Department of Chemistry, Faculty of Science, University of Mohaghegh Ardabili, P.O. Box 179, Ardabil, Iran
10.22034/abec.2023.702332
Abstract
The quantitative structure-property relationship (QSPR) method has been used for the prediction of carbonate potentiometric selectivity of plasticized polymeric membrane sensors. The variable selection tools of genetic algorithm (GA) combined with the multiple linear regressions (MLR) as linear and support vector machine (SVM) as nonlinear regression methods have been used. The K-means clustering method has been used for dividing the data set into the training set and test set. The validation of the models was done by the internal cross-validation and external test set. The results showed that the GA-SVM was a very accurate method in predicting of carbonate potentiometric selectivity with high correlation coefficients of 0.983 and 0.965 for the training and test sets. The results of this study and the interpretation of entered descriptors in the model can help to design new selective ligands.
Pourbasheer, E. (2023). High Accurate Prediction of Carbonate Selectivity of PVC-Plasticized Membranes Sensors by Genetic Algorithm-Support Vector Machine. Analytical and Bioanalytical Electrochemistry, 15(2), 150-165. doi: 10.22034/abec.2023.702332
MLA
Eslam Pourbasheer. "High Accurate Prediction of Carbonate Selectivity of PVC-Plasticized Membranes Sensors by Genetic Algorithm-Support Vector Machine". Analytical and Bioanalytical Electrochemistry, 15, 2, 2023, 150-165. doi: 10.22034/abec.2023.702332
HARVARD
Pourbasheer, E. (2023). 'High Accurate Prediction of Carbonate Selectivity of PVC-Plasticized Membranes Sensors by Genetic Algorithm-Support Vector Machine', Analytical and Bioanalytical Electrochemistry, 15(2), pp. 150-165. doi: 10.22034/abec.2023.702332
VANCOUVER
Pourbasheer, E. High Accurate Prediction of Carbonate Selectivity of PVC-Plasticized Membranes Sensors by Genetic Algorithm-Support Vector Machine. Analytical and Bioanalytical Electrochemistry, 2023; 15(2): 150-165. doi: 10.22034/abec.2023.702332
)