Third International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications (MAVEBA 2003)

Florence, Italy
December 10-12, 2003

Automatic Detection of Chronic Pig Coughing from Continuous Registration in Field Situations

A. Van Hirtum (1), Marcella Guarino (2), A. Costa (2), P. Jans (1), K. Ghesquiere (1), J.-M. Aerts (1), P. L. Navarotto (2), Daniel Berckmans (1)

(1) Laboratory for Agricultural Buildings ResearchKatholieke Universiteit Leuven, Belgium
(2) Department of Veterinary and Technological Sciences for Food safety, Faculty of Veterinary Medicine, Milan, Italy

Cough is an important and present symptom in many respiratory diseases affecting the airways and lungs. Therefore it is interesting to monitor cough in a continuous, on-line way. The objective of this study was to test a cough recognition algorithm in real pig houses. Cough sounds were registered on 150 days old, 60 kg heavy Landrace x Large White x Duroc crosses with a microphone placed at 20-50cm from the animal. The analysis was done on a feature vector, containing energy, timederivate energy and mean power spectral density. The feature vector was compared to the reference set using dynamic time warping. This resulted in a correct classification of 90%.

Index Terms. Sound analysis, Cough, Diagnostic system, Health management

Full Paper (reprinted with permission from Firenze University Press)

Bibliographic reference.  Hirtum, A. Van / Guarino, Marcella / Costa, A. / Jans, P. / Ghesquiere, K. / Aerts, J.-M. / Navarotto, P. L. / Berckmans, Daniel (2003): "Automatic detection of chronic pig coughing from continuous registration in field situations", In MAVEBA-2003, 251-254.