Imaxe de Portada

Machine Learning-based Calibration Approach for Low-cost Air Pollution Sensors MQ-7 and MQ-131

Gardado en:
Publicado en:Nature Environment and Pollution Technology vol. 23, no. 1 (Mar 2024), p. 401
Autor Principal: Rathnayake, L R S D
Outros autores: Sakura, G B, Weerasekara, N A, Sandaruwan, P D
Publicado:
Technoscience Publications
Materias:
Sri Lanka
Outliers (statistics)
Humidity
Regression analysis
Sensors
Carbon monoxide
Artificial neural networks
Calibration
Air quality
Pollution monitoring
Air pollution
Machine learning
Outdoor air quality
Air monitoring
Visualization
Learning algorithms
Neural networks
Variables
Algorithms
Economic
Environmental
Acceso en liña:Citation/Abstract
Full Text
Full Text - PDF
Etiquetas: Engadir etiqueta
Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!
Resumo:Air quality is a vital concern globally, and Sri Lanka, according to WHO statistics, faces challenges in achieving optimal air quality levels. To address this, we introduced an innovative loT-based Air Pollution Monitoring (ARM) Box. This solution incorporates readily available Commercial Off-The-Shelf (COTS) sensors, specifically MQ-7 and MQ-131, for measuring concentrations of Carbon Monoxide (CO) and Ozone (03) ,Arduino and "ThingSpeak" platform. Yet, those COTS sensors are not factory-calibrated. Therefore, we implemented machine learning algorithms, including linear regression and deep neural network models, to enhance the accuracy of CO and 03 concentration measurements from these non-calibrated sensors. Our findings indicate promising correlations when dealing with MQ-7 and MQ-131 measurements after removing outliers.
ISSN:0972-6268
2395-3454
0971-4871
DOI:10.46488/NEPT.2024.v23i01.034
Fonte:Engineering Database