Level Set Methods in Image Processing

This thesis gives an overview of the use of the level set methods in the field of image science. The similar fast marching method is discussed for comparison, also the narrow band and the particle level set methods are introduced. The level set method is a numerical scheme for representing, deforming and recovering structures in an arbitrary dimensions. It approximates and tracks the moving interfaces, dynamic curves and surfaces. The level set method does not define how and why some boundary is advancing the way it is but simply represents and tracks the boundary. The principal idea of the level set method is to represent the N dimensional boundary in the N+l dimensions. This gives the generality to represent even the complex boundaries. The level set methods can be powerful tools to represent dynamic boundaries, but they can require lot of computing power. Specially the basic level set method have considerable computational burden. This burden can be alleviated with more sophisticated versions of the level set algorithm like the narrow band level set method or with the programmable hardware implementation. Also the parallel approach can be used in suitable applications. It is concluded that these methods can be used in a quite broad range of image applications, like computer vision and graphics, scientific visualization and also to solve problems in computational physics. Level set methods and methods derived and inspired by it will be in the front line of image processing also in the future.

Application of Neural Network Methods in the Prediction of Stock Markets

The purpose of the research is to define practical profit which can be achieved using neural network methods as a prediction instrument. The thesis investigates the ability of neural networks to forecast future events. This capability is checked on the example of price prediction during intraday trading on stock market. The executed experiments show predictions of average 1, 2, 5 and 10 minutes’ prices based on data of one day and made by two different types of forecasting systems. These systems are based on the recurrent neural networks and back propagation neural nets. The precision of the predictions is controlled by the absolute error and the error of market direction. The economical effectiveness is estimated by a special trading system. In conclusion, the best structures of neural nets are tested with data of 31 days’ interval. The best results of the average percent of profit from one transaction (buying + selling) are 0.06668654, 0.188299453, 0.349854787 and 0.453178626, they were achieved for prediction periods 1, 2, 5 and 10 minutes. The investigation can be interesting for the investors who have access to a fast information channel with a possibility of every-minute data refreshment.

New kernel functions and learning methods for text and data mining

Recent advances in machine learning methods enable increasingly the automatic construction of various types of computer assisted methods that have been difficult or laborious to program by human experts. The tasks for which this kind of tools are needed arise in many areas, here especially in the fields of bioinformatics and natural language processing. The machine learning methods may not work satisfactorily if they are not appropriately tailored to the task in question. However, their learning performance can often be improved by taking advantage of deeper insight of the application domain or the learning problem at hand. This thesis considers developing kernel-based learning algorithms incorporating this kind of prior knowledge of the task in question in an advantageous way. Moreover, computationally efficient algorithms for training the learning machines for specific tasks are presented. In the context of kernel-based learning methods, the incorporation of prior knowledge is often done by designing appropriate kernel functions. Another well-known way is to develop cost functions that fit to the task under consideration. For disambiguation tasks in natural language, we develop kernel functions that take account of the positional information and the mutual similarities of words. It is shown that the use of this information significantly improves the disambiguation performance of the learning machine. Further, we design a new cost function that is better suitable for the task of information retrieval and for more general ranking problems than the cost functions designed for regression and classification. We also consider other applications of the kernel-based learning algorithms such as text categorization, and pattern recognition in differential display. We develop computationally efficient algorithms for training the considered learning machines with the proposed kernel functions. We also design a fast cross-validation algorithm for regularized least-squares type of learning algorithm. Further, an efficient version of the regularized least-squares algorithm that can be used together with the new cost function for preference learning and ranking tasks is proposed. In summary, we demonstrate that the incorporation of prior knowledge is possible and beneficial, and novel advanced kernels and cost functions can be used in algorithms efficiently.

