Non-Naive Bayesian classifier for Farmer Advisory System

Abstract

Agri-mining is a recent trend that helps the farmer through an Information Technology domain that is needed to improve the crop yield system. In this paper, create an effective classifier. For that purpose, Soybean dataset is used for analysis and is pre-processed for improving the accuracy of the classifier. Then the pre-processed input is given to the Non-Naive classifier which performs classification by using the Error Distribution method in the Kernel space. A new Non-Naive Bayesian algorithm is proposed in this project work which improves the performance of the Naive Bayesian algorithm by using Error Distribution functions. The result is compared with Naive Bayesian algorithm using the performance measures such that the ROC and Confusion Matrix. Then the performance of the proposed model is proved to be better than the Naive Bayesian algorithm.