Erik Vranken

Computer-assisted image analysis to quantify daily growth rates of broiler chickens.

1. The objective was to investigate the possibility of detecting daily body weight changes of broiler chickens with computer-assisted image analysis. 2. The experiment included 50 broiler chickens reared under commercial conditions. Ten out of 50 chickens were randomly selected and video recorded (upper view) 18 times during the 42-d growing period. The number of surface and periphery pixels from the images was used to derive a relationship between body dimension and live weight. 3. The relative error in weight estimation, expressed in terms of the standard deviation of the residuals from image surface data was 10%, while it was found to be 15% for the image periphery data. 4. Image-processing systems could be developed to assist the farmer in making important management and marketing decisions.

Proportional-integral-plus (PIP) control of ventilation rate in agricultural buildings

This paper is concerned with proportional-integral-plus (PIP) control of ventilation rate in mechanically ventilated agricultural buildings. The PIP controller can be interpreted as a logical extension of conventional proportional-integral/proportional-integral-derivative (PI/PID) controllers, but with inherent model-based predictive control action. In particular, the paper considers the design of an optimal, scheduled gain PIP algorithm for a 22 m3 forced ventilation test chamber at the Katholieke Universiteit Leuven. Such a PIP approach proves more robust to pressure disturbances than an equivalent PID design and constitutes a preliminary step towards the development of the complete micro-climate controller.

An assessment of optimal air temperatures in pig houses by the quantification of behavioural and health-related problems

Air temperatures were measured every 2 h in 12 growing-finishing pig houses. All houses were operated on the all-in, all-out, principle. Data were collected for two fattening periods in each house. Stocking density, feeding system, pig type, and the farmers skill were standardized. Every 2 weeks, the houses were visited and live weight, mortality rate, the incidence of coughing and tail biting, and the extent of dirty lying areas were recorded. Air temperature limits could be isolated from the complex of factors affecting behavioural and health problems of pigs observed within these experiments. Sensitive periods within the growth period of the pigs seem to exist. At the onset of the fattening period (20 to 30 kg), pigs which have been transported from other farms need special care. During summer, mortality rate was lowered when the periodicity of the temperature cycles was lowered for 40- to 50-kg pigs, whereas for heavier pigs the mean maximal air temperature was important also. With respect to coughing, a statistically significant negative relation with the air temperature in the pig house was found for all weight classes, with interactions from the number of different temperature cycles within a 24-h period. In order to avoid dirty lying areas for 20- to 40-kg animals, air temperatures should be between 20 to 24°C, whereas for diarrhoea, animals of 40 to 50 kg were especially sensitive to the occurrence of low air temperatures. For minimizing tail biting, an optimal air temperature range of 20 to 22°C is suggested.

Evaluation of Control Strategies for Fogging Systems in Pig Facilities

During hot periods, heat loss from non-sweating animals can be improved by fogging water, in order to cool the ambient air and enhance sensible heat dissipation. A dynamic simulation model was used to test control settings for fogging (turning on the system at 1.5°C and 3°C above setpoint temperature, fogging system duty cycle 30 s and continuous) and ventilation (control range 3°C and 6°C, maximum available ventilation rate 32 and 43 air volume changes per hour). The control settings were evaluated by the number of simulated hours in specific temperature-humidity categories, by maximum temperature-humidity index (THI), as well as by the simulated energy use and water consumption of the control strategies. The validation during four growing-finishing periods resulted in an agreement within the accuracy of the temperature and humidity measurements: the difference between simulated and measured values averaged 0.2°C and 3% RH and 0.6°C and 3% RH with and without evaporative cooling, respectively. The efficacy of the fogging system, as measured by reductions in THI, predicted that alert situations were reduced from 13% to 1%, and all dangerous or emergency situations were eliminated. A year-round simulation resulted in water consumption of 2.5 L pig-1 day-1 if fogging was used on maximum settings and was lowered by about 25% for an optimized ventilation setting, namely a reduced maximum ventilation rate combined with shifting the temperature at which fogging was turned on. The results demonstrate that water and energy consumption can be reduced clearly without considerable negative effects on THI and indoor air climate.

