Prediction of Residual Dye Using Machine Learning Algorithms for an Eco-Friendly Dyeing Process

Whan Lee; Hye Kyung Choi; Seyed Mohammad Mehdi Sajadieh; Sang Do Noh; Hyun Sik Son

doi:10.1007/978-3-031-43670-3_34

Prediction of Residual Dye Using Machine Learning Algorithms for an Eco-Friendly Dyeing Process

Whan Lee
, Hye Kyung Choi
, Seyed Mohammad Mehdi Sajadieh
, Sang Do Noh
, Hyun Sik Son

Department of Systems Management Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

The manufacturing industry should prioritize carbon neutrality and eco-friendly processes owing to the environmental problems caused by the increase in the carbon footprint and waste resulting from the growing population and rapid industrial development. The dyeing industry generates a significant amount of waste and energy loss, resulting in notable environmental pollution. Therefore, process-optimization is essential for predicting and minimizing the amount of residual dye after the dyeing process and reducing the energy loss to promote eco-friendly operations. This study presents a regression model based on an artificial intelligence (AI) algorithm to achieve high forecasting accuracy for predicting the amount of residual dye. The following three tree-based machine learning models were employed to construct the prediction model: decision tree(DT), random forest(RF), and gradient boosting (GB). The performance of the model was evaluated using performance indicators, and GB (R 2 = 0.95) was selected as the optimal prediction model. This study demonstrates the potential of AI algorithms for achieving high forecasting accuracy in predicting the amount of residual dye in the manufacturing industry, particularly in the dyeing industry. The selected prediction model showcases its ability to accurately forecast the amount of residual dye. These findings highlight the importance of eco-friendly processes and suggest promoting eco-friendly practices in the dyeing industry, reducing waste and environmental pollution.

Original language	English
Title of host publication	Advances in Production Management Systems. Production Management Systems for Responsible Manufacturing, Service, and Logistics Futures - IFIP WG 5.7 International Conference, APMS 2023, Proceedings
Editors	Erlend Alfnes, Anita Romsdal, Jan Ola Strandhagen, Gregor von Cieminski, David Romero
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	491-505
Number of pages	15
ISBN (Print)	9783031436697
DOIs	https://doi.org/10.1007/978-3-031-43670-3_34
State	Published - 2023
Event	IFIP WG 5.7 International Conference on Advances in Production Management Systems, APMS 2023 - Trondheim, Norway Duration: 17 Sep 2023 → 21 Sep 2023

Publication series

Name	IFIP Advances in Information and Communication Technology
Volume	691 AICT
ISSN (Print)	1868-4238
ISSN (Electronic)	1868-422X

Conference

Conference	IFIP WG 5.7 International Conference on Advances in Production Management Systems, APMS 2023
Country/Territory	Norway
City	Trondheim
Period	17/09/23 → 21/09/23

UN SDGs

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

SDG 9 Industry, Innovation, and Infrastructure
SDG 12 Responsible Consumption and Production
SDG 13 Climate Action

Keywords

Artificial Intelligence
Dyeing Process
Green Manufacturing
Machine Learning

Access to Document

10.1007/978-3-031-43670-3_34

Cite this

Lee, W., Choi, H. K., Sajadieh, S. M. M., Do Noh, S., & Son, H. S. (2023). Prediction of Residual Dye Using Machine Learning Algorithms for an Eco-Friendly Dyeing Process. In E. Alfnes, A. Romsdal, J. O. Strandhagen, G. von Cieminski, & D. Romero (Eds.), Advances in Production Management Systems. Production Management Systems for Responsible Manufacturing, Service, and Logistics Futures - IFIP WG 5.7 International Conference, APMS 2023, Proceedings (pp. 491-505). (IFIP Advances in Information and Communication Technology; Vol. 691 AICT). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-43670-3_34

Lee, Whan ; Choi, Hye Kyung ; Sajadieh, Seyed Mohammad Mehdi et al. / Prediction of Residual Dye Using Machine Learning Algorithms for an Eco-Friendly Dyeing Process. Advances in Production Management Systems. Production Management Systems for Responsible Manufacturing, Service, and Logistics Futures - IFIP WG 5.7 International Conference, APMS 2023, Proceedings. editor / Erlend Alfnes ; Anita Romsdal ; Jan Ola Strandhagen ; Gregor von Cieminski ; David Romero. Springer Science and Business Media Deutschland GmbH, 2023. pp. 491-505 (IFIP Advances in Information and Communication Technology).

