Decision Tree Learning Algorithm and Naïve Bayes Classifier Algorithm Comparative Classification for Mango Pulp Weevil Mating Activity

Abstract

Mango pulp weevil (MPW) behavior has been long studied but frequency characterization of the said pest in different adult activities was not yet explored. This study focused on the comparative classification of the mating activity of the MPW. Data was collected on a controlled environment with an acoustic chamber built, and the frequency was acquired using a MEMS (Micro Electro-Mechanical Systems) microphone, connected through a microcontroller. Two different algorithms namely the Decision Tree Learning algorithm and Naïve Bayes Classifier algorithm, were tested and compared. Performance in the filtering and optimization of the two algorithms were evaluated in three different stages of mating, the pre-mating, mating and post-mating stage. Comparison of the results of the two algorithms for the premating stage, the Decision tree algorithm reached 75% accuracy while Naïve Bayes algorithm had 95% accuracy, for the mating stage, it was 55% as compared to 70% and in post mating stage, 45% accuracy for the Decision Tree Learning algorithm and 85% for the Naïve Bayes algorithm. These results showed that Naïve Bayes classifier is more accurate in classifying the different stages of MPW activity.