Zharfanudin Afif
Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Negeri Surabaya, Indonesia

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Classification of Panthera Species Based on Vocalization Using Higuchi Fractal Dimension and K-Nearest Neighbor Zharfanudin Afif; Dwi Juniati
CAUCHY: Jurnal Matematika Murni dan Aplikasi Vol 11, No 2 (2026): CAUCHY: JURNAL MATEMATIKA MURNI DAN APLIKASI
Publisher : Mathematics Department, Maulana Malik Ibrahim State Islamic University of Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18860/cauchy.v11i2.45890

Abstract

The genus Panthera, comprising the lion, jaguar, leopard, tiger, and snow leopard, exhibitscomplex vocalization characteristics as biological communication mechanisms in its naturalenvironment. However, manual acoustic identification is limited by environmental variability,individual sound variations, and recording noise, necessitating an automated approach.This study applies the Higuchi Fractal Dimension (HFD) for feature extraction and theK-Nearest Neighbor (KNN) algorithm for classification to recognize vocalizations of fiveextant Panthera species. The dataset consists of 100 recordings (20 per species) from theTierstimmenarchiv repository, preprocessed by noise reduction, two-second segment selection,mono conversion, resampling, and amplitude normalization. An empirical fundamentalfrequency (F0) verification showed a range of 53 to 367 Hz, confirming the adequacy of theDWT decomposition depth. The signals were decomposed using DWT (Daubechies 4, 7levels), and HFD was computed on the resulting coefficients with Kmax of 10, 16, 28, 32, 50,and 60. Performance was evaluated using repeated nested stratified cross-validation (5-foldouter loop repeated 10 times; 5-fold inner loop for selecting Kmax and k), together with anablation study of DWT approximation (cA) and detail (cD) coefficients and a non-DWTbaseline computed directly from the preprocessed signal. The highest mean accuracy, 70.80%(SD = 8.77%), was obtained by combining all detail coefficients with the three highest-levelapproximation coefficients, and was stable across randomly sampled seeds (SD = 1.06%).The non-DWT baseline reached only 56.40%. These results indicate that HFD computedon DWT sub-band provides discriminative features for classifying Panthera vocalizations,although repeated individuals across folds cannot be ruled out.