On the differential evolution algorithm and its appliation to training radial basis function networks

The parameter setting of a differential evolution algorithm must meet several requirements: efficiency, effectiveness, and reliability. Problems vary. The solution of a particular problem can be represented in different ways. An algorithm most efficient in dealing with a particular representation may be less efficient in dealing with other representations. The development of differential evolution-based methods contributes substantially to research on evolutionary computing and global optimization in general. The objective of this study is to investigatethe differential evolution algorithm, the intelligent adjustment of its controlparameters, and its application. In the thesis, the differential evolution algorithm is first examined using different parameter settings and test functions. Fuzzy control is then employed to make control parameters adaptive based on an optimization process and expert knowledge. The developed algorithms are applied to training radial basis function networks for function approximation with possible variables including centers, widths, and weights of basis functions and both having control parameters kept fixed and adjusted by fuzzy controller. After the influence of control variables on the performance of the differential evolution algorithm was explored, an adaptive version of the differential evolution algorithm was developed and the differential evolution-based radial basis function network training approaches were proposed. Experimental results showed that the performance of the differential evolution algorithm is sensitive to parameter setting, and the best setting was found to be problem dependent. The fuzzy adaptive differential evolution algorithm releases the user load of parameter setting and performs better than those using all fixedparameters. Differential evolution-based approaches are effective for training Gaussian radial basis function networks.

Color ad spectral image assessment using novel quality and fidelity techniques

The ongoing development of the digital media has brought a new set of challenges with it. As images containing more than three wavelength bands, often called spectral images, are becoming a more integral part of everyday life, problems in the quality of the RGB reproduction from the spectral images have turned into an important area of research. The notion of image quality is often thought to comprise two distinctive areas – image quality itself and image fidelity, both dealing with similar questions, image quality being the degree of excellence of the image, and image fidelity the measure of the match of the image under study to the original. In this thesis, both image fidelity and image quality are considered, with an emphasis on the influence of color and spectral image features on both. There are very few works dedicated to the quality and fidelity of spectral images. Several novel image fidelity measures were developed in this study, which include kernel similarity measures and 3D-SSIM (structural similarity index). The kernel measures incorporate the polynomial, Gaussian radial basis function (RBF) and sigmoid kernels. The 3D-SSIM is an extension of a traditional gray-scale SSIM measure developed to incorporate spectral data. The novel image quality model presented in this study is based on the assumption that the statistical parameters of the spectra of an image influence the overall appearance. The spectral image quality model comprises three parameters of quality: colorfulness, vividness and naturalness. The quality prediction is done by modeling the preference function expressed in JNDs (just noticeable difference). Both image fidelity measures and the image quality model have proven to be effective in the respective experiments.

Epälineaaristen regressiomenetelmien vertaaminen robottikäden otemallinnuksessa

Tässä työssä verrattiin monikerrosperseptronin, radiaalikantafunktioverkon, tukivektoriregression ja relevanssivektoriregression soveltuvuutta robottikäden otemallinnukseen. Menetelmille ohjelmoitiin koeympäristö Matlabiin, jossa mallit koestettiin kolmiulotteisella kappaledatalla. Koejärjestely sisälsi kaksi vaihetta. Kokeiden ensimmäisessä vaiheessa menetelmille haettiin sopivat parametrit ja toisessa vaiheessa menetelmät koestettiin. Kokeilla kerättiin dataa menetelmien keskinäiseen vertailuun. Vertailussa huomioitiin laskentanopeus, koulutusaika ja tarkkuus. Tukivektoriregressio löydettiin potentiaaliseksi vaihtoehdoksi mallintamiseen. Tukivektoriregression koetuloksia analysoitiin muita menetelmiä enemmän hyvien koetulosten takia.

Spatial modeling techniques for mapping and characterization of acid sulfate soils

