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.

Statistical and Information-Theoretic Methods for Data-Analysis

In this Thesis, we develop theory and methods for computational data analysis. The problems in data analysis are approached from three perspectives: statistical learning theory, the Bayesian framework, and the information-theoretic minimum description length (MDL) principle. Contributions in statistical learning theory address the possibility of generalization to unseen cases, and regression analysis with partially observed data with an application to mobile device positioning. In the second part of the Thesis, we discuss so called Bayesian network classifiers, and show that they are closely related to logistic regression models. In the final part, we apply the MDL principle to tracing the history of old manuscripts, and to noise reduction in digital signals.

Geant4 Hadronic Cascade Models and CMS Data Analysis : Computational Challenges in the LHC era

This work belongs to the field of computational high-energy physics (HEP). The key methods used in this thesis work to meet the challenges raised by the Large Hadron Collider (LHC) era experiments are object-orientation with software engineering, Monte Carlo simulation, the computer technology of clusters, and artificial neural networks. The first aspect discussed is the development of hadronic cascade models, used for the accurate simulation of medium-energy hadron-nucleus reactions, up to 10 GeV. These models are typically needed in hadronic calorimeter studies and in the estimation of radiation backgrounds. Various applications outside HEP include the medical field (such as hadron treatment simulations), space science (satellite shielding), and nuclear physics (spallation studies). Validation results are presented for several significant improvements released in Geant4 simulation tool, and the significance of the new models for computing in the Large Hadron Collider era is estimated. In particular, we estimate the ability of the Bertini cascade to simulate Compact Muon Solenoid (CMS) hadron calorimeter HCAL. LHC test beam activity has a tightly coupled cycle of simulation-to-data analysis. Typically, a Geant4 computer experiment is used to understand test beam measurements. Thus an another aspect of this thesis is a description of studies related to developing new CMS H2 test beam data analysis tools and performing data analysis on the basis of CMS Monte Carlo events. These events have been simulated in detail using Geant4 physics models, full CMS detector description, and event reconstruction. Using the ROOT data analysis framework we have developed an offline ANN-based approach to tag b-jets associated with heavy neutral Higgs particles, and we show that this kind of NN methodology can be successfully used to separate the Higgs signal from the background in the CMS experiment.

Accelerator Mass Spectrometry and Bayesian Data Analysis

Accelerator mass spectrometry (AMS) is an ultrasensitive technique for measuring the concentration of a single isotope. The electric and magnetic fields of an electrostatic accelerator system are used to filter out other isotopes from the ion beam. The high velocity means that molecules can be destroyed and removed from the measurement background. As a result, concentrations down to one atom in 10^16 atoms are measurable. This thesis describes the construction of the new AMS system in the Accelerator Laboratory of the University of Helsinki. The system is described in detail along with the relevant ion optics. System performance and some of the 14C measurements done with the system are described. In a second part of the thesis, a novel statistical model for the analysis of AMS data is presented. Bayesian methods are used in order to make the best use of the available information. In the new model, instrumental drift is modelled with a continuous first-order autoregressive process. This enables rigorous normalization to standards measured at different times. The Poisson statistical nature of a 14C measurement is also taken into account properly, so that uncertainty estimates are much more stable. It is shown that, overall, the new model improves both the accuracy and the precision of AMS measurements. In particular, the results can be improved for samples with very low 14C concentrations or measured only a few times.

Residual noise covariance for Planck low-resolution data analysis

Aims: Develop and validate tools to estimate residual noise covariance in Planck frequency maps. Quantify signal error effects and compare different techniques to produce low-resolution maps. Methods: We derive analytical estimates of covariance of the residual noise contained in low-resolution maps produced using a number of map-making approaches. We test these analytical predictions using Monte Carlo simulations and their impact on angular power spectrum estimation. We use simulations to quantify the level of signal errors incurred in different resolution downgrading schemes considered in this work. Results: We find an excellent agreement between the optimal residual noise covariance matrices and Monte Carlo noise maps. For destriping map-makers, the extent of agreement is dictated by the knee frequency of the correlated noise component and the chosen baseline offset length. The significance of signal striping is shown to be insignificant when properly dealt with. In map resolution downgrading, we find that a carefully selected window function is required to reduce aliasing to the sub-percent level at multipoles, ell > 2Nside, where Nside is the HEALPix resolution parameter. We show that sufficient characterization of the residual noise is unavoidable if one is to draw reliable contraints on large scale anisotropy. Conclusions: We have described how to compute the low-resolution maps, with a controlled sky signal level, and a reliable estimate of covariance of the residual noise. We have also presented a method to smooth the residual noise covariance matrices to describe the noise correlations in smoothed, bandwidth limited maps.

Income Inequality and Healt: A Multi-Country Analysis

This paper investigates the effect of income inequality on health status. A model of health status was specified in which the main variables were income level, income inequality, the level of savings and the level of education. The model was estimated using a panel data set for 44 countries covering six time periods. The results indicate that income inequality (measured by the Gini coefficient) has a significant effect on health status when we control for the levels of income, savings and education. The relationship is consistent regardless of the specification of health status and income. Thus, the study results provide some empirical support for the income inequality hypothesis.

Econometric models of Finnish non-industrial private forest owners' timber supply and timber stock

This dissertation examines the short- and long-run impacts of timber prices and other factors affecting NIPF owners' timber harvesting and timber stocking decisions. The utility-based Faustmann model provides testable hypotheses of the exogenous variables retained in the timber supply analysis. The timber stock function, derived from a two-period biomass harvesting model, is estimated using a two-step GMM estimator based on balanced panel data from 1983 to 1991. Timber supply functions are estimated using a Tobit model adjusted for heteroscedasticity and nonnormality of errors based on panel data from 1994 to 1998. Results show that if specification analysis of the Tobit model is ignored, inconsistency and biasedness can have a marked effect on parameter estimates. The empirical results show that owner's age is the single most important factor determining timber stock; timber price is the single most important factor in harvesting decision. The results of the timber supply estimations can be interpreted using utility-based Faustmann model of a forest owner who values a growing timber in situ.

