Cover Image

Optimization and design of machine learning computational technique for prediction of physical separation process

Machine learning (ML) methods were developed and optimized for description and understanding a physical separation process. Indeed, this work indicates application of machine learning technique for a real physical system and optimization of process parameters to achieve the target. A bunch of datase...

Full description

Saved in:
Bibliographic Details
Main Authors: Haiqing Li, Chairun Nasirin, Azher M. Abed, Dmitry Olegovich Bokov, Lakshmi Thangavelu, Haydar Abdulameer Marhoon, Md Lutfor Rahman
Format: Article
Language:English
English
Published: Elsevier B.V 2022
Subjects:
T57.6-57.97 Operations research. Systems analysis
Online Access:https://eprints.ums.edu.my/id/eprint/32773/1/Optimization%20and%20design%20of%20machine%20learning%20computational%20technique%20for%20prediction%20of%20physical%20separation%20process.ABSTRACT.pdf
https://eprints.ums.edu.my/id/eprint/32773/2/Optimization%20and%20design%20of%20machine%20learning%20computational%20technique%20for%20prediction%20of%20physical%20separation%20process.pdf
https://eprints.ums.edu.my/id/eprint/32773/
https://www.sciencedirect.com/science/article/pii/S187853522100695X
https://doi.org/10.1016/j.arabjc.2021.103680
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.ums.eprints.32773
record_format eprints
spelling my.ums.eprints.327732022-06-15T01:51:26Z https://eprints.ums.edu.my/id/eprint/32773/ Optimization and design of machine learning computational technique for prediction of physical separation process Haiqing Li Chairun Nasirin Azher M. Abed Dmitry Olegovich Bokov Lakshmi Thangavelu Haydar Abdulameer Marhoon Md Lutfor Rahman T57.6-57.97 Operations research. Systems analysis Machine learning (ML) methods were developed and optimized for description and understanding a physical separation process. Indeed, this work indicates application of machine learning technique for a real physical system and optimization of process parameters to achieve the target. A bunch of datasets were extracted from resources for physical adsorption process in removal of impurities from water as a case study to test the developed machine learning model. The case study process is adsorption process which has extensive application in science and engineering. The machine learning (ML) method was developed, and the parameters were optimized in order to get the best simulation’s performance for adsorption process. The data are used to correlate the adsorption capacity of the material to the adsorption parameters including dosage and solution pH. Randomized training and validation were performed to predict the process’s output, and great agreement was obtained between the predicted values and the observed values with R2 values greater than 0.9 for all cases of training and validation at the optimum conditions. Three different machine learning techniques including Random Forest (RF), Extra Tree (ET), and Gradient Boosting (GB) were employed for the adsorption data. Quantitatively, R2 scores of 0.958, 0.998, and 0.999 were obtained for RF, GB, and ET, respectively. It was indicated that GB and ET models performed almost the same and better than RF in prediction of adsorption data. Elsevier B.V 2022-01-04 Article PeerReviewed text en https://eprints.ums.edu.my/id/eprint/32773/1/Optimization%20and%20design%20of%20machine%20learning%20computational%20technique%20for%20prediction%20of%20physical%20separation%20process.ABSTRACT.pdf text en https://eprints.ums.edu.my/id/eprint/32773/2/Optimization%20and%20design%20of%20machine%20learning%20computational%20technique%20for%20prediction%20of%20physical%20separation%20process.pdf Haiqing Li and Chairun Nasirin and Azher M. Abed and Dmitry Olegovich Bokov and Lakshmi Thangavelu and Haydar Abdulameer Marhoon and Md Lutfor Rahman (2022) Optimization and design of machine learning computational technique for prediction of physical separation process. Journal of King Saud University - Engineering Sciences, 15. ISSN 1878-5352 https://www.sciencedirect.com/science/article/pii/S187853522100695X https://doi.org/10.1016/j.arabjc.2021.103680
institution Universiti Malaysia Sabah
building UMS Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Sabah
content_source UMS Institutional Repository
url_provider http://eprints.ums.edu.my/
language English
English
topic T57.6-57.97 Operations research. Systems analysis
spellingShingle T57.6-57.97 Operations research. Systems analysis
Haiqing Li
Chairun Nasirin
Azher M. Abed
Dmitry Olegovich Bokov
Lakshmi Thangavelu
Haydar Abdulameer Marhoon
Md Lutfor Rahman
Optimization and design of machine learning computational technique for prediction of physical separation process
description Machine learning (ML) methods were developed and optimized for description and understanding a physical separation process. Indeed, this work indicates application of machine learning technique for a real physical system and optimization of process parameters to achieve the target. A bunch of datasets were extracted from resources for physical adsorption process in removal of impurities from water as a case study to test the developed machine learning model. The case study process is adsorption process which has extensive application in science and engineering. The machine learning (ML) method was developed, and the parameters were optimized in order to get the best simulation’s performance for adsorption process. The data are used to correlate the adsorption capacity of the material to the adsorption parameters including dosage and solution pH. Randomized training and validation were performed to predict the process’s output, and great agreement was obtained between the predicted values and the observed values with R2 values greater than 0.9 for all cases of training and validation at the optimum conditions. Three different machine learning techniques including Random Forest (RF), Extra Tree (ET), and Gradient Boosting (GB) were employed for the adsorption data. Quantitatively, R2 scores of 0.958, 0.998, and 0.999 were obtained for RF, GB, and ET, respectively. It was indicated that GB and ET models performed almost the same and better than RF in prediction of adsorption data.
format Article
author Haiqing Li
Chairun Nasirin
Azher M. Abed
Dmitry Olegovich Bokov
Lakshmi Thangavelu
Haydar Abdulameer Marhoon
Md Lutfor Rahman
author_facet Haiqing Li
Chairun Nasirin
Azher M. Abed
Dmitry Olegovich Bokov
Lakshmi Thangavelu
Haydar Abdulameer Marhoon
Md Lutfor Rahman
author_sort Haiqing Li
title Optimization and design of machine learning computational technique for prediction of physical separation process
title_short Optimization and design of machine learning computational technique for prediction of physical separation process
title_full Optimization and design of machine learning computational technique for prediction of physical separation process
title_fullStr Optimization and design of machine learning computational technique for prediction of physical separation process
title_full_unstemmed Optimization and design of machine learning computational technique for prediction of physical separation process
title_sort optimization and design of machine learning computational technique for prediction of physical separation process
publisher Elsevier B.V
publishDate 2022
url https://eprints.ums.edu.my/id/eprint/32773/1/Optimization%20and%20design%20of%20machine%20learning%20computational%20technique%20for%20prediction%20of%20physical%20separation%20process.ABSTRACT.pdf
https://eprints.ums.edu.my/id/eprint/32773/2/Optimization%20and%20design%20of%20machine%20learning%20computational%20technique%20for%20prediction%20of%20physical%20separation%20process.pdf
https://eprints.ums.edu.my/id/eprint/32773/
https://www.sciencedirect.com/science/article/pii/S187853522100695X
https://doi.org/10.1016/j.arabjc.2021.103680
_version_ 1760231072217432064
score 13.211869

Similar Items