Analysis of Poultry Vocalizations for Age Estimation using Cepstral Coefficients and C4.5 Classification

Abstract. Poultry scientists and researchers have been studying the possibility of identifying bird stress from the vocal patterns of broiler i¬‚ocks. Being able to identify stress or sickness in a i¬‚ock can lead to early interventions. However, as the i¬‚ock ages, the vocal properties change. This paper presents the preliminary results of an age classii¬cation technique using the C4.5 decision three algorithm using Mel-frequency cepstral coefi¬cients (MFCCs), audio frequencies commonly used from speech processing. Sound data was collected continuously over a 61-day period. The i¬‚ock was composed of 400 Cobb500TM broilers raised under research conditions mimicking commercial operations. Results of the data processing and the C4.5 classii¬cation indicate that age can be determined within one day of error with 70% frequency. This process of determining age of a i¬‚ock is intended to be the i¬rst step in a larger comprehensive system for identifying the condition of the i¬‚ock and assessing animal welfare.