Estimating the welfare status at an individual level on the farm is a current issue to improve livestock animal monitoring. New technologies showed opportunities to analyze livestock behavior with ...machine learning and sensors. The aim of the study was to estimate some components of the welfare status of gestating sows based on machine learning methods and behavioral data. The dataset used was a combination of individual and group measures of behavior (activity, social and feeding behaviors). A clustering method was used to estimate the welfare status of 69 sows (housed in four groups) during different periods (sum of 2 days per week) of gestation (between 6 and 10 periods, depending on the group). Three clusters were identified and labelled (scapegoat, gentle and aggressive). Environmental conditions and the sows' health influenced the proportion of sows in each cluster, contrary to the characteristics of the sow (age, body weight or body condition). The results also confirmed the importance of group behavior on the welfare of each individual. A decision tree was learned and used to classify the sows into the three categories of welfare issued from the clustering step. This classification relied on data obtained from an automatic feeder and automated video analysis, achieving an accuracy rate exceeding 72%. This study showed the potential of an automatic decision support system to categorize welfare based on the behavior of each gestating sow and the group of sows.
Early social housing is known to benefit cognitive development in laboratory animals. Pre-weaned dairy calves are typically separated from their dam immediately after birth and housed alone, but no ...work to date has addressed the effect of individual housing on cognitive performance of these animals. The aim of this study was to determine the effects of individual versus social housing on two measures of cognitive performance: reversal learning and novel object recognition. Holstein calves were either housed individually in a standard calf pen (n = 8) or kept in pairs using a double pen (n = 10). Calves were tested twice daily in a Y-maze starting at 3 weeks of age. Calves were initially trained to discriminate two colours (black and white) until they reached a learning criterion of 80% correct over three consecutive sessions. Training stimuli were then reversed (i.e. the previously rewarded colour was now unrewarded, and vice-versa). Calves from the two treatments showed similar rates of learning in the initial discrimination task, but the individually housed calves showed poorer performance in the reversal task. At 7 weeks of age, calves were tested for their response to a novel object in eight tests over a two-day period. Pair-housed calves showed declining exploration with repeated testing but individually reared calves did not. The results of these experiments provide the first direct evidence that individual housing impairs cognitive performance in dairy calves.
In modern pig production, sows are transported by road to abattoirs. For reasons of biosecurity, commercial trucks may have limited access to farms. According to Danish regulations, sows can be kept ...in stationary transfer vehicles away from the farm for up to two hours before being loaded onto the commercial truck. We aimed to describe the behaviour of sows in transfer vehicles. This preliminary, exploratory study included data from 11 loads from a total of six Danish sow herds. Selection of animals to be slaughtered was done by the farmers. Clinical registrations were made before collection of the sows, after which they (in groups of 7-13) were mixed and moved to the transfer vehicle (median stocking density: 1.2 sow/m²), and driven a short distance to a public road. The duration of the stays in the transfer vehicles before being loaded onto the commercial trucks ranged from 6-59 min. During this period, the median frequency of aggressive interactions per load was 18 (range: 4-65), whereas the median frequency of lying per load was 1 (range: 0-23). The duration of the stay correlated positively with the frequency of aggressive interactions (r
= 0.89;
= 11;
< 0.001) and with the frequency of lying (r
= 0.62;
= 11;
< 0.05). Frequency of aggressive interactions correlated positively with the temperature inside the transfer vehicle (r
= 0.89;
= 7;
< 0.001). These preliminary results are the first to describe the behaviour of cull sows during waiting in transfer vehicles, and may suggest that this period can be challenging for sow welfare, especially for longer stays and during hot days.
•Environment, animal and feed characteristics influence nutrient utilization in pigs.•Mathematical models can be used to estimate real-time daily nutrient requirements.•Thanks to technological ...advances, each pig can receive its daily nutrient requirements.•Precision feeding may also reduce feed cost and environment load.
