Obesity Level Classification Based on Decision Tree and Naïve Bayes Classifiers

Salisu Garba, Marzuk Abdullahi, Umar Abdullahi Umar and Nura Tijjani Wurno

Keywords: Boosting and bagging technique, classification models, enhanced decision tree, naïve Bayes classifiers, obesity level


This paper proposed an approach for obesity levels classification. The main contribution of this work is the use of boosting and bagging techniques in the decision tree (DT) and naïve Bayes (NB) classification model to improve the accuracy of obesity levels classification. This is achieved by introducing a boosting and bagging technique to further improve the recognition rate of obesity levels in the DT model, eliminating the correlated features, and eliminating the zero observations problem in the NB model. To validate the accuracy of the proposed approach, empirical evaluation was carried out using WEKA to determine the accuracy, precision, and recall. The results show that the DT classification model performs better in terms of accuracy and average precision. The proposed approach can help in software development for the classification of individuals with obesity.