Time-series analysis for online recognition and localization of sick pig (Sus scrofa) cough sounds

Abstract

This paper considers the online localization of sick animals in pig houses. It presents an automated online recognition and localization procedure for sick pig cough sounds. The instantaneous energy of the signal is initially used to detect and extract individual sounds from a continuous recording and their duration is used as a preclassifier. Autoregression (AR) 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 sick cough sounds. It is shown that the distribution of just three AR parameters provides an adequate classifier for sick pig coughs. A localization technique based on the time difference of arrival is evaluated on field data and is shown that it is of acceptable accuracy for this particular application. The algorithm is applied on continuous recordings from a pig house to evaluate its effectiveness. The correct identification ratio ranged from 73% (27% false positive identifications) to 93% (7% false positive identifications) depending on the position of the microphone that was used for the recording. Although the false negative identifications are about 50% it is shown that this accuracy can be enough for the purpose of this tool. 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.

Remotely Sensed Imagery for Early Detection of Respiratory Disease in Pigs: A Pilot Study

“…Non-invasive methods have been investigated to detect illness in several animals. For example, microphones are being used to assess coughing sounds as a warning of developing outbreak of respiratory infections [10][11][12]. Moreover, computer vision techniques have been increasingly studied to evaluate their potential to detect several illnesses in animals.…”

Sound Localisation in Practice: An Application in Localisation of Sick Animals in Commercial Piggeries

“…This fully automatic algorithm has been applied to the recordings of the previous subsection. Using the algorithm of Exadaktylos et al (2008b), about 50% of the manually labelled cough sounds were correctly identified by the algorithm and subsequently the result is visualised in Fig. 9, where the dark areas identify potential cough hazards.…”

“…Depending on the classification approach (e.g. Exadaktylos et al, 2008b), the characteristics of the filter can vary. However, this does not affect the performance of the sound extraction algorithm presented here.…”

“…Van Hirtum & Berckmans, 2001) and algorithms have been developed for automatic detection of coughs (e.g. Van Hirtum & Berckmans, 2003b, Exadaktylos et al, 2008a, Exadaktylos et al, 2008b. …”

Heat stress assessment by swine related vocalizations

“…The strength of this technique is its non-invasiveness and the possibility to work on-line to continuously monitor the animals. The capabilities of such a system, based on the classification algorithms, have been tested in previous studies investigating respiratory diseases (Exadaktylos et al, 2008) or animal welfare . The aim is to increase our understanding of animal vocalizations and welfare by studying their responses to typical stressful conditions.…”