@inproceedings{03af492f9df74266ae8375ad59b60ea6,

title = "Prediction of Residual Dye Using Machine Learning Algorithms for an Eco-Friendly Dyeing Process",

abstract = "The manufacturing industry should prioritize carbon neutrality and eco-friendly processes owing to the environmental problems caused by the increase in the carbon footprint and waste resulting from the growing population and rapid industrial development. The dyeing industry generates a significant amount of waste and energy loss, resulting in notable environmental pollution. Therefore, process-optimization is essential for predicting and minimizing the amount of residual dye after the dyeing process and reducing the energy loss to promote eco-friendly operations. This study presents a regression model based on an artificial intelligence (AI) algorithm to achieve high forecasting accuracy for predicting the amount of residual dye. The following three tree-based machine learning models were employed to construct the prediction model: decision tree(DT), random forest(RF), and gradient boosting (GB). The performance of the model was evaluated using performance indicators, and GB (R 2 = 0.95) was selected as the optimal prediction model. This study demonstrates the potential of AI algorithms for achieving high forecasting accuracy in predicting the amount of residual dye in the manufacturing industry, particularly in the dyeing industry. The selected prediction model showcases its ability to accurately forecast the amount of residual dye. These findings highlight the importance of eco-friendly processes and suggest promoting eco-friendly practices in the dyeing industry, reducing waste and environmental pollution.",

keywords = "Artificial Intelligence, Dyeing Process, Green Manufacturing, Machine Learning",

author = "Whan Lee and Choi, \{Hye Kyung\} and Sajadieh, \{Seyed Mohammad Mehdi\} and \{Do Noh\}, Sang and Son, \{Hyun Sik\}",

note = "Publisher Copyright: {\textcopyright} 2023, IFIP International Federation for Information Processing.; IFIP WG 5.7 International Conference on Advances in Production Management Systems, APMS 2023 ; Conference date: 17-09-2023 Through 21-09-2023",

year = "2023",

doi = "10.1007/978-3-031-43670-3\_34",

language = "English",

isbn = "9783031436697",

series = "IFIP Advances in Information and Communication Technology",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "491--505",

editor = "Erlend Alfnes and Anita Romsdal and Strandhagen, \{Jan Ola\} and \{von Cieminski\}, Gregor and David Romero",

booktitle = "Advances in Production Management Systems. Production Management Systems for Responsible Manufacturing, Service, and Logistics Futures - IFIP WG 5.7 International Conference, APMS 2023, Proceedings",

}

Lee, W, Choi, HK, Sajadieh, SMM, Do Noh, S & Son, HS 2023, Prediction of Residual Dye Using Machine Learning Algorithms for an Eco-Friendly Dyeing Process. in E Alfnes, A Romsdal, JO Strandhagen, G von Cieminski & D Romero (eds), Advances in Production Management Systems. Production Management Systems for Responsible Manufacturing, Service, and Logistics Futures - IFIP WG 5.7 International Conference, APMS 2023, Proceedings. IFIP Advances in Information and Communication Technology, vol. 691 AICT, Springer Science and Business Media Deutschland GmbH, pp. 491-505, IFIP WG 5.7 International Conference on Advances in Production Management Systems, APMS 2023, Trondheim, Norway, 17/09/23. https://doi.org/10.1007/978-3-031-43670-3_34

Prediction of Residual Dye Using Machine Learning Algorithms for an Eco-Friendly Dyeing Process. / Lee, Whan; Choi, Hye Kyung; Sajadieh, Seyed Mohammad Mehdi et al.
Advances in Production Management Systems. Production Management Systems for Responsible Manufacturing, Service, and Logistics Futures - IFIP WG 5.7 International Conference, APMS 2023, Proceedings. ed. / Erlend Alfnes; Anita Romsdal; Jan Ola Strandhagen; Gregor von Cieminski; David Romero. Springer Science and Business Media Deutschland GmbH, 2023. p. 491-505 (IFIP Advances in Information and Communication Technology; Vol. 691 AICT).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Prediction of Residual Dye Using Machine Learning Algorithms for an Eco-Friendly Dyeing Process

