Volume 18, No. 6, 2021

Gain Ratio With Optimization Based Feature Selection Method



Precipitation in any form—such as rain, snow, and hail—can affect day-to-day outdoor activities. Rainfall prediction is one of the challenging tasks in weather forecasting process. Accurate rainfall prediction is now more difficult than before due to the extreme climate variations. Machine learning techniques can predict rainfall by extracting hidden patterns from historical weather data. Selection of an appropriate classification technique for prediction is a difficult job. In this research work, Gain Ratio and Differential Evolution hybridized for choosing the most relevant features. Once, the suitable features subset is obtained, the classification algorithm called Artificial Neural Network (ANN), and other classifiers are adopted, that could classify the info in the manner that is effective the selected features.

Pages: 6479-6491

Keywords: Feature Selection, Classification, Information Gain, Gain Ratio, Optimization, Decision Tree, Artificial Neural Network.

Full Text