Comparison the capability of artificial neural network (ANN) and EOS for prediction of solid solubilities in supercritical carbon dioxide

Prediction of degree of crystallinity for the LTA zeolite using artificial neural networks

“…The weights and biases can be adjusted by training the network using the standard back propagation algorithm. Our previous findings [29,30,[33][34][35]40] justified that designing the MLP model from normalized data is easier than working on the original data. Therefore, in the present study all the variables have been mapped between [0 1] intervals.…”

“…Artificial neural networks (ANN) are developed by mathematical simulation of behavior of the human neural system [27][28][29][30]. Excellent performance of the ANN approaches in tracking behavior of various scientific problems, combined with their simplicity and flexibility have led to high popularity of these intelligent and non-linear methods in the recent years [31][32][33].…”

“…By training the ANN model, it is possible to relate dependent and independent variables of the most nonlinear multivariable systems with arbitrary complexity [27][28][29][30]. Back propagation, cascade correlation, and conjugate gradient are the most popular learning algorithms [38].…”

“…An ideal number of hidden neurons is not known at all, and often determined by trial and error process [29,30]. Large numbers of hidden neuron suffer from an over-fitting, and often need high computation efforts, while small numbers of hidden neuron are unable to relate dependent to independent variables with an acceptable accuracy [33][34][35].…”

Density, viscosity and refractive index prediction of binary and ternary mixtures systems of ionic liquid

“…Our neural network, a Multilayer Perceptron are trained with a back propagation algorithm, gradient descent algorithm, that transfers the estimation error back through the network until it reaches an acceptable error by modifying weight values through several iterations 11, [13][14][15]17 . The use of predictive models based on artificial intelligence are widely used in many fields such as; Food Chemistry to optimization of ultrahigh pressure extraction of green tea polyphenols 19 , Medicine for automatic electrocardiogram analysis 20 , Engineering to Active pulse structural control to control civil engineering structures under dynamic loading 21 , Mathematics 22 , Physics to predict maximum temperature cooling in single chips 23 , Environmental Sciences for monitoring and diagnosis of a combined heat and power plant 24 , Hydrology for flow prediction 25 , Food authenticity 26 , Aerobiology 27 , or in Chemistry to analysis of chromatographic behavior of indinavir and its degradation products 28 , prediction of solid solubilities in supercritical carbon dioxide 29 , determining the rejection of neutral organic compounds by polyamide nanofiltration and reverse osmosis membranes 30 , predict of ethene + oct-1-ene copolymerization ideal conditions 31 , prediction density in ionic liquid 32 , conductivity 33 , viscosity 34 and to estimate the water content 35 . The ultimate goal of this paper is to develop a predictive model to determine accurately the density, viscosity and refractive index of binary and ternary mixtures of ionic liquids using their individual properties, avoiding unnecessary waste of economic resources, reagents and labour.…”