Digitoitujen väri-infrailmakuvien numeerinen monikuvatulkinta metsäninventoinnissa

The use of remote sensing imagery as auxiliary data in forest inventory is based on the correlation between features extracted from the images and the ground truth. The bidirectional reflectance and radial displacement cause variation in image features located in different segments of the image but forest characteristics remaining the same. The variation has so far been diminished by different radiometric corrections. In this study the use of sun azimuth based converted image co-ordinates was examined to supplement auxiliary data extracted from digitised aerial photographs. The method was considered as an alternative for radiometric corrections. Additionally, the usefulness of multi-image interpretation of digitised aerial photographs in regression estimation of forest characteristics was studied. The state owned study area located in Leivonmäki, Central Finland and the study material consisted of five digitised and ortho-rectified colour-infrared (CIR) aerial photographs and field measurements of 388 plots, out of which 194 were relascope (Bitterlich) plots and 194 were concentric circular plots. Both the image data and the field measurements were from the year 1999. When examining the effect of the location of the image point on pixel values and texture features of Finnish forest plots in digitised CIR photographs the clearest differences were found between front-and back-lighted image halves. Inside the image half the differences between different blocks were clearly bigger on the front-lighted half than on the back-lighted half. The strength of the phenomenon varied by forest category. The differences between pixel values extracted from different image blocks were greatest in developed and mature stands and smallest in young stands. The differences between texture features were greatest in developing stands and smallest in young and mature stands. The logarithm of timber volume per hectare and the angular transformation of the proportion of broadleaved trees of the total volume were used as dependent variables in regression models. Five different converted image co-ordinates based trend surfaces were used in models in order to diminish the effect of the bidirectional reflectance. The reference model of total volume, in which the location of the image point had been ignored, resulted in RMSE of 1,268 calculated from test material. The best of the trend surfaces was the complete third order surface, which resulted in RMSE of 1,107. The reference model of the proportion of broadleaved trees resulted in RMSE of 0,4292 and the second order trend surface was the best, resulting in RMSE of 0,4270. The trend surface method is applicable, but it has to be applied by forest category and by variable. The usefulness of multi-image interpretation of digitised aerial photographs was studied by building comparable regression models using either the front-lighted image features, back-lighted image features or both. The two-image model turned out to be slightly better than the one-image models in total volume estimation. The best one-image model resulted in RMSE of 1,098 and the two-image model resulted in RMSE of 1,090. The homologous features did not improve the models of the proportion of broadleaved trees. The overall result gives motivation for further research of multi-image interpretation. The focus may be improving regression estimation and feature selection or examination of stratification used in two-phase sampling inventory techniques. Keywords: forest inventory, digitised aerial photograph, bidirectional reflectance, converted image co­ordinates, regression estimation, multi-image interpretation, pixel value, texture, trend surface

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.

Inverse Problem for Fractional Brownian Motion with Discrete Data

The problem of recovering information from measurement data has already been studied for a long time. In the beginning, the methods were mostly empirical, but already towards the end of the sixties Backus and Gilbert started the development of mathematical methods for the interpretation of geophysical data. The problem of recovering information about a physical phenomenon from measurement data is an inverse problem. Throughout this work, the statistical inversion method is used to obtain a solution. Assuming that the measurement vector is a realization of fractional Brownian motion, the goal is to retrieve the amplitude and the Hurst parameter. We prove that under some conditions, the solution of the discretized problem coincides with the solution of the corresponding continuous problem as the number of observations tends to infinity. The measurement data is usually noisy, and we assume the data to be the sum of two vectors: the trend and the noise. Both vectors are supposed to be realizations of fractional Brownian motions, and the goal is to retrieve their parameters using the statistical inversion method. We prove a partial uniqueness of the solution. Moreover, with the support of numerical simulations, we show that in certain cases the solution is reliable and the reconstruction of the trend vector is quite accurate.

Computational Methods for Reconstruction and Analysis of Genome-Scale Metabolic Networks

