AiCareAir: Hybrid-Ensemble Internet-of-Things Sensing Unit Model for Air Pollutant Control
The detrimental effects on human health caused by air pollution show that being able to predict air quality is a task of utmost significance. The application of artificial intelligence (AI) and the Internet of Things (IoT) is seen as promising in this domain. The performances of state-of-the-art mod...
Gespeichert in:
Veröffentlicht in: | IEEE sensors journal 2024-07, Vol.24 (13), p.21558-21565 |
---|---|
Hauptverfasser: | , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 21565 |
---|---|
container_issue | 13 |
container_start_page | 21558 |
container_title | IEEE sensors journal |
container_volume | 24 |
creator | Borah, Jintu Mohd. Nadzir, Mohd. Shahrul Cayetano, Mylene G. Majumdar, Shubhankar Ghayvat, Hemant Srivastava, Gautam |
description | The detrimental effects on human health caused by air pollution show that being able to predict air quality is a task of utmost significance. The application of artificial intelligence (AI) and the Internet of Things (IoT) is seen as promising in this domain. The performances of state-of-the-art models in terms of prediction accuracy vary with different pollutants and are acceptable only for certain pollutants. This article uses machine learning (ML) and deep learning (DL) models to predict the concentrations of six major air pollutants. Data are collected over eight months with 1400 daily instances from sensors deployed in Kuala Lumpur, Malaysia. As an intelligibly robust system, in this article a hybrid-ensemble model is proposed using a combination of ML models, specifically random forest, K-nearest neighbor (KNN), extreme gradient boosting (XGBoost), and neural network (NN) models, namely, long short-term memory (LSTM), gated recurrent units (GRUs), and convolutional NNs (CNNs). Here, a hybrid-ensemble learning model is created using five various ML models as weak learners. In previous ensemble models, a homogeneous group of weak learners are used; however, this work uses a heterogeneous group of weak learners. The prediction accuracy is compared using R2 score, absolute, squared, and root-mean-squared errors (RMSEs). |
doi_str_mv | 10.1109/JSEN.2024.3397735 |
format | Article |
fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_10529960</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10529960</ieee_id><sourcerecordid>3073299104</sourcerecordid><originalsourceid>FETCH-LOGICAL-c284t-efcd8f4736534c585bd798b70d4cef4aeee162bf6d5696ae567d4ac511ce02a43</originalsourceid><addsrcrecordid>eNpNkF1LwzAUhosoOD9-gOBFwOvMpEma1rsxp07mB2wT8Sak7enMqMlMWmT_3pYN8eq8F8_7cHij6IKSIaUku36cT56HMYn5kLFMSiYOogEVIsVU8vSwz4xgzuT7cXQSwpoQmkkhB9HHyIy1h5HxN-hhm3tT4okN8JXXgKa2AW-hwa7Ci09jVwHNwYYuoKU1DXpyJdSoch51dfTq6rpttG3Q2NnGu_osOqp0HeB8f0-j5d1kMX7As5f76Xg0w0Wc8gZDVZRpxSVLBOOFSEVeyizNJSl5ARXXAECTOK-SUiRZokEksuS6EJQWQGLN2WmEd97wA5s2VxtvvrTfKqeNujVvI-X8StW2VZTFRJCOv9rxG---WwiNWrvW2-5FxYhkcZZR0lvpjiq8C8FD9eelRPWTq35y1U-u9pN3nctdx3RP_-NF50wI-wVFv32S</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3073299104</pqid></control><display><type>article</type><title>AiCareAir: Hybrid-Ensemble Internet-of-Things Sensing Unit Model for Air Pollutant Control</title><source>IEEE Electronic Library (IEL)</source><creator>Borah, Jintu ; Mohd. Nadzir, Mohd. Shahrul ; Cayetano, Mylene G. ; Majumdar, Shubhankar ; Ghayvat, Hemant ; Srivastava, Gautam</creator><creatorcontrib>Borah, Jintu ; Mohd. Nadzir, Mohd. Shahrul ; Cayetano, Mylene G. ; Majumdar, Shubhankar ; Ghayvat, Hemant ; Srivastava, Gautam</creatorcontrib><description>The detrimental effects on human health caused by air pollution show that being able to predict air quality is a task of utmost significance. The application of artificial intelligence (AI) and the Internet of Things (IoT) is seen as promising in this domain. The performances of state-of-the-art models in terms of prediction accuracy vary with different pollutants and are acceptable only for certain pollutants. This article