Automatic Classification of Context in Induced Barking

Abstract

In this study, we present the results of classification experiments of induced dog barks in different contexts of behaviour. We applied four validation schemes to trained models in order to determine the level of individuals dependency for context classification. We did an analysis based on feature selection techniques to determine the best acoustic low-level descriptors for this task. Results showed that classification performance decreases when the model is evaluated leaving out acoustic information of individuals in the training stage. The acoustic feature set used in our experiments shown better results in comparison with other works using the same data.

Classification of Barking Context of Domestic Dog using High-Level Descriptors

“…Due to the positive results in previous similar classification analyzes [8][9][10], we used Support Vector Machine (SVM), Random Forest (RF) and Naive Bayes (NB) to conduct every experimentation in this study and store their results within Table 4 to Table 7. In addition, we also validated the stability of these machine learning algorithms with two validation methods:…”

“…These problems, coupled with the individual recognition, have shown better results in contrast with the ones obtained in the context classification. As determined by [9] the context classification of barks relies highly on the barking individual. It was reported that when a dog-independent classification model is used, a decrease in accuracy occurs, which explains the reason for low performance in the problem of context recognition.…”

Assessment of the Emotional State in Domestic Dogs using a Bi-dimensional Model of Emotions and a Machine Learning Approach for the Analysis of its Vocalizations

“…We used the acoustic characterization described in the section 2.4 and applied the machine learning technique Support Vector Machines (SVM) using a polynomial kernel to classify different dog vocalizations and various types of barks. We selected SVM given that this technique has been successfully used to classify human emotions employing a similar acoustic feature set [18]. Unlike the assessment presented in section 2.3, where we based the analysis on the human evaluations, in this section, it is done using automated tools.…”

Shared calls in repertoires of two locally distant gray parrots (Psittacus erithacus)

“…This method's main advantage is that it avoids categorizer's subjectivity and it can be highly accurate (e.g. Pérez-Espinosa et al 2015;Tchernichovski et al 2000). On the other hand, it is limited by the range of feature sets used, which need not be applicable to a particular categorization (Giret et al 2011).…”