A Practical and Adaptive Approach to Predicting Indoor CO<sub>2</sub>

COVID-19 has underlined the importance of monitoring indoor air quality (IAQ) to guarantee safe conditions in enclosed environments. Due to its strict correlation with human presence, carbon dioxide (CO<sub>2</sub>) represents one of the pollutants that most affects environmental health....

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Giacomo Segala, Roberto Doriguzzi-Corin, Claudio Peroni, Tommaso Gazzini, Domenico Siracusa
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
T
Acceso en línea:https://doaj.org/article/9b22b0dbbb8e49e79e056b6e46d28a0e
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:9b22b0dbbb8e49e79e056b6e46d28a0e
record_format dspace
spelling oai:doaj.org-article:9b22b0dbbb8e49e79e056b6e46d28a0e2021-11-25T16:37:50ZA Practical and Adaptive Approach to Predicting Indoor CO<sub>2</sub>10.3390/app1122107712076-3417https://doaj.org/article/9b22b0dbbb8e49e79e056b6e46d28a0e2021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/10771https://doaj.org/toc/2076-3417COVID-19 has underlined the importance of monitoring indoor air quality (IAQ) to guarantee safe conditions in enclosed environments. Due to its strict correlation with human presence, carbon dioxide (CO<sub>2</sub>) represents one of the pollutants that most affects environmental health. Therefore, forecasting future indoor CO<sub>2</sub> plays a central role in taking preventive measures to keep CO<sub>2</sub> level as low as possible. Unlike other research that aims to maximize the prediction accuracy, typically using data collected over many days, in this work we propose a practical approach for predicting indoor CO<sub>2</sub> using a limited window of recent environmental data (i.e., temperature; humidity; CO<sub>2</sub> of, e.g., a room, office or shop) for training neural network models, without the need for any kind of model pre-training. After just a week of data collection, the error of predictions was around 15 parts per million (ppm), which should enable the system to regulate heating, ventilation and air conditioning (HVAC) systems accurately. After a month of data we reduced the error to about 10 ppm, thereby achieving a high prediction accuracy in a short time from the beginning of the data collection. Once the desired mobile window size is reached, the model can be continuously updated by sliding the window over time, in order to guarantee long-term performance.Giacomo SegalaRoberto Doriguzzi-CorinClaudio PeroniTommaso GazziniDomenico SiracusaMDPI AGarticleindoor air qualitycarbon dioxideair pollutionartificial intelligencedeep learningTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10771, p 10771 (2021)
institution DOAJ
collection DOAJ
language EN
topic indoor air quality
carbon dioxide
air pollution
artificial intelligence
deep learning
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
spellingShingle indoor air quality
carbon dioxide
air pollution
artificial intelligence
deep learning
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
Giacomo Segala
Roberto Doriguzzi-Corin
Claudio Peroni
Tommaso Gazzini
Domenico Siracusa
A Practical and Adaptive Approach to Predicting Indoor CO<sub>2</sub>
description COVID-19 has underlined the importance of monitoring indoor air quality (IAQ) to guarantee safe conditions in enclosed environments. Due to its strict correlation with human presence, carbon dioxide (CO<sub>2</sub>) represents one of the pollutants that most affects environmental health. Therefore, forecasting future indoor CO<sub>2</sub> plays a central role in taking preventive measures to keep CO<sub>2</sub> level as low as possible. Unlike other research that aims to maximize the prediction accuracy, typically using data collected over many days, in this work we propose a practical approach for predicting indoor CO<sub>2</sub> using a limited window of recent environmental data (i.e., temperature; humidity; CO<sub>2</sub> of, e.g., a room, office or shop) for training neural network models, without the need for any kind of model pre-training. After just a week of data collection, the error of predictions was around 15 parts per million (ppm), which should enable the system to regulate heating, ventilation and air conditioning (HVAC) systems accurately. After a month of data we reduced the error to about 10 ppm, thereby achieving a high prediction accuracy in a short time from the beginning of the data collection. Once the desired mobile window size is reached, the model can be continuously updated by sliding the window over time, in order to guarantee long-term performance.
format article
author Giacomo Segala
Roberto Doriguzzi-Corin
Claudio Peroni
Tommaso Gazzini
Domenico Siracusa
author_facet Giacomo Segala
Roberto Doriguzzi-Corin
Claudio Peroni
Tommaso Gazzini
Domenico Siracusa
author_sort Giacomo Segala
title A Practical and Adaptive Approach to Predicting Indoor CO<sub>2</sub>
title_short A Practical and Adaptive Approach to Predicting Indoor CO<sub>2</sub>
title_full A Practical and Adaptive Approach to Predicting Indoor CO<sub>2</sub>
title_fullStr A Practical and Adaptive Approach to Predicting Indoor CO<sub>2</sub>
title_full_unstemmed A Practical and Adaptive Approach to Predicting Indoor CO<sub>2</sub>
title_sort practical and adaptive approach to predicting indoor co<sub>2</sub>
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/9b22b0dbbb8e49e79e056b6e46d28a0e
work_keys_str_mv AT giacomosegala apracticalandadaptiveapproachtopredictingindoorcosub2sub
AT robertodoriguzzicorin apracticalandadaptiveapproachtopredictingindoorcosub2sub
AT claudioperoni apracticalandadaptiveapproachtopredictingindoorcosub2sub
AT tommasogazzini apracticalandadaptiveapproachtopredictingindoorcosub2sub
AT domenicosiracusa apracticalandadaptiveapproachtopredictingindoorcosub2sub
AT giacomosegala practicalandadaptiveapproachtopredictingindoorcosub2sub
AT robertodoriguzzicorin practicalandadaptiveapproachtopredictingindoorcosub2sub
AT claudioperoni practicalandadaptiveapproachtopredictingindoorcosub2sub
AT tommasogazzini practicalandadaptiveapproachtopredictingindoorcosub2sub
AT domenicosiracusa practicalandadaptiveapproachtopredictingindoorcosub2sub
_version_ 1718413091754999808