NEW PREDICTION MODEL BASED ON CELLULAR GENETIC PROGRAM USING TWO-PHASE PRIVATE CLUSTERING

Abstract

In recent years, forest fires have increased drastically due to global warming. Forest fire prediction is the best way to control the spread of fire. The model presented, for the first time, in this paper can predict the spreading of fire in both homogeneous and inhomogeneous forests and can easily incorporate weather conditions and land topography. We propose a cellular automaton (CA) that simulates the spread of wildfire. We embed the CA inside of a genetic program (GP) that learns the state transition rules from spatially registered synthetic wildfire data.. Several machine learning classification techniques, including logistic regression, support vector classifier, decision tree. In addition to natural role in ecosystem dynamics natural disasters that threaten human lives, property and ecosystems efficient algorithm to perform optimal label flipping poisoning attacks and reliable suspicious data points mitigating the effect of such poisoning attacks. A novel BDI-GIS model was then proposed intention was defined based on spatial or non-spatial data and GIS functions. The cluster based model was developed to determine the prediction of forest fires and implemented it on a real dataset