Nutrient requirement change over time and individual variability in pigs influences the efficiency of nutrient utilization. These variabilities should be considered to predict nutrient requirements more accurately. The goal of precision feeding is to develop systems able to estimate and deliver, at the right time, a ration with a quantity and composition adapted to the daily requirements of each animal. It would improve feed and nutrient efficiency, which is a major issue for the sustainability of all pig production systems. The objectives of this review were: 1) to define feed efficiency and present the factors that affect it, as well as challenges to and strategies for improving it; 2) to define precision feeding and the sources of variability in nutrient requirements and show the need for new technology to obtain real-time data; and 3) to present current models and applications of precision feeding for fattening pigs and sows. Feed efficiency is expressed as the ratio of mean daily weight gain to mean daily feed consumption over a given period. In practice, the inverse of this ratio is generally used for breeding animals and represents the efficiency of converting feed into weight gain (feed conversion ratio, FCR). Several factors influence FCR, such as spillage, feed digestibility, composition of weight gain, feed intake and nutrient utilization. Selecting the appropriate form of feed and the appropriate nutrient density and supply, as well as reducing negative effects of environmental factors should improve FCR. New feeding technologies (e.g. sensors, feeders) allow group-housed animals to be fed based on their individual requirements, which improves group efficiency. Predictive models of nutrient requirements and excretion, such as InraPorc, have been developed and used to select the best feeding strategies. For growing pigs, precision feeding strategies are a promising solution to reduce nutrient excretion by adjusting the nutrient supply to each individual at different points in time. Recent simulations indicate that precision feeding might also be a relevant strategy for sows.
Competition for feed in a group of gestating sows leads to aggression around feeding stations, which has a negative impact on their welfare. This study investigates the potential of teaching ...gestating sows an individual sound signal to reduce aggression resulting from competition for feed access, and thus improve their welfare in a group. A total of 32 sows were used. In a test room, “learning” sows (n = 16) went through 4 individual learning phases (27 days in total) to associate the individual sound signal with an invitation to feed from a one-way feeding station and to discriminate this individual sound signal from other unknown sound signals. After the learning phases, sows were subjected to a 3-day evaluation phase in groups of 4 sows. The "naive" sows (n = 16) were also introduced to the test room individually for 18 days, and in groups of 4 for 3 days without following the learning procedure. Learning sows correctly responded to 100% of their individual sound signal after only 8 days of individual learning, suggesting that they successfully associated the sound signal with feed access. Distinguishing between different sounds was harder as shown by only 18.8% of success after an unknown sound emission at the end of the individual learning phases. Naïve sows reduced the time spent in the feeder compared to learning sows (P < 0.001). On the second day of the group phase, learning sows were less aggressive than naïve sows (P < 0.05). Compared to high-ranking sows, low-ranking sows displayed a reduced number of spontaneous approaches to the feeder during the last individual learning phase (P < 0.001), and higher success rates in the group phase (P < 0.05). The study suggests that, for group-housed sows fed by an individual feeder, teaching sows an individual sound signal can modify their feeding and social behaviors, enhancing their overall well-being during feeding time. Furthermore, the results suggest that this individual learning may be particularly beneficial for low-ranking sows.
•Sows were able to rapidly associate a sound as a call to feed.•Sows could partially discriminate their individual sound from the others.•Individual call to feed reduced aggression between sows around the feeder.•Low ranking sows showed greater abilities to adapt to the individual call to feed.
Simulations of precision feeding (PF) in which gestating sows were individually fed a daily mixture of two diets with different amino acid contents indicated a reduction in protein intake, feed ...costs, and environmental losses compared to sows fed a conventional single diet (CF). These results have not been verified on farm. Thus, the objective of the present study was to compare the effect of this PF strategy on productive and reproductive performances of gestating sows compared to the CF strategy. As the effects of such a strategy has not been reported yet on sows’ feeding behavior (frequency of visits and time spent in the feeder), it constituted the second objective of this study. The experiment included 131 gestating sows divided into the two feeding strategies regarding their parity and body weight at insemination. Feed supply was similar for the two strategies. The results matched those from simulations as sows fed the PF strategy reduced their lysine ingestion of around 25%, which therefore reduced nitrogen excretion of 18.5%, and feed costs by 3.4 euros per gestation or 8 euros per ton of feed. Phosphorus intake and excretion were also reduced with PF compared to CF (around 8% and 9%, respectively). Reproductive performance, defined as the number of piglets per litter and the litter weight, was not affected by the feeding strategy. All sows usually ate their daily ration in one “feeding visit.” The PF sows did a constant number of “non-feeding visits” to the feeder during gestation (on average 4.25 visits/d), while the CF sows did more non-feeding visits at the beginning of the gestation (on average 4.42 visits/d) and less at the end of the gestation (on average 3.69 visits/d) than the PF sows (P < 0.01). The sows spent 54% of their daily time in the feeder for feeding visits, and 46% for non-feeding visits. The PF sows spent more daily time for non-feeding visits than CF sows (32.4 vs. 29.7 min/d, respectively, P < 0.01). Time spent at the feeder for feeding visits or non-feeding visits was constant over the gestation for the CF sows (35.3 and 29.2 min/d, respectively) while for the PF sows it increased over gestation. In conclusion, the PF strategy can be used to reduce lysine intake without influencing reproductive performance while reducing protein intake and feed costs. Feeding behaviors were barely affected by the feeding strategies but may serve as management indicators to detect sick or injured animals.
