Skip to content
Licensed Unlicensed Requires Authentication Published by De Gruyter March 3, 2017

Approach of Different Properties of Alkylammonium Surfactants using Artificial Intelligence and Response Surface Methodology

Bewertung der Eigenschaften von Alkylammoniumtensiden mittels künstlicher Intelligenz und Response-Surface-Methoden
Gonzalo Astray and Juan Carlos Mejuto


Response surface methodology (RSM) and artificial neural networks (ANNs) architectures to predict the density, speed of sound, kinematic viscosity, and surface tension of aqueous solutions were developed. All models implemented using the root mean square error (RMSE) for training and validation phase were evaluated. The ANN models implemented show good values of R2 (upper than 0.974) and low errors in terms of average percentage deviation (APD) (lower than 2.92 %). Nevertheless, RSM models present low APD values for density and speed of sound prediction (lower than 0.31 %) and higher APD values around 5.18 % for kinematic viscosity and 14.73 % for surface tension. The results show that the different individual artificial neural networks implemented are a useful tool to predict the density, speed of sound, kinematic viscosity, and surface tension with reasonably accuracy.


Es wurden Response-Surface-Methoden (RSM) und künstliche neuronale Netzwerke (ANNs) zur Vorhersage der Dichte, der Schallgeschwindigkeit, der kinematischen Viskosität und der Oberflächenspannung von wässrigen Lösungen entwickelt. Alle umgesetzten Modelle wurden in der Trainings- und Validierungsphase mit der Methode der mittleren quadratischen Fehler (RMSE) bewertet. Die umgesetzten ANN-Modelle lieferten gute R2-Werte (größer als 0,974) und hinsichtlich der durchschnittlichen prozentualen Abweichung (APD) geringe Fehler (geringer als 2,92 %). Dennoch erreichten die RSM-Modelle niedrige APD-Werte für die Dichte und die Schallgeschwindigkeit (kleiner als 0,31 %) und höhere APD-Werte von etwa 5,18 % für die kinematische Viskosität und von 14,73 % für die Oberflächenspannung. Die Ergebnisse machen deutlich, dass die verschiedenen individuellen künstlichen neuronalen Netzwerke nützlich sind, um die Dichte, die Schallgeschwindigkeit, die kinematischen Viskosität und die Oberflächenspannung mit einer hinreichenden Genauigkeit vorherzusagen.

*Correspondence address, Dr. Gonzalo Astray, University of Vigo, Faculty of Science, Physical Chemistry Department, Ourense, Spain, E-Mail:

Juan Carlos Mejuto currently is Full Professor in the Physical Chemistry Department of University of Vigo at Ourense Campus. He is the head of the Colloids group at Ourense Campus. His research interest comprises (i) physical organic and physical inorganic chemistry, (ii) reactivity mechanisms in homogeneous and micro heterogeneous media, (iii) stability of self-assembly aggregates and (iv) supramolecular chemistry.

Gonzalo Astray take his PhD at University of Vigo. His research interest is focused in the applications of Artificial Neural Networks to chemical and biological problems.


1. Gómez-DíazD., NavazaJ. M. and SanjurjoB.: Density, kinematic viscosity, speed of sound, and surface tension of hexyl, octyl, and decyl trimethyl ammonium bromide aqueous solutions, J Chem Eng Data52 (2007) 889891. 10.1021/je060486kSearch in Google Scholar

2. HörmannK. and ZimmerA.: Drug delivery and drug targeting with parenteral lipid nanoemulsions – A review, J Control Release223 (2016) 8598. 10.1016/j.jconrel.2015.12.016Search in Google Scholar PubMed

3. PusapatiM. R., GuntukuG., YarlagaddaA. C., NagarajuG., SoumyaM. and LakshmiT. B. V.: An overview of classification, production and biomedical applications of biosurfactants, Res J Pharm Technol7 (2014) 608617. DOI: not available.Search in Google Scholar

