Original scientific paper
https://doi.org/10.15255/KUI.2020.063
Critical Properties and Acentric Factors of Pure Compounds Modelling Based on QSPR-SVM with Dragonfly Algorithm
Mohammed Moussaoui
orcid.org/0000-0002-4748-1353
; Laboratory of Biomaterials and Transport Phenomena (LBMPT), University of Médéa, Médéa, Algeria
Maamar Laidi
orcid.org/0000-0002-8977-9895
; Laboratory of Biomaterials and Transport Phenomena (LBMPT), University of Médéa, Médéa, Algeria
Salah Hanini
; Laboratory of Biomaterials and Transport Phenomena (LBMPT), University of Médéa, Médéa, Algeria
Abdallah El Hadj Abdallah
; Department of Chemistry, University of Blida1, Blida, Algeria
Mohamed Hentabli
orcid.org/0000-0002-6693-0708
; Laboratory Quality Control, Physico-Chemical Department, Antibiotical Saidal of Médéa, Algeria
Abstract
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.
Keywords
support vector machine; critical properties; Dragonfly optimisation algorithm; quantitative structure-property relationship
Hrčak ID:
259339
URI
Publication date:
24.6.2021.
Visits: 847 *