E. Vranken

Design of laying nests in furnished cages: influence of nesting material, nest box position and seclusion

1. Preferences for three nesting materials and nest box positions were investigated simultaneously in two trials using a furnished cage: one with 18 individual laying hens and one with 18 groups of 5 hens. Following a habituation period in pre-test cages, every hen or group of hens was tested for 2 d: once without and once with plastic flaps at the entrance of the nest boxes. 2. Hens preferred peat and artificial turf to coated wire mesh for egg laying. 3. One nest box position was clearly preferred to both other nest boxes. The hens’ choice of nest box position was influenced by the pre-test cage in which they had been habituated. 4. The presence of plastic flaps at the entrance of the nest boxes had no influence on the proportion of eggs laid on the different nesting materials or on the proportion of floor eggs. 5. Individual and group testing resulted in the same overall results despite the presence of a distinct group effect.

A computer vision method for on-line behavioral quantification of individually caged poultry

In addition to production, physiology, and health, behavior is an important issue with respect to animal welfare when evaluating novel housing systems. Behavioral characteristics are usually evaluated by audio-visual observation done by a human observer present on the scene. This method is time consuming, expensive, subjective, and prone to human error. Automated objective surveillance, by means of inexpensive cameras and image-processing techniques, has the ability to generate data that provide an objective measure of behavior, without disturbing the animals. The specific purpose of this study was to develop a fully automatic on-line image-processing technique to quantify the behavior of a single laying hen as opposed to the current human visual observation. The image-processing system is based on the principle that the classification of behavior can be translated into classification of time series of different postures of the hen. The hen’s postures can be recognized in the camera image. The classification of the hen’s behavior is performed by dynamic analysis of a set of measurable parameters, which are calculated from the images using image-processing techniques. The parameters were chosen based on their computational demands and analysis of their discriminative power regarding the different types of a specific behavior. A first implementation of the system allowed us to identify three different types of individual behavior (standing, walking, and scratching). The objective of further investigation will be the classification of up to 15 different types of behavior, such as pecking, eating, drinking, wing stretching, etc.

Perching behaviour and perch height preference of laying hens in furnished cages varying in height.

1. The objective was to investigate the effect of cage height on perch height preference and perching behaviour in laying hens. Twelve groups of two hens and 12 groups of 14 hens were tested in furnished cages equipped with two wooden perches. These stepwise perches were designed such that hens could choose between 7 different heights (6, 11, 16, 21, 26, 31 and 36 cm). Day- and night-time perching behaviour was observed on 4 consecutive days with a different cage height each day: 150, 55, 50 and 45 cm. 2. Given that a minimum perch–roof distance of 19 to 24 cm was available, hens preferred to roost on the highest perches at night. 3. Lowering cage height not only forced hens to use lower perches, but also reduced time spent on the perches during the day (two-hen and 14-hen test) and night (14-hen test). Moreover, it affected daytime behavioural activities (more standing and less preening) on the perches in the two-hen tests (but not in the 14-hen tests). 4. During the day lower perches were used more for standing and walking, higher perches more for sitting and sleeping. This behavioural differentiation was most pronounced in the highest cages. 5. Perch preference and perching behaviour depend on both the floor–perch distance and the perch–roof distance. Higher cages provide more opportunity for higher perches (which hens prefer), for better three-dimensional spacing (and consequently reduced density at floor level) and for behavioural differentiation according to perch height.

Evaluation of Step Overlap as an Automatic Measure in Dairy Cow Locomotion

The aim of this study was to explore the possibility of capturing cow locomotion activity by computer vision techniques and to calculate the correlation between step overlap and manually measured locomotion scores. In two experiments, a total of 208 video recordings of 85 individual lactating cows were gait scored visually by an observer. The side-view videos were recorded when cows were freely passing the experimental setup. After image processing, the imprint location, step overlap, body size, and relative step overlap were calculated. The values of automatically measured step overlap showed a high correlation with the manually measured step overlap (R2 = 0.739, p < 0.001; R2 = 0.809, p < 0.001). The maximal step overlap allowed differentiation between gait scores 1 and 3 (p = 0.032) and between gait scores 2 and 3 (p = 0.039). The difference between gait scores 1 and 2 was not significant (p = 0.079). There was a large variation between individual cows, in both the progress of lameness and the influence on step overlap. Changes in step overlap were also seen that were not matched by changes in gait score. Step overlap is a variable that shows a relationship with manual gait scores, but it is not strong enough to be used as a single classifier for lameness in all cows.

Do heavy broiler chickens visit automatic weighing systems less than lighter birds

1. In previous studies it was found that automatic broiler weighing systems can have accuracy problems. Researchers reported poor agreement between automatic and manual mean weighing used as a reference. The difference was observed especially after 4 to 5 weeks and this was explained by assuming that heavier birds visited the weighing system less at the end of the growing period. 2. Our study tested this hypothesis under practical production conditions. 3. In total, 193 536 digital images of broilers on and in the neighbourhood of the platforms were collected over three growing periods of 6 weeks. The area (upper view) of the broilers was calculated using image analysis techniques. 4. The hypothesis that the weighing system was used less frequently by heavier animals was confirmed. More specifically, statistical differences between the area of broilers on and in the neighbourhood of the weighing system could be demonstrated for week 5.

