The application of fuzzy lattice reasoning to nocturnal animal vocalization recognition

摘要

A nocturnal animal identification system is proposed in this work to assist in the recognition of different kinds of nocturnal animals. Firstly, each sound sample was separated as syllables. Next, the syllables were converted into Mel Frequencies Cepstral Coefficients (MFCCs) as the main identification feature of the proposed work. A decision tree was then built and the clustering results were classified with a fuzzy lattice reasoning (FLR) classifier. A series of simulations were conducted and the results showed that the proposed approach can effectively increase the recognition rate. In future work, we plan to expand the database of sound samples to increase the accuracy rate for each species.