4. BurnettC. L., HeldrethB., BergfeldW. F., BelsitoD. V., HillR. A., KlaassenC. D., LieblerD. C., MarksJ. G., ShankR. C., SlagaT. J., SnyderP. W. and AndersenF. A.: Safety Assessment of PEGylated oils as used in cosmetics, Int J Toxicol.33 (2014) 13S39S. 10.1177/1091581814546337Search in Google Scholar PubMed

5. PolarzS., OdendalJ. A., HermannS. and KlaiberA.: Amphiphilic hybrids containing inorganic constituent: More than soap, Curr Opin Colloid Interface Sci20 (2015) 151160. 10.1016/j.cocis.2015.07.006Search in Google Scholar

6. GersterF. M., VernezD., WildP. P. and HopfN. B.: Hazardous substances in frequently used professional cleaning products, Int J Occup Environ Health20 (2014) 4660. 10.1179/2049396713Y.0000000052Search in Google Scholar PubMed PubMed Central

7. Gómez-DíazD., NavazaJ. M. and SanjurjoB.: Density, kinematic viscosity, speed of sound, and surface tension of tetradecyl and octadecyl trimethyl ammonium bromide aqueous solutions, J Chem Eng Data52 (2007) 20912093. 10.1021/je7003148Search in Google Scholar

8. AkintundeA. M., AjalaS. O. and BetikuE.: Optimization of Bauhinia monandra seed oil extraction via artificial neural network and response surface methodology: A potential biofuel candidate, Ind Crops Prod67 (2015) 387394. 10.1016/j.indcrop.2015.01.056Search in Google Scholar

9. BasD. and BoyaciI. H.: Modeling and optimization II: Comparison of estimation capabilities of response surface methodology with artificial neural networks in a biochemical reaction, J Food Eng78 (2007) 846854. 10.1016/j.jfoodeng.2005.11.025Search in Google Scholar

10. BoxG. E. P. and WilsonK. B.: On the experimental attainment of optimum conditions. J R Stat Soc B13 (1951) 145. DOI: not available.Search in Google Scholar

11. FangS. E. and PereraR.: A response surface methodology based damage identification technique, Smart Mater. Struct.18, 6 (2009). 10.1088/0964-1726/18/6/065009Search in Google Scholar

12. CarvalhoR. A., MariaT. M. C., MoraesI. C. F., BergoP. V. A., KamimuraE. S., HabitanteA. M. Q. B. and SobralP. J. A.: Study of some physical properties of biodegradable films based on blends of gelatin and poly(vinyl alcohol) using a response-surface methodology, Materials Science and Engineering: C29 (2009) 485491. 10.1016/j.msec.2008.08.030Search in Google Scholar

13. MadambaP. S.: The Response Surface Methodology: An Application to Optimize Dehydration Operations of Selected Agricultural Crops, LWT – Food Science and Technology35 (2002) 584592. 10.1006/fstl.2002.0914Search in Google Scholar

14. MartínezM., GullónB., YáñezR., AlonsoJ. L. and ParajóJ. C.: Direct enzymatic production of oligosaccharide mixtures from sugar beet pulp: Experimental evaluation and mathematical modeling, J Agric Food Chem57 (2009) 55105517. 10.1021/jf900654 gSearch in Google Scholar

15. JungE. and JooN.: Roselle (Hibiscus sabdariffa l.) and soybean oil effects on quality characteristics of pork patties studied by response surface methodology, Meat Sci94 (2013) 391401. 10.1016/j.meatsci.2013.02.008Search in Google Scholar PubMed

16. DesaiK. M., SurvaseS. A., SaudagarP. S., LeleS. S. and SinghalR. S.: Comparison of artificial neural network (ANN) and response surface methodology (RSM) in fermentation media optimization: Case study of fermentative production of scleroglucan, Biochem Eng J41 (2008) 266273. 10.1016/j.bej.2008.05.009Search in Google Scholar

17. RenY., SuganthanP. N. and SrikanthN.: A comparative study of empirical mode decomposition-based short-term wind speed forecasting methods, IEEE Trans Sustainable Energy6 (2015) 236244. 10.1109/TSTE.2014.2365580Search in Google Scholar

