Using steepness coefficient to improve artificial neural network performance for environmental modeling

• Autorzy: Demir , Karadeniz A. , Demir N.M.
• Języki publikacji: EN

Abstrakty

EN

This paper presents results from a research study in which the effects of steepness coefficient (S) for the activation function of a back propagation neural network (BPNN) were investigated, and optimum values of S for each activation function were suggested for environmental modeling purposes. A BPNN algorithm was implemented in Excel Visual Basic for Applications with built-in activation functions of sigmoid, hyperbolic tangent, and sinc. Various steepness coefficients were employed for modeling cyclone Euler numbers for pressure drop estimation with three different activation functions. Best results for sigmoid function were obtained for S = 1.00 with a median value of mean square errors (MSEs) of 4.33*10-4. For hyperbolic tangent function, the optimum value of S was found as 0.2 with a median MSE value of 2.02*10-4. The median value of MSEs obtained with BPNN sinc function was 1.20*10-3 for S = 0.50. Results showed, for environmental modeling problems, that any activation function can be used with satisfactory results provided that an optimized value of the steepness coefficient is used, which is considered problem specific.

• Wydawca: -
• Czasopismo: Polish Journal of Environmental Studies
• Rocznik: 2016
• Tom: 25
• Numer: 4
• Opis fizyczny: p.1467-1477,fig.,ref.

Twórcy

autor

Demir

• Environmental Engineering Department, Faculty of Civil Engineering, Yildiz Technical University, 34220, Esenler, Istanbul, Turkeyy

autor

Karadeniz A.

• Environmental Engineering Department, Faculty of Civil Engineering, Yildiz Technical University, 34220, Esenler, Istanbul, Turkey

autor

Demir N.M.

• Environmental Engineering Department, Faculty of Civil Engineering, Yildiz Technical University, 34220, Esenler, Istanbul, Turkey

Bibliografia

• 1. Sibi P., Jones A.A., Siddarth P. Analysis of different activation functions using back propagation neural networks. Journal of Theoretical and Applied Information Technology 47 (3), 1264, 2013.
• 2. Elsayed K., Lacor C. Modeling and pareto optimization of gas cyclone separator performance using RBF type artificial neural networks and genetic algorithms. Powder Technol. 217, 84, 2012.
• 3. Azadi S., Karimi-Jashni A. Verifying the performance of artificial neural network and multiple linear regression in predicting the mean seasonal municipal solid waste generation rate: A case study of Fars province, Iran. Waste Manage. 48, 14, 2016.
• 4. Jahandideh S., Jahandideh S., Barzegari E., Askarian M., Movahedi M.M., Hosseini S., Jahandideh M. The use of artificial neural networks and multiple linear regression to predict rate of medical waste generation. Waste Manage. 29, 2874, 2009.
• 5. David C., Arivazhagan M., Ibrahim M. Spent wash decolourization using nano-Al2O3/kaolin photocatalyst: Taguchi and ANN approach. Journal of Saudi Chemical Society 19, 537, 2015.
• 6. Ye J., Cong X., Zhang P., Zeng G., Hoffmann E., Wu Y., Zhang H., Fang W. Operational parameter impact and back propagation artificial neural network modeling for phosphate adsorption onto acid-activated neutralized red mud. J. Mol. Liq. 216, 35, 2016.
• 7. Banerjee P., Sau S., Das P., Mukhopadhayay A. Optimization and modelling of synthetic azo dye wastewater treatment using graphene oxide nanplatelets: Characterization toxicity evaluation and optimization using artificial neural network. Ecotox. Environ. Safe. 119, 47, 2015.
• 8. Simic V.M., Rajkovic K.M., Stojicevic S.S., Velickovic D.T., Nikolic NC., Lazic M.L., Karabegovic I.T. Optimization of microwave-assisted extraction of total phenolic compounds from chokeberries by response surface methodology and artificial neural network. Sep. Purif. Technol. 160, 89, 2016.
• 9. Zhao B., Su Y. Artificial neural network-based modeling of pressure drop cefficient for cyclone separators. Chem. Eng. Res. Des. 88, 606, 2010.
• 10. Huang M., Wan J., Ma Y., Li W., Sun X., Wan Y. A fast predicting neural fuzzy model for on-line estimation of nutrient dynamics in an anoxic/oxic process. Bioresour. Technol. 101, 1642, 2010.
• 11. Aghav R.M., Kumar S., Mukherjee S.N. Artificial neural network modeling in competitive adsorption of phenol and resorcinol from water environment using some carbonaceous adsorbents. J Hazard. Mater. 188, 67, 2011.
• 12. Bhatti M.S., Kapoor D., Kalia R.K., Reddy A.S., Thukral A.K. RSM and ANN modeling for electrocoagulation of copper from simulated wastewater: Multi objective optimization using genetic algorithm approach. Desalination 274, 74, 2011.
• 13. Bayram A., Kankal , M. Artificial neural network modeling of dissolved oxygen concentrations in a Turkish Watershed. Pol. J. Environ. Stud. 24 (4), 1507, 2015.
• 14. Samli R., Sivri N., Sevgen S., Kiremitci V.Z. Applying artificial neural networks for the estimation of chlorophyll-a concentrations along the Istanbul Coast. Pol. J. Environ. Stud. 23 (4), 1281, 2014.
• 15. Hernandez-Ramirez D.A., Herrera-Lopez E.J., Rivera A.L., del Real-Olvera J. Artificial neural network modeling of slaughterhouse wastewater removal of COD and TSS by electrocoagulation. Stud. Fuzziness Soft Comput. 312, 273, 2014.
• 16. Wu W., Dandy G.C., Maier H.R. Protocol for developing ANN models and its application to the assessment of the quality of the ANN model development in drinking water quality modelling. Environ. Modell. Softw. 54, 108, 2014.
• 17. Elsayed K., Lacor C. CFD modeling and multiobjective optimization of cyclone geometry using desirability function, artificial neural networks and genetic algorithms. Appl. Math. Model. 37, 5680, 2013.
• 18. Talebi H.A., Patel R.V., Khorasani K. Control of flexible-link manipulators using neural networks. Lecture Notes in Control and Information Sciences 261, 79, 2001.
• 19. Demir S. A practical model for estimating pressure drop in cyclone separators: An experimental study. Powder Technol. 268, 329, 2014.
• 20. Karadeniz A. Effect of modifications on stairmand high efficiency type cyclone geometry on particle collection efficiency and pressure drop. MSc Thesis, Graduate School of Natural and Applied Sciences, Yıldız Technical University, Istanbul (in Turkish), 2015.
• 21. Cortes C., Gil A. Modeling the gas and particle flow inside cyclone separators. Prog. Energ. Combust. 33, 409, 2007.
• 22. Chen J., Shi M. A universal model to calculate cyclone pressure drop. Powder Technol. 171, 184, 2007

Identyfikatory

DOI

10.15244/pjoes/61958