Please use this identifier to cite or link to this item: https://idr.l2.nitk.ac.in/jspui/handle/123456789/14408
Full metadata record
DC FieldValueLanguage
dc.contributor.advisorDeka, Paresh Chandra-
dc.contributor.authorBanhatti, Aniruddha Gopal-
dc.date.accessioned2020-08-11T11:46:41Z-
dc.date.available2020-08-11T11:46:41Z-
dc.date.issued2013-
dc.identifier.urihttp://idr.nitk.ac.in/jspui/handle/123456789/14408-
dc.description.abstractThe accurate prediction of hydrological behavior in both urban and rural watershed can provide valuable information for the urban planning, land use, design of civil projects and water resources management. Hydrology system is influenced by many factors such as weather, land cover, infiltration, evapotranspiration, so it includes a good deal of stochastic dependent component, multi-time scale and highly non-linear characteristics. Hydrologic time series are often non-linear and non- stationary. In spite of high flexibility of Artificial Neural Network (ANN) in modeling hydrologic time series, sometimes signals are highly non-stationary and exhibit seasonal irregularity. In such situation, ANN may not be able to cope with non-stationary data if pre-processing of input and/or output data is not performed. Pre-processing data refers to analyzing and transforming input and output variables in order to detect trends, minimize noise, underline important relationship and flatten the variables distribution in a time series. These analyses and transformations help the model learn relevant patterns. Pre-processing techniques, which facilitate stabilization of the mean and variance, and seasonality removal, are often applied to remove non- stationary aspect in data used to build soft computing models. In this study, different data pre-processing techniques are presented to deal with irregularity components that exist in a hydrologic time series data of the Brahmaputra basin within India at the Pandu gauging station near Guwahati city and Pancharatna gauging station further 150km downstream of Pandu by using daily time unit and their properties are evaluated by performing one step ahead flow forecasting using ANN. Three different preprocessed datasets are used for the analysis. Various ANN models are generated by varying network internal architecture with different input scenarios. The model results were evaluated by using Root Mean Square Error (RMSE)and Mean Absolute Percentage Error (MAPE) and found that Logarithmic based pre-processing techniques provide better forecasting performance among various pre-processing techniques. The results indicate that detecting non-stationary aspect and selecting an appropriate preprocessing technique is highly beneficial in improving the prediction performance of ANN model.en_US
dc.language.isoenen_US
dc.publisherNational Institute of Technology Karnataka, Surathkalen_US
dc.subjectDepartment of Applied Mechanics and Hydraulicsen_US
dc.subjectBrahmaputra Riveren_US
dc.subjectGauging Stationen_US
dc.subjectPanduen_US
dc.subjectPancharatnaen_US
dc.subjectGuwahatien_US
dc.subjectTime Seriesen_US
dc.subjectData Preprocessingen_US
dc.subjectANNen_US
dc.subjectFFBPen_US
dc.subjectActivation Functionen_US
dc.subjectRMSEen_US
dc.subjectMAPEen_US
dc.titleEffect Of Data Preprocessing On The Prediction Accuracy Of Artificial Neural Network Model in Hydrologic Time Seriesen_US
dc.typeThesisen_US
Appears in Collections:1. Ph.D Theses

Files in This Item:
File Description SizeFormat 
082012AM08P05.pdf5 MBAdobe PDFThumbnail
View/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.