Components of productivity growth in Finnish agriculture

The objective was to measure productivity growth and its components in Finnish agriculture, especially in dairy farming. The objective was also to compare different methods and models - both parametric (stochastic frontier analysis) and non-parametric (data envelopment analysis) - in estimating the components of productivity growth and the sensitivity of results with respect to different approaches. The parametric approach was also applied in the investigation of various aspects of heterogeneity. A common feature of the first three of five articles is that they concentrate empirically on technical change, technical efficiency change and the scale effect, mainly on the basis of the decompositions of Malmquist productivity index. The last two articles explore an intermediate route between the Fisher and Malmquist productivity indices and develop a detailed but meaningful decomposition for the Fisher index, including also empirical applications. Distance functions play a central role in the decomposition of Malmquist and Fisher productivity indices. Three panel data sets from 1990s have been applied in the study. The common feature of all data used is that they cover the periods before and after Finnish EU accession. Another common feature is that the analysis mainly concentrates on dairy farms or their roughage production systems. Productivity growth on Finnish dairy farms was relatively slow in the 1990s: approximately one percent per year, independent of the method used. Despite considerable annual variation, productivity growth seems to have accelerated towards the end of the period. There was a slowdown in the mid-1990s at the time of EU accession. No clear immediate effects of EU accession with respect to technical efficiency could be observed. Technical change has been the main contributor to productivity growth on dairy farms. However, average technical efficiency often showed a declining trend, meaning that the deviations from the best practice frontier are increasing over time. This suggests different paths of adjustment at the farm level. However, different methods to some extent provide different results, especially for the sub-components of productivity growth. In most analyses on dairy farms the scale effect on productivity growth was minor. A positive scale effect would be important for improving the competitiveness of Finnish agriculture through increasing farm size. This small effect may also be related to the structure of agriculture and to the allocation of investments to specific groups of farms during the research period. The result may also indicate that the utilization of scale economies faces special constraints in Finnish conditions. However, the analysis of a sample of all types of farms suggested a more considerable scale effect than the analysis on dairy farms.

Data fusion and matching by maximizing statistical dependencies

The core aim of machine learning is to make a computer program learn from the experience. Learning from data is usually defined as a task of learning regularities or patterns in data in order to extract useful information, or to learn the underlying concept. An important sub-field of machine learning is called multi-view learning where the task is to learn from multiple data sets or views describing the same underlying concept. A typical example of such scenario would be to study a biological concept using several biological measurements like gene expression, protein expression and metabolic profiles, or to classify web pages based on their content and the contents of their hyperlinks. In this thesis, novel problem formulations and methods for multi-view learning are presented. The contributions include a linear data fusion approach during exploratory data analysis, a new measure to evaluate different kinds of representations for textual data, and an extension of multi-view learning for novel scenarios where the correspondence of samples in the different views or data sets is not known in advance. In order to infer the one-to-one correspondence of samples between two views, a novel concept of multi-view matching is proposed. The matching algorithm is completely data-driven and is demonstrated in several applications such as matching of metabolites between humans and mice, and matching of sentences between documents in two languages.

Sustainability and Mission Drift in Microfinance

Microfinance institutions (MFIs) are constrained by double bottom-lines: meeting social obligations (the first bottom-line) and obtaining financial self-sufficiency (the second bottom-line). The proponents of the first bottom-line, however, are increasingly concerned that there is a trade-off between these two bottom-lines—i.e., getting hold of financial self-sufficiency may lead MFIs to drift away from their original social mission of serving the very poor, commonly known as mission drift in microfinance which is still a controversial issue. This study aims at addressing the concerns for mission drift in microfinance in a performance analysis framework. Chapter 1 deals with theoretical background, motivation and objectives of the topic. Then the study explores the validity of three major and related present-day concerns. Chapter 2 explores the impact of profitability on outreach-quality in MFIs, commonly known as mission drift, using a unique panel database that contains 4-9 years’ observations from 253 MFIs in 69 countries. Chapter 3 introduces factor analysis, a multivariate tool, in the process of analysing mission drift in microfinance and the exercise in this chapter demonstrates how the statistical tool of factor analysis can be utilised to examine this conjecture. In order to explore why some microfinance institutions (MFIs) perform better than others, Chapter 4 looks at factors which have an impact on several performance indicators of MFIs—profitability or sustainability, repayment status and cost indicators—based on quality-data on 353 institutions in 77 countries. The study also demonstrates whether such mission drift can be avoided while having self-sustainability. In Chapter 5 we examine the impact of capital and financing structure on the performance of microfinance institutions where estimations with instruments have been performed using a panel dataset of 782 MFIs in 92 countries for the period 2000-2007. Finally, Chapter 6 concludes the study by summarising the results from the previous chapters and suggesting some directions for future studies.

Panel Cointegration of Chinese A and B Shares

This paper uses panel unit root and cointegration methods to test the stationarity of the premium on domestic investors’ A shares over foreign investors’ B shares and cointegration between the A and B share prices on the Chinese stock exchanges. We find that the A share price premium is nonstationary until 2001, when the A and B share markets were partially merged, and that the A and B share prices are cointegrated in the panel.Cointegration is more likely to be found for firms in the service sector and for firms that issued B shares recently.