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.

Urban ecosystem services at the plant-soil interface

Continuing urbanization is a crucial driver of land transformation, having widespread impacts on virtually all ecosystems. Terrestrial ecosystems, including disturbed ones, are dependent on soils, which provide a multitude of ecosystem services. As soils are always directly and/or indirectly impacted through land transformation, land cover change causes soil change. Knowledge of ecosystem properties and functions in soils is increasing in importance as humans continue to concentrate into already densely-populated areas. Urban soils often have hampered functioning due to various disturbances resulting from human activity. Innovative solutions are needed to bring the lacking ecosystem services and quality of life to these urban environments. For instance, the ecosystem services of the urban green infrastructure may be substantially improved through knowledge of their functional properties. In the research forming this thesis, the impacts of four plant species (Picea abies, Calluna vulgaris, Lotus corniculatus and Holcus lanatus) on belowground biota and regulatory ecosystem services were investigated in two different urban soil types. The retention of inorganic nitrogen and phosphorus in the plant-soil system, decomposition of plant litter, primary production, and the degradation of polycyclic aromatic hydrocarbons (PAHs) were examined in the field and under laboratory conditions. The main objective of the research was to determine whether the different plant species (representing traits with varying litter decomposability) will give rise to dissimilar urban belowground communities with differing ecological functions. Microbial activity as well as the abundance of nematodes and enchytraeid worm biomass was highest below the legume L. corniculatus. L. corniculatus and the grass H. lanatus, producing labile or intermediate quality litter, enhanced the proportion of bacteria in the soil rhizosphere, while the recalcitrant litter-producing shrub C. vulgaris and the conifer P. abies stimulated the growth of fungi. The loss of nitrogen from the plant-soil system was small for H. lanatus and the combination of C. vulgaris + P. abies, irrespective of their energy channel composition. These presumably nitrogen-conservative plant species effectively diminished the leaching losses from the plant-soil systems with all the plant traits present. The laboratory experiment revealed a difference in N allocation between the plant traits: C. vulgaris and P. abies sequestered significantly more N in aboveground shoots in comparison to L. corniculatus and H. Lanatus. Plant rhizosphere effects were less clear for phosphorus retention, litter decomposition and the degradation of PAH compounds. This may be due to the relatively short experimental durations, as the maturation of the plant-soil system is likely to take a considerably longer time. The empirical studies of this thesis demonstrated that the soil communities rapidly reflect changes in plant coverage, and this has consequences for the functionality of soils. The energy channel composition of soils can be manipulated through plants, which was also supported by the results of the separate meta-analysis conducted in this thesis. However, further research is needed to understand the linkages between the biological community properties and ecosystem services in strongly human-modified systems.