Metabolism is the cellular subsystem responsible for generation of energy from nutrients and production of building blocks for larger macromolecules. Computational and statistical modeling of metabolism is vital to many disciplines including bioengineering, the study of diseases, drug target identification, and understanding the evolution of metabolism. In this thesis, we propose efficient computational methods for metabolic modeling. The techniques presented are targeted particularly at the analysis of large metabolic models encompassing the whole metabolism of one or several organisms. We concentrate on three major themes of metabolic modeling: metabolic pathway analysis, metabolic reconstruction and the study of evolution of metabolism. In the first part of this thesis, we study metabolic pathway analysis. We propose a novel modeling framework called gapless modeling to study biochemically viable metabolic networks and pathways. In addition, we investigate the utilization of atom-level information on metabolism to improve the quality of pathway analyses. We describe efficient algorithms for discovering both gapless and atom-level metabolic pathways, and conduct experiments with large-scale metabolic networks. The presented gapless approach offers a compromise in terms of complexity and feasibility between the previous graph-theoretic and stoichiometric approaches to metabolic modeling. Gapless pathway analysis shows that microbial metabolic networks are not as robust to random damage as suggested by previous studies. Furthermore the amino acid biosynthesis pathways of the fungal species Trichoderma reesei discovered from atom-level data are shown to closely correspond to those of Saccharomyces cerevisiae. In the second part, we propose computational methods for metabolic reconstruction in the gapless modeling framework. We study the task of reconstructing a metabolic network that does not suffer from connectivity problems. Such problems often limit the usability of reconstructed models, and typically require a significant amount of manual postprocessing. We formulate gapless metabolic reconstruction as an optimization problem and propose an efficient divide-and-conquer strategy to solve it with real-world instances. We also describe computational techniques for solving problems stemming from ambiguities in metabolite naming. These techniques have been implemented in a web-based sofware ReMatch intended for reconstruction of models for 13C metabolic flux analysis. In the third part, we extend our scope from single to multiple metabolic networks and propose an algorithm for inferring gapless metabolic networks of ancestral species from phylogenetic data. Experimenting with 16 fungal species, we show that the method is able to generate results that are easily interpretable and that provide hypotheses about the evolution of metabolism.

A Probabilistic Approach to the Primary Visual Cortex

What can the statistical structure of natural images teach us about the human brain? Even though the visual cortex is one of the most studied parts of the brain, surprisingly little is known about how exactly images are processed to leave us with a coherent percept of the world around us, so we can recognize a friend or drive on a crowded street without any effort. By constructing probabilistic models of natural images, the goal of this thesis is to understand the structure of the stimulus that is the raison d etre for the visual system. Following the hypothesis that the optimal processing has to be matched to the structure of that stimulus, we attempt to derive computational principles, features that the visual system should compute, and properties that cells in the visual system should have. Starting from machine learning techniques such as principal component analysis and independent component analysis we construct a variety of sta- tistical models to discover structure in natural images that can be linked to receptive field properties of neurons in primary visual cortex such as simple and complex cells. We show that by representing images with phase invariant, complex cell-like units, a better statistical description of the vi- sual environment is obtained than with linear simple cell units, and that complex cell pooling can be learned by estimating both layers of a two-layer model of natural images. We investigate how a simplified model of the processing in the retina, where adaptation and contrast normalization take place, is connected to the nat- ural stimulus statistics. Analyzing the effect that retinal gain control has on later cortical processing, we propose a novel method to perform gain control in a data-driven way. Finally we show how models like those pre- sented here can be extended to capture whole visual scenes rather than just small image patches. By using a Markov random field approach we can model images of arbitrary size, while still being able to estimate the model parameters from the data.

The range expansion of the European map butterfly in Finland

Climate change will influence the living conditions of all life on Earth. For some species the change in the environmental conditions that has occurred so far has already increased the risk of extinction, and the extinction risk is predicted to increase for large numbers of species in the future. Some species may have time to adapt to the changing environmental conditions, but the rate and magnitude of the change are too great to allow many species to survive via evolutionary changes. Species responses to climate change have been documented for some decades. Some groups of species, like many insects, respond readily to changes in temperature conditions and have shifted their distributions northwards to new climatically suitable regions. Such range shifts have been well documented especially in temperate zones. In this context, butterflies have been studied more than any other group of species, partly for the reason that their past geographical ranges are well documented, which facilitates species-climate modelling and other analyses. The aim of the modelling studies is to examine to what extent shifts in species distributions can be explained by climatic and other factors. Models can also be used to predict the future distributions of species. In this thesis, I have studied the response to climate change of one species of butterfly within one geographically restricted area. The study species, the European map butterfly (Araschnia levana), has expanded rapidly northwards in Finland during the last two decades. I used statistical and dynamic modelling approaches in combination with field studies to analyse the effects of climate warming and landscape structure on the expansion. I studied possible role of molecular variation in phosphoglucose isomerase (PGI), a glycolytic enzyme affecting flight metabolism and thereby flight performance, in the observed expansion of the map butterfly at two separate expansion fronts in Finland. The expansion rate of the map butterfly was shown to be correlated with the frequency of warmer than average summers during the study period. The result is in line with the greater probability of occurrence of the second generation during warm summers and previous results on this species showing greater mobility of the second than first generation individuals. The results of a field study in this thesis indicated low mobility of the first generation butterflies. Climatic variables alone were not sufficient to explain the observed expansion in Finland. There are also problems in transferring the climate model to new regions from the ones from which data were available to construct the model. The climate model predicted a wider distribution in the south-western part of Finland than what has been observed. Dynamic modelling of the expansion in response to landscape structure suggested that habitat and landscape structure influence the rate of expansion. In southern Finland the landscape structure may have slowed down the expansion rate. The results on PGI suggested that allelic variation in this enzyme may influence flight performance and thereby the rate of expansion. Genetic differences of the populations at the two expansion fronts may explain at least partly the observed differences in the rate of expansion. Individuals with the genotype associated with high flight metabolic rate were most frequent in eastern Finland, where the rate of range expansion has been highest.