uses machine learning (ML) and deep learning (DL) models to predict the concentrations of six major air pollutants. Data are collected over eight months with 1400 daily instances from sensors deployed in Kuala Lumpur, Malaysia. As an intelligibly robust system, in this article a hybrid-ensemble model is proposed using a combination of ML models, specifically random forest, K-nearest neighbor (KNN), extreme gradient boosting (XGBoost), and neural network (NN) models, namely, long short-term memory (LSTM), gated recurrent units (GRUs), and convolutional NNs (CNNs). Here, a hybrid-ensemble learning model is created using five various ML models as weak learners. In previous ensemble models, a homogeneous group of weak learners are used; however, this work uses a heterogeneous group of weak learners. The prediction accuracy is compared using <inline-formula> <tex-math notation="LaTeX">R2 </tex-math></inline-formula> score, absolute, squared, and root-mean-squared errors (RMSEs).</description><identifier>ISSN: 1530-437X</identifier><identifier>ISSN: 1558-1748</identifier><identifier>EISSN: 1558-1748</identifier><identifier>DOI: 10.1109/JSEN.2024.3397735</identifier><identifier>CODEN: ISJEAZ</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Accuracy ; Adam optimizer ; Air pollution ; Air quality ; Artificial intelligence ; Atmospheric modeling ; Computer Science ; Convolutional neural networks ; convolutional neural networks (CNNs) ; Datavetenskap ; Deep learning ; Ensemble learning ; gated recurrent units (GRUs) ; Internet of Things ; Keras API ; Long short term memory ; long short-term memory (LSTM) ; Machine learning ; Outdoor air quality ; Pollutants ; Pollution measurement ; Predictive models ; Scikit learn ; Sensors</subject><ispartof>IEEE sensors journal, 2024-07, Vol.24 (13), p.21558-21565</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c284t-efcd8f4736534c585bd798b70d4cef4aeee162bf6d5696ae567d4ac511ce02a43</cites><orcidid>0000-0001-9851-4103 ; 0000-0002-3703-4904 ; 0000-0002-1166-9397 ; 0000-0002-5491-0216</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10529960$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>230,314,780,784,796,885,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10529960$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-132050$$DView record from Swedish Publication Index$$Hfree_for_read</backlink></links><search><creatorcontrib>Borah, Jintu</creatorcontrib><creatorcontrib>Mohd. Nadzir, Mohd. Shahrul</creatorcontrib><creatorcontrib>Cayetano, Mylene G.</creatorcontrib><creatorcontrib>Majumdar, Shubhankar</creatorcontrib><creatorcontrib>Ghayvat, Hemant</creatorcontrib><creatorcontrib>Srivastava, Gautam</creatorcontrib><title>AiCareAir: Hybrid-Ensemble Internet-of-Things Sensing Unit Model for Air Pollutant Control</title><title>IEEE sensors journal</title><addtitle>JSEN</addtitle><description>The detrimental effects on human health caused by air pollution show that being able to predict air quality is a task of utmost significance. The application of artificial intelligence (AI) and the Internet of Things (IoT) is seen as promising in this domain. The performances of state-of-the-art models in terms of prediction accuracy vary with different pollutants and are acceptable only for certain pollutants. This article uses machine learning (ML) and deep learning (DL) models to predict the concentrations of six major air pollutants. Data are collected over eight months with 1400 daily instances from sensors deployed in Kuala Lumpur, Malaysia. As an intelligibly robust system, in this article a hybrid-ensemble model is proposed using a combination of ML models, specifically random forest, K-nearest neighbor (KNN), extreme gradient boosting (XGBoost), and neural network (NN) models, namely, long short-term memory (LSTM), gated recurrent units (GRUs), and convolutional NNs (CNNs). Here, a hybrid-ensemble learning model is created using five various ML models as weak learners. In previous ensemble models, a homogeneous group of weak learners are used; however, this work uses a heterogeneous group of weak learners. The prediction accuracy is compared using <inline-formula> <tex-math notation="LaTeX">R2 </tex-math></inline-formula> score, absolute, squared, and root-mean-squared errors (RMSEs).