Search

When purebred laying hen chicks hatch, they remain at a rearing farm until approximately 17 weeks of age, after which they are transferred to a laying farm. Chicks or pullets are removed from the flocks during these 17 weeks if they display any rearing abnormality. The aim of this study was to investigate associations between single nucleotide polymorphisms (SNPs) and rearing success of 4 purebred White Leghorns layer lines by implementing a Bayesian network approach. Phenotypic traits and SNPs of four purebred genetic White Leghorn layer lines were available for 23,000 rearing batches obtained between 2010 and 2020. Associations between incubation traits (clutch size, embryo mortality), rearing traits (genetic line, first week mortality, rearing abnormalities, natural death, rearing success, pullet flock age, and season) and SNPs were analyzed, using a two-step Bayesian Network (BN) approach. Furthermore, the SNPs were connected to their corresponding genes, which were further explored in bioinformatics databases. BN analysis revealed a total of 28 SNPs associated with some of the traits: ten SNPs were associated with clutch size, another 10 with rearing abnormalities, a single SNP with natural death, and seven SNPs with first week mortality. Exploration via bioinformatics databases showed that one of the SNPs (ENAH) had a protein predicted network composed of 11 other proteins. The major hub of this SNP was CDC42 protein, which has a role in egg production and reproduction. The results highlight the power of BNs in knowledge discovery and how their application in complex biological systems can help getting a deeper understanding of functionality underlying genetic variation of rearing success in laying hens. Improved welfare and production might result from the identified SNPs. Selecting for these SNPs through breeding could reduce stress and increase livability during rearing.

When purebred laying hen chicks hatch, they remain at a rearing farm until approximately 17 weeks of age, after which they are transferred to a laying farm. Chicks or pullets are removed from the flocks during these 17 weeks if they display any rearing abnormality. The aim of this study was to investigate associations between single nucleotide polymorphisms (SNPs) and rearing success of 4 purebred White Leghorns layer lines by implementing a Bayesian network approach. Phenotypic traits and SNPs of four purebred genetic White Leghorn layer lines were available for 23,000 rearing batches obtained between 2010 and 2020. Associations between incubation traits (clutch size, embryo mortality), rearing traits (genetic line, first week mortality, rearing abnormalities, natural death, rearing success, pullet flock age, and season) and SNPs were analyzed, using a two-step Bayesian Network (BN) approach. Furthermore, the SNPs were connected to their corresponding genes, which were further explored in bioinformatics databases. BN analysis revealed a total of 28 SNPs associated with some of the traits: ten SNPs were associated with clutch size, another 10 with rearing abnormalities, a single SNP with natural death, and seven SNPs with first week mortality. Exploration via bioinformatics databases showed that one of the SNPs (ENAH) had a protein predicted network composed of 11 other proteins. The major hub of this SNP was CDC42 protein, which has a role in egg production and reproduction. The results highlight the power of BNs in knowledge discovery and how their application in complex biological systems can help getting a deeper understanding of functionality underlying genetic variation of rearing success in laying hens. Improved welfare and production might result from the identified SNPs. Selecting for these SNPs through breeding could reduce stress and increase livability during rearing.

Intensive longitudinal data can be used to explore important associations and patterns between various types of inputs and outcomes. Nonlinear relations and irregular measurement occasions can pose problems to develop an accurate model for these kinds of data. This paper focuses on the development, fitting and evaluation of a prediction model with irregular intensive longitudinal data. A three-step process for developing a prediction tool for (daily) monitoring and prediction is outlined and illustrated for intensive weight measurements in piglets. Step 1 addresses a nonlinear relation in the data by developing and applying a normalizing transformation. Step 2 addresses the intermittent nature of the time points by aligning the measurement times to a common time grid with a broken-stick model. Step 3 addresses the prediction problem by selecting and evaluating inputs and covariates in the model to obtain accurate predictions. The final model predicts future outcomes accurately, while allowing for nonlinearities between input and output and for different measurement histories of individuals. The methodology described can be used to develop a tool to deal with intensive irregular longitudinal data that uses the available information in an optimal way. The resulting tool demonstrated to perform well for piglet weight prediction and can be adapted to many different applications.

