Quasiconformal mappings and inequalities involving special functions

This PhD thesis in Mathematics belongs to the field of Geometric Function Theory. The thesis consists of four original papers. The topic studied deals with quasiconformal mappings and their distortion theory in Euclidean n-dimensional spaces. This theory has its roots in the pioneering papers of F. W. Gehring and J. Väisälä published in the early 1960’s and it has been studied by many mathematicians thereafter. In the first paper we refine the known bounds for the so-called Mori constant and also estimate the distortion in the hyperbolic metric. The second paper deals with radial functions which are simple examples of quasiconformal mappings. These radial functions lead us to the study of the so-called p-angular distance which has been studied recently e.g. by L. Maligranda and S. Dragomir. In the third paper we study a class of functions of a real variable studied by P. Lindqvist in an influential paper. This leads one to study parametrized analogues of classical trigonometric and hyperbolic functions which for the parameter value p = 2 coincide with the classical functions. Gaussian hypergeometric functions have an important role in the study of these special functions. Several new inequalities and identities involving p-analogues of these functions are also given. In the fourth paper we study the generalized complete elliptic integrals, modular functions and some related functions. We find the upper and lower bounds of these functions, and those bounds are given in a simple form. This theory has a long history which goes back two centuries and includes names such as A. M. Legendre, C. Jacobi, C. F. Gauss. Modular functions also occur in the study of quasiconformal mappings. Conformal invariants, such as the modulus of a curve family, are often applied in quasiconformal mapping theory. The invariants can be sometimes expressed in terms of special conformal mappings. This fact explains why special functions often occur in this theory.

Ion-exchange resins as stationary phase in reactive chromatography

Dynamic behavior of bothisothermal and non-isothermal single-column chromatographic reactors with an ion-exchange resin as the stationary phase was investigated. The reactor performance was interpreted by using results obtained when studying the effect of the resin properties on the equilibrium and kinetic phenomena occurring simultaneously in the reactor. Mathematical models were derived for each phenomenon and combined to simulate the chromatographic reactor. The phenomena studied includes phase equilibria in multicomponent liquid mixture¿ion-exchange resin systems, chemicalequilibrium in the presence of a resin catalyst, diffusion of liquids in gel-type and macroporous resins, and chemical reaction kinetics. Above all, attention was paid to the swelling behavior of the resins and how it affects the kinetic phenomena. Several poly(styrene-co-divinylbenzene) resins with different cross-link densities and internal porosities were used. Esterification of acetic acid with ethanol to produce ethyl acetate and water was used as a model reaction system. Choosing an ion-exchange resin with a low cross-link density is beneficial inthe case of the present reaction system: the amount of ethyl acetate as well the ethyl acetate to water mole ratio in the effluent stream increase with decreasing cross-link density. The enhanced performance of the reactor is mainly attributed to increasing reaction rate, which in turn originates from the phase equilibrium behavior of the system. Also mass transfer considerations favor the use ofresins with low cross-link density. The diffusion coefficients of liquids in the gel-type ion-exchange resins were found to fall rapidly when the extent of swelling became low. Glass transition of the polymer was not found to significantlyretard the diffusion in sulfonated PS¿DVB ion-exchange resins. It was also shown that non-isothermal operation of a chromatographic reactor could be used to significantly enhance the reactor performance. In the case of the exothermic modelreaction system and a near-adiabatic column, a positive thermal wave (higher temperature than in the initial state) was found to travel together with the reactive front. This further increased the conversion of the reactants. Diffusion-induced volume changes of the ion-exchange resins were studied in a flow-through cell. It was shown that describing the swelling and shrinking kinetics of the particles calls for a mass transfer model that explicitly includes the limited expansibility of the polymer network. A good description of the process was obtained by combining the generalized Maxwell-Stefan approach and an activity model that was derived from the thermodynamics of polymer solutions and gels. The swelling pressure in the resin phase was evaluated by using a non-Gaussian expression forthe polymer chain length distribution. Dimensional changes of the resin particles necessitate the use of non-standard mathematical tools for dynamic simulations. A transformed coordinate system, where the mass of the polymer was used as a spatial variable, was applied when simulating the chromatographic reactor columns as well as the swelling and shrinking kinetics of the resin particles. Shrinking of the particles in a column leads to formation of dead volume on top of the resin bed. In ordinary Eulerian coordinates, this results in a moving discontinuity that in turn causes numerical difficulties in the solution of the PDE system. The motion of the discontinuity was eliminated by spanning two calculation grids in the column that overlapped at the top of the resin bed. The reactive and non-reactive phase equilibrium data were correlated with a model derived from thethermodynamics of polymer solution and gels. The thermodynamic approach used inthis work is best suited at high degrees of swelling because the polymer matrixmay be in the glassy state when the extent of swelling is low.