18. DowellJ. A., HussainA., DevaneJ. and YoungD.: Artificial neural networks applied to the in vitro-in vivo correlation of an extended-release formulation: Initial trials and experience, J Pharm Sci88 (1999) 154160. 10.1021/js970148pSearch in Google Scholar PubMed

19. Sánchez-MesaJ. A., GalanC., Martínez-HerasJ. A. and Hervás-Martínez,C.: The use of a neural network to forecast daily grass pollen concentration in a Mediterranean region: The southern part of the Iberian Peninsula, Clinical and Experimental Allergy32 (2002) 16061612. 10.1046/j.1365-2222.2002.01510.xSearch in Google Scholar PubMed

20. ChandwaniV., AgrawalV. and NagarR.: Modeling slump of ready mix concrete using genetic algorithms assisted training of Artificial Neural Networks, Expert Syst Appl42 (2015) 885893. 10.1016/j.eswa.2014.08.048Search in Google Scholar

21. NastosP. T., PaliatsosA. G., KoukouletsosK. V., LarissiI. K. and MoustrisK. P.: Artificial neural networks modeling for forecasting the maximum daily total precipitation at Athens, Greece, Atmos Res144 (2014) 141150. 10.1016/j.atmosres.2013.11.013Search in Google Scholar

22. AstrayG., CadernoP. V., Ferreiro-LageJ. A., GalvezJ. F. and MejutoJ. C.: Prediction of ethene + oct-1-ene copolymerization ideal conditions using artificial neuron networks, J Chem Eng Data55 (2010) 35423547. 10.1021/je1001973Search in Google Scholar

23. ChengJ., ChenX., ZhaoS. and ZhangY.: Antioxidant-capacity-based models for the prediction of acrylamide reduction by flavonoids, Food Chem168 (2015) 9099. 10.1016/j.foodchem.2014.07.008Search in Google Scholar PubMed

24. AstrayG., Iglesias-OteroM. A., MoldesO. A. and MejutoJ. C.: Predicting critical micelle concentration values of non-ionic surfactants by using artificial neural networks, Tenside Surfactants Deterg50 (2013) 118124. 10.3139/113.110242Search in Google Scholar

25. MoldesÓA., MoralesJ., CidA., AstrayG., MontoyaI. A. and MejutoJ. C.: Electrical percolation of AOT-based microemulsions with n-alcohols, J Mol Liq215 (2016) 1823. 10.1016/j.molliq.2015.12.021Search in Google Scholar

26. MoldesÓ. A., CidA., MontoyaI. A. and MejutoJ. C.: Linear polyethers as additives for AOT-based microemulsions: Prediction of percolation temperature changes using artificial neural networks, Tenside Surfactants Deterg52 (2015) 264270. 10.3139/113.110374Search in Google Scholar

27. Hernández SuárezM., Astray DopazoG., Larios LópezD. and EspinosaF.: Identification of Relevant Phytochemical Constituents for Characterization and Authentication of Tomatoes by General Linear Model Linked to Automatic Interaction Detection (GLM-AID) and Artificial Neural Network Models (ANNs), PLoS ONE10 (2015). 10.1371/journal.pone.0128566Search in Google Scholar PubMed PubMed Central

28. AstrayG., Fernández-GonzálezM., Rodríguez-RajoF. J., LópezD. and MejutoJ. C.: Airborne castanea pollen forecasting model for ecological and allergological implementation, Sci Total Environ548–549 (2016) 110121. 10.1016/j.scitotenv.2016.01.035Search in Google Scholar PubMed

29. CybenkoG.: Approximation by superpositions of a sigmoidal function, Mathematics of Control, Signals, and Systems2 (1989) 303314. 10.1007/BF02551274Search in Google Scholar

Received: 2016-11-15
Accepted: 2016-11-25
Published Online: 2017-03-03
Published in Print: 2017-03-15

© 2017, Carl Hanser Publisher, Munich

Scroll Up Arrow