IDENTIFIKASI HEWAN BERDASARKAN POLA AKUSTIK DENGAN PRINSIP EKSTRAKSI WAVELET DAN KLASIFIKASI MULTI-LABEL JARINGAN SYARAF TIRUAN

An acoustic identification and classification system of frogs has been designed based on the principle wavelet extraction label using an artificial neural network (ANN). This consists electronic detection for frog audio as well interface MATLAB 2018b software ANN provider device. As input network, 5 types were used, namely rock (Limnonectes macrodon), blentung (Kaloula baleata), hip (Limnonectesblythii), rice field (Fejervarya cancrivora), trench frog. limnocharis). ), each with 12 sound samples. Before being inserted into 3 levels samples extracted denoised symlet 3. Furthermore, in training process, validation test used. After training, was able to identify type tested.