The sound makes the difference: the utility of real time sound analysis for health monitoring in pigs
S. Ferrari, M. Silva, Vasileios Exadaktylos, Daniël Berckmans, Marcella Guarino · 2013
Respiratory diseases are causes of mortality and loss of productivity in intensive pig farming. Cough is one of the symptoms and a key element for screening and diagnosis. This research shows a summary on how sound analysis may be used for intensive piggeries health monitoring: comparing the acoustic features of different type of cough sounds, analysing their acoustic features and how they may be used in an algorithm-based alarm system to automatically identify cough sounds and provide farmers an early warning about the health status of their herds. The features investigated were peak frequency, duration of sound, energy envelope and time constant. This work considers at the end an automated online recognition and localization procedure for sick pig cough sounds where the instantaneous energy of the signal is used to detect and extract individual sounds and their duration is used as a pre-classifier. Auto regression analysis is then employed to calculate an estimate of the sound signal and the parameters of the estimated signal are subsequently evaluated to identify the sounds. A localization technique based on the time difference of arrival is evaluated on in field data and is shown that it is of acceptable accuracy for this particular application. Finally, it is suggested that the presented application can be used to online monitor the welfare in a pig house, and provide early diagnosis of a cough hazard and faster treatment of sick animals.