Wavelet neural network modeling in QSPR for prediction of solubility of 25 anthraquinone dyes at different temperatures and pressures in supercritical carbon dioxide

A new optimization method for parameter determination in modeling solid solubility in supercritical CO2

“…Recently, neural network [13][14][15] and least square support vector machine (LS-SVM) [16] have been used to model and predict the solid solubility in supercritical carbon dioxide. Interestingly, a hybrid modeling method of combining the EOS with a feed forward neural network has been proposed for modeling the supercritical extraction of ␣-pinene, resulting in very satisfactory performance [17].…”

A comparison between neural network method and semi empirical equations to predict the solubility of different compounds in supercritical carbon dioxide

“…Kamali and Mousavi [17] published a paper about modeling of supercritical extraction of ␣-pinene by means of artificial neural network. Tabaraki et al used artificial neural network with quantitative structure-property relationship (QSPR) method for solubility prediction of anthraquinone dyes [18].…”

A comparative QSPR study on aqueous solubility of polycyclic aromatic hydrocarbons by GA-SVM, GA-RBFNN and GA-PLS

“…However, because of large expenditures of money, time and equipment, measured S w data for PAHs were rather scarce. Thus a great deal of effort had been put into attempting the estimation of S w through statistical modeling, and a variety of quantitative structure-property relationship (QSPR) models were proposed (Chen et al, 2003;Niu et al, 2005;Niu et al, 2006a;Tabaraki et al, 2006;Xu et al, 2007).…”

“…Along with the development of intelligent algorithms, artificial neural network (ANN) was used to fit the nonlinearity continuous functions, and the capability of prediction was improved (Tabaraki et al, 2006;Arab Chamjangali et al, 2007). Support vector machine (SVM), proposed by Vapnik (1995), is a new learning method based on statistics theory.…”