Learning Preferences with Kernel-Based Methods

Learning of preference relations has recently received significant attention in machine learning community. It is closely related to the classification and regression analysis and can be reduced to these tasks. However, preference learning involves prediction of ordering of the data points rather than prediction of a single numerical value as in case of regression or a class label as in case of classification. Therefore, studying preference relations within a separate framework facilitates not only better theoretical understanding of the problem, but also motivates development of the efficient algorithms for the task. Preference learning has many applications in domains such as information retrieval, bioinformatics, natural language processing, etc. For example, algorithms that learn to rank are frequently used in search engines for ordering documents retrieved by the query. Preference learning methods have been also applied to collaborative filtering problems for predicting individual customer choices from the vast amount of user generated feedback. In this thesis we propose several algorithms for learning preference relations. These algorithms stem from well founded and robust class of regularized least-squares methods and have many attractive computational properties. In order to improve the performance of our methods, we introduce several non-linear kernel functions. Thus, contribution of this thesis is twofold: kernel functions for structured data that are used to take advantage of various non-vectorial data representations and the preference learning algorithms that are suitable for different tasks, namely efficient learning of preference relations, learning with large amount of training data, and semi-supervised preference learning. Proposed kernel-based algorithms and kernels are applied to the parse ranking task in natural language processing, document ranking in information retrieval, and remote homology detection in bioinformatics domain. Training of kernel-based ranking algorithms can be infeasible when the size of the training set is large. This problem is addressed by proposing a preference learning algorithm whose computation complexity scales linearly with the number of training data points. We also introduce sparse approximation of the algorithm that can be efficiently trained with large amount of data. For situations when small amount of labeled data but a large amount of unlabeled data is available, we propose a co-regularized preference learning algorithm. To conclude, the methods presented in this thesis address not only the problem of the efficient training of the algorithms but also fast regularization parameter selection, multiple output prediction, and cross-validation. Furthermore, proposed algorithms lead to notably better performance in many preference learning tasks considered.

Application of capillary electrophoretic methods for determining carbohydrates and aliphatic carboxylic acids formed during wood processing

Knowledge of the behaviour of cellulose, hemicelluloses, and lignin during wood and pulp processing is essential for understanding and controlling the processes. Determination of monosaccharide composition gives information about the structural polysaccharide composition of wood material and helps when determining the quality of fibrous products. In addition, monitoring of the acidic degradation products gives information of the extent of degradation of lignin and polysaccharides. This work describes two capillary electrophoretic methods developed for the analysis of monosaccharides and for the determination of aliphatic carboxylic acids from alkaline oxidation solutions of lignin and wood. Capillary electrophoresis (CE), in its many variants is an alternative separation technique to chromatographic methods. In capillary zone electrophoresis (CZE) the fused silica capillary is filled with an electrolyte solution. An applied voltage generates a field across the capillary. The movement of the ions under electric field is based on the charge and hydrodynamic radius of ions. Carbohydrates contain hydroxyl groups that are ionised only in strongly alkaline conditions. After ionisation, the structures are suitable for electrophoretic analysis and identification through either indirect UV detection or electrochemical detection. The current work presents a new capillary zone electrophoretic method, relying on in-capillary reaction and direct UV detection at the wavelength of 270 nm. The method has been used for the simultaneous separation of neutral carbohydrates, including mono- and disaccharides and sugar alcohols. The in-capillary reaction produces negatively charged and UV-absorbing compounds. The optimised method was applied to real samples. The methodology is fast since no other sample preparation, except dilution, is required. A new method for aliphatic carboxylic acids in highly alkaline process liquids was developed. The goal was to develop a method for the simultaneous analysis of the dicarboxylic acids, hydroxy acids and volatile acids that are oxidation and degradation products of lignin and wood polysaccharides. The CZE method was applied to three process cases. First, the fate of lignin under alkaline oxidation conditions was monitored by determining the level of carboxylic acids from process solutions. In the second application, the degradation of spruce wood using alkaline and catalysed alkaline oxidation were compared by determining carboxylic acids from the process solutions. In addition, the effectiveness of membrane filtration and preparative liquid chromatography in the enrichment of hydroxy acids from black liquor was evaluated, by analysing the effluents with capillary electrophoresis.

