Influence prediction of alkylamines upon electrical percolation of AOT-based microemulsions using artificial neural networks

Lago Antonio Montoya; Oscar Adrían Moldes; Antonio Cid Samamed; Conzalo Astray; Juan Francisco Gálvez; Juan Carlos Mejuto

doi:10.3139/113.110399

Influence prediction of alkylamines upon electrical percolation of AOT-based microemulsions using artificial neural networks

Lago Antonio Montoya, Oscar Adrían Moldes, Antonio Cid Samamed, Conzalo Astray, Juan Francisco Gálvez, Juan Carlos Mejuto

Research output: Contribution to journal › Article › peer-review

6 Citations (Scopus)

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.

Original language	English
Pages (from-to)	473-476
Number of pages	4
Journal	Tenside, Surfactants, Detergents
Volume	52
Issue number	6
DOIs	https://doi.org/10.3139/113.110399
Publication status	Published - 1 Nov 2015

Keywords

Additive
Alkylamine
AOT
Artificial neural networks
Conductivity
Isooctane
Microemulsions
Multilayer perceptron
Percolation
Prediction
Simulation

Access to Document

10.3139/113.110399Licence: Unspecified

Cite this

@article{2803a07ae85a486b8847f34f1f201eb7,

title = "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.",

keywords = "Additive, Alkylamine, AOT, Artificial neural networks, Conductivity, Isooctane, Microemulsions, Multilayer perceptron, Percolation, Prediction, Simulation",

author = "Montoya, {Lago Antonio} and Moldes, {Oscar Adr{\'i}an} and Samamed, {Antonio Cid} and Conzalo Astray and G{\'a}lvez, {Juan Francisco} and Mejuto, {Juan Carlos}",

note = "Sem PDF. Financial support is gratefully acknowledged for the Portuguese Science and Technology post-doctoral grant SFRH/BPD/78849/2011 conceded to Dr. Cid. Also from Xunta de Galicia, Conselleria de Cultura, Educacion e Ordenacion Universitaria for Dr. Astray's grant (Plan I2C) P.P.0000 421S 140.08.",

year = "2015",

month = nov,

day = "1",

doi = "10.3139/113.110399",

language = "English",

volume = "52",

pages = "473--476",

journal = "Tenside, Surfactants, Detergents",

issn = "0932-3414",

publisher = "Carl Hanser Verlag",

number = "6",

}

TY - JOUR

T1 - Influence prediction of alkylamines upon electrical percolation of AOT-based microemulsions using artificial neural networks

AU - Montoya, Lago Antonio

AU - Moldes, Oscar Adrían

AU - Samamed, Antonio Cid

AU - Astray, Conzalo

AU - Gálvez, Juan Francisco

AU - Mejuto, Juan Carlos

N1 - Sem PDF. Financial support is gratefully acknowledged for the Portuguese Science and Technology post-doctoral grant SFRH/BPD/78849/2011 conceded to Dr. Cid. Also from Xunta de Galicia, Conselleria de Cultura, Educacion e Ordenacion Universitaria for Dr. Astray's grant (Plan I2C) P.P.0000 421S 140.08.

PY - 2015/11/1

Y1 - 2015/11/1

N2 - 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.

AB - 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.

KW - Additive

KW - Alkylamine

KW - AOT

KW - Artificial neural networks

KW - Conductivity

KW - Isooctane

KW - Microemulsions

KW - Multilayer perceptron

KW - Percolation

KW - Prediction

KW - Simulation

UR - http://www.scopus.com/inward/record.url?scp=84950138234&partnerID=8YFLogxK

U2 - 10.3139/113.110399

DO - 10.3139/113.110399

M3 - Article

AN - SCOPUS:84950138234

SN - 0932-3414

VL - 52

SP - 473

EP - 476

JO - Tenside, Surfactants, Detergents

JF - Tenside, Surfactants, Detergents

IS - 6

ER -

Influence prediction of alkylamines upon electrical percolation of AOT-based microemulsions using artificial neural networks

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this