It is important to detect negative behavior of animals for breeding in order to improve their health and welfare. In this work, AI is employed to assist individual animal detection and tracking, which enables the future analysis of behavior for individual animals. The study involves animal groups of pigs and laying hens. First, two state-of-the-art deep learning-based Multi-Object Tracking (MOT) methods are investigated, namely Joint Detection and Embedding (JDE) and FairMOT. Both models detect and track individual animals automatically and continuously. Second, a weighted association algorithm is proposed, which is feasible for both MOT methods to optimize the object re-identification (re-ID), thereby improving the tracking performance. The proposed methods are evaluated on manually annotated datasets. The best tracking performance on pigs is obtained by FairMOT with the weighted association, resulting in an IDF1 of 90.3%, MOTA of 90.8%, MOTP of 83.7%, number of identity switches of 14, and an execution rate of 20.48 fps. For the laying hens, FairMOT with the weighted association also achieves the best tracking performance, with an IDF1 of 88.8%, MOTA of 86.8%, MOTP of 72.8%, number of identity switches of 2, and an execution rate of 21.01 fps. These results show a promising high accuracy and robustness for the individual animal tracking.

It is important to detect negative behavior of animals for breeding in order to improve their health and welfare. In this work, AI is employed to assist individual animal detection and tracking, which enables the future analysis of behavior for individual animals. The study involves animal groups of pigs and laying hens. First, two state-of-the-art deep learning-based Multi-Object Tracking (MOT) methods are investigated, namely Joint Detection and Embedding (JDE) and FairMOT. Both models detect and track individual animals automatically and continuously. Second, a weighted association algorithm is proposed, which is feasible for both MOT methods to optimize the object re-identification (re-ID), thereby improving the tracking performance. The proposed methods are evaluated on manually annotated datasets. The best tracking performance on pigs is obtained by FairMOT with the weighted association, resulting in an IDF1 of 90.3%, MOTA of 90.8%, MOTP of 83.7%, number of identity switches of 14, and an execution rate of 20.48 fps. For the laying hens, FairMOT with the weighted association also achieves the best tracking performance, with an IDF1 of 88.8%, MOTA of 86.8%, MOTP of 72.8%, number of identity switches of 2, and an execution rate of 21.01 fps. These results show a promising high accuracy and robustness for the individual animal tracking

Contains fulltext : 217421.pdf (Publisher’s version ) (Open Access)

Contains fulltext : 217421.pdf (Publisher’s version ) (Open Access)

Contains fulltext : 217421.pdf (Publisher’s version ) (Open Access)

The selected use case was an experiment in which the gait score of turkeys was determined, here 3 animals can be used for educational purposes. This gait scoring is traditionally performed by an expert. In this experiment different type of sensors were used to explore to what extent these sensors can describe or mirror the gait score of the expert. Data & Sensors Gait score (visually by expert) Force Plate (Kistler) Accelerometers / inertial measurement units {IMUs} (Xsense MTw awinda) 3D Video camera (Intel Realsense D415)

Current artificial insemination (AI) laboratory practices assess semen quality of each boar ejaculate to decide which ones to process into AI doses. This decision is aided with two, world-wide used, motility parameters that come available through computer assisted semen analysis (CASA). This decision process, however, still results in AI doses with variable and sometimes suboptimal fertility outcomes (e.g., small litter size). The hypothesis was that the decision which ejaculates to process into AI doses can be improved by adding more data from CASA systems, and data from other sources, in combination with a data-driven model. Available data consisted of ejaculates that passed the initial decision, and thus, were processed into AI doses and used to inseminate sows. Data were divided into a training set (6793 records) and a validation set (1191 records) for model development, and an independent test set (1434 records) for performance assessment. Gradient Boosting Machine (GBM) models were developed to predict four fertility phenotypes of interest (gestation length, total number born, number born alive, and number of stillborn piglets). Each fertility phenotype was considered as a numeric and as a binary outcome parameter, totaling to eight different fertility phenotypes. Data used to further improve the decision process originated from four sources: 1) CASA information, 2) boar ejaculate information, 3) breeding value estimations, and 4) weather information. These data were used to create seven prediction sets, where each new set added parameters to the ones included in the previous set. The GBM models predicted fertility phenotypes with low correlations (for numeric phenotypes) and area under the curve values (for binary phenotypes) on the test data. Hence, results demonstrated that a combination of more data and GBM did not enable further improvement of the AI dose quality checks, resulting in the rejection of our hypothesis. However, our study revealed parameters