Gizzerosine-induced histopathological lesions in broiler chicks

1. The aim of this study was to investigate pathomorphological changes in broiler chicks fed with different doses of gizzerosine, a substance produced during the heat treatments of fish meal. 2. The experiment was carried out in Ross broiler chicks which were divided into three groups: group A received 100% of non-medicated commercial mash for broiler chicks. During an experimental 5-d period, 50% of commercial mash was replaced with unheated fish meal (0.65 ppm gizzerosine) in group B and in group C with heated fish meal (1.15 ppm gizzerosine). Fourteen chicks from each group were killed every day. Samples of gastrointestinal and lymphoid organs, lung, pancreas, liver, brain and kidney tissue were sampled for histopathological analysis. Organs were embedded in paraffin and stained with hematoxylin-eosin stain and using periodic acid-Schiff reagent (PAS) and Sudan III (frozen sections). 3. Necropsy did not reveal notable differences between treated groups. There were no significant histopathological changes in immunocompetent organs nor in the lungs, the pancreas, the kidney or the brain. Sharply demarcated multiple vacuoles were observed in the myocardium in group C toward the end of the experiment. In group C, the prevalent changes in the gizzard and the proventriculus were slight to severe cuticle erosions and oedema of the lamina propria with or without multiple vacuoles, respectively, towards the end of the experiment. The most prominent changes toward the end of the experiment were dispersed cell vacuolisation in duodenal, jejunual, ileal and caecal lamina propria in group C. 4. In conclusion, it should be emphasised that extra-gizzard gizzerosine-induced lesions are probably not mediated by H 2 -receptor stimulation, but could be a consequence of cellular hypoxia.

How do pigs behave before starting an aggressive interaction? Identification of typical body positions in the early stage of aggression using video labelling techniques.

The aim of this study was to identify, quantify, and describe pre-signs of aggression in pigs and the early stages of aggressive interactions. The experiment was carried out at a commercial farm on a group of 11 male pigs weighing on average 23 kg and kept in a pen of4 m x 2.5 m. In total 8 hours were videorecorded during the first 3 days after mixing. As a result, 177 aggressive interactions were identified and labelled to find pre-sign body positions before aggressive interactions, attack positions and aggressive acts performed from these positions. A total of 12 positions were classified as pre-signs (P1-P12) and 7 of them were identified immediately at the start of aggressive interactions (P6-P12). Most common pre-sign positions were P3-pigs approaching and facing each other (24%) and P2-initiator pigs approaching from the lateral side (18%). In 80% of the cases the duration of pre-signs was 1-2 sec 72% of all aggressive interactions were short (1 to 10 sec). The most frequent attack positions were P12-inverse parallel (39.5%), P7-nose to nose, 90 degrees (19.77%) and P9-nose to head (13.5%). The most frequent aggressive acts from attack positions were head knocking (34.4%), pressing (34.4%) and biting of different body parts (29.4%). Head knocking was mostly observed in relation to P7 and P2 positions and biting was common in the P7 position. In conclusion, pigs adopt specific pre-signs and body positions before the escalation of aggressive interactions. This could be used as potential sign to identify a beginning aggression.

Can an automated labelling method based on accelerometer data replace a human labeller? - Postural profile of farrowing sows

