Particulate Matter Concentration Estimation from Images Based on Convolutional Neural Network

Anju S. Mohan; Lizy Abraham

doi:10.1007/978-981-19-7513-4_5

Particulate Matter Concentration Estimation from Images Based on Convolutional Neural Network

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Abstract

Air pollution is a critical environmental issue that causes severe health risks. Accurate estimation of air pollutants can facilitate air pollution control and alert the public. PM_2.5 (particulate matter with diameters less than 2.5 μm) is hazardous, and its estimation requires high-cost sensors. This paper proposes an image-based PM_2.5 estimation model, a low-cost alternative. The proposed method is a convolutional neural network (CNN) architecture for estimating PM_2.5 concentration from images. The experiments conducted on the Beijing dataset show promising results, and therefore our proposed image-based CNN model can be used to estimate PM_2.5 concentrations.

Original language	English
Title of host publication	Evolution in Computational Intelligence - Proceedings of the 10th International Conference on Frontiers in Intelligent Computing
Subtitle of host publication	Theory and Applications, FICTA 2022
Editors	Vikrant Bhateja, Xin-She Yang, Jerry Chun-Wei Lin, Ranjita Das
Publisher	Springer
Pages	49-59
Number of pages	11
ISBN (Print)	9789811975127
DOIs	https://doi.org/10.1007/978-981-19-7513-4_5
Publication status	Published - 26 Apr 2023
Externally published	Yes
Event	10th International Conference on Frontiers in Intelligent Computing: Theory and Applications, FICTA 2022 - Aizawl, India Duration: 18 Jun 2022 → 19 Jun 2022

Publication series

Name	Smart Innovation, Systems and Technologies
Volume	326 SIST
ISSN (Print)	2190-3018
ISSN (Electronic)	2190-3026

Conference

Conference	10th International Conference on Frontiers in Intelligent Computing: Theory and Applications, FICTA 2022
Country/Territory	India
City	Aizawl
Period	18/06/2022 → 19/06/2022

Keywords

Air quality
Convolutional neural network
Deep learning
Image analysis
Particulate matter
PM estimation

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-981-19-7513-4_5

Cite this

Mohan, A. S., & Abraham, L. (2023). Particulate Matter Concentration Estimation from Images Based on Convolutional Neural Network. In V. Bhateja, X.-S. Yang, J. C.-W. Lin, & R. Das (Eds.), Evolution in Computational Intelligence - Proceedings of the 10th International Conference on Frontiers in Intelligent Computing: Theory and Applications, FICTA 2022 (pp. 49-59). (Smart Innovation, Systems and Technologies; Vol. 326 SIST). Springer. https://doi.org/10.1007/978-981-19-7513-4_5

Mohan, Anju S. ; Abraham, Lizy. / Particulate Matter Concentration Estimation from Images Based on Convolutional Neural Network. Evolution in Computational Intelligence - Proceedings of the 10th International Conference on Frontiers in Intelligent Computing: Theory and Applications, FICTA 2022. editor / Vikrant Bhateja ; Xin-She Yang ; Jerry Chun-Wei Lin ; Ranjita Das. Springer, 2023. pp. 49-59 (Smart Innovation, Systems and Technologies).

@inbook{fd2164363a9a457fae9275da1fb9af14,

title = "Particulate Matter Concentration Estimation from Images Based on Convolutional Neural Network",

abstract = "Air pollution is a critical environmental issue that causes severe health risks. Accurate estimation of air pollutants can facilitate air pollution control and alert the public. PM2.5 (particulate matter with diameters less than 2.5 μm) is hazardous, and its estimation requires high-cost sensors. This paper proposes an image-based PM2.5 estimation model, a low-cost alternative. The proposed method is a convolutional neural network (CNN) architecture for estimating PM2.5 concentration from images. The experiments conducted on the Beijing dataset show promising results, and therefore our proposed image-based CNN model can be used to estimate PM2.5 concentrations.",

keywords = "Air quality, Convolutional neural network, Deep learning, Image analysis, Particulate matter, PM estimation",

author = "Mohan, {Anju S.} and Lizy Abraham",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 10th International Conference on Frontiers in Intelligent Computing: Theory and Applications, FICTA 2022 ; Conference date: 18-06-2022 Through 19-06-2022",

year = "2023",

month = apr,

day = "26",

doi = "10.1007/978-981-19-7513-4_5",

language = "English",

isbn = "9789811975127",

series = "Smart Innovation, Systems and Technologies",

publisher = "Springer",

pages = "49--59",

editor = "Vikrant Bhateja and Xin-She Yang and Lin, {Jerry Chun-Wei} and Ranjita Das",

