Optimal Frequency Characterization of Mango Pulp Weevil Mating Activity using Naïve Bayes Classifier Algorithm

Mango Pulp Weevil (MPW) is a highly quarantined pest that is an immense problem to most countries in Asia because of its destructive nature to mango harvest. Investigation of the frequency characteristic of this pest of is an untouched area of research. This study introduces the idea of frequency detection and classification of the mating activities of MPW using acoustic sensors and a machine learning algorithm, specifically the Naïve Bayes Algorithm. Soundproof chamber was built, and specimen monitoring is done during the night. Frequency acquisition was done using MEMS (Micro Electro Mechanical Systems) microphone as the acoustic sensor. The frequency is filtered and optimized by the trained Naïve Bayes Algorithm. The optimal pre-mating frequency ranges from 1450Hz to 2000Hz, while the optimal mating frequency ranges from 800Hz to 950Hz, and lastly, the optimal post-mating frequency ranges from 1000Hz to 1250Hz.