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.

MCMC Analysis for Optimization of Stochastic Models

In any decision making under uncertainties, the goal is mostly to minimize the expected cost. The minimization of cost under uncertainties is usually done by optimization. For simple models, the optimization can easily be done using deterministic methods.However, many models practically contain some complex and varying parameters that can not easily be taken into account using usual deterministic methods of optimization. Thus, it is very important to look for other methods that can be used to get insight into such models. MCMC method is one of the practical methods that can be used for optimization of stochastic models under uncertainty. This method is based on simulation that provides a general methodology which can be applied in nonlinear and non-Gaussian state models. MCMC method is very important for practical applications because it is a uni ed estimation procedure which simultaneously estimates both parameters and state variables. MCMC computes the distribution of the state variables and parameters of the given data measurements. MCMC method is faster in terms of computing time when compared to other optimization methods. This thesis discusses the use of Markov chain Monte Carlo (MCMC) methods for optimization of Stochastic models under uncertainties .The thesis begins with a short discussion about Bayesian Inference, MCMC and Stochastic optimization methods. Then an example is given of how MCMC can be applied for maximizing production at a minimum cost in a chemical reaction process. It is observed that this method performs better in optimizing the given cost function with a very high certainty.

Adaptive Markov chain Monte Carlo and Bayesian filtering for state space models

This thesis is concerned with the state and parameter estimation in state space models. The estimation of states and parameters is an important task when mathematical modeling is applied to many different application areas such as the global positioning systems, target tracking, navigation, brain imaging, spread of infectious diseases, biological processes, telecommunications, audio signal processing, stochastic optimal control, machine learning, and physical systems. In Bayesian settings, the estimation of states or parameters amounts to computation of the posterior probability density function. Except for a very restricted number of models, it is impossible to compute this density function in a closed form. Hence, we need approximation methods. A state estimation problem involves estimating the states (latent variables) that are not directly observed in the output of the system. In this thesis, we use the Kalman filter, extended Kalman filter, Gauss–Hermite filters, and particle filters to estimate the states based on available measurements. Among these filters, particle filters are numerical methods for approximating the filtering distributions of non-linear non-Gaussian state space models via Monte Carlo. The performance of a particle filter heavily depends on the chosen importance distribution. For instance, inappropriate choice of the importance distribution can lead to the failure of convergence of the particle filter algorithm. In this thesis, we analyze the theoretical Lᵖ particle filter convergence with general importance distributions, where p ≥2 is an integer. A parameter estimation problem is considered with inferring the model parameters from measurements. For high-dimensional complex models, estimation of parameters can be done by Markov chain Monte Carlo (MCMC) methods. In its operation, the MCMC method requires the unnormalized posterior distribution of the parameters and a proposal distribution. In this thesis, we show how the posterior density function of the parameters of a state space model can be computed by filtering based methods, where the states are integrated out. This type of computation is then applied to estimate parameters of stochastic differential equations. Furthermore, we compute the partial derivatives of the log-posterior density function and use the hybrid Monte Carlo and scaled conjugate gradient methods to infer the parameters of stochastic differential equations. The computational efficiency of MCMC methods is highly depend on the chosen proposal distribution. A commonly used proposal distribution is Gaussian. In this kind of proposal, the covariance matrix must be well tuned. To tune it, adaptive MCMC methods can be used. In this thesis, we propose a new way of updating the covariance matrix using the variational Bayesian adaptive Kalman filter algorithm.

Testing the Random Walk Hypothesis on the Baltic Stock Markets

The purpose of the thesis is to analyze whether the returns of general stock market indices of Estonia, Latvia and Lithuania follow the random walk hypothesis (RWH), and in addition, whether they are consistent with the weak-form efficiency criterion. Also the existence of the day-of-the-week anomaly is examined in the same regional markets. The data consists of daily closing quotes of the OMX Tallinn, Riga and Vilnius total return indices for the sample period from January 3, 2000 to August 28, 2009. Moreover, the full sample period is also divided into two sub-periods. The RWH is tested by applying three quantitative methods (i.e. the Augmented Dickey-Fuller unit root test, serial correlation test and non-parametric runs test). Ordinary Least Squares (OLS) regression with dummy variables is employed to detect the day-of-the-week anomalies. The random walk hypothesis (RWH) is rejected in the Estonian and Lithuanian stock markets. The Latvian stock market exhibits more efficient behaviour, although some evidence of inefficiency is also found, mostly during the first sub-period from 2000 to 2004. Day-of-the-week anomalies are detected on every stock market examined, though no longer during the later sub-period.

