harvard Style

de Araújo T., Silva L. and Moreira A. (2020). Deviation Prediction and Correction on Low-Cost Atmospheric Pressure Sensors using a Machine-Learning Algorithm.In Proceedings of the 9th International Conference on Sensor Networks - Volume 1: SENSORNETS, ISBN 978-989-758-403-9, pages 41-51. DOI: 10.5220/0008968400410051

in Bibtex Style

@conference{sensornets20,
author={Tiago de Araújo and Lígia Silva and Adriano Moreira},
title={Deviation Prediction and Correction on Low-Cost Atmospheric Pressure Sensors using a Machine-Learning Algorithm},
booktitle={Proceedings of the 9th International Conference on Sensor Networks - Volume 1: SENSORNETS,},
year={2020},
pages={41-51},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008968400410051},
isbn={978-989-758-403-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Conference on Sensor Networks - Volume 1: SENSORNETS,
TI - Deviation Prediction and Correction on Low-Cost Atmospheric Pressure Sensors using a Machine-Learning Algorithm
SN - 978-989-758-403-9
AU - de Araújo T.
AU - Silva L.
AU - Moreira A.
PY - 2020
SP - 41
EP - 51
DO - 10.5220/0008968400410051