جستجو در تالارهای گفتگو

Prediction of economic growth by extreme learning approach based on science and technology transfer Petra Karanikic´1 • Igor Mladenovic´2 • Svetlana Sokolov-Mladenovic´2 • Meysam Alizamir3 Springer Science+Business Media Dordrecht 2016 Abstract The purpose of this research is to develop and apply the extreme learning machine (ELM) to forecast gross domestic product (GDP) growth rate. Economic growth may be developed on the basis on combination of different factors. In this investigation was analyzed the economic growth prediction based on the science and technology transfer. The main goal was to analyze the influence of number of granted European patents on the economic growth by field of technology. GDP was used as economic growth indicator. The ELM results are compared with genetic programming (GP) and artificial neural network (ANN). The reliability of the computational models were accessed based on simulation results and using several statistical indicators. Coefficient of determination for ELM method is 0.9841, for ANN method it is 0.7956 and for the GP method it is 0.7561. Based upon simulation results, it is demonstrated that ELM can be utilized effectively in applications of GDP forecasting. Keywords GDP Forecasting Extreme learning machine Economic growth SP_3881_10.1007%2Fs11135-016-0337-y.pdf

Forecasting Daily Stream Flows of Vaniar River Using Genetic Programming and Neural Networks Approaches Original Article, C31 Roushangar K, Vojoudi Mehrabani F, Alami M.T Journal. Civil Eng. Urban. 3(4):197-200. 2013 ABSTRACT:This study compares three different artificial intelligence approaches, namely, gene expression programming (GEP), and artificial neural networks (ANN), in daily as well as monthly streamflow forecasting. Daily streamflow data from Vaniar River in the Northwestern Iran were used. Coefficient of determination, root mean square error and scatter index were used to compare simulation results. The study demonstrates that the optimal results were obtained from the triple-input models including streamflows of current and two previous days and that the GEP model performed better than the ANN model in daily streamflow forecasting. Keywords: Gene Expression Programming, Neural Networks, Forecasting منبع: [Hidden Content] دانلود: [Hidden Content].,31-197-200.pdf J. Civil Eng. Urban.,31-197-200.pdf