Discerning pig screams in production environments

J Vandermeulen; C Bahr; E Tullo; I Fontana; S Ott; M Kashiha; M Guarino; C P H Moons; F A M Tuyttens; T A Niewold; D Berckmans

doi:10.1371/journal.pone.0123111

Discerning pig screams in production environments

PLoS One. 2015 Apr 29;10(4):e0123111. doi: 10.1371/journal.pone.0123111. eCollection 2015.

Authors

J Vandermeulen¹, C Bahr¹, E Tullo², I Fontana², S Ott³, M Kashiha¹, M Guarino², C P H Moons⁴, F A M Tuyttens⁵, T A Niewold⁶, D Berckmans¹

Affiliations

¹ M3-BIORES-Measure, Model & Manage Bioresponses, KU Leuven, Leuven, Belgium.
² Department of Health, Animal Science and Food Safety, Università degli Studi di Milano, Milan, Italy.
³ Livestock-Nutrition-Quality, KU Leuven, Leuven, Belgium; Departement of Animal Nutrition, Genetics and Ethology, Laboratory for Ethology, Ghent university, Merelbeke, Belgium.
⁴ Departement of Animal Nutrition, Genetics and Ethology, Laboratory for Ethology, Ghent university, Merelbeke, Belgium.
⁵ Departement of Animal Nutrition, Genetics and Ethology, Laboratory for Ethology, Ghent university, Merelbeke, Belgium; Institute for Agricultural and Fisheries Research (ILVO), Animal Sciences Unit, Melle, Belgium.
⁶ Livestock-Nutrition-Quality, KU Leuven, Leuven, Belgium.

Abstract

Pig vocalisations convey information about their current state of health and welfare. Continuously monitoring these vocalisations can provide useful information for the farmer. For instance, pig screams can indicate stressful situations. When monitoring screams, other sounds can interfere with scream detection. Therefore, identifying screams from other sounds is essential. The objective of this study was to understand which sound features define a scream. Therefore, a method to detect screams based on sound features with physical meaning and explicit rules was developed. To achieve this, 7 hours of labelled data from 24 pigs was used. The developed detection method attained 72% sensitivity, 91% specificity and 83% precision. As a result, the detection method showed that screams contain the following features discerning them from other sounds: a formant structure, adequate power, high frequency content, sufficient variability and duration.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Animals
Area Under Curve
ROC Curve
Stress, Physiological
Swine
Tape Recording
Vocalization, Animal / classification*

Grants and funding

This research was part of a project funded by Agentschap voor Innovatie door Wetenschap en Technologie (project number: 080530/LBO). http://www.iwt.be/. The projects promotors received the funding (Berckmans, D., Bahr, C., Moons, C. P. H. and odberg F.(last person was replaced because of retirement by Tuyttens F. A. M.). These promotors paid the following PhD students: Vandermeulen, J, Ott, S and Kashiha, M. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.