Open AccessA Novel Method of Rainfall Prediction using MLP-FFN and Hybrid Neural Network Algorithm
Author(s) -
G. Thailambal,
Ms. P. Shanmugalakshmi,
R. Durga
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.j9607.0881019
Subject(s) - artificial neural network , crossover , preprocessor , computer science , multilayer perceptron , perceptron , algorithm , set (abstract data type) , artificial intelligence , point (geometry) , data mining , pattern recognition (psychology) , mathematics , geometry , programming language
The present work proposes a cross breed neural system and multilayer perceptron_ feed forward system based model for precipitation forecast. The crossover models are multistep technique. At first, the information is bunched into a sensible number of groups, at that point for each bunch has prepared independently by Neural Network (NN). Also, as a preprocessing stages a component choice stage is incorporated. Feed forward choice calculation is utilized to locate the most reasonable arrangement of highlights for foreseeing precipitation. To set up the creativity of the proposed cross breed forecast model (Hybrid Neural Network or HNN) has been contrasted and two surely understood models in particular multilayer perceptron feed-forward system (MLP-FFN) utilizing diverse execution measurements. The reproduction results have uncovered that the proposed model is essentially superior to conventional strategies in anticipating precipitation.