</description><subject>Accuracy</subject><subject>Adam optimizer</subject><subject>Air pollution</subject><subject>Air quality</subject><subject>Artificial intelligence</subject><subject>Atmospheric modeling</subject><subject>Computer Science</subject><subject>Convolutional neural networks</subject><subject>convolutional neural networks (CNNs)</subject><subject>Datavetenskap</subject><subject>Deep learning</subject><subject>Ensemble learning</subject><subject>gated recurrent units (GRUs)</subject><subject>Internet of Things</subject><subject>Keras API</subject><subject>Long short term memory</subject><subject>long short-term memory (LSTM)</subject><subject>Machine learning</subject><subject>Outdoor air quality</subject><subject>Pollutants</subject><subject>Pollution measurement</subject><subject>Predictive models</subject><subject>Scikit learn</subject><subject>Sensors</subject><issn>1530-437X</issn><issn>1558-1748</issn><issn>1558-1748</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkF1LwzAUhosoOD9-gOBFwOvMpEma1rsxp07mB2wT8Sak7enMqMlMWmT_3pYN8eq8F8_7cHij6IKSIaUku36cT56HMYn5kLFMSiYOogEVIsVU8vSwz4xgzuT7cXQSwpoQmkkhB9HHyIy1h5HxN-hhm3tT4okN8JXXgKa2AW-hwa7Ci09jVwHNwYYuoKU1DXpyJdSoch51dfTq6rpttG3Q2NnGu_osOqp0HeB8f0-j5d1kMX7As5f76Xg0w0Wc8gZDVZRpxSVLBOOFSEVeyizNJSl5ARXXAECTOK-SUiRZokEksuS6EJQWQGLN2WmEd97wA5s2VxtvvrTfKqeNujVvI-X8StW2VZTFRJCOv9rxG---WwiNWrvW2-5FxYhkcZZR0lvpjiq8C8FD9eelRPWTq35y1U-u9pN3nctdx3RP_-NF50wI-wVFv32S</recordid><startdate>20240701</startdate><enddate>20240701</enddate><creator>Borah, Jintu</creator><creator>Mohd. Nadzir, Mohd. Shahrul</creator><creator>Cayetano, Mylene G.</creator><creator>Majumdar, Shubhankar</creator><creator>Ghayvat, Hemant</creator><creator>Srivastava, Gautam</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>7U5</scope><scope>8FD</scope><scope>L7M</scope><scope>ADTPV</scope><scope>AOWAS</scope><scope>D92</scope><orcidid>https://orcid.org/0000-0001-9851-4103</orcidid><orcidid>https://orcid.org/0000-0002-3703-4904</orcidid><orcidid>https://orcid.org/0000-0002-1166-9397</orcidid><orcidid>https://orcid.org/0000-0002-5491-0216</orcidid></search><sort><creationdate>20240701</creationdate><title>AiCareAir: Hybrid-Ensemble Internet-of-Things Sensing Unit Model for Air Pollutant Control</title><author>Borah, Jintu ; Mohd. Nadzir, Mohd. Shahrul ; Cayetano, Mylene G. ; Majumdar, Shubhankar ; Ghayvat, Hemant ; Srivastava, Gautam</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c284t-efcd8f4736534c585bd798b70d4cef4aeee162bf6d5696ae567d4ac511ce02a43</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accuracy</topic><topic>Adam optimizer</topic><topic>Air pollution</topic><topic>Air quality</topic><topic>Artificial intelligence</topic><topic>Atmospheric modeling</topic><topic>Computer Science</topic><topic>Convolutional neural networks</topic><topic>convolutional neural networks (CNNs)</topic><topic>Datavetenskap</topic><topic>Deep learning</topic><topic>Ensemble learning</topic><topic>gated recurrent units (GRUs)</topic><topic>Internet of Things</topic><topic>Keras API</topic><topic>Long short term memory</topic><topic>long short-term memory (LSTM)</topic><topic>Machine learning</topic><topic>Outdoor air quality</topic><topic>Pollutants</topic><topic>Pollution measurement</topic><topic>Predictive models</topic><topic>Scikit learn</topic><topic>Sensors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Borah, Jintu</creatorcontrib><creatorcontrib>Mohd. Nadzir, Mohd. Shahrul</creatorcontrib><creatorcontrib>Cayetano, Mylene G.