Cognitive Functions After Traumatic Brain Injury. A 30-year Follow-up Study

Many cognitive deficits after TBI (traumatic brain injury) are well known, such as memory and concentration problems, as well as reduced information-processing speed. What happens to patients and cognitive functioning after immediate recovery is poorly known. Cognitive functioning is flexible and may be influenced by genetic, psychological and environmental factors decades after TBI. The general aim of this thesis was to describe the long-term cognitive course after TBI, to find variables that may contribute to it, and how the cognitive functions after TBI are associated with specific medical factors and reduced survival. The original study group consisted of 192 patients with TBI who were originally assessed with the Mild Deterioration Battery (MDB) on average two years after the injury, during the years 1966 – 1972. During a 30-year follow-up, we studied the risks for reduced survival, and the mortality of the patients was compared with the general population using the Standardized Mortality Ratio (SMR). Sixty-one patients were re-assessed during 1998-2000. These patients were evaluated with the MDB, computerized testing, and with various other neuropsychological methods for attention and executive functions. Apolipoprotein-E (ApoE) genotyping and magnetic resonance imaging (MRI) based on volumetric analysis of the hippocampus and lateral ventricles were performed. Depressive symptoms were evaluated with the short form of the Beck depression inventory. The cognitive performance at follow-up was compared with a control group that was similar to the study group in regard to age and education. The cognitive outcome of the patients with TBI varied after three decades. The majority of the patients showed a decline in their cognitive level, the rest either improved or stayed at the same level. Male gender and higher age at injury were significant risk factors for the decline. Whereas most cognitive domains declined during the follow-up, semantic memory behaved in the opposite way, showing recovery after TBI. In the follow-up assessment, the memory decline and impairments in the set-shifting domain of executive functions were associated with MRI-volumetric measures, whereas reduction in information-processing speed was not associated with the MRI measures. The presence of local contusions was only weakly associated with cognitive functions. Only few cognitive methods for attention were capable of discriminating TBI patients with and without depressive symptoms. On the other hand, most complex attentional tests were sensitive enough to discriminate TBI patients (non-depressive) from controls. This means that complex attention functions, mediated by the frontal lobes, are relatively independent of depressive symptoms post-TBI. The presence of ApoE4 was associated with different kinds of memory processes including verbal and visual episodic memory, semantic memory and verbal working memory, depending on the length of time since TBI. Many other cognitive processes were not affected by the presence of ApoE4. Age at injury and poor vocational outcome were independent risk factors for reduced survival in the multivariate analysis. Late mortality was higher among younger subjects (age < 40 years at death) compared with the general population which should be borne in mind when assessing the need for rehabilitation services and long-term follow-up after TBI.

