# Multiscale Sample Entropy-Based Feature Extraction with Gaussian Mixture Model for Detection and Classification of Blue Whale Vocalization

## TL;DR

This paper introduces a new method for detecting and classifying blue whale vocalizations using multiscale entropy and Gaussian mixture models, outperforming traditional techniques.

## Contribution

The novel contribution is the use of multiscale sample entropy combined with a GMM-based feature selection method for improved blue whale call classification.

## Key findings

- The MSE-GMM method outperforms PCA-GMM, DMD-GMM, and WF-GMM in classification accuracy and error rates.
- A GMM-based feature selection method is proposed to evaluate correlated features and improve model performance.
- The method is tested using data from the Antarctic open source library.

## Abstract

A multiscale sample entropy (MSE) algorithm is presented as a time domain feature extraction method to study the vocal behavior of blue whales through continuous acoustic monitoring. Additionally, MSE is applied to the Gaussian mixture model (GMM) for blue whale call detection and classification. The performance of the proposed MSE-GMM algorithm is experimentally assessed and benchmarked against traditional methods, including principal component analysis (PCA), wavelet-based feature (WF) extraction, and dynamic mode decomposition (DMD), all combined with the GMM. This study utilizes recorded data from the Antarctic open source library. To improve the accuracy of classification models, a GMM-based feature selection method is proposed, which evaluates both positively and negatively correlated features while considering inter-feature correlations. The proposed method demonstrates enhanced performance over conventional PCA-GMM, DMD-GMM, and WF-GMM methods, achieving higher accuracy and lower error rates when classifying the non-stationary and complex vocalizations of blue whales.