We detect postural behaviour of farrowing sows on the basis of accelerometer data.Postural behaviours detected are active, resting in lateral and sternal positions.We detect postural behaviour of sows with accuracy of 70% in cross-validation.Accuracy is too low to detect the effect of pen type on behaviour of the animals.Accuracy is high enough to detect the effect of crating on behaviour of the animals. The objective of this research was to develop a method for the automated classification of sows postures based on accelerometer data. The second objective was to evaluate if the technique can be used in a reliable way instead of human labelling to automatically create postural profiles of sows. The experiment took place at the research farm of The University of Veterinary Medicine Vienna. The farm had a herd of 120 Large White sows. Data were collected from sows housed in three types of farrowing pens: wing, trapezoid and SWAP (Sow Welfare and Piglet Protection). The behaviour of 18 sows was video recorded and labelled for a period of 24h before the start of farrowing until the end of farrowing. The focus of labelling was on three types of postural behaviours: active, resting in lateral position (RLP) and resting in sternal position (RSP). Each sow had a specific ear tag with a 3 axis accelerometer sensor. Acceleration was measured at a frequency of 10Hz. Linear discriminant analysis (LDA) was used to classify the three labelled postural behaviours on the basis of acceleration data. To evaluate how the LDA classifier would generalise to an independent dataset an 18-fold cross-validation method was used. The overall classification accuracy of postural behaviours with the developed method was 70% in cross-validation and 73% on the training set. Comparison of labelling and classification results revealed that the accuracy is not good enough to detect the effect of pen type on the behaviour of the animals. However, the influence of crating on time spent resting in either a lateral or sternal position was correctly recognised with the automated method. The developed method could be further tested for the automated monitoring of the health and welfare status of sows.

Cognitive Enrichment in Piglet Rearing: An Approach to Enhance Animal Welfare and to Reduce Aggressive Behaviour

It is known that pigs raised in enriched environments express less aggressive behaviour. For this reason, a new method of cognitive environmental enrichment was experimented at the University of Veterinary Medicine Hannover, Germany. In the first phase, 78 suckling piglets were trained to learn the link between a sound given by an electronic feeder and a feed reward in the form of chocolate candies during a period of 8 days. In the second phase, the same piglets were used in resident-intruder tests to verify the potential of the feeding system to interrupt aggressive behaviour. The analysis of all training rounds revealed that piglets learned the commands during 8 days of training and the interest of the piglets increased within training days (P < 0.05). In the resident-intruder test, 79.5% of aggressive interactions were broken by feeder activation. In interactions where either the aggressor or the receiver reacted, a high number of fights were stopped (96.7% versus 93.1%) indicating that it was not relevant if the aggressor or the receiver responded to the feeder activation. We conclude that the electronic feeding system has the potential to be used as cognitive enrichment for piglets, being suitable for reducing aggressive behaviour in resident-intruder situations.

NON-LINEAR MODELING OF BROILER GROWTH USING A TIME-VARIANT PARAMETER ESTIMATION METHOD

Controlling the growth trajectory of broiler chickens is a possibility to reduce the negative growth responses related to fast growth, such as increased body fat deposition, a decrease of reproduction capacity, metabolic diseases, a high incidence of skeletal diseases, and sudden death syndrome. In previous research, a growth control algorithm for broilers was developed based on a compact adaptive growth prediction model, assuming a linear relationship between cumulative food intake and animal weight. Because the growth response of broilers to cumulative food intake is a non-linear process, this article investigates the validity of the assumption of linearity in an adaptive modeling approach in terms of prediction accuracy. The dynamic growth response of the broiler chickens was modeled and predicted using a time-variant parameter estimation procedure. A recursive non-linear model was used to estimate the model parameters and to predict the growth response every 24 h based on a fixed number of actual and past measurements. Tests were performed on 43 data sets. A comparison was made with the prediction accuracy of the recursive linear modeling approach. The non-linear modeling approach made it possible to predict the growth of the broiler chickens up to 7 days ahead with a mean relative prediction error of 5%, or less. This non-linear model reduces the prediction error significantly with a maximum of 1.5% in comparison to the linear modeling approach. It can be concluded that for growth control purposes the dynamic growth response of broiler chickens is slightly better modeled assuming non-linear dynamics in a short time window.

Proportional-Integral-Plus (PIP) Control of Agricultural Buildings

Abstract This paper is concerned with Proportional-Integral-Plus. (PIP) control system design for agricultural buildings. The objective is to regulate the ventilation system to either maintain the comfort and welfare of housed animals or to control the microclimate of a greenhouse, whilst minimising the costs to the farmer. The PIP controller can be interpreted as a logical extension of conventional PI/PID controllers, but with Inherent model-based predictive control action. The paper considers the design of PIP controllers for two test ventilation chambers based at the Katholieke Universiteit Leuven: the first chamber is for controlling temperature and the second for ventilation rate.