Deep Learning-Based Indoor Air Quality Forecasting Framework for Indoor Subway Station Platforms

Particulate matter (PM) of sizes less than 10 µm (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>P</mi><msub><mi>M</mi><mrow><mn>10</mn></mrow><...

Full description

Bibliographic Details
Main Authors: Ahtesham Bakht, Shambhavi Sharma, Duckshin Park, Hyunsoo Lee
Format: Article
Language:English
Published: MDPI AG 2022-09-01
Series:Toxics
Subjects:
Online Access:https://www.mdpi.com/2305-6304/10/10/557
_version_ 1797469789741907968
author Ahtesham Bakht
Shambhavi Sharma
Duckshin Park
Hyunsoo Lee
author_facet Ahtesham Bakht
Shambhavi Sharma
Duckshin Park
Hyunsoo Lee
author_sort Ahtesham Bakht
collection DOAJ
description Particulate matter (PM) of sizes less than 10 µm (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>P</mi><msub><mi>M</mi><mrow><mn>10</mn></mrow></msub></mrow></semantics></math></inline-formula>) and 2.5 µm (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>P</mi><msub><mi>M</mi><mrow><mn>2.5</mn></mrow></msub></mrow></semantics></math></inline-formula>) found in the environment is a major health concern. As PM is more prevalent in an enclosed environment, such as a subway station, this can have a negative impact on the health of commuters and staff. Therefore, it is essential to continuously monitor PM on underground subway platforms and control it using a subway ventilation control system. In order to operate the ventilation system in a predictive way, a credible prediction model for indoor air quality (IAQ) is proposed. While the existing deterministic methods require extensive calculations and domain knowledge, deep learning-based approaches showed good performance in recent studies. In this study, we develop an effective hybrid deep learning framework to forecast future <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>P</mi><msub><mi>M</mi><mrow><mn>10</mn></mrow></msub></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>P</mi><msub><mi>M</mi><mrow><mn>2.5</mn></mrow></msub></mrow></semantics></math></inline-formula> on a subway platform using past air quality data. This hybrid framework is an integration of several deep learning frameworks, namely, convolution neural network (CNN), long short-term memory (LSTM), and deep neural network (DNN), and is called hybrid CNN-LSTM-DNN; it has the characteristics to capture temporal patterns and informative characteristics from the indoor and outdoor air quality parameters compared with the standalone deep learning models. The effectiveness of the proposed <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>P</mi><msub><mi>M</mi><mrow><mn>10</mn></mrow></msub></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>P</mi><msub><mi>M</mi><mrow><mn>2.5</mn></mrow></msub></mrow></semantics></math></inline-formula> forecasting framework is demonstrated using comparisons with the different existing deep learning models.
first_indexed 2024-03-09T19:26:06Z
format Article
id doaj.art-a77679bb6d474bf797b9af2d17e2ae89
institution Directory Open Access Journal
issn 2305-6304
language English
last_indexed 2024-03-09T19:26:06Z
publishDate 2022-09-01
publisher MDPI AG
record_format Article
series Toxics
spelling doaj.art-a77679bb6d474bf797b9af2d17e2ae892023-11-24T02:57:00ZengMDPI AGToxics2305-63042022-09-01101055710.3390/toxics10100557Deep Learning-Based Indoor Air Quality Forecasting Framework for Indoor Subway Station PlatformsAhtesham Bakht0Shambhavi Sharma1Duckshin Park2Hyunsoo Lee3School of Industrial Engineering, Kumoh National Institute of Technology, Gumi 39177, KoreaTransportation System Engineering, University of Science and Technology (UST), Daejeon 34113, KoreaTransportation System Engineering, University of Science and Technology (UST), Daejeon 34113, KoreaSchool of Industrial Engineering, Kumoh National Institute of Technology, Gumi 39177, KoreaParticulate matter (PM) of sizes less than 10 µm (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>P</mi><msub><mi>M</mi><mrow><mn>10</mn></mrow></msub></mrow></semantics></math></inline-formula>) and 2.5 µm (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>P</mi><msub><mi>M</mi><mrow><mn>2.5</mn></mrow></msub></mrow></semantics></math></inline-formula>) found in the environment is a major health concern. As PM is more prevalent in an enclosed environment, such as a subway station, this can have a negative impact on the health of commuters and staff. Therefore, it is essential to continuously monitor PM on underground subway platforms and control it using a subway ventilation control system. In order to operate the ventilation system in a predictive way, a credible prediction model for indoor air quality (IAQ) is proposed. While the existing deterministic methods require extensive calculations and domain knowledge, deep learning-based approaches showed good performance in recent studies. In this study, we develop an effective hybrid deep learning framework to forecast future <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>P</mi><msub><mi>M</mi><mrow><mn>10</mn></mrow></msub></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>P</mi><msub><mi>M</mi><mrow><mn>2.5</mn></mrow></msub></mrow></semantics></math></inline-formula> on a subway platform using past air quality data. This hybrid framework is an integration of several deep learning frameworks, namely, convolution neural network (CNN), long short-term memory (LSTM), and deep neural network (DNN), and is called hybrid CNN-LSTM-DNN; it has the characteristics to capture temporal patterns and informative characteristics from the indoor and outdoor air quality parameters compared with the standalone deep learning models. The effectiveness of the proposed <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>P</mi><msub><mi>M</mi><mrow><mn>10</mn></mrow></msub></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>P</mi><msub><mi>M</mi><mrow><mn>2.5</mn></mrow></msub></mrow></semantics></math></inline-formula> forecasting framework is demonstrated using comparisons with the different existing deep learning models.https://www.mdpi.com/2305-6304/10/10/557particulate matterindoor subway stationdeep learninghybrid CNN-LSTMventilation control
spellingShingle Ahtesham Bakht
Shambhavi Sharma
Duckshin Park
Hyunsoo Lee
Deep Learning-Based Indoor Air Quality Forecasting Framework for Indoor Subway Station Platforms
Toxics
particulate matter
indoor subway station
deep learning
hybrid CNN-LSTM
ventilation control
title Deep Learning-Based Indoor Air Quality Forecasting Framework for Indoor Subway Station Platforms
title_full Deep Learning-Based Indoor Air Quality Forecasting Framework for Indoor Subway Station Platforms
title_fullStr Deep Learning-Based Indoor Air Quality Forecasting Framework for Indoor Subway Station Platforms
title_full_unstemmed Deep Learning-Based Indoor Air Quality Forecasting Framework for Indoor Subway Station Platforms
title_short Deep Learning-Based Indoor Air Quality Forecasting Framework for Indoor Subway Station Platforms
title_sort deep learning based indoor air quality forecasting framework for indoor subway station platforms
topic particulate matter
indoor subway station
deep learning
hybrid CNN-LSTM
ventilation control
url https://www.mdpi.com/2305-6304/10/10/557
work_keys_str_mv AT ahteshambakht deeplearningbasedindoorairqualityforecastingframeworkforindoorsubwaystationplatforms
AT shambhavisharma deeplearningbasedindoorairqualityforecastingframeworkforindoorsubwaystationplatforms
AT duckshinpark deeplearningbasedindoorairqualityforecastingframeworkforindoorsubwaystationplatforms
AT hyunsoolee deeplearningbasedindoorairqualityforecastingframeworkforindoorsubwaystationplatforms