Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/202347
Title: EFFECTIVE RAINFALL PREDICTION USING HYBRID INTELLIGENT SYSTEMS
Researcher: SUDHA.M
Guide(s): Valarmathi.B
Keywords: HYBRID INTELLIGENT SYSTEMS
University: VIT University
Completed Date: 
Abstract: newline Rainfall prediction is a multidimensional, dynamic, data-intensive and chaotic process. It is one of the several computational tasks identified by meteorologists as the core problem in weather modeling across the globe. This investigation aims to determine the significant atmospheric parameters and appropriate predictive techniques to enhance the precision of weather prediction system using hybrid data-driven approach. The remarkable contribution of this thesis is to improve the efficiency of the data-driven approach by exploiting the empirical characteristics of the input weather parameters. The research outcomes reveal that, the fundamental and generic data mining techniques are ineffective to comprehend the hidden input-output relationship. Therefore, this research newlineintroduces an optimal feature selection using Maximum Frequency Weighted Reduct newlineSelection (MFWRS) and Reduct Selection Using Genetic Algorithm (RSGA) to identify newlinethe effective input parameters in modeling short-term rainfall forecast scenario. newlineThe thesis further outlines the application of different intelligent computing newlineapproaches based on rough sets, fuzzy sets, evolutionary computing, neural networks and newlinetheir implications for the practical workings of short-term rainfall forecasting. The newlineproposed hybrid frameworks modeled using Adaptive Neuro-Fuzzy Inference Systems, newlineFuzzy Rule-Based Classification and contemporary data mining techniques performed newlinesubstantially better when trained with feature subsets generated using the proposed newlineoptimal reduct selection techniques. The thesis introduces an unconventional Adaptive newlineRough-Evolutionary Neuro Approach (ARENA) and Adaptive Rough Neuro-Fuzzy newlineApproach (ARNFA) based hybrid intelligent systems. The proposed ARENA achieved newline98.01% prediction accuracy with a nominal error rate of 1.99%. The methodical analysis newlinerevealed ARENA as an appropriate tool to deal with the real-world rainfall prediction newlineefficiently by means of identifying significant weather parameters.
Pagination: 3MB
URI: http://hdl.handle.net/10603/202347
Appears in Departments:School of Information Technology and Engineering

Files in This Item:
File Description SizeFormat 
596 certificates.pdfAttached File299.49 kBAdobe PDFView/Open
596 pli pages.pdf486.83 kBAdobe PDFView/Open
chapter-1-18-25.pdf157.01 kBAdobe PDFView/Open
chapter 2-26-44.pdf178.96 kBAdobe PDFView/Open
chapter 3-45-59.pdf363.46 kBAdobe PDFView/Open
chapter 4-60-69.pdf375.36 kBAdobe PDFView/Open
chapter 5-70-89.pdf389.5 kBAdobe PDFView/Open
chapter 6-90-104.pdf552.58 kBAdobe PDFView/Open
chapter 8 -115-128.pdf407.08 kBAdobe PDFView/Open
chapter 9 -129-132.pdf127.32 kBAdobe PDFView/Open
list of publications.pdf7.84 kBAdobe PDFView/Open
reference.pdf318.93 kBAdobe PDFView/Open
title-1.pdf8.96 kBAdobe PDFView/Open


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