This research aimed at assessing the effects of a ceiling fan ventilation system on health, feeding, social behaviour and growth response of finishing young bulls fattened indoors during a mild summer season. A total of 69 Charolais young bulls were housed in six pens without any mechanical ventilation system (Control) and in six pens equipped with ceiling fans. The experimental period lasted 98 days from June until mid-September 2014. Four experimental days were considered in order to assess the effect of the ventilation system under two different microclimatic conditions: 2 alert days at monthly interval with temperature humidity index (THI) between 75 and 78, and 2 normal days with THI⩽74. Health and behaviour of the bulls were evaluated through 8-h observation sessions starting after morning feed delivery. The study was carried out during a rather cool summer with a climate average THI of 68.9 and 4 days with average THI>75. Despite these mild climate conditions, ceiling fans lowered litter moisture and acted as a preventive measure for bulls' dirtiness (odd ratio=47.9; 95% CI 19.6 to 117.4). The risk of abnormal breathing was increased for Control bulls (odd ratio=40.7; 95% CI 5.4 to 304.2). When exposed to alert THI conditions, respiration rate and panting scores increased and rumination duration dropped in Control bulls compared with bulls provided with a ceiling fan. During observations under alert THI, bulls spent less time eating, more time being inactive and consumed more water compared with normal THI conditions. Bulls' daily dry matter intake measured during the observation sessions decreased on alert compared with normal THI days (P<0.001) due to a drop of intake during the daylight hours. Ceiling fan treatment had no effect on bulls' growth performance or water consumption but these results most likely depended on the mild climate conditions. Ceiling fans proved to mitigate some of the negative effects of heat stress on bulls' behaviour (rumination, lying down and drinking water) and respiration rate, however. The lack of a significant improvement of bulls' growth response should not discourage beef farmers from using ceiling fans in indoor systems, considering the likely increase in frequency and intensity of heat waves in the planet's temperate areas induced by global warming.

The accurate detection of behavioural changes represents a promising method of detecting the early onset of disease in dairy cows. This study assessed the performance of deep learning (DL) in classifying dairy cows’ behaviour from accelerometry data acquired by single sensors on the cows’ left flanks and compared the results with those obtained through classical machine learning (ML) from the same raw data. Twelve cows with a tri-axial accelerometer were observed for 136 ± 29 min each to detect five main behaviours: standing still, moving, feeding, ruminating and resting. For each 8 s time interval, 15 metrics were calculated, obtaining a dataset of 211,720 observation units and 15 columns. The entire dataset was randomly split into training (80%) and testing (20%) datasets. The DL accuracy, precision and sensitivity/recall were calculated and compared with the performance of classical ML models. The best predictive model was an 8-layer convolutional neural network (CNN) with an overall accuracy and F1 score equal to 0.96. The precision, sensitivity/recall and F1 score of single behaviours had the following ranges: 0.93–0.99. The CNN outperformed all the classical ML algorithms. The CNN used to monitor the cows’ conditions showed an overall high performance in successfully predicting multiple behaviours using a single accelerometer.

Intensive fattening of late-maturing breeds on concrete or rubberized slatted floors is the prevalent beef production system in mainland Europe. The rationale behind this study is that specific beef breeds with different slaughter weights might have a diverse response to different flooring systems. The study aimed at assessing whether growth performance, health, behaviour and claw condition of two beef breeds, Charolais (CH) and Limousine (LIM), would be affected by their housing on concrete (CS) or rubber-covered (RCS) fully slatted floor. A total of 228 CH (116 on CS; 112 on RCS) and 115 LIM (57 on CS; 58 on RCS) were housed in four and two commercial farms, respectively, in groups of 9.0 ± 2.1 animals/pen with an average space allowance of 3.1 ± 0.2 m2. Draining gaps of CS and RCS pens were 16.9 ± 1.7% and 11.6 ± 1.2% of the total surface, respectively. Bulls of both breeds had similar initial body weight (429.4 ± 31.5 kg for CH; 369.6 ± 31.7 kg for LIM), and they were slaughtered when they reached suitable finishing. Charolais had a higher final body weight (BW) than LIM (750.8 ± 8.6 v. 613.7 ± 10.9 kg; P < 0.01), and bulls of both breeds on RCS had higher average daily gain than on CS (1.47 ± 0.02 v. 1.39 ± 0.02 kg/day; P < 0.05). The percentage of bulls early culled or treated for locomotor disorders were reduced by RCS only for LIM, while RCS tended to prevent the occurrence of bursitis for both breeds. During two 8-h behavioural observations, bulls on RCS performed more head butt/displacements and chases than on CS, and they reduced the frequency of abnormal lying down events. The use of RCS increased mounts’ frequency only in LIM, while its reduced drainage capacity impaired only the cleanliness of CH. Postmortem hoof inspection showed longer claw dorsal wall and diagonal lengths, and sharper toe angles for CH on RCS than LIM on both floors. Results of this study point out that fully slatted floors, regardless of being rubberized or not, are not suitable for bulls finished at a final BW above 700 kg due to their detrimental effects on health and welfare. The use of RCS could be recommended as an alternative to CS only if bulls are slaughtered at a lower final BW (around 600 kg), like in the case of LIM breed.