Acid sulfate (a.s.) soils constitute a major environmental issue. Severe ecological damage results from the considerable amounts of acidity and metals leached by these soils in the recipient watercourses. As even small hot spots may affect large areas of coastal waters, mapping represents a fundamental step in the management and mitigation of a.s. soil environmental risks (i.e. to target strategic areas). Traditional mapping in the field is time-consuming and therefore expensive. Additional more cost-effective techniques have, thus, to be developed in order to narrow down and define in detail the areas of interest. The primary aim of this thesis was to assess different spatial modeling techniques for a.s. soil mapping, and the characterization of soil properties relevant for a.s. soil environmental risk management, using all available data: soil and water samples, as well as datalayers (e.g. geological and geophysical). Different spatial modeling techniques were applied at catchment or regional scale. Two artificial neural networks were assessed on the Sirppujoki River catchment (c. 440 km2) located in southwestern Finland, while fuzzy logic was assessed on several areas along the Finnish coast. Quaternary geology, aerogeophysics and slope data (derived from a digital elevation model) were utilized as evidential datalayers. The methods also required the use of point datasets (i.e. soil profiles corresponding to known a.s. or non-a.s. soil occurrences) for training and/or validation within the modeling processes. Applying these methods, various maps were generated: probability maps for a.s. soil occurrence, as well as predictive maps for different soil properties (sulfur content, organic matter content and critical sulfide depth). The two assessed artificial neural networks (ANNs) demonstrated good classification abilities for a.s. soil probability mapping at catchment scale. Slightly better results were achieved using a Radial Basis Function (RBF) -based ANN than a Radial Basis Functional Link Net (RBFLN) method, narrowing down more accurately the most probable areas for a.s. soil occurrence and defining more properly the least probable areas. The RBF-based ANN also demonstrated promising results for the characterization of different soil properties in the most probable a.s. soil areas at catchment scale. Since a.s. soil areas constitute highly productive lands for agricultural purpose, the combination of a probability map with more specific soil property predictive maps offers a valuable toolset to more precisely target strategic areas for subsequent environmental risk management. Notably, the use of laser scanning (i.e. Light Detection And Ranging, LiDAR) data enabled a more precise definition of a.s. soil probability areas, as well as the soil property modeling classes for sulfur content and the critical sulfide depth. Given suitable training/validation points, ANNs can be trained to yield a more precise modeling of the occurrence of a.s. soils and their properties. By contrast, fuzzy logic represents a simple, fast and objective alternative to carry out preliminary surveys, at catchment or regional scale, in areas offering a limited amount of data. This method enables delimiting and prioritizing the most probable areas for a.s soil occurrence, which can be particularly useful in the field. Being easily transferable from area to area, fuzzy logic modeling can be carried out at regional scale. Mapping at this scale would be extremely time-consuming through manual assessment. The use of spatial modeling techniques enables the creation of valid and comparable maps, which represents an important development within the a.s. soil mapping process. The a.s. soil mapping was also assessed using water chemistry data for 24 different catchments along the Finnish coast (in all, covering c. 21,300 km2) which were mapped with different methods (i.e. conventional mapping, fuzzy logic and an artificial neural network). Two a.s. soil related indicators measured in the river water (sulfate content and sulfate/chloride ratio) were compared to the extent of the most probable areas for a.s. soils in the surveyed catchments. High sulfate contents and sulfate/chloride ratios measured in most of the rivers demonstrated the presence of a.s. soils in the corresponding catchments. The calculated extent of the most probable a.s. soil areas is supported by independent data on water chemistry, suggesting that the a.s. soil probability maps created with different methods are reliable and comparable.

Spectral Retinal Images Reconstruction

While red-green-blue (RGB) image of retina has quite limited information, retinal multispectral images provide both spatial and spectral information which could enhance the capability of exploring the eye-related problems in their early stages. In this thesis, two learning-based algorithms for reconstructing of spectral retinal images from the RGB images are developed by a two-step manner. First, related previous techniques are reviewed and studied. Then, the most suitable methods are enhanced and combined to have new algorithms for the reconstruction of spectral retinal images. The proposed approaches are based on radial basis function network to learn a mapping from tristimulus colour space to multi-spectral space. The resemblance level of reproduced spectral images and original images is estimated using spectral distance metrics spectral angle mapper, spectral correlation mapper, and spectral information divergence, which show a promising result from the suggested algorithms.

