Show simple item record

dc.contributor.advisorTayfur, Gökmenen
dc.contributor.authorBirgili, Savaşen
dc.date.accessioned2014-07-22T13:50:50Z
dc.date.available2014-07-22T13:50:50Z
dc.date.issued2002en
dc.identifier.urihttp://hdl.handle.net/11147/3079
dc.descriptionThesis (Master)--Izmir Institute of Technology, Environmental Engineering, Izmir, 2002en
dc.descriptionIncludes bibliographical references (leaves: 68-72)en
dc.descriptionText in English; Abstract: Turkish and Englishen
dc.descriptionxiv, 88 leavesen
dc.description.abstractIn this study, a systematic approach to the development of the artificial neural networks based forecasting model is presented. S02, and dust values are predicted with different topologies, inputs and transfer functions. Temperature and wind speed values are used as input parameters for the models. The back-propagation learning algorithm is used to train the networks. R 2 (correlation coefficient), and daily average errors are employed to investigate the accuracy of the networks. MATLAB 6 neural network toolbox is used for this study. The study results indicate that the neural networks are able to make accurate predictions even with the limited number of parameters. Results also show that increasing the topology of the network and number of the inputs, increases the accuracy of the network. Best results for the S02 forecasting are obtained with the network with two hidden layers, hyperbolic tangent function as transfer function and three input variables (R2 was found as 0,94 and daily average error was found as 3,6 j..lg/m3).The most accurate results for the dust forecasting are also obtained with the network with two hidden layer, hyperbolic tangent function as transfer function and three input variables (R2 was found as 0,92 and daily average error was found as 3,64 j..lg/m3).S02 and dust predictions using their last seven days values as an input are also studied, and R2 is calculated as 0,94 and daily average error is calculated as 4,03 Jlg/m3 for S02 prediction and R2 is calculated as 0,93 and daily average error is calculated as 4,32 Jlg/m3 for dust prediction and these results show that the neural network can make accurate predictions.en
dc.language.isoengen
dc.publisherIzmir Institute of Technologyen
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subject.lcshNeural networks (Computer science)en
dc.titleArtificial neural networks model for air quality in the region of İzmiren
dc.typemasterThesisen
dc.contributor.departmentIzmir Institute of Technology. Environmental Engineeringen
dc.relation.publicationcategoryTezen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record