ENHANCHMENT OF AGRICULTURE CLASSIFICATION BY USING DIFFERENT CLASSIFICATION SYSTEMS

Abstract

Agriculture is the main source of income for most of the people of African’s countries. So there is a need to transform the huge agriculture data into technologies and make them available to the farmers. The aim of this work is to find out the best classification algorithm enhances the classification of the agricultural dataset according to countries, area harvested, yield, production, and seed. Five classification algorithms are used namely J48, PART, Decision Table, IBK, and NaivBayes. Real agricultural dataset of the production in African countries is used and applied on WEKA software. The obtained results revealed that J48 algorithm outperformed in terms of error rate and provides slightly better performance than PART and Decision Table. IBK and NaiveBayes classification algorithms are not suitable for this dataset. This means that trees classifiers and rules classifiers are good for this dataset.