Neck Muscle Function and Adolescent Headache

Muscular function of the neck region may be of importance for the etiology of headache, especially of tension-type headache. However, very few data exist on the association of neck muscle function with different types of headache in adolescents. The main aim of the study was to examine the association of neck muscle function with adolescent headache. The associations between leisure time activities, endurance strength of the upper extremities (UE endurance) and mobility of the neck-shoulder region and adolescent headache were studied. In addition, the associations of force production, EMG/force ratio, co-activation and fatigue characteristics, and cross-sectional area (CSA) of neck muscles with adolescent headache were studied. The study is part of a population-based cohort study of 12-year-old children with and without headache. The study had five phases (years 1998-2003). At the age of 13 years, a sample of 183 adolescents (183/311) participated in endurance strength and mobility measurements of the neck-shoulder region. In addition, the type and level of physical and other leisure activity were elicited with open and structured questions. At the age of 17 years, a random sample of 89 adolescents (89/202) participated in force and EMG measurements of the neck-shoulder muscles. In addition, at the age of 17 years, a sample of 65 adolescents (65/89) participated in CSA measurements of the neck muscles. At the age of 13 years, intensive participation in overall sports activity was associated with migraine. Frequent computer use was associated both with migraine and tension-type headache. The type of sports or other leisure activity classified them on the basis of body loading was not associated with headache type. In girls, low UE endurance of both sides, and low cervical rotation of the dominant side, were associated with tension-type headache, and low UE endurance of non-dominant side with migraine. In boys, no associations occurred between UE endurance and mobility variables and headache types. At the age of 17 years, in girls, high EMG/force ratios between the EMG of the left agonist sternocleidomastoid muscle (SCM) and maximal neck flexion and neck rotation force to the right side as well as high co-activation of right antagonist cervical erector spinae (CES) muscles during maximal neck flexion force were associated with migraine-type headache. In girls, neck force production was not associated with headache types but low left shoulder flexion force was associated with tension-type headache. In boys, no associations were found between EMG and force variables and headache. Increased SCM muscles fatigue of both sides was associated with tension-type headache. In boys, the small CSA of the right SCM muscle and, in girls, of combined right SCM and scalenus muscles was associated with tension-type headache. Similarly, in boys, the large CSA of the right SCM muscle, of the combined right SCM and scalenus muscles, of the left semispinalis capitis muscle, of the combined left semispinalis and splenius muscles was associated with migraine. No other differences in the CSA of neck flexion or extension muscles were found. Differences in the neuromucular function of the neck-shoulder muscles were associated with adolescent headache, especially in girls. Differences in the cross-sectional area of unilateral neck muscles were associated with headache, especially in boys. Differences in the neuromuscular function and in the cross-sectional area of the neck muscles also occurred between different types of headache. It remains to be established whether the findings are primary or secondary to adolescent migraine and tension headache. Keywords: adolescent, cross-sectional area, electromyography, endurance strength, fatigue, force, headache, leisure time activity, migraine, mobility, neck muscles, tension-type headache

Improving Cross Direction Basis Weight Profile in a Fourdrinier Paper Machine

The purpose of this study was to improve PM7’s basis weight CD profile in Stora Enso’s Berghuizer mill and to search mechanical defects which affect to the formation of the basis weight CD profile. In the theoretical part PM7’s structure was presented and the formation of the basis weight and caliper CD profiles was examined as well as disturbances which are affecting to the formation. The function of the control system was scrutinised for the side of CD profiles as well as the formation of the measured CD profiles. Tuning of the control system was examined through the response model and filtering. Specification of the response model and filtering was explained and how to determine 2sigma statistical number. In the end of the theoretical part ATPA hardware and a new profile browser were introduced. In the experimental part focus was in the beginning to search and remove mechanical defects which are affecting to CD profiles. The next step was to verify the reliability of the online measurements, to study the stability of the basis weight CD profile and to find out so called fingerprint, a basis weight CD profile which is unique for each paper machine. New response model and filtering value for basis weight CD profile was determined by bump tests. After a follow up period the affect of the new response model and filtering was analysed.

