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

Abstract

In bioacoustic recognition approaches, a "flat" classifier is usually trained to recognize several species of anurans, where the number of classes is equal to the number of species. Consequently, the complexity of the classification function increases proportionally with the number 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. To accomplish this, we transform the original single-labelled problem into a multi-output problem (multi-label and multi-class) considering the biological taxonomy of the species. We then develop a top-down method using a set of classifiers organized as a hierarchical tree. We test and compare two hierarchical methods, using (1) one classifier per parent node and (2) one classifier per level, against a flat approach. Thus, we conclude that 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 better understand the problem and achieve additional conclusions by the inspection of the confusion matrices at the three classification levels. In addition, we propose a soft decision rule based on the joint probabilities of hierarchy pathways. With this we are able to identify and reject confusing cases. We carry out our experiments using 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 methods in a dataset with sixty individual frogs, from ten different species, eight genera, and four families, achieving a final Macro-Fscore of 80 and 70% with and without applying the rejection rule, respectively.

Explainable Machine Learning for Scientific Insights and Discoveries

“…Classical tools such as confusion matrices are also used as interpretation tools on the way to scientific outcomes. In a bio-acoustic application for the recognition of anurans using acoustic sensors, Colonna et al [2018] use a hierarchical approach to jointly classify on three taxonomic levels, namely the family, the genus, and the species. Investigating the confusion matrix per level enabled for example the identification of bio-acoustic similarities between different species.…”

CORIGAN: Assessing multiple species and interactions within images

“…To reduce the risk of false positives and false negatives (especially when dealing with unknown species), hierarchical classification approaches could be developed. These methods are a known technique to improve model generalization and have been shown to be relevant in handling biological data (Colonna, Gama, & Nakamura, ; Redmon & Farhadi, ).…”

Insect interaction analysis based on object detection and CNN

“…A way to handle these issues can be an implementation of a hierarchical classification. Such algorithms have already been successfully used in general object detection methods [13] as well as for handling ecological data [14].…”