Theses/Dissertations/Projects

Permanent URI for this collection

https://ir.bellsuniversity.edu.ng/handle/123456789/230

Browse

Browsing Theses/Dissertations/Projects by Subject "Information communication technology"

Now showing 1 - 1 of 1
  • No Thumbnail Available
    ItemMetadata only
    Neuro-Fuzzy Approach to River Sediment Yield Prediction
    (Bells University of Technology, 2016-07-28) OLUWATOBI, Balogun; Prof. E. R. Adagunodo
    The advancement of Information and Communication Technology has created an unlimited space for exploration in different areas in order to make meaningful observations and predict at an optimum accuracy. All around the world, data are being generated every moment in large quantities, but these data are of no use until they can be converted to useful information. The limitation of existing models used for predicting River Sediment yield in order to forestall against natural and economic disasters forms the basis of the motivation of this research. By taking advantage of the opportunities presented by the advancement of technology, this research focuses on predicting the sediment yield from Oyan gauging station of Ogun-Osun River Basin and comparing the output with the result with other existing result. Some conventional methods available for sediment load/yield estimation are largely empirical. In this research, an ANFIS(Adaptive Neuro-Fuzzy Inference System) is used to predict the sediment yield of Oyan gauging of Ogun-Osun River Basin. The ANFIS is a feed forward layered architecture and uses the back propagation algorithm to train the network. For this research, four inputs are used, the water stage and water discharge, water temperature, and rainfall. During the simulation, the ANFIS Neuro fuzzy model fitted the observed sediment data better than the ANN(Artificial Neural Network) in the validation stages except when fed with three variable where the ANN model has a root mean error of 23.2996 as compared to that of ANFIS Neuro-fuzzy which had a root square error of 23.3443.But when fed with two and four input, the ANFIS Neuro-fuzzy model performed better than the ANN model with a Root mean square error of 23.3134 for two input ad 23.2129 for four input as compared to that of ANN which had 23,4762 for two input and 23.5304 for four input. The ANFIS model proved to have a better prediction capability that its other contemporaries and can be used efficiently predict sediment yield movement from water bodies to plan and forestall against eventualities.