Detection and identification of manatee individual vocalizations in Panamanian wetlands using spectrogram clustering

Abstract

This work presents a methodology to automatically detect and identify manatee vocalizations in continuous passive acoustic underwater recordings. Given that vocalizations of each manatee present a slightly different frequency content, it is possible to identify individuals using a non-invasive acoustic approach. The recordings are processed in four stages, including detection, denoising, classification, and manatee counting and identification by vocalization clustering. The main contribution of this work is considering the vocalization spectrogram as an image (i.e., two-dimensional pattern) and representing it in terms of principal component analysis coefficients that feed a clustering approach. A performance study is carried out for each stage of the scheme. The methodology is tested to analyze three years of recordings from two wetlands in Panama to support ongoing efforts to estimate the manatee population.

Bioacoustic Classification of Antillean Manatee Vocalization Spectrograms Using Deep Convolutional Neural Networks

“…A scheme of the proposed analysis methodology used in this article is shown Figure 1. This research extends previous work from the authors presented in [5] by focusing in the denoising, spectrogram creation and classification aspects.…”

“…In this context, the authors proposed a reliable scheme to identify and count manatee using underwater passive recordings to support other fragmentary efforts to estimate the Antillean manatee population in Panamanian wetlands [5], considerably improving previous population estimates described in [3]. This scheme takes advantage of the features of the bioacoustic sounds (vocalizations) produced by manatees that were previously described in [6,7].…”

Combining convolutional neural networks with unsupervised learning for acoustic monitoring of robotic manufacturing facilities

“…The concept of unsupervised analysis has been studied for robotic systems, for example with autonomous vehicles. 27 Researchers have also explored approaches for combining unsupervised clustering with supervised audio classification in application spaces such as emotion recognition and the analysis of animal vocalizations, [28][29][30][31] though the concept has not previously been considered for industrial system monitoring.…”

Consideraciones para la incorporación de la Inteligencia Artificial en un programa de pregrado de Ingeniería Eléctrica

“…Área de relación de la ingeniería eléctrica Ejemplos de aplicaciones Algoritmos de agrupamiento Procesamiento de señales  Señales de radar (Matuszewski, 2018).  Señales de sonido (Merchan et al, 2019) Circuitos eléctricos  Diseño de circuitos (Lin y Liu, 2010).…”