Perceptred Feature Based Kriging Gradient Boost Classification for Big Data Driven Marine Weather Forecasting

Marine Weather Forecasting with Big Data with minimum time, error and maximum accuracy is of major concern to be addressed. In this work, a method called, Perceptred-based Feature and Kriging Gradient Boost Classification (PF-KGBC) is introduced with big data with the objective of improving the prediction performance marine weather with high accuracy and less time consumption. The PF-KGBC method is split into two parts. They are feature selection using perceptron classifier model and classification using Kriging EnsembledeXtreme Gradient Boost for marine weather forecasting. With the assistance of supervised learning algorithm based on perceptron classifier that involves a functional inputAfter feature selection process, Kriging EnsembledeXtreme Gradient Boost Classification is performed with the purpose of forecasting marine weather data. PF-KGBC compared by conventional techniques and performance was implemented by Java platform. The proposed method has prediction results and improvements were observed with various metrics.