Designing a Demand Forecasting Process in the Fast Moving Consumer Goods Context

The purpose of this thesis was to study the design of demand forecasting processes. A literature review in the field of forecasting was conducted, including general forecasting process design, forecasting methods and techniques, the role of human judgment in forecasting and forecasting performance measurement. The purpose of the literature review was to identify the important design choices that an organization aiming to design or re-design their demand forecasting process would have to make. In the empirical part of the study, these choices and the existing knowledge behind them was assessed in a case study where a demand forecasting process was re-designed for a company in the fast moving consumer goods business. The new target process is described, as well as the reasoning behind the design choices made during the re-design process. As a result, the most important design choices are highlighted, as well as their immediate effect on other processes directly tied to the demand forecasting process. Additionally, some new insights on the organizational aspects of demand forecasting processes are explored. The preliminary results indicate that in this case the new process did improve forecasting accuracy, although organizational issues related to the process proved to be more challenging than anticipated.

Agility in international fast fashion retailing

The birth of Internet technologies, the developments of fast fashion and multiple retailing channels have created a need for a new, more integrated way for doing retailing. Agility in fast fashion retailing could be seen as a significant way of responding to these changes and furthermore, as a way to respond to consumers’ altering demands. The purpose of this study was to explore the ways in which agile supply chains and integrated multichannel retailing influence the international fast fashion retailing. A framework for agility in retail was developed based on available theoretical considerations in distribution and communication channels. Qualitative research methods and qualitative content analysis were used. Four expert interviews were carried out to gain new perspectives to the objectives. The rest of the data was collected from an industry specific document, expert video and two expert lectures. Following the data collection, the research material was analyzed with qualitative content analysis. The empirical findings on agility in retail were presented based on a coding frame. It was found that agility in retail has multiple parts, which are overlapping and affecting one another. Furthermore, instead of viewing the agile supply chain and integrated multichannel retailing separately of each other as usual, it was found that they should be integrated, and the term “agility” was proposed to denote this approach. Also, it was found that the most common drivers and constrains of integrated multichannel retailing were the new Internet technologies and customer demand. Brick-and-mortar store, online store, mobile devices and social media were found to be the most common retailing channels. Furthermore, in-store technology, click-and-collect approach, NFC-buying, RFID-technology as well as 3D- digital simulations on fabrics and patterns will enhance agility even more in the future. In addition, environmental issues, customer experiences and communication will be important factors. This study has provided new practical insights for the future retailing. Furthermore, it has contributed to the academic research by discussing the traditional approaches of agility in fast fashion retail and bringing in new insights.

Application and development of numerical methods for the modelling of innovative gas cooled fission reactors

Innovative gas cooled reactors, such as the pebble bed reactor (PBR) and the gas cooled fast reactor (GFR) offer higher efficiency and new application areas for nuclear energy. Numerical methods were applied and developed to analyse the specific features of these reactor types with fully three dimensional calculation models. In the first part of this thesis, discrete element method (DEM) was used for a physically realistic modelling of the packing of fuel pebbles in PBR geometries and methods were developed for utilising the DEM results in subsequent reactor physics and thermal-hydraulics calculations. In the second part, the flow and heat transfer for a single gas cooled fuel rod of a GFR were investigated with computational fluid dynamics (CFD) methods. An in-house DEM implementation was validated and used for packing simulations, in which the effect of several parameters on the resulting average packing density was investigated. The restitution coefficient was found out to have the most significant effect. The results can be utilised in further work to obtain a pebble bed with a specific packing density. The packing structures of selected pebble beds were also analysed in detail and local variations in the packing density were observed, which should be taken into account especially in the reactor core thermal-hydraulic analyses. Two open source DEM codes were used to produce stochastic pebble bed configurations to add realism and improve the accuracy of criticality calculations performed with the Monte Carlo reactor physics code Serpent. Russian ASTRA criticality experiments were calculated. Pebble beds corresponding to the experimental specifications within measurement uncertainties were produced in DEM simulations and successfully exported into the subsequent reactor physics analysis. With the developed approach, two typical issues in Monte Carlo reactor physics calculations of pebble bed geometries were avoided. A novel method was developed and implemented as a MATLAB code to calculate porosities in the cells of a CFD calculation mesh constructed over a pebble bed obtained from DEM simulations. The code was further developed to distribute power and temperature data accurately between discrete based reactor physics and continuum based thermal-hydraulics models to enable coupled reactor core calculations. The developed method was also found useful for analysing sphere packings in general. CFD calculations were performed to investigate the pressure losses and heat transfer in three dimensional air cooled smooth and rib roughened rod geometries, housed inside a hexagonal flow channel representing a sub-channel of a single fuel rod of a GFR. The CFD geometry represented the test section of the L-STAR experimental facility at Karlsruhe Institute of Technology and the calculation results were compared to the corresponding experimental results. Knowledge was gained of the adequacy of various turbulence models and of the modelling requirements and issues related to the specific application. The obtained pressure loss results were in a relatively good agreement with the experimental data. Heat transfer in the smooth rod geometry was somewhat under predicted, which can partly be explained by unaccounted heat losses and uncertainties. In the rib roughened geometry heat transfer was severely under predicted by the used realisable k − epsilon turbulence model. An additional calculation with a v2 − f turbulence model showed significant improvement in the heat transfer results, which is most likely due to the better performance of the model in separated flow problems. Further investigations are suggested before using CFD to make conclusions of the heat transfer performance of rib roughened GFR fuel rod geometries. It is suggested that the viewpoints of numerical modelling are included in the planning of experiments to ease the challenging model construction and simulations and to avoid introducing additional sources of uncertainties. To facilitate the use of advanced calculation approaches, multi-physical aspects in experiments should also be considered and documented in a reasonable detail.