The Structural Basis for inorganic Pyrophosphatase Catalysis and Regulation

Inorganic pyrophosphatases (PPases) are essential enzymes for every living cell. PPases provide the necessary thermodynamic pull for many biosynthetic reactions by hydrolyzing pyrophosphate. There are two types of PPases: integral membrane-bound and soluble enzymes. The latter type is divided into two non-homologous protein families, I and II. Family I PPases are present in all kingdoms of life, whereas family II PPases are only found in prokaryotes, including archae. Family I PPases, particularly that from Saccharomyces cerevisiae, are among the most extensively characterized phosphoryl transfer enzymes. In the present study, we have solved the structures of wild-type and seven active site variants of S. cerevisiae PPase bound to its natural metal cofactor, magnesium ion. These structures have facilitated derivation of the complete enzyme reaction scheme for PPase, fulfilling structures of all the reaction intermediates. The main focus in this study was on a novel subfamily of family II PPases (CBSPPase) containing a large insert formed by two CBS domains and a DRTGG domain within the catalytic domain. The CBS domain (named after cystathionine beta-synthase in which it was initially identified) usually occurs as tandem pairs with two or four copies in many proteins in all kingdoms of life. The structure formed by a pair of CBS domains is also known as a Bateman domain. CBS domains function as regulatory units, with adenylate ligands as the main effectors. The DRTGG domain (designated based on its most conserved residues) occurs less frequently and only in prokaryotes. Often, the domain co-exists with CBS domains, but its function remains unknown. The key objective of the current study was to explore the structural rearrangements in the CBS domains induced by regulatory adenylate ligands and their functional consequences. Two CBS-PPases were investigated, one from Clostridium perfringens (cpCBS-PPase) containing both CBS and DRTGG domains in its regulatory region and the other from Moorella thermoacetica (mt CBS-PPase) lacking the DRTGG domain. We additionally constructed a separate regulatory region of cpCBS-PPase (cpCBS). Both full-length enzymes and cpCBS formed homodimers. Two structures of the regulatory region of cpCBS-PPase complexed with the inhibitor, AMP, and activator, diadenosine tetraphosphate, were solved. The structures were significantly different, providing information on the structural pathway from bound adenylates to the interface between the regulatory and catalytic parts. To our knowledge, these are the first reported structures of a regulated CBS enzyme, which reveal large conformational changes upon regulator binding. The activator-bound structure was more open, consistent with the different thermostabilities of the activator- and inhibitor-bound forms of cpCBS-PPase. The results of the functional studies on wild-type and variant CBS-PPases provide support for inferences made on the basis of structural analyses. Moreover, these findings indicate that CBS-PPase activity is highly sensitive to adenine nucleotide distribution between AMP, ADP and ATP, and hence to the energy level of the cell. CBS-PPase activity is markedly inhibited at low energy levels, allowing PPi energy to be used for cell survival instead of being converted into heat.

Orthogonal function method in modelling paper web quality variation

This work is devoted to the analysis of signal variation of the Cross-Direction and Machine-Direction measurements from paper web. The data that we possess comes from the real paper machine. Goal of the work is to reconstruct the basis weight structure of the paper and to predict its behaviour to the future. The resulting synthetic data is needed for simulation of paper web. The main idea that we used for describing the basis weight variation in the Cross-Direction is Empirical Orthogonal Functions (EOF) algorithm, which is closely related to Principal Component Analysis (PCA) method. Signal forecasting in time is based on Time-Series analysis. Two principal mathematical procedures that we used in the work are Autoregressive-Moving Average (ARMA) modelling and Ornstein–Uhlenbeck (OU) process.

Collective Memory Embodied in Poetry as Poison. The Mnemonic Role of Romantic Poets Discussed on the Basis of Adam Mickiewicz’ Konrad Wallenrod and Forefathers (Part III)

This thesis constitutes an interdisciplinary approach to the Polish Romanticism combining literature studies with memory studies, nationalism research and psychoanalysis. This phenomenon-based study attempts to answer the question, how the Polish national poet Adam Mickiewicz (1798–1855) – or more exactly the implied authors in his works – perceived the role of poetry in mnemonic terms and how it changes in course of time. Consequently, ‘memory in literature’ (Astrin Erll and Ansger Nünning) is discussed here. Two pieces of writing by Mickiewicz – Konrad Wallenrod [1828] and the third part of Forefathers [1832], where a bard respectively a poetic genius appears – are seen as meta-texts defining goals of poets in time of the political non-existence of a state. Poetry is supposed to keep memory of the glorious past alive, kindle the love for the motherland, support the collective identity of a group and initiate a liberation movement. Poets function as memory guards, leaders of the nation and prophets. Thus, literature is a medium of collective memory – it stores crucial contents, transmits them and acts as a cue. Nevertheless, shifting the focus from the community towards well-being of individuals, which is consistent with the postmodern thinking, the impact that poetry has on members of a given memory culture (Jan Assmann) can be described in ‘vampiric’ terms (Maria Janion). Poetry embodying collective memory may be compared to ‘poison’, ‘infecting’ people with a nationalistic way of thinking to their disadvantage as far as their personal lives are concerned.