booktitle = "Evolution in Computational Intelligence - Proceedings of the 10th International Conference on Frontiers in Intelligent Computing",

address = "United States",

}

Mohan, AS & Abraham, L 2023, Particulate Matter Concentration Estimation from Images Based on Convolutional Neural Network. in V Bhateja, X-S Yang, JC-W Lin & R Das (eds), Evolution in Computational Intelligence - Proceedings of the 10th International Conference on Frontiers in Intelligent Computing: Theory and Applications, FICTA 2022. Smart Innovation, Systems and Technologies, vol. 326 SIST, Springer, pp. 49-59, 10th International Conference on Frontiers in Intelligent Computing: Theory and Applications, FICTA 2022, Aizawl, India, 18/06/2022. https://doi.org/10.1007/978-981-19-7513-4_5

Particulate Matter Concentration Estimation from Images Based on Convolutional Neural Network. / Mohan, Anju S.; Abraham, Lizy.
Evolution in Computational Intelligence - Proceedings of the 10th International Conference on Frontiers in Intelligent Computing: Theory and Applications, FICTA 2022. ed. / Vikrant Bhateja; Xin-She Yang; Jerry Chun-Wei Lin; Ranjita Das. Springer, 2023. p. 49-59 (Smart Innovation, Systems and Technologies; Vol. 326 SIST).

Research output: Chapter in Book/Report/Conference proceeding › Chapter

TY - CHAP

T1 - Particulate Matter Concentration Estimation from Images Based on Convolutional Neural Network

AU - Mohan, Anju S.

AU - Abraham, Lizy

PY - 2023/4/26

Y1 - 2023/4/26

N2 - Air pollution is a critical environmental issue that causes severe health risks. Accurate estimation of air pollutants can facilitate air pollution control and alert the public. PM2.5 (particulate matter with diameters less than 2.5 μm) is hazardous, and its estimation requires high-cost sensors. This paper proposes an image-based PM2.5 estimation model, a low-cost alternative. The proposed method is a convolutional neural network (CNN) architecture for estimating PM2.5 concentration from images. The experiments conducted on the Beijing dataset show promising results, and therefore our proposed image-based CNN model can be used to estimate PM2.5 concentrations.

AB - Air pollution is a critical environmental issue that causes severe health risks. Accurate estimation of air pollutants can facilitate air pollution control and alert the public. PM2.5 (particulate matter with diameters less than 2.5 μm) is hazardous, and its estimation requires high-cost sensors. This paper proposes an image-based PM2.5 estimation model, a low-cost alternative. The proposed method is a convolutional neural network (CNN) architecture for estimating PM2.5 concentration from images. The experiments conducted on the Beijing dataset show promising results, and therefore our proposed image-based CNN model can be used to estimate PM2.5 concentrations.

KW - Air quality

KW - Convolutional neural network

KW - Deep learning

KW - Image analysis

KW - Particulate matter

KW - PM estimation

UR - http://www.scopus.com/inward/record.url?scp=85161453320&partnerID=8YFLogxK

U2 - 10.1007/978-981-19-7513-4_5

DO - 10.1007/978-981-19-7513-4_5

M3 - Chapter

AN - SCOPUS:85161453320

SN - 9789811975127

T3 - Smart Innovation, Systems and Technologies

SP - 49

EP - 59

BT - Evolution in Computational Intelligence - Proceedings of the 10th International Conference on Frontiers in Intelligent Computing

A2 - Bhateja, Vikrant

A2 - Yang, Xin-She

A2 - Lin, Jerry Chun-Wei

A2 - Das, Ranjita

PB - Springer

T2 - 10th International Conference on Frontiers in Intelligent Computing: Theory and Applications, FICTA 2022

Y2 - 18 June 2022 through 19 June 2022

ER -

Mohan AS, Abraham L. Particulate Matter Concentration Estimation from Images Based on Convolutional Neural Network. In Bhateja V, Yang XS, Lin JCW, Das R, editors, Evolution in Computational Intelligence - Proceedings of the 10th International Conference on Frontiers in Intelligent Computing: Theory and Applications, FICTA 2022. Springer. 2023. p. 49-59. (Smart Innovation, Systems and Technologies). doi: 10.1007/978-981-19-7513-4_5

Particulate Matter Concentration Estimation from Images Based on Convolutional Neural Network

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this