A Classification Scheme Based on Directed Acyclic Graphs for Acoustic Farm Monitoring

Intelligent farming as part of the green revolution is advancing the world of agriculture in such a way that farms become evolving, with the scope being the optimization of animal production in an eco-friendly way. In this direction, we propose exploiting the acoustic modality for farm monitoring. Such information could be used in a stand-alone or complimentary mode to monitor constantly animal population and behavior. To this end, we designed a scheme classifying the vocalizations produced by farm animals. More precisely, we propose a directed acyclic graph, where each node carries out a binary classification task using hidden Markov models. The topological ordering follows a criterion derived from the Kullback-Leibler divergence. During the experimental phase, we employed a publicly available dataset including vocalizations of seven animals typically encountered in farms, where we report promising recognition rates outperforming state of the art classifiers.

I. Introduction

The area of Computational Bioacoustic Scene Analysis has received increasing attention by the scientific community in the last decades [1], [2], [3], [4]. Such interest is motivated by the potential benefits that can be acquired towards addressing major environmental challenges including invasive species, infectious diseases, climate and land-use change, etc. Availability of accurate information regarding range, population size and trends is crucial for quantifying the conservation status of the species of interest. Such information can be obtained via classical observer-based survey techniques; however these are becoming inadequate since they are a) expensive, b) subject to weather conditions, c) cover a limited amount of time and space, etc. To this end, autonomous recording units (ARUs) are extensively employed by biologists [5], [6]. An ARU which could be useful for the specific application is available at https://www.wildlifeacoustics.com/products/song-meter-sm4. This is also motivated by the cost of the involved acoustic sensors which is constantly decreasing due to the advancements in the field of electronics.