Automatic Lameness Detection in a Milking Robot : Instrumentation, measurement software, algorithms for data analysis and a neural network model

The aim of this thesis is to develop a fully automatic lameness detection system that operates in a milking robot. The instrumentation, measurement software, algorithms for data analysis and a neural network model for lameness detection were developed. Automatic milking has become a common practice in dairy husbandry, and in the year 2006 about 4000 farms worldwide used over 6000 milking robots. There is a worldwide movement with the objective of fully automating every process from feeding to milking. Increase in automation is a consequence of increasing farm sizes, the demand for more efficient production and the growth of labour costs. As the level of automation increases, the time that the cattle keeper uses for monitoring animals often decreases. This has created a need for systems for automatically monitoring the health of farm animals. The popularity of milking robots also offers a new and unique possibility to monitor animals in a single confined space up to four times daily. Lameness is a crucial welfare issue in the modern dairy industry. Limb disorders cause serious welfare, health and economic problems especially in loose housing of cattle. Lameness causes losses in milk production and leads to early culling of animals. These costs could be reduced with early identification and treatment. At present, only a few methods for automatically detecting lameness have been developed, and the most common methods used for lameness detection and assessment are various visual locomotion scoring systems. The problem with locomotion scoring is that it needs experience to be conducted properly, it is labour intensive as an on-farm method and the results are subjective. A four balance system for measuring the leg load distribution of dairy cows during milking in order to detect lameness was developed and set up in the University of Helsinki Research farm Suitia. The leg weights of 73 cows were successfully recorded during almost 10,000 robotic milkings over a period of 5 months. The cows were locomotion scored weekly, and the lame cows were inspected clinically for hoof lesions. Unsuccessful measurements, caused by cows standing outside the balances, were removed from the data with a special algorithm, and the mean leg loads and the number of kicks during milking was calculated. In order to develop an expert system to automatically detect lameness cases, a model was needed. A probabilistic neural network (PNN) classifier model was chosen for the task. The data was divided in two parts and 5,074 measurements from 37 cows were used to train the model. The operation of the model was evaluated for its ability to detect lameness in the validating dataset, which had 4,868 measurements from 36 cows. The model was able to classify 96% of the measurements correctly as sound or lame cows, and 100% of the lameness cases in the validation data were identified. The number of measurements causing false alarms was 1.1%. The developed model has the potential to be used for on-farm decision support and can be used in a real-time lameness monitoring system.

Genetic variability in high temperature effects on seed-set in sorghum

Sorghum (Sorghum bicolor (L.) Moench) is grown as a dryland crop in semiarid subtropical and tropical environments where it is often exposed to high temperatures around flowering. Projected climate change is likely to increase the incidence of exposure to high temperature, with potential adverse effects on growth, development and grain yield. The objectives of this study were to explore genetic variability for the effects of high temperature on crop growth and development, in vitro pollen germination and seed-set. Eighteen diverse sorghum genotypes were grown at day : night temperatures of 32 : 21 degrees C (optimum temperature, OT) and 38 : 21 degrees C (high temperature, HT during the middle of the day) in controlled environment chambers. HT significantly accelerated development, and reduced plant height and individual leaf size. However, there was no consistent effect on leaf area per plant. HT significantly reduced pollen germination and seed-set percentage of all genotypes; under HT, genotypes differed significantly in pollen viability percentage (17-63%) and seed-set percentage (7-65%). The two traits were strongly and positively associated (R-2 = 0.93, n = 36, P < 0.001), suggesting a causal association. The observed genetic variation in pollen and seed-set traits should be able to be exploited through breeding to develop heat-tolerant varieties for future climates.

Inheritance of resistance to root-lesion nematodes (Pratylenchus thornei and P. neglectus) in five doubled-haploid populations of wheat

Nematode species Pratylenchus thornei and P. neglectus are the two most important root-lesion nematodes affecting wheat (Triticum aestivum L.) and other grain crops in Australia. For practical plant breeding, it will be valuable to know the mode of inheritance of resistance and whether the same set of genes confer resistance to both species. We evaluated reactions to P. thornei and P. neglectus of glasshouse-inoculated plants of five doubled-haploid populations derived from five resistant synthetic hexpaloid wheat lines, each crossed to the susceptible Australian wheat cultivar Janz. For each cross we determined genetic variance, heritability and minimum number of effective resistance genes for each nematode species. Distributions of nematode numbers for both species were continuous for all doubled-haploid populations. Heritabilities were high and the resistances were controlled by 4-7 genes. There was no genetic correlation between resistance to P. thornei and to P. neglectus in four of the populations and a significant but low correlation in one. Therefore, resistances to P. thornei and to P. neglectus are probably inherited quantitatively and independently in four of these synthetic hexaploid wheat populations, with the possibility of at least one genetic factor contributing to resistance to both species in one of the populations. Parents with the greatest level of resistance will be the best to use as donor parents to adapted cultivars, and selection of resistance to both species in early generations will be optimal to carry resistance through successive cycles of inbreeding to produce resistant cultivars for release.