Critical Properties and Acentric Factors of Pure Compounds Modelling Based on QSPR-SVM with Dragonfly Algorithm
This work aimed to model the critical pressure, temperature, volume properties, and acentric factors of 6700 pure compounds based on five relevant descriptors and two thermodynamic properties. To that end, four methods were used, namely, multi-linear regression (MLR), artificial neural networks (ANN...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Croatian Society of Chemical Engineers
2021-06-01
|
| Series: | Kemija u Industriji |
| Subjects: | |
| Online Access: | http://silverstripe.fkit.hr/kui/assets/Uploads/2-375-386-KUI-7-8-2021.pdf |
| _version_ | 1819000833015021568 |
|---|---|
| author | Mohammed Moussaoui Maamar Laidi Salah Hanini Abdallah Abdellah El Hadj Mohamed Hentabli |
| author_facet | Mohammed Moussaoui Maamar Laidi Salah Hanini Abdallah Abdellah El Hadj Mohamed Hentabli |
| author_sort | Mohammed Moussaoui |
| collection | DOAJ |
| description | This work aimed to model the critical pressure, temperature, volume properties, and acentric factors of 6700 pure compounds based on five relevant descriptors and two thermodynamic properties. To that end, four methods were used, namely, multi-linear regression (MLR), artificial neural networks (ANNs), support vector machines (SVMs) using sequential minimal optimisation (SMO), and hybrid SVM with Dragonfly optimisation algorithm (SVM-DA) to model each property. The results suggested that hybrid SVM-DA had better prediction performance compared to the other models in terms of average absolute relative deviation (AARD%) of {0.7551, 1.962, 1.929, and 2.173} and R2 of {0.9699, 0.9673, 0.9856, and 0.9766} for critical temperature, critical pressure, critical volume, and acentric factor, respectively. The developed models can be used to estimate the property of newly designed compounds only from their molecular structure. |
| first_indexed | 2024-12-20T22:39:35Z |
| format | Article |
| id | doaj.art-95f6b01a0485479ca91a5718e3c78ba1 |
| institution | Directory Open Access Journal |
| issn | 0022-9830 1334-9090 |
| language | English |
| last_indexed | 2024-12-20T22:39:35Z |
| publishDate | 2021-06-01 |
| publisher | Croatian Society of Chemical Engineers |
| record_format | Article |
| series | Kemija u Industriji |
| spelling | doaj.art-95f6b01a0485479ca91a5718e3c78ba12022-12-21T19:24:31ZengCroatian Society of Chemical EngineersKemija u Industriji0022-98301334-90902021-06-01707-837538610.15255/KUI.2020.063Critical Properties and Acentric Factors of Pure Compounds Modelling Based on QSPR-SVM with Dragonfly AlgorithmMohammed Moussaoui0Maamar Laidi1Salah Hanini2Abdallah Abdellah El Hadj3Mohamed Hentabli4Laboratory of Biomaterials and Transport Phenomena (LBMPT), University of Médéa, Médéa, AlgeriaLaboratory of Biomaterials and Transport Phenomena (LBMPT), University of Médéa, Médéa, AlgeriaLaboratory of Biomaterials and Transport Phenomena (LBMPT), University of Médéa, Médéa, AlgeriaDepartment of Chemistry, University of Blida1, Blida, Algeria Laboratory Quality Control, Physico-Chemical Department, Antibiotical Saidal of Médéa, AlgeriaThis work aimed to model the critical pressure, temperature, volume properties, and acentric factors of 6700 pure compounds based on five relevant descriptors and two thermodynamic properties. To that end, four methods were used, namely, multi-linear regression (MLR), artificial neural networks (ANNs), support vector machines (SVMs) using sequential minimal optimisation (SMO), and hybrid SVM with Dragonfly optimisation algorithm (SVM-DA) to model each property. The results suggested that hybrid SVM-DA had better prediction performance compared to the other models in terms of average absolute relative deviation (AARD%) of {0.7551, 1.962, 1.929, and 2.173} and R2 of {0.9699, 0.9673, 0.9856, and 0.9766} for critical temperature, critical pressure, critical volume, and acentric factor, respectively. The developed models can be used to estimate the property of newly designed compounds only from their molecular structure.http://silverstripe.fkit.hr/kui/assets/Uploads/2-375-386-KUI-7-8-2021.pdfsupport vector machinecritical propertiesdragonfly optimisation algorithmquantitative structure-property relationship |
| spellingShingle | Mohammed Moussaoui Maamar Laidi Salah Hanini Abdallah Abdellah El Hadj Mohamed Hentabli Critical Properties and Acentric Factors of Pure Compounds Modelling Based on QSPR-SVM with Dragonfly Algorithm Kemija u Industriji support vector machine critical properties dragonfly optimisation algorithm quantitative structure-property relationship |
| title | Critical Properties and Acentric Factors of Pure Compounds Modelling Based on QSPR-SVM with Dragonfly Algorithm |
| title_full | Critical Properties and Acentric Factors of Pure Compounds Modelling Based on QSPR-SVM with Dragonfly Algorithm |
| title_fullStr | Critical Properties and Acentric Factors of Pure Compounds Modelling Based on QSPR-SVM with Dragonfly Algorithm |
| title_full_unstemmed | Critical Properties and Acentric Factors of Pure Compounds Modelling Based on QSPR-SVM with Dragonfly Algorithm |
| title_short | Critical Properties and Acentric Factors of Pure Compounds Modelling Based on QSPR-SVM with Dragonfly Algorithm |
| title_sort | critical properties and acentric factors of pure compounds modelling based on qspr svm with dragonfly algorithm |
| topic | support vector machine critical properties dragonfly optimisation algorithm quantitative structure-property relationship |
| url | http://silverstripe.fkit.hr/kui/assets/Uploads/2-375-386-KUI-7-8-2021.pdf |
| work_keys_str_mv | AT mohammedmoussaoui criticalpropertiesandacentricfactorsofpurecompoundsmodellingbasedonqsprsvmwithdragonflyalgorithm AT maamarlaidi criticalpropertiesandacentricfactorsofpurecompoundsmodellingbasedonqsprsvmwithdragonflyalgorithm AT salahhanini criticalpropertiesandacentricfactorsofpurecompoundsmodellingbasedonqsprsvmwithdragonflyalgorithm AT abdallahabdellahelhadj criticalpropertiesandacentricfactorsofpurecompoundsmodellingbasedonqsprsvmwithdragonflyalgorithm AT mohamedhentabli criticalpropertiesandacentricfactorsofpurecompoundsmodellingbasedonqsprsvmwithdragonflyalgorithm |