Effects of Obesity and Weight Loss Following Bariatric Surgery on Brain Function, Structural Integrity and Metabolism

Obesity is one of the key challenges to health care system worldwide and its prevalence is estimated to rise to pandemic proportions. Numerous adverse health effects follow with increasing body weight, including increased risk of hypertension, diabetes, hypercholesterolemia, musculoskeletal pain and cancer. Current evidence suggests that obesity is associated with altered cerebral reward circuit functioning and decreased inhibitory control over appetitive food cues. Furthermore, obesity causes adverse shifts in metabolism and loss of structural integrity within the brain. Prior cross-sectional studies do not allow delineating which of these cerebral changes are recoverable after weight loss. We compared morbidly obese subjects with healthy controls to unravel brain changes associated with obesity. Bariatric surgery was used as an intervention to study which cerebral changes are recoverable after weight loss. In Study I we employed functional magnetic resonance imaging (fMRI) to detect the brain basis of volitional appetite control and its alterations in obesity. In Studies II-III we used diffusion tensor imaging (DTI) and voxel-based morphometry (VBM) to quantify the effects of obesity and the effects of weight loss on structural integrity of the brain. In study IV we used positron emission tomography (PET) with [18F]-FDG in fasting state and during euglycemic hyperinsulinemia to quantify effects of obesity and weight loss on brain glucose uptake. The fMRI experiment revealed that a fronto-parietal network is involved in volitional appetite control. Obese subjects had lower medial frontal and dorsal striatal brain activity during cognitive appetite control and increased functional connectivity within the appetite control circuit. Obese subjects had initially lower grey matter and white matter densities than healthy controls in VBM analysis and loss of integrity in white matter tracts as measured by DTI. They also had initially elevated glucose metabolism under insulin stimulation but not in fasting state. After the weight loss following bariatric surgery, obese individuals’ brain volumes recovered and the insulin-induced increase in glucose metabolism was attenuated. In conclusion, obesity is associated with altered brain function, coupled with loss of structural integrity and elevated glucose metabolism, which are likely signs of adverse health effects to the brain. These changes are reversed by weight loss after bariatric surgery, implicating that weight loss has a causal role on these adverse cerebral changes. Altogether these findings suggest that weight loss also promotes brain health.Key words: brain, obesity, bariatric surgery, appetite control, structural magnetic resonance

Postoperative Bowel Function and Related Factors in Enhanced Recovery Protocol with Patients Undergoing Hepatectomy

Patients’ bowel dysfunction is a major factor that weakens the results of surgical care as it can cause pain and weaken patients’ rehabilitation. Bowel dysfunction is a common postoperative problem, yet most incidents remain undocumented. The nursing profession has a significant role in enhancing the bowel function postoperatively. However, studies of postoperative bowel function after hepatectomy are scarce and somewhat incongruous. Enhanced recovery protocols are innovative models of care aiming for better outcomes of surgical care. Enhanced recovery protocols can improve gastrointestinal function after surgery, yet patients are also known to be satisfied with their care. The aim was to investigate if postoperative bowel function day varies between patients in terms of age, gender, ASA score, type of surgery, histology, patients’ experienced pain and experienced satisfaction three days after discharge and three months after operation in patients undergoing hepatectomy. The goal was to produce information for basis of scientific research, to give nurses in clinical setting more tools to work with hepatectomy patients undergoing enhanced recovery protocol and to produce information to nurse managers to use in process management of patients undergoing enhanced recovery protocol. The design of this study is descriptive. Data was collected retrospectively from hepatectomy patients (n = 134) undergoing enhanced recovery protocol within the first year of enhanced recovery protocol implementation. The data was based on registers and analyzed statistically. Mean age of patients was 62 years and mean day of discharge was 4. Main (n = 72) histology of the patients was colorectal liver metastases. Mean bowel function day was 3. Most of the patients were very satisfied or satisfied with the care three days after discharge (99%) and three months (90%) after operation. Most of the patients (72%) experienced moderate pain three days after discharge, but three months after operation 47% of the patients did not experience pain and 48% experienced moderate pain. There were no statistically significant differences in bowel function between different age groups, genders, ASA score groups or histologies. Neither were there statistically significant differences in postoperative bowel function in terms of experienced satisfaction or pain. There were statistically significant differences in postoperative bowel function between different types of surgery (p < 0.01). Nurses should take into consideration hepatectomy patients’ type of surgery and pay special attention in supporting major open hepatectomy patients’ postoperative bowel function. Nurses should educate patients undergoing major open hepatectomy about prolonged postoperative bowel function.