Characterization of vowel patterns in broiler chickens under heat stress

• Grant number: 21/09298-9
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: December 01, 2021
• End date: July 31, 2023
• Field of knowledge: Agronomical Sciences - Agricultural Engineering - Rural Buildings and Ambience
• Principal Investigator: Késia Oliveira da Silva Miranda
• Grantee: Gabriela Camargo
• Host Institution: Escola Superior de Agricultura Luiz de Queiroz (ESALQ). Universidade de São Paulo (USP). Piracicaba , SP, Brazil

Abstract

Chicken meat is one of the most consumed proteins in the world, being the search for increasingly intensified production systems is fundamental. Environments intensives can generate stressful situations for the birds, with that increased the need to adopt new measures for the management and monitoring of animals in it concerns your behavior and physical condition. In this sense, an environment of less stressful production promotes healthy birds, with good genetic expression for weight gain, production of quality meat, and animal welfare. For this study a non-invasive monitoring tool was chosen that makes it possible to monitor the animal from a distance in order to eliminate possible stressors, through the characterization of the vowel patterns of broiler chickens under heat stress. will be used vocalizations of 90 animals of the same age Cobb commercial lineage that are part of an experiment that was conducted at the Climate Chamber of Department of Biosystems Engineering - NUPEA of the Superior School of Agriculture "Luiz de Queiroz", August 2020, located in the municipality of Piracicaba/SP. With the CEUA protocol number 2019-24. A microphone unidirectional was used for sound capture, as well as group images were recorded by a digital camera, so that they are then used as a validation of the behaviors found in the audios. For sound processing an algorithm in MATLAB® mathematical software (R2018a) will be developed. You patterns extracted from the audios will be used as input variables of a network which will be trained to identify the behaviors expressed in an automated. In this way, it is expected to develop an automatic analysis method behavior of broiler chickens, through the classification of the behavior of the animals subjected to a heat stress condition. (AU)