•Precision feeding aims at adjusting feed supply to individual nutrient requirements.•Precision feeding reduced reducing protein intake and feeding costs.•Environmental load decreased with precision feeding.•Reproductive performance was not affected by precision feeding.•Feeding behaviors were barely affected by precision feeding.
Abstract
Conventional feeding for sows is usually based on the average herd’s nutrient requirements. Thus, sows can be under- or over- fed leading to extra feed costs and environmental losses. New ...technologies, as sensors and AI, bring opportunities to measure and integrate individual variability into nutrient requirements estimations. The objective is therefore to go towards precision feeding (PF) combining on-farm data as input for a dynamic nutritional model with smart feeders to provide individual and daily-adjusted rations. As a first step, a mechanistic model (InraPorc) was upgraded and applied to databases to calculate daily nutrient requirements at the individual scale for sows. For lactating sows, it highlighted that milk production and appetite influenced the amount and composition of the optimal ration to be fed to each sow. For gestating sows, it showed that parity, gestation stage, and activity level influenced nutrient requirements. The second step was to develop algorithms to predict the parameters of interest defined in the first step and not measured daily on-farm. For lactating sows, feed intake and litter weight at weaning (as proxy for milk production) were accurately predicted using supervised methods: respectively, clustering k-shape and a linear regression. For gestating sows, an algorithm is being developed to identify individual activities via video recordings. The third step is to test on farm the decision support systems (DSS) composed of the models and algorithms. An interface allows the link between the DSS and the feeders, and another allows the farmers to enter observational data. During on-farm trials, nitrogen and phosphorus excretions as well as feed costs were reduced for sows fed with PF compared to sows fed a conventional diet. To conclude, AI allows mechanistic models and algorithms to be integrated on farm for sows for an on real-time individual adjustment of the nutrient supply.
Père de l'archéologie médiévale à Lyon, Jean-François Reynaud a mené avec le succès que l'on sait ses recherches sur le Lyon paléochrétien et médiéval. Puis il a ouvert ses investigations sur la ...région Rhône-Alpes, en ajoutant à la pratique de l'archéologie sédimentaire, celle, encore balbutiante, de l'archéologie du bâti. Son enseignement a reflété ses activités scientifiques, assurant à l'université Lumière Lyon 2 une riche moisson de maîtrises, DEA et thèses composés dans ces deux domaines. Les travaux que ses collègues, disciples et amis ont réunis dans ce volume de mélanges sont le fruit de l'enseignement et de la formation pratique que Jean-François Reynaud a dispensés au fil de sa carrière. Aussi a-t-il paru souhaitable d'y associer les nouvelles générations – la relève – qui sont les héritières par voie directe. Leurs interventions montreront que le dynamisme initial s'est conservé, la recherche amplifiée et les intérêts diversifiés. Les monographies de site ouvrent le volume. Elles constituent des laboratoires vivants où s'élaborent méthodes et problématiques, où se dessinent de grandes synthèses historiques et où la restauration et la conservation du patrimoine puisent des conseils performants. Dans un second temps, l'organisation de l'espace religieux fait entrer le lecteur dans le domaine délicat des relations entre l'architecture, l'image monumentale, la liturgie et la vie quotidienne au sein de l'église, du quartier canonial ou du monastère. Au fil des siècles, la morphogenèse des lieux et des bâtiments se nourrit de ces données déterminantes. Enfin, est abordée la pertinence de ces approches fondées sur des méthodes renouvelées englobant largement l'histoire de l'art et l'archéologie, de la sculpture et des techniques de construction aux analyses spatiales et à la conservation des sites archéologiques.