CLIMATE CONTROL BASED ON TEMPERATURE MEASUREMENT IN THE ANIMAL-OCCUPIED ZONE OF A PIG ROOM WITH GROUND CHANNEL VENTILATION

It is known that there can be a significant temperature difference between the position of the climate controller sensor (room temperature) and the animal-occupied zone (AOZ) in a pig room. This study explores the advantages of using AOZ temperature in climate control. The objectives were: (1) to evaluate a current climate control system in a practical room with ground channel ventilation for weaned piglets by comparing AOZ and room temperature, and (2) to determine advantages of control of the heating system based on AOZ temperature by a model-based predictive (MBP) controller. Comparison of AOZ and room temperature showed that during the first 10 days of the two experimental batches, AOZ temperature was lower and showed greater fluctuations than room temperature, most likely due to the switching of the heating system (on/off). Animals close to the sensor could disturb the AOZ measurement. This was not the case during colder nights, when animals moved away from the sensor and the measured AOZ temperature was a good indicator of the air temperature around the animals. The data for those periods were suitable for use in this climate control study, but when applying the system in practice the disturbing effect needs to be prevented by better protection of the AOZ sensor. For the second objective, the course of the AOZ temperature was modeled based on data for five nights when the heating switched on and off several times (goodness of fit Rt 2 = 0.77). One of the models was integrated in a simulated MBP controller that uses the model to predict future AOZ temperature; the controller switches the heating system on before the AOZ gets too cold and off before it gets too warm. The simulated AOZ temperature was more stable during an 11 h cold period; the standard deviation was reduced from 0.44°C to 0.18°C.

Effects of Different Target Trajectories on the Broiler Performance in Growth Control

Applying altered trajectories in broiler growth control with early feed restriction and a consequent accelerated catch-up growth has been approved to result in a better feed conversion ratio and a reduction in mortality. The properties of the growth trajectory and the resulting time and duration of the feed restriction can be crucial for animal welfare and production performance. The objective of this work was to test broiler growth control strategy online in field conditions using different target trajectories. Several experiments were conducted, and the best target trajectory has been proven to result in an end weight of 2,616 g and feed conversion ratio of 1.54 for Ross-type birds and an end weight of 2,472 g and a feed conversion ratio of 1.67 for Cobb-type birds.

End-weight prediction in broiler growth

1. Two different methods, categorised as input–output and single output models, were evaluated for slaughter weight prediction of broiler chickens. The input–output models included linear and non-linear recursive modelling with a time-varying model structure, whereas the output models consisted only of empirical growth equations and several growth curve fitting techniques. 2. The results suggested that a simple linear growth curve fitting method gives the greatest accuracy in a prediction horizon of 4 d or less. Error is minimised to an average of 0·14% when 4 d of past information is used to fit a line to predict the end weight one day ahead.

OPTICAL FLOW ALGORITHM TO QUANTIFY THE TWO-DIMENSIONAL VELOCITY COMPONENTS OF A VISUALIZED AIR JET

In a ventilated space, the incoming air jet and the resulting airflow pattern play key roles in the removal and distribution of heat, moisture, harmful gases, and particles from or around living organisms (man, animal, and plant). In this research, an optical flow algorithm was used to visualize and quantify the two-dimensional velocity components of a visualized air jet in a ventilated room. The airflow is visualized by adding smoke particles to the air. The results of the optical flow algorithm are in agreement with experimental measurements, and the algorithm is a low-cost alternative technique to measure the two-dimensional velocity components. This technique might be used to quantify the airflow pattern by image analysis. The maximum absolute error of the mean air speed calculated by the optical flow algorithm compared to the measured mean air speed distribution is 0.0162 m/s, which is a relative error of 16%.

Controlling the Growth of Broilers by Using Food Supply as Control Input

Selection programs for broilers, combined with improvements in nutrition, have led to a reduction of the age at which the animals reach the commercially desired slaughter weight. This evolution has also resulted in several negative growth responses (increased body fat deposition, a decrease of reproduction capacity, metabolic diseases and a high incidence of skeletal diseases). A possible way to correct for these negative growth responses is to alter the growth trajectory in such a way that the initial growth is lowered followed by an accelerated growth, i.e. compensatory growth. The objective of the reported research was to control the growth trajectory of broiler chickens during the production process based on an adaptive compact dynamic process model. More specifically, the daily food supply was calculated, based on a model-based control algorithm, with the aim to follow a predefined (compensatory) growth trajectory as close as possible. For the modelling of the dynamic growth response of broiler chickens to the control input food supply, an on-line parameter estimation procedure was used. More specifically, the algorithm estimated the parameter values on-line (every time new process information becomes available) based on a small window of actual and past measured data of process input(s) and output(s). In this research, parameters were estimated every day based on measured information of food supply and animal weights of past five days. Six experiments with model-based growth control were conducted on a small scale (50 animals) and on a large scale (2900 animals). To test the usefulness of the model-based algorithm, different predefined reference trajectories were followed. More specifically, 2 strong restricted, 2 weak restricted and 1 strong compensatory growth trajectories. In 85 % of the cases, the control algorithm managed to follow the predefined reference trajectory with a Mean Relative Error (MRE) that varied between 3.7 % and 5.3 %.