RESUMEN
Welfare-oriented regulations cause farmers worldwide to shift towards more welfare-friendly, e.g., loose housing systems such as aviaries with litter. In contrast to the traditional cage housing systems, good technical results can only be obtained if the behavior of hens is considered. With increasing flock sizes, the automation of behavioural assessment can be beneficial. This research aims to show a proof of principle of tools for analyzing laying-hen behaviors by using wearable inertia sensor technology and a machine learning model (ML). For this aim, the behaviors of hens were classified into three classes: static, semi-dynamic, and highly dynamic behavior. The activities of hens were continuously recorded on video and synchronized with the sensor signals. Two hens were equipped with sensors, one marked green and one blue, for five days to collect the data. The training data set indicated that the ML model can accurately classify the highly dynamic behaviors with a one-second time window; a four-second time window is accurate for static and semi-dynamic behaviors. The Bagged Trees model, with an overall accuracy of 89% was the best ML model with the F1-scores of 89%, 91%, and 87% for static, semi-dynamic, and highly dynamic behaviors. The Bagged Trees model also performed well in classifying the behaviors of the hen in the validation data set with an overall F1-score of 0.92 (uniform either % or decimals). This research illustrates that the combination of wearable inertia sensors and machine learning is a viable technique for analyzing the laying-hen behaviors and supporting farmers in the management of hens in loose housing systems.
RESUMEN
To assess their potential to control poultry red mites (Dermanyssus gallinae), we tested selected predaceous mites (Androlaelaps casalis and Stratiolaelaps scimitus) that occur naturally in wild bird nests or sometimes spontaneously invade poultry houses. This was done under laboratory conditions in cages, each with 2-3 laying hens, initially 300 poultry red mites and later the release of 1,000 predators. These small-scale tests were designed to prevent mite escape from the cages and they were carried out in three replicates at each of three temperature regimes: 26, 30 (constant day and night) and 33-25 °C (day-night cycle). After 6 weeks total population sizes of poultry red mites and predatory mites were assessed. For the temperature regimes of 26 and 33/25 °C S. scimitus reduced the poultry red mite population relative to the control experiments by a factor 3 and 30, respectively, and A. casalis by a factor of 18 and 55, respectively. At 30 °C the predators had less effect on red mites, with a reduction of 1.3-fold for S. scimitus and 5.6-fold for A. casalis. This possibly reflected hen manure condition or an effect of other invertebrates in the hen feed. Poultry red mite control was not negatively affected by temperatures as high as 33 °C and was always better in trials with A. casalis than in those with S. scimitus. In none of the experiments predators managed to eradicate the population of poultry red mites. This may be due to a prey refuge effect since most predatory mites were found in and around the manure tray at the bottom of the cage, whereas most poultry red mites were found higher up in the cage (i.e. on the walls, the cover, the perch, the nest box and the food box). The efficacy of applying predatory mites in the poultry industry may be promoted by reducing this refuge effect, boosting predatory mite populations using alternative prey and prolonged predator release devices. Biocontrol success, however, will strongly depend on how the poultry is housed in practice (free range, cage or aviary systems) and on which chemicals are applied to disinfect poultry houses and to control other pests.