NADPH-Dependent Thioredoxin System In Regulation of Chloroplast Functions

Photosynthesis, the process in which carbon dioxide is converted into sugars using the energy of sunlight, is vital for heterotrophic life on Earth. In plants, photosynthesis takes place in specific organelles called chloroplasts. During chloroplast biogenesis, light is a prerequisite for the development of functional photosynthetic structures. In addition to photosynthesis, a number of other metabolic processes such as nitrogen assimilation, the biosynthesis of fatty acids, amino acids, vitamins, and hormones are localized to plant chloroplasts. The biosynthetic pathways in chloroplasts are tightly regulated, and especially the reduction/oxidation (redox) signals play important roles in controlling many developmental and metabolic processes in chloroplasts. Thioredoxins are universal regulatory proteins that mediate redox signals in chloroplasts. They are able to modify the structure and function of their target proteins by reduction of disulfide bonds. Oxidized thioredoxins are restored via the action of thioredoxin reductases. Two thioredoxin reductase systems exist in plant chloroplasts, the NADPHdependent thioredoxin reductase C (NTRC) and ferredoxin-thioredoxin reductase (FTR). The ferredoxin-thioredoxin system that is linked to photosynthetic light reactions is involved in light-activation of chloroplast proteins. NADPH can be produced via both the photosynthetic electron transfer reactions in light, and in darkness via the pentose phosphate pathway. These different pathways of NADPH production enable the regulation of diverse metabolic pathways in chloroplasts by the NADPH-dependent thioredoxin system. In this thesis, the role of NADPH-dependent thioredoxin system in the redox-control of chloroplast development and metabolism was studied by characterization of Arabidopsis thaliana T-DNA insertion lines of NTRC gene (ntrc) and by identification of chloroplast proteins regulated by NTRC. The ntrc plants showed the strongest visible phenotypes when grown under short 8-h photoperiod. This indicates that i) chloroplast NADPH-dependent thioredoxin system is non-redundant to ferredoxinthioredoxin system and that ii) NTRC particularly controls the chloroplast processes that are easily imbalanced in daily light/dark rhythms with short day and long night. I identified four processes and the redox-regulated proteins therein that are potentially regulated by NTRC; i) chloroplast development, ii) starch biosynthesis, iii) aromatic amino acid biosynthesis and iv) detoxification of H₂O₂. Such regulation can be achieved directly by modulating the redox state of intramolecular or intermolecular disulfide bridges of enzymes, or by protecting enzymes from oxidation in conjunction with 2-cysteine peroxiredoxins. This thesis work also demonstrated that the enzymatic antioxidant systems in chloroplasts, ascorbate peroxidases, superoxide dismutase and NTRC-dependent 2-cysteine peroxiredoxins are tightly linked up to prevent the detrimental accumulation of reactive oxygen species in plants.

Creating possibilities for collective creativity : Brokerage Functions in Practice-Based Innovation

In the network era, creative achievements like innovations are more and more often created in interaction among different actors. The complexity of today‘s problems transcends the individual human mind, requiring not only individual but also collective creativity. In collective creativity, it is impossible to trace the source of new ideas to an individual. Instead, creative activity emerges from the collaboration and contribution of many individuals, thereby blurring the contribution of specific individuals in creating ideas. Collective creativity is often associated with diversity of knowledge, skills, experiences and perspectives. Collaboration between diverse actors thus triggers creativity and gives possibilities for collective creativity. This dissertation investigates collective creativity in the context of practice-based innovation. Practice-based innovation processes are triggered by problem setting in a practical context and conducted in non-linear processes utilising scientific and practical knowledge production and creation in cross-disciplinary innovation networks. In these networks diversity or distances between innovation actors are essential. Innovation potential may be found in exploiting different kinds of distances. This dissertation presents different kinds of distances, such as cognitive, functional and organisational which could be considered as sources of creativity and thus innovation. However, formation and functioning of these kinds of innovation networks can be problematic. Distances between innovating actors may be so great that a special interpretation function is needed – that is, brokerage. This dissertation defines factors that enhance collective creativity in practice-based innovation and especially in the fuzzy front end phase of innovation processes. The first objective of this dissertation is to study individual and collective creativity at the employee level and identify those factors that support individual and collective creativity in the organisation. The second objective is to study how organisations use external knowledge to support collective creativity in their innovation processes in open multi-actor innovation. The third objective is to define how brokerage functions create possibilities for collective creativity especially in the context of practice-based innovation. The research objectives have been studied through five substudies using a case-study strategy. Each substudy highlights various aspects of creativity and collective creativity. The empirical data consist of materials from innovation projects arranged in the Lahti region, Finland, or materials from the development of innovation methods in the Lahti region. The Lahti region has been chosen as the research context because the innovation policy of the region emphasises especially the promotion of practice-based innovations. The results of this dissertation indicate that all possibilities of collective creativity are not utilised in internal operations of organisations. The dissertation introduces several factors that could support collective creativity in organisations. However, creativity as a social construct is understood and experienced differently in different organisations, and these differences should be taken into account when supporting creativity in organisations. The increasing complexity of most potential innovations requires collaborative creative efforts that often exceed the boundaries of the organisation and call for the involvement of external expertise. In practice-based innovation different distances are considered as sources of creativity. This dissertation gives practical implications on how it is possible to exploit different kinds of distances knowingly. It underlines especially the importance of brokerage functions in open, practice-based innovation in order to create possibilities for collective creativity. As a contribution of this dissertation, a model of brokerage functions in practice-based innovation is formulated. According to the model, the results and success of brokerage functions are based on the context of brokerage as well as the roles, tasks, skills and capabilities of brokers. The brokerage functions in practice-based innovation are also possible to divide into social and cognitive brokerage.