Development of novel computational models based on artificial intelligence technique to predict the viscosity of ionic liquids-water mixtures
This paper delves into the practical application of K-Nearest Neighbors (KNN), Kernel Ridge Regression (KRR), and Lasso Regression for the prediction of viscosity of ionic liquids in a dataset characterized by categorical variables (Cation, Anion) and numeric variables (T(K), xIL(mol%)). Indeed, mol...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2024-02-01
|
Series: | Case Studies in Thermal Engineering |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2214157X24001072 |
_version_ | 1797311530093510656 |
---|---|
author | Longyi Ran Zheng Wang Bing Yang Alireza Amiri-Margavi Najim Alshahrani |
author_facet | Longyi Ran Zheng Wang Bing Yang Alireza Amiri-Margavi Najim Alshahrani |
author_sort | Longyi Ran |
collection | DOAJ |
description | This paper delves into the practical application of K-Nearest Neighbors (KNN), Kernel Ridge Regression (KRR), and Lasso Regression for the prediction of viscosity of ionic liquids in a dataset characterized by categorical variables (Cation, Anion) and numeric variables (T(K), xIL(mol%)). Indeed, mole percentage of ionic liquids and temperature were considered as inputs for the models. The models' effectiveness is rigorously assessed, with K-Nearest Neighbors notably exhibiting exceptional predictive performance. To enhance model accuracy, Tabu Search is employed as an optimization tool for hyperparameter tuning. Numeric results showcase KNN's superiority, supported by a remarkable R2 test score of 0.91628 and the lowest RMSE among the models. Tabu Search optimization further refines model performance, emphasizing the critical role of hyperparameter tuning in achieving robust regression models in predicting the viscosity of ionic liquid-water mixtures. This study contributes valuable insights into the optimization process, demonstrating tangible improvements in predictive accuracy for viscosity predictions in similar contexts. |
first_indexed | 2024-03-08T02:01:04Z |
format | Article |
id | doaj.art-a3939be1cd8d457e8fff1d472ce5ff74 |
institution | Directory Open Access Journal |
issn | 2214-157X |
language | English |
last_indexed | 2024-03-08T02:01:04Z |
publishDate | 2024-02-01 |
publisher | Elsevier |
record_format | Article |
series | Case Studies in Thermal Engineering |
spelling | doaj.art-a3939be1cd8d457e8fff1d472ce5ff742024-02-14T05:17:16ZengElsevierCase Studies in Thermal Engineering2214-157X2024-02-0154104076Development of novel computational models based on artificial intelligence technique to predict the viscosity of ionic liquids-water mixturesLongyi Ran0Zheng Wang1Bing Yang2Alireza Amiri-Margavi3Najim Alshahrani4Chongqing Chemical Industry Vocational College, Chongqing, 401220, China; Corresponding author.Chongqing Chemical Industry Vocational College, Chongqing, 401220, ChinaChongqing Chemical Industry Vocational College, Chongqing, 401220, ChinaDepartment of Mechanical Engineering and Materials Science, University of Pittsburgh, 3700 O'Hara Street, Pittsburgh, PA, 15213, USASaudi Aramco Engineering Services, Inspection Department, Dhahran, Saudi ArabiaThis paper delves into the practical application of K-Nearest Neighbors (KNN), Kernel Ridge Regression (KRR), and Lasso Regression for the prediction of viscosity of ionic liquids in a dataset characterized by categorical variables (Cation, Anion) and numeric variables (T(K), xIL(mol%)). Indeed, mole percentage of ionic liquids and temperature were considered as inputs for the models. The models' effectiveness is rigorously assessed, with K-Nearest Neighbors notably exhibiting exceptional predictive performance. To enhance model accuracy, Tabu Search is employed as an optimization tool for hyperparameter tuning. Numeric results showcase KNN's superiority, supported by a remarkable R2 test score of 0.91628 and the lowest RMSE among the models. Tabu Search optimization further refines model performance, emphasizing the critical role of hyperparameter tuning in achieving robust regression models in predicting the viscosity of ionic liquid-water mixtures. This study contributes valuable insights into the optimization process, demonstrating tangible improvements in predictive accuracy for viscosity predictions in similar contexts.http://www.sciencedirect.com/science/article/pii/S2214157X24001072Machine learningIonic liquidsViscosityKernel ridge regressionK-nearest neighborsLasso regression |
spellingShingle | Longyi Ran Zheng Wang Bing Yang Alireza Amiri-Margavi Najim Alshahrani Development of novel computational models based on artificial intelligence technique to predict the viscosity of ionic liquids-water mixtures Case Studies in Thermal Engineering Machine learning Ionic liquids Viscosity Kernel ridge regression K-nearest neighbors Lasso regression |
title | Development of novel computational models based on artificial intelligence technique to predict the viscosity of ionic liquids-water mixtures |
title_full | Development of novel computational models based on artificial intelligence technique to predict the viscosity of ionic liquids-water mixtures |
title_fullStr | Development of novel computational models based on artificial intelligence technique to predict the viscosity of ionic liquids-water mixtures |
title_full_unstemmed | Development of novel computational models based on artificial intelligence technique to predict the viscosity of ionic liquids-water mixtures |
title_short | Development of novel computational models based on artificial intelligence technique to predict the viscosity of ionic liquids-water mixtures |
title_sort | development of novel computational models based on artificial intelligence technique to predict the viscosity of ionic liquids water mixtures |
topic | Machine learning Ionic liquids Viscosity Kernel ridge regression K-nearest neighbors Lasso regression |
url | http://www.sciencedirect.com/science/article/pii/S2214157X24001072 |
work_keys_str_mv | AT longyiran developmentofnovelcomputationalmodelsbasedonartificialintelligencetechniquetopredicttheviscosityofionicliquidswatermixtures AT zhengwang developmentofnovelcomputationalmodelsbasedonartificialintelligencetechniquetopredicttheviscosityofionicliquidswatermixtures AT bingyang developmentofnovelcomputationalmodelsbasedonartificialintelligencetechniquetopredicttheviscosityofionicliquidswatermixtures AT alirezaamirimargavi developmentofnovelcomputationalmodelsbasedonartificialintelligencetechniquetopredicttheviscosityofionicliquidswatermixtures AT najimalshahrani developmentofnovelcomputationalmodelsbasedonartificialintelligencetechniquetopredicttheviscosityofionicliquidswatermixtures |