Radio-frequency-based measurement methods for bearing current analysis in induction motors

The most common reason for a low-voltage induction motor breakdown is a bearing failure. Along with the increasing popularity of modern frequency converters, bearing failures have become the most important motor fault type. Conditions in which bearing currents are likely to occur are generated as a side effect of fast du/dt switching transients. Once present, different types of bearing currents can accelerate the mechanical wear of bearings by causing deformation of metal parts in the bearing and degradation of the lubricating oil properties.The bearing current phenomena are well known, and several bearing current measurement and mitigation methods have been proposed. Nevertheless, in order to develop more feasible methods to measure and mitigate bearing currents, better knowledge of the phenomena is required. When mechanical wear is caused by bearing currents, the resulting aging impact has to be monitored and dealt with. Moreover, because of the stepwise aging mechanism, periodically executed condition monitoring measurements have been found ineffective. Thus, there is a need for feasible bearing current measurement methods that can be applied in parallel with the normal operation of series production drive systems. In order to reach the objectives of feasibility and applicability, nonintrusive measurement methods are preferred. In this doctoral dissertation, the characteristics and conditions of bearings that are related to the occurrence of different kinds of bearing currents are studied. Further, the study introduces some nonintrusive radio-frequency-signal-based approaches to detect and measure parameters that are associated with the accelerated bearing wear caused by bearing currents.

Tactical sourcing, fast lane for medium value purchases

Medium value purchases make up a vast portion of organisations’ purchases. Medium value purchases differ from large purchases that the purchases value is smaller and quantity higher. They are not managed efficiently if they are managed as large purchases. However, they should not be managed as small purchases as they have savings possibilities that are not obtained with a process that is designed for small purchases. This study offers a solution for medium value spend management. The solution is tactical sourcing. The tactical sourcing is designed for Tieto Corporation’s need and it was influenced by Six Sigma methods and tools.

Elokuvien levittäminen Internetissä

Movie distribution on the Internet has become more common in recent years along with fast broadband internet connections. The problem so far has been that the greatest part of movie distribution on the Internet has been illegal. This is about to change because the major film distributors are finally starting to rent and sell movies more and more on the Internet due to their growing confidence in new copy protection methods. The importance of movie online distribution to the movie industry is still tiny but it is increasing rapidly as is investing in new business models and distribution methods in the USA and Europe. This thesis examines the basic concepts of online movie distribution, such as distribution techniques and copy protection, the main companies that rent and sell movies on the internet and their business models, the effects of movie piracy and non-commercial distribution channels. The intention was to provide the reader with an overview of different aspects of movie distribution on the Internet and its future. The conclusion was that movie distribution on the Internet will play a bigger financial part in the future although it was still too early to say just how significant that will be. We will probably see many corresponding distribution techniques, like peer-to-peer networks and streaming servers distributing and broadcasting movies to different end-user platforms like television, PC and portable media players. Internet distribution of movies will not revolutionize movie distribution in the next couple of years but it will make possible new efficient and inexpensive ways to distribute movies globally which will in turn increase the possibilities for revenue, especially for small independent movie producers and distributors.