Select the Most Suitable Inputs to the Artificial Neural Network Model by Using the ACO Algorithm

Document Type : Research Article


Associate Professor Department of Water Engineering College of Agriculture University of Birjand


the performance criteria have used in this study is including mean square error (MSE), sum square error (SSE), Nash_Sutcliffe and correlation coefficient. The result indicated the best ANNa model is ANNa2 with MSE equal 0.0017. Inputs in this model are Total Cation, Total Hardness and Calcium. The best ANNb model is ANNb3 with MSE equal 0.0012. Inputs in this model are Sodium adsorption ratio, pH, Total Hardness and Calcium. Also, the results indicated that using ACO algorithm for finding the best input parameters had increased neural network performance, in ANNb models than ANNa for validation network and for test network we see with increases inputs the performance of network increases. According to results we can say that against try and error for finding the best inputs, we can use the parameter that those had a high correlation between target parameter as first step. But parameters that have high correlation between target parameter, necessarily don't the best inputs. But the parameter that those had a high correlation between target parameter as inputs of neural network. Also, we find that the ACO algorithm can be used as a method of input variable selection and that improved the performance of neural network.


Main Subjects

Khoshnazar A, Nasrabadi T and Abbasimaedeh P. Evaluating the efficiency of artificial neural network in prediction of electrical conductivity of Zarrinehroud river. Journal of Human and Environment. 2013; 10(22):1-16. [Persian]
[2]. Banejad H, Kamali M, Amirmoradi K and Olyaie E. Forecasting some of the qualitative parameters of rivers using wavelet artificial neural network hybrid (w-ann) model (case study: Jajroud river of Tehran and Gharaso river of Kermanshah). Journal of Health and Environment, 2013; 6(3): 277-294. [Persian]
[3]. Barzegar R, Adamowski J and Asghari Moghaddam A. Application of wavelet-artificial intelligence hybrid models for water quality prediction: a case study in Aji-chay river, Iran. Stochastic Environmental Research and Risk Assessment, 2016; 30(7):1797-1819.
[4]. Sattari MT, Rezazadeh Joudi A and Kusiak A. Estimation of water quality parameters with data-driven model. Journal American Water Works Association. 2016; 108:4.
[5]. Kanda EK, Kipkorir EC and Kosgei JR. Dissolved oxygen modelling using artificial neural network: a case of river nzoia, lake victoria basin, kenya. Journal of Water Security, 2016; 2:1-7.
[6]. Seght Foroosh A, Monjezi M and Khademi Hamidi J. Optimization of blasting operation using hybrid Neural Network-Ant Colony (Case Study: Delkan Iron Mine). Journal of Modeling and Engineering. 2017; DOI: 10.22075/JME.2017.2449. [Persian]
[7]. Faghih H. Evaluating artificial neural network and its optimization using genetic algorithm in estimation of monthly precipitation data (case study: Kurdistan region). Journal of Water and Soil Science (Journal of Science and Technology of Agriculture and Natural Resources). 2010. 14(51): 27-44. [Persian]
[8]. Socha K and Blum C. An ant colony optimization algorithm for continuous optimization: application to feed-forward neural network training. Journal of Neural Computing and Applications. 2007; 16: 235-247.
[9]. Emami Skardi MJ, Afshar A, Saadatpour M and Solis SS. Hybrid ACO–ANN-based multi-objective simulation–optimization model for pollutant load control at basin scale. Environmental Modeling and Assessment. 2015; 20(1): 29-39.
[10]. Valdez F, Castillo O and Melin P. Ant colony optimization for the design of modular neural networks in pattern recognition. In Neural Networks (IJCNN), International Joint Conference. 2016; 163-168.
[11]. Zho G. Ant colony optimization training feed-forward neural network based on elitist selection strategy. Boletín técnico. 2017; 55(1): 200-206.
[12]. Zeynali MJ, Nikbakht S, Mohammadezapour O. Prediction input flows to Mollasadra reservoir by using artificial neural network. 5th Iranian Water Resources Management Conference. Shahid Beheshti University. 29 Jul 2013. [Persian]
 [13]. Zeynali MJ, Mohammadrezapour O and Forughi F. Comparison of imperialist competitive algorithm (ICA) and ant colony algorithm (ACO) for optimizing exploitation of Doroudzan reservoir with application of chain constraints approach. Journal of Water and Soil Conservation. 2016; 22(6): 231-243. [Persian]
Volume 5, Issue 1
April 2018
Pages 59-68
  • Receive Date: 08 April 2017
  • Revise Date: 10 July 2017
  • Accept Date: 08 July 2017
  • First Publish Date: 21 March 2018
  • Publish Date: 21 March 2018