Locomotion is an important welfare and health trait in turkey production. Current breeding values for locomotion are often based on subjective scoring. Sensor technologies could be applied to obtain objective evaluation of turkey gait. Inertial measurement units (IMUs) measure acceleration and rotational velocity, which makes them attractive devices for gait analysis. The aim of this study was to compare three different methods for step detection from IMU data from turkeys. This is an essential step for future feature extraction for the evaluation of turkey locomotion. Data from turkeys walking through a corridor with IMUs attached to each upper leg were annotated manually. We evaluated change point detection, local extrema approach, and gradient boosting machine in terms of step detection and precision of start and end point of the steps. All three methods were successful in step detection, but local extrema approach showed more false detections. In terms of precision of start and end point of steps, change point detection performed poorly due to significant irregular delay, while gradient boosting machine was most precise. For the allowed distance to the annotated steps of 0.2 s, the precision of gradient boosting machine was 0.81 and the recall was 0.84, which is much better in comparison to the other two methods (<0.61). At an allowed distance of 1 s, performance of the three models was similar. Gradient boosting machine was identified as the most accurate for signal segmentation with a final goal to extract information about turkey gait; however, it requires an annotated training dataset.

Damaging behaviors, like feather pecking (FP), have large economic and welfare consequences in the commercial laying hen industry. Selective breeding can be used to obtain animals that are less likely to perform damaging behavior on their pen-mates. However, with the growing tendency to keep birds in large groups, identifying specific birds that are performing or Animals 2019, 9, 108; doi:10.3390/ani9030108 www.mdpi.com/journal/animals Animals 2019, 9, 108 2 of 21 receiving FP is difficult. With current developments in sensor technologies, it may now be possible to identify laying hens in large groups that show less FP behavior and select them for breeding. We propose using a combination of sensor technology and genomic methods to identify feather peckers and victims in groups. In this review, we will describe the use of “-omics” approaches to understand FP and give an overview of sensor technologies that can be used for animal monitoring, such as ultra-wideband, radio frequency identification, and computer vision. We will then discuss the identification of indicator traits from both sensor technologies and genomics approaches that can be used to select animals for breeding against damaging behavior.

Previous work [1] has demonstrated the possibility of high resolution imaging through the use of a single element and a aberration mask. This thesis will expand on the previous work by examining the proposed method for errors in the creation of the model. The analysis is preformed by examining the various aspects of the measurements setup and underlying theoretical model, after which measurements are performed to determine their contribution and correctness with regard to the model. Results demonstrated a systematic error of a non-linear frequency scaling and semi-linear phase shift. The origin of the error lies in the unwanted addition of transfer functions of some of the components. A Tikhonov regularized least squares method is proposed to estimate this transfer function and supply compensation based on all the measurements. The results of application of this method on the uncalibrated model are demonstrated through 1D imaging experiments. The result of which show a signicant improvement over the previous uncalibrated results. After which the possibility of calibration due to a singular measurement is explored and a adaptation of the Tikhonov regularized least squares method is proposed for close approximation of the previously found transfer function. Further to obtain an indication of possible remaining hurdles and successes with this method, extensive simulations are preformed to examine the individual impact of various sources of noise and interference.

Previous work [1] has demonstrated the possibility of high resolution imaging through the use of a single element and a aberration mask. This thesis will expand on the previous work by examining the proposed method for errors in the creation of the model. The analysis is preformed by examining the various aspects of the measurements setup and underlying theoretical model, after which measurements are performed to determine their contribution and correctness with regard to the model. Results demonstrated a systematic error of a non-linear frequency scaling and semi-linear phase shift. The origin of the error lies in the unwanted addition of transfer functions of some of the components. A Tikhonov regularized least squares method is proposed to estimate this transfer function and supply compensation based on all the measurements. The results of application of this method on the uncalibrated model are demonstrated through 1D imaging experiments. The result of which show a signicant improvement over the previous uncalibrated results. After which the possibility of calibration due to a singular measurement is explored and a adaptation of the Tikhonov regularized least squares method is proposed for close approximation of the previously found transfer function. Further to obtain an indication of possible remaining hurdles and successes with this method, extensive simulations are preformed to examine the individual impact of various sources of noise and interference.

Damaging behaviors, like feather pecking (FP), have large economic and welfare consequences in the commercial laying hen industry. Selective breeding can be used to obtain animals that are less likely to perform damaging behavior on their pen-mates. However, with the growing tendency to keep birds in large groups, identifying specific birds that are performing or receiving FP is difficult. With current developments in sensor technologies, it may now be possible to identify laying hens in large groups that show less FP behavior and select them for breeding. We propose using a combination of sensor technology and genomic methods to identify feather peckers and victims in groups. In this review, we will describe the use of “-omics” approaches to understand FP and give an overview of sensor technologies that can be used for animal monitoring, such as ultra-wideband, radio frequency identification, and computer vision. We will then discuss the identification of indicator traits from both sensor technologies and genomics approaches that can be used to select animals for breeding against damaging behavior.