Recognizing Family, Genus, and Species of Anuran Using a Hierarchical Classification Approach

Abstract

In bioacoustic recognition approaches, a "flat" classifier is usually trained to recognize several species of anuran, where the number of classes is equal to the number of species. Consequently, the complexity of the classification function increases proportionally to the amount of species. To avoid this issue we propose a "hierarchical" approach that decomposes the problem into three taxonomic levels: the family, the genus, and the species level. To accomplish this, we transform the original singlelabel problem into a multi-dimensional problem (multi-label and multiclass) considering the Linnaeus taxonomy. Then, we develop a top-down method using a set of classifiers organized as a hierarchical tree. Thus, it is possible to predict the same set of species as a flat classifier, and additionally obtain new information about the samples and their taxonomic relationship. This helps us to understand the problem better and achieve additional conclusions by the inspection of the confusion matrices at the three levels of classification. In addition, we carry out our experiments using a Cross-Validation performed by individuals. This form of CV avoids mixing syllables that belong to the same specimens in the testing and training sets, preventing an overestimate of the accuracy and generalizing the predictive capabilities of the system. We tested our system in a dataset with sixty individual frogs, from ten different species, eight genus, and four families, achieving a final Micro-and Average-accuracy equal to 86% and 62% respectively.

DCG++: A data-driven metric for geometric pattern recognition

“…Scientists take advantage of their vocalization capability and apply acoustics surveys to identify their numbers. Interestingly, time series of their calls have also been used to identify families, genera, and species among those anurans [54]. In fact, there is a large body of literature on that topic that goes beyond the scope of this paper.…”

A comparison of hierarchical multi-output recognition approaches for anuran classification

“…Finally, Colonna et al (2016b) proposed and evaluated an LCPN approach to recognizing anuran species. The results were promising, however, a baseline comparison against a flat classifier or another hierarchical approach was not presented.…”

Evolução da semissupervisão em detecção online de agrupamentos

“…O aprendizado semissupervisionado, proposto pioneiramente em [Scudder 1965], foi desenvolvido a partir da necessidade de propor e avaliar o desempenho das técnicas que utilizam conhecimento prévio, ou seja, quando têm-se alguma informação adicional ou conhecimento sobre o domínio. No contexto de agrupamento de dados, em geral, essa informação adicional é conhecida como restrições e é um conjunto pequeno usado para auxiliar o algoritmo no processo de detecção dos agrupamentos [Chapelle et al 2006]. Espera-se um desempenho superior dos algoritmos quando faz-se uso da informação de semissupervisão em relação as técnicas não supervisionadas.…”