AU - Lee, Whan

AU - Choi, Hye Kyung

AU - Sajadieh, Seyed Mohammad Mehdi

AU - Do Noh, Sang

AU - Son, Hyun Sik

PY - 2023

Y1 - 2023

N2 - The manufacturing industry should prioritize carbon neutrality and eco-friendly processes owing to the environmental problems caused by the increase in the carbon footprint and waste resulting from the growing population and rapid industrial development. The dyeing industry generates a significant amount of waste and energy loss, resulting in notable environmental pollution. Therefore, process-optimization is essential for predicting and minimizing the amount of residual dye after the dyeing process and reducing the energy loss to promote eco-friendly operations. This study presents a regression model based on an artificial intelligence (AI) algorithm to achieve high forecasting accuracy for predicting the amount of residual dye. The following three tree-based machine learning models were employed to construct the prediction model: decision tree(DT), random forest(RF), and gradient boosting (GB). The performance of the model was evaluated using performance indicators, and GB (R 2 = 0.95) was selected as the optimal prediction model. This study demonstrates the potential of AI algorithms for achieving high forecasting accuracy in predicting the amount of residual dye in the manufacturing industry, particularly in the dyeing industry. The selected prediction model showcases its ability to accurately forecast the amount of residual dye. These findings highlight the importance of eco-friendly processes and suggest promoting eco-friendly practices in the dyeing industry, reducing waste and environmental pollution.

AB - The manufacturing industry should prioritize carbon neutrality and eco-friendly processes owing to the environmental problems caused by the increase in the carbon footprint and waste resulting from the growing population and rapid industrial development. The dyeing industry generates a significant amount of waste and energy loss, resulting in notable environmental pollution. Therefore, process-optimization is essential for predicting and minimizing the amount of residual dye after the dyeing process and reducing the energy loss to promote eco-friendly operations. This study presents a regression model based on an artificial intelligence (AI) algorithm to achieve high forecasting accuracy for predicting the amount of residual dye. The following three tree-based machine learning models were employed to construct the prediction model: decision tree(DT), random forest(RF), and gradient boosting (GB). The performance of the model was evaluated using performance indicators, and GB (R 2 = 0.95) was selected as the optimal prediction model. This study demonstrates the potential of AI algorithms for achieving high forecasting accuracy in predicting the amount of residual dye in the manufacturing industry, particularly in the dyeing industry. The selected prediction model showcases its ability to accurately forecast the amount of residual dye. These findings highlight the importance of eco-friendly processes and suggest promoting eco-friendly practices in the dyeing industry, reducing waste and environmental pollution.

KW - Artificial Intelligence

KW - Dyeing Process

KW - Green Manufacturing

KW - Machine Learning

UR - https://www.scopus.com/pages/publications/85174444335

U2 - 10.1007/978-3-031-43670-3_34

DO - 10.1007/978-3-031-43670-3_34

M3 - Conference contribution

AN - SCOPUS:85174444335

SN - 9783031436697

T3 - IFIP Advances in Information and Communication Technology

SP - 491

EP - 505

BT - Advances in Production Management Systems. Production Management Systems for Responsible Manufacturing, Service, and Logistics Futures - IFIP WG 5.7 International Conference, APMS 2023, Proceedings

A2 - Alfnes, Erlend

A2 - Romsdal, Anita

A2 - Strandhagen, Jan Ola

A2 - von Cieminski, Gregor

A2 - Romero, David

PB - Springer Science and Business Media Deutschland GmbH

T2 - IFIP WG 5.7 International Conference on Advances in Production Management Systems, APMS 2023

Y2 - 17 September 2023 through 21 September 2023

ER -

Lee W, Choi HK, Sajadieh SMM, Do Noh S, Son HS. Prediction of Residual Dye Using Machine Learning Algorithms for an Eco-Friendly Dyeing Process. In Alfnes E, Romsdal A, Strandhagen JO, von Cieminski G, Romero D, editors, Advances in Production Management Systems. Production Management Systems for Responsible Manufacturing, Service, and Logistics Futures - IFIP WG 5.7 International Conference, APMS 2023, Proceedings. Springer Science and Business Media Deutschland GmbH. 2023. p. 491-505. (IFIP Advances in Information and Communication Technology). doi: 10.1007/978-3-031-43670-3_34

Prediction of Residual Dye Using Machine Learning Algorithms for an Eco-Friendly Dyeing Process

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this