</creatorcontrib><creatorcontrib>Majumdar, Shubhankar</creatorcontrib><creatorcontrib>Ghayvat, Hemant</creatorcontrib><creatorcontrib>Srivastava, Gautam</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>SwePub</collection><collection>SwePub Articles</collection><collection>SWEPUB Linnéuniversitetet</collection><jtitle>IEEE sensors journal</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Borah, Jintu</au><au>Mohd. Nadzir, Mohd. Shahrul</au><au>Cayetano, Mylene G.</au><au>Majumdar, Shubhankar</au><au>Ghayvat, Hemant</au><au>Srivastava, Gautam</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>AiCareAir: Hybrid-Ensemble Internet-of-Things Sensing Unit Model for Air Pollutant Control</atitle><jtitle>IEEE sensors journal</jtitle><stitle>JSEN</stitle><date>2024-07-01</date><risdate>2024</risdate><volume>24</volume><issue>13</issue><spage>21558</spage><epage>21565</epage><pages>21558-21565</pages><issn>1530-437X</issn><issn>1558-1748</issn><eissn>1558-1748</eissn><coden>ISJEAZ</coden><abstract>The detrimental effects on human health caused by air pollution show that being able to predict air quality is a task of utmost significance. The application of artificial intelligence (AI) and the Internet of Things (IoT) is seen as promising in this domain. The performances of state-of-the-art models in terms of prediction accuracy vary with different pollutants and are acceptable only for certain pollutants. This article uses machine learning (ML) and deep learning (DL) models to predict the concentrations of six major air pollutants. Data are collected over eight months with 1400 daily instances from sensors deployed in Kuala Lumpur, Malaysia. As an intelligibly robust system, in this article a hybrid-ensemble model is proposed using a combination of ML models, specifically random forest, K-nearest neighbor (KNN), extreme gradient boosting (XGBoost), and neural network (NN) models, namely, long short-term memory (LSTM), gated recurrent units (GRUs), and convolutional NNs (CNNs). Here, a hybrid-ensemble learning model is created using five various ML models as weak learners. In previous ensemble models, a homogeneous group of weak learners are used; however, this work uses a heterogeneous group of weak learners. The prediction accuracy is compared using <inline-formula> <tex-math notation="LaTeX">R2 </tex-math></inline-formula> score, absolute, squared, and root-mean-squared errors (RMSEs).</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/JSEN.2024.3397735</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0001-9851-4103</orcidid><orcidid>https://orcid.org/0000-0002-3703-4904</orcidid><orcidid>https://orcid.org/0000-0002-1166-9397</orcidid><orcidid>https://orcid.org/0000-0002-5491-0216</orcidid></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 1530-437X |
ispartof | IEEE sensors journal, 2024-07, Vol.24 (13), p.21558-21565 |
issn | 1530-437X 1558-1748 1558-1748 |
language | eng |
recordid | cdi_ieee_primary_10529960 |
source | IEEE Electronic Library (IEL) |
subjects | Accuracy Adam optimizer Air pollution Air quality Artificial intelligence Atmospheric modeling Computer Science Convolutional neural networks convolutional neural networks (CNNs) Datavetenskap Deep learning Ensemble learning gated recurrent units (GRUs) Internet of Things Keras API Long short term memory long short-term memory (LSTM) Machine learning Outdoor air quality Pollutants Pollution measurement Predictive models Scikit learn Sensors |
title | AiCareAir: Hybrid-Ensemble Internet-of-Things Sensing Unit Model for Air Pollutant Control |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T16%3A01%3A31IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=AiCareAir:%20Hybrid-Ensemble%20Internet-of-Things%20Sensing%20Unit%20Model%20for%20Air%20Pollutant%20Control&rft.jtitle=IEEE%20sensors%20journal&rft.au=Borah,%20Jintu&rft.date=2024-07-01&rft.volume=24&rft.issue=13&rft.spage=21558&rft.epage=21565&rft.pages=21558-21565&rft.issn=1530-437X&rft.eissn=1558-1748&rft.coden=ISJEAZ&rft_id=info:doi/10.1109/JSEN.2024.3397735&rft_dat=%3Cproquest_RIE%3E3073299104%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3073299104&rft_id=info:pmid/&rft_ieee_id=10529960&rfr_iscdi=true |