Observations of the solar wind-magnetosphere-ionosphere coupling

In this thesis, the solar wind-magnetosphere-ionosphere coupling is studied observationally, with the main focus on the ionospheric currents in the auroral region. The thesis consists of five research articles and an introductory part that summarises the most important results reached in the articles and places them in a wider context within the field of space physics. Ionospheric measurements are provided by the International Monitor for Auroral Geomagnetic Effects (IMAGE) magnetometer network, by the low-orbit CHAllenging Minisatellite Payload (CHAMP) satellite, by the European Incoherent SCATter (EISCAT) radar, and by the Imager for Magnetopause-to-Aurora Global Exploration (IMAGE) satellite. Magnetospheric observations, on the other hand, are acquired from the four spacecraft of the Cluster mission, and solar wind observations from the Advanced Composition Explorer (ACE) and Wind spacecraft. Within the framework of this study, a new method for determining the ionospheric currents from low-orbit satellite-based magnetic field data is developed. In contrast to previous techniques, all three current density components can be determined on a matching spatial scale, and the validity of the necessary one-dimensionality approximation, and thus, the quality of the results, can be estimated directly from the data. The new method is applied to derive an empirical model for estimating the Hall-to-Pedersen conductance ratio from ground-based magnetic field data, and to investigate the statistical dependence of the large-scale ionospheric currents on solar wind and geomagnetic parameters. Equations describing the amount of field-aligned current in the auroral region, as well as the location of the auroral electrojets, as a function of these parameters are derived. Moreover, the mesoscale (10-1000 km) ionospheric equivalent currents related to two magnetotail plasma sheet phenomena, bursty bulk flows and flux ropes, are studied. Based on the analysis of 22 events, the typical equivalent current pattern related to bursty bulk flows is established. For the flux ropes, on the other hand, only two conjugate events are found. As the equivalent current patterns during these two events are not similar, it is suggested that the ionospheric signatures of a flux rope depend on the orientation and the length of the structure, but analysis of additional events is required to determine the possible ionospheric connection of flux ropes.

Studies of solar and stellar flares using multi-instrument data

Solar flares were first observed by plain eye in white light by William Carrington in England in 1859. Since then these eruptions in the solar corona have intrigued scientists. It is known that flares influence the space weather experienced by the planets in a multitude of ways, for example by causing aurora borealis. Understanding flares is at the epicentre of human survival in space, as astronauts cannot survive the highly energetic particles associated with large flares in high doses without contracting serious radiation disease symptoms, unless they shield themselves effectively during space missions. Flares may be at the epicentre of man s survival in the past as well: it has been suggested that giant flares might have played a role in exterminating many of the large species on Earth, including dinosaurs. Having said that prebiotic synthesis studies have shown lightning to be a decisive requirement for amino acid synthesis on the primordial Earth. Increased lightning activity could be attributed to space weather, and flares. This thesis studies flares in two ways: in the spectral and the spatial domain. We have extracted solar spectra using three different instruments, namely GOES (Geostationary Operational Environmental Satellite), RHESSI (Reuven Ramaty High Energy Solar Spectroscopic Imager) and XSM (X-ray Solar Monitor) for the same flares. The GOES spectra are low resolution obtained with a gas proportional counter, the RHESSI spectra are higher resolution obtained with Germanium detectors and the XSM spectra are very high resolution observed with a silicon detector. It turns out that the detector technology and response influence the spectra we see substantially, and are important to understanding what conclusions to draw from the data. With imaging data, there was not such a luxury of choice available. We used RHESSI imaging data to observe the spatial size of solar flares. In the present work the focus was primarily on current solar flares. However, we did make use of our improved understanding of solar flares to observe young suns in NGC 2547. The same techniques used with solar monitors were applied with XMM-Newton, a stellar X-ray monitor, and coupled with ground based Halpha observations these techniques yielded estimates for flare parameters in young suns. The material in this thesis is therefore structured from technology to application, covering the full processing path from raw data and detector responses to concrete physical parameter results, such as the first measurement of the length of plasma flare loops in young suns.

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.