Automatic detection and recognition of pig wasting diseases using sound data in audio surveillance systems.

Automatic detection of pig wasting diseases is an important issue in the management of group-housed pigs. Further, respiratory diseases are one of the main causes of mortality among pigs and loss of productivity in intensive pig farming. In this study, we propose an efficient data mining solution for the detection and recognition of pig wasting diseases using sound data in audio surveillance systems. In this method, we extract the Mel Frequency Cepstrum Coefficients (MFCC) from sound data with an automatic pig sound acquisition process, and use a hierarchical two-level structure: the Support Vector Data Description (SVDD) and the Sparse Representation Classifier (SRC) as an early anomaly detector and a respiratory disease classifier, respectively. Our experimental results show that this new method can be used to detect pig wasting diseases both economically (even a cheap microphone can be used) and accurately (94% detection and 91% classification accuracy), either as a standalone solution or to complement known methods to obtain a more accurate solution.

Reduction of PMWS-associated clinical signs and co-infections by vaccination against PCV2.

The effects of a single-dose recombinant Porcine circovirus type 2 (PCV2) open reading frame 2 (ORF2) subunit vaccine were studied in a post-weaning multisystemic wasting syndrome (PMWS)-affected pig herd. A total of 1519 3-week-old piglets were allocated randomly into two treatment groups and either vaccinated against PCV2 or treated with a placebo. Study animals were followed from the time of vaccination until the end of finishing. Onset of PCV2 viraemia and clinical signs of PMWS (wasting, cough, dyspnoea, pallor and lethargy) were observed when animals were approximately 9-10 weeks old. Compared to placebo-treated animals, vaccinated animals had a significantly reduced PCV2 viral load and duration of viraemia (p < 0.0001). This reduction in viraemia was not affected by the level of maternal anti-PCV2 antibodies present at the time of vaccination. During the period of viraemia (10-26 weeks of age) vaccinated animals exhibited a 53% reduction in mortality rate (p = 0.0010), a 4.84 kg higher body weight gain (p < 0.0001) and a significant reduction in clinical signs (p < or = 0.0004). Furthermore, lung samples of vaccinated animals had a considerably reduced number of co-infections with PRRSV and Mycoplasma hyorhinis than lung samples of placebo-treated animals. These data indicate that vaccination against PCV2 alone protects pigs from clinical signs and co-infections associated with PMWS.

Postweaning multisystemic wasting syndrome in Danish pig herds: productivity, clinical signs and pathology.

A case-control study of 74 herds with postweaning multisystemic wasting syndrome (pmws) and 74 matched control herds was carried out. In the case herds the mortality rates of weaner and finisher pigs were 11.2 and 5.2 per cent respectively, compared with 3.1 and 3.2 per cent in the control herds. In most case herds, pmws developed within the first four weeks after weaning. Wasting, diarrhoea and respiratory signs were observed in 10 per cent of the weaner pigs (7 to 30 kg) in the case herds compared with 7 per cent in the control herds. The average daily gains of the weaner pigs and finisher pigs were 36 g and 52 g less in the case herds than in the control herds. By examining three weaner pigs from each herd the pmws diagnosis was confirmed by histopathology and immunohistochemistry in 78 per cent of the case herds, but at least one pmws-positive weaner pig was found in 19 of the control herds. The prevalence of pmws-positive pigs among illthriven weaner pigs was 45 per cent (101/222) in the case herds, and 12 per cent (27/222) in the control herds. Specific gross pathological findings were associated with a positive pmws diagnosis; pigs with heavy, rubber-like lungs, atonic intestines, and enlarged bronchial and inguinal lymph nodes, had a 0.7 probability of a positive pmws diagnosis by laboratory examinations. However, for illthriven pigs, this probability of having pmws was equal in the case herds and the control herds.