Influence Prediction of Alkylamines Upon Electrical Percolation of AOT-based Microemulsions Using Artificial Neural Networks

Abstract

Simulations for the electrical percolation of AOT/iC8/H2O w/o microemulsions added with alkylamines have been carried out by means of multilayer perceptron. Five variables have been elected as inputs: amine concentration, molecular weight, log P, hydrocarbon chain length (as number of carbons), and pKa. As a result, a neural model consisting in five input neurons, two middle layers (with fifteen and ten neurons respectively) and one output neuron was chosen because of its better performance, with a RMSE of 0.54 °C for the prediction set, with R2 = 0.9976.

Prediction Models to Control Aging Time in Red Wine

“…One of the most important advantages is that ANN models can extract information from complex data matrices due their ability to learn the relationship between independent and dependent variables [ 26 ]. For this reason, ANNs are applied in many different research fields, such as: Hydrology, to model the water quality using different water quality variables [ 27 ], Biotechnology, to optimize 1,3-propanediol production using microorganisms like Lactobacillus brevis N1E9.3.3 [ 28 ] or to optimize oil extraction from Bauhinia monandra seed [ 18 ], Food technology, to develop an authentication model to predict the cultivar, the production type and the harvest date for tomatoes [ 29 ] or to authenticate extra virgin oil varieties [ 30 ], Chemistry, to predict percolation temperature [ 31 ], to predict the solvent accessibility of proteins [ 32 ], or in other fields where the ANN has proved its capacity for medical, economic or agro-food science purposes [ 21 ]. …”

Prediction Models to Control Aging Time in Red Wine

“…One of the most important advantages for ANN is that it can extract information from complex data matrix due its capability to learn the relationship between independent and dependent variables (Chiang and Chang, 2009). According to this advantage, ANNs are applied in many different research fields, such as: i) Hydrology to model the water quality using different water quality variables (Gazzaz, Yusoff, Aris, Juahir and Ramli, 2012), ii) in Biotechnology to optimize 1,3-propanediol production using microorganisms like Lactobacillus brevis N1E9.3.3 (Narisetty, Astray, Gullón, Castro, Parameswaran and Pandey, 2017) or to optimize oil extraction from Bauhinia monandra seed that it is a potential biofuel candidate (Akintunde, Ajala and Betiku, 2015), iii) in Food technology to develop an authentication model to predict the cultivar, the production type and the harvest date for tomatoes (Hernández Suárez M., Astray Dopazo G., Larios López D. and Espinosa F., 2015) to authenticate extra virgin oil varieties (Bucci, Magrí, Magrí, Marini and Marini, 2002), iv) in Chemistry to predict percolation temperature (Montoya, Moldes, Cid, Astray, Gálvez and Mejuto, 2015), to predict the solvent accessibility of proteins (Ahmad and Gromiha, 2003), or in other fields where the ANN has proved its capacity for medical, economic or agro-food science purposes (Gonzalez-Fernandez, Iglesias-Otero, Esteki, Moldes, Mejuto and Simal-Gandara, 2018). SVM was first introduced by Boser et al in 1992 (Capron, Massart andSmeyers-Verbeke, 2007, Boser, Guyon andVapnik, 1992).…”

Influence of Amphiphiles on Percolation of AOT-Based Microemulsions Prediction Using Artificial Neural Networks

“…Different neural models were developed with different 55 amine experimental cases, where 42 experimental cases were used to train the models and 13 experimental cases were used to validate the model [60]. The best neural model presents a topology with five input nodes, two intermediate layers (with 15 and 10 nodes) and one node in the output layer to `predict percolation temperature [60].…”

“…The input variables used for the n-alkylamine model were as follows: (i) additive concentration, (ii) log P, (iii) pK a , (iv) hydrocarbon chain length and (v) molecular mass of the additive [60]. Different neural models were developed with different 55 amine experimental cases, where 42 experimental cases were used to train the models and 13 experimental cases were used to validate the model [60].…”

“…In order to evaluate the effect of amphiphiles on percolation threshold, the influence of 1-n-alcohols [59], 2-n-alcohols [59], n-alkylamines [60][61][62][63] and n-alkyl acids [64,65] had been analysed. This allowed us to estimate the influence of the chain length of the molecule with constant head group and also the influence of the head group while the chain length remains invariant (see Figure 9).…”