RESUMO
This pilot study tested an on-farm protocol based on resource, management, and animal-based measures to evaluate the on-farm health and welfare of rabbits kept in four different housing systems. In detail, the four housing systems were (1) standard breeding cages for reproducing does (3,300 cm2) with their litters associated with bicellular cages for growing rabbits (1,200 cm2); (2) dual-purpose cages for both reproducing does and growing rabbits (3,655 cm2); (3) enriched cages (4,739 cm2) for both reproducing does and growing rabbits equipped with a wire-mesh elevated platform (1,015 cm2); (4) parks (30,977 cm2) made up of four modules (7,744 cm2 each) joined by removing the wire net walls between them with growing rabbits kept in collective parks and reproducing does individually in the single modules. A total of 12 commercial farms (three farms/four housing systems) were visited during three seasons (summer, autumn, and winter) on two occasions each: (1) a pre-weaning visit for recordings on reproducing does and litters and (2) a pre-slaughtering visit for recordings on growing rabbits. At the pre-weaning visit, the prevalence of health concerns did not differ among does and litters kept in the different housing systems. At the pre-slaughtering visit, a higher prevalence of dermatomycosis was found in farms with dual-purpose cages and parks. Overall, taking into account the limitations due to the small sample size per housing system and the field conditions, the on-farm assessment tested in the present pilot study did not highlight major differences in the welfare and health of reproducing does and their kits as well as of growing rabbits in farms using different housing systems, which need to be confirmed on a large number of farms. The study also outlined the role of several management and environmental factors changing from one farm to another, which stresses the troubles of accounting for on-farm rabbit welfare and health exclusively to the housing system.
RESUMO
To improve animal welfare in collective park housing systems, this study assessed the effects of the provision of gnawing hay blocks and the group composition (F: females, M: males, FM: mixed sex) on performance, behavior, and reactivity of 288 growing rabbits reared in 18 parks (16 rabbits/park) from 31 to 73 days of age. The presence of gnawing blocks inside the feeding area of the parks scarcely affected performance and budget time, but decreased the time spent in the resting area compared to parks without blocks (p < 0.001); it increased the time spent moving during the open field test (p < 0.05) and the rate of rabbits that approached the object in the novel-object test (p < 0.05). As for sex-group composition, the feed conversion ratio was lower in parks F and FM than in park M (p < 0.05). During the open-field test, FM rabbits spent more time moving (p < 0.05), whereas M rabbits displayed self-grooming for a longer time (p < 0.01). Results related to production, behavior, and reactivity indicate the provision of gnawing blocks for welfare improvement, but do not support the change from current mixed-sex to single-sex rearing.
RESUMO
Image analysis using machine learning (ML) algorithms could provide a measure of animal welfare by measuring comfort behaviours and undesired behaviours. Using a PLF technique based on images, the present study aimed to test a machine learning tool for measuring the number of hens on the ground and identifying the number of dust-bathing hens in an experimental aviary. In addition, two YOLO (You Only Look Once) models were compared. YOLOv4-tiny needed about 4.26 h to train for 6000 epochs, compared to about 23.2 h for the full models of YOLOv4. In validation, the performance of the two models in terms of precision, recall, harmonic mean of precision and recall, and mean average precision (mAP) did not differ, while the value of frame per second was lower in YOLOv4 compared to the tiny version (31.35 vs. 208.5). The mAP stands at about 94% for the classification of hens on the floor, while the classification of dust-bathing hens was poor (28.2% in the YOLOv4-tiny compared to 31.6% in YOLOv4). In conclusion, ML successfully identified laying hens on the floor, whereas other PLF tools must be tested for the classification of dust-bathing hens.
