Using bioacoustic signals and Support Vector Machine for automatic classification of insects

Abstract

This work presents a new approach for automatic recognition of insects through intelligent systems. Insect species employ a set of sound signals for communication purposes which are specie-specific. Based on this fact, an acoustic signal recognition method has been designed to allow an efficient taxonomic classification of this animal group. In this paper, the sound signals have been characterized by Mel and Linear Frequency Cepstral Coefficients (MFCCs and LFCCs) to compare their efficacy. Then, a Support Vector Machine algorithm has been used for classification achieving an average success rate of 99.08% over 88 insect species.