Investigating effect of the preprocessing of the data on the accuracy of the modeling solid waste generation through ANNs

Document Type : Research Article

Authors

1 Ph.D. Student, Department of Civil and Environmental Engineering, Tehran University

2 Professor, Department of Civil and Environmental Engineering, Tehran University

Abstract

Waste generation in today industries is a serious problem. Waste generation from the production stage to the final disposal is an inevitable issue. Development of the cities and the industrialization causes the everyday increasing in solid waste generation. Therefore, knowing the waste values is an essential tool for solid waste management systems. In this research, artificial neural network is used as a financial tool for modeling solid waste generation in Mashhad. For this purpose, first, some pre-processing on the dependent and independent variables are done and the effect of this procedure on the accuracy of the model is investigated. Research findings clearly indicate that by using some preprocessing on the input data accurate results can be obtained. Three different conditions have been evaluated and the best one is selected which contains logarithm, trend removing and standardizing. The selected network has two hidden layers with five neurons in each one. Network performance parameters are MAPE, MSE and R2 that equals to 0.06, 0.46 and 0.86 respectively.

Keywords


 
[1] عبدلی،م . ع، " مدیریت مواد زائد جامد شهری"، انتشارات سازمان شهرداری های کشور، جلد اول، 1379
[2] Beigl,P.; Wassermann,G.; Schneider,F., and Salhofer,S. “Forecasting municipal solid waste generation in major European cities”, In:Pahl Wostl, C., Schmidt, S.,Jakeman, T.(Eds.), iEMSs 2004 International Congress: Complexity and Integrated Resources Management. Osnabrueck, Germany, 2004.
[3] Bach, H.; Mild, A.; Natter, M.; Weber, A. “Combining socio-demographic and logistic factors to explain the generation and collection of waste paper”, Resources Conservation and Recycling, vol.41, pp. 65– 73, 2004.
[4] Chung, s. “Projecting municipal solid waste: The case of domestic waste in HongKong special administration region”, Environmental enginerring science, vol. 27, pp. 13- 20, 2010.
[5] Chung.s. “Projection of trends in solid waste generation:The case of HongKong SAR”. Resource, conservation and recycling. Vol. 54, pp.759- 768, 2010.
[6] Daskalopoulos, E.; Badr, O., and Probert. S.D. “Municipal solidwaste: A prediction methodology for the generation rate and composition in the European Union countries and the United States of America”, Resources, Conservationand Recycling, vol.24, pp.155– 166, 1998.
[7] Dyson, B.; Chang, N. “Forecasting municipal solidwaste generation in a fast-growin Urban region with system dynamics modeling”, WasteManagement, vol. 25, pp. 669– 679, 2005.
[8] Iffat, A.; Leslie, S. “A Neural Network Approach to Time Series Forecasting”, proceeding of the world congress on engineering,vol.2,july, pp. 1-3,London,uk, 2009.
[9] Ojeda Benítez, S. “Mathematical modeling to predict residential solid waste generation”, Waste Management, vol. 28, pp. S7– S13, 2008.
[10] Noori,R.;Abdoli, M.; Jalili Ghazizade, M.; Samieifard,R. “Comparison of Neural Network and Principal Component-Regression Analysis to Predict the Solid Waste Generation in Tehran”, Iranian J Publ Health, Vol.38, pp. 74- 84, 2009.
[11] Noori, R., Abdoli, M.A.; AmeriGhasrodashti, A., JaliliGhazizade, M. “Prediction of Municipal Solid Waste Generation with Combination of Support Vector Machine and Principal Component Analysis: A Case Study of Mashhad”, Environmental Progress &Sustainable Energy, vol.28, pp. 249- 258, 2008.
[12] okka,L., Antikainen,R., Kauppi, P; “Municipal solid waste production and composition in Finland Changes in the period 1960– 2002 and prospects until 2020”, Resources, Conservation and Recycling, vol. 50, pp. 475– 488, 2007.
[13] Tawfiq, A.; Ibrahim El, Amin., “Artificial neural networks as applied to long-term demand forecasting”, Artificial Intelligence in Engineering, vol.13, pp. 189– 197, 2009.
[14] Zhang, G. “Timeseries forecasting using a hybrid ARIMA and neural network model”, Neurocomputing, vol. 50, pp. 159– 175, 2003.