Evaluating multidimensional visualization techniques in data mining tasks

Visual data mining (VDM) tools employ information visualization techniques in order to represent large amounts of high-dimensional data graphically and to involve the user in exploring data at different levels of detail. The users are looking for outliers, patterns and models – in the form of clusters, classes, trends, and relationships – in different categories of data, i.e., financial, business information, etc. The focus of this thesis is the evaluation of multidimensional visualization techniques, especially from the business user’s perspective. We address three research problems. The first problem is the evaluation of projection-based visualizations with respect to their effectiveness in preserving the original distances between data points and the clustering structure of the data. In this respect, we propose the use of existing clustering validity measures. We illustrate their usefulness in evaluating five visualization techniques: Principal Components Analysis (PCA), Sammon’s Mapping, Self-Organizing Map (SOM), Radial Coordinate Visualization and Star Coordinates. The second problem is concerned with evaluating different visualization techniques as to their effectiveness in visual data mining of business data. For this purpose, we propose an inquiry evaluation technique and conduct the evaluation of nine visualization techniques. The visualizations under evaluation are Multiple Line Graphs, Permutation Matrix, Survey Plot, Scatter Plot Matrix, Parallel Coordinates, Treemap, PCA, Sammon’s Mapping and the SOM. The third problem is the evaluation of quality of use of VDM tools. We provide a conceptual framework for evaluating the quality of use of VDM tools and apply it to the evaluation of the SOM. In the evaluation, we use an inquiry technique for which we developed a questionnaire based on the proposed framework. The contributions of the thesis consist of three new evaluation techniques and the results obtained by applying these evaluation techniques. The thesis provides a systematic approach to evaluation of various visualization techniques. In this respect, first, we performed and described the evaluations in a systematic way, highlighting the evaluation activities, and their inputs and outputs. Secondly, we integrated the evaluation studies in the broad framework of usability evaluation. The results of the evaluations are intended to help developers and researchers of visualization systems to select appropriate visualization techniques in specific situations. The results of the evaluations also contribute to the understanding of the strengths and limitations of the visualization techniques evaluated and further to the improvement of these techniques.

Diameter structure of stratum and ecological groups of a Semideciduous Forest area in Dionísio-MG

The objective of this study was to obtain homogeneous groups of species and information on their density, dominance and volume, in terms of ecological group and diameter structure of an area of Submontane Semideciduous forest (Mata do Mumbaça) in Dionísio, MG. This work was conducted with data of the diameter distribution per species from floristic and phytosociological (Mata do Mumbaça) survey of 120 plots with 10 x 10 m each one. The 120 plots were contiguous and corresponding to a total sample area of 12,000 m² distributed over the topographic units (Low Ramp, Lower Slope, Upper Slope and Hill Top). The topographic units Low Ramp, Lower Slope and Upper Slope were in the middle stage of succession as they presented incipient stratification into two strata (canopy and understory) i.e. canopy ranging from 5 to 12 m high. However, the stratum Hill Top was classified as intermediate/advanced succession because it had a total height equal to or greater than 12 m. The distribution of individual trees of the four strata on diameter classes showed a typical J-inverted pattern that is, high concentration of individuals in smaller diameter classes and a sharp reduction towards the larger classes. In relation to absolute dominance and total volume of species, the ecological group that stood out in the four strata (Low Ramp, Lower Slope, Upper Slope and Hill Top) was the initial secondary, which were in the intermediate stage of secondary, rapidly developing into the mature phase.

DYNAMICS AND PREDICTION OF DIAMETRIC STRUCTURE IN TWO ATLANTIC FOREST FRAGMENTS IN NORTHEASTERN BRAZIL

ABSTRACT Monitoring analyses aim to understand the processes that drive changes in forest structure and, along with prediction studies, may assist in the management planning and conservation of forest remnants. The objective of this study was to analyze the forest dynamics in two Atlantic rainforest fragments in Pernambuco, Brazil, and to predict their future forest diameter structure using the Markov chain model. We used continuous forest inventory data from three surveys in two forest fragments of 87 ha (F1) and 388 ha (F2). We calculated the annual rates of mortality and recruitment, the mean annual increment, and the basal area for each of the 3-year periods. Data from the first and second surveys were used to project the third inventory measurements, which were compared to the observed values in the permanent plots using chi-squared tests (a = 0.05). In F1, a decrease in the number of individuals was observed due to mortality rates being higher than recruitment rates; however, there was an increase in the basal area. In this fragment, the fit to the Markov model was adequate. In F2, there was an increase in both the basal area and the number of individuals during the 6-year period due to the recruitment rate exceeding the mortality rate. For this fragment, the fit of the model was unacceptable. Hence, for the studied fragments, the demographic rates influenced the stem density more than the floristic composition. Yet, even with these intense dynamics, both fragments showed active growth.

Probabilistic structure of an annual extreme rainfall series of a coastal area of the State of São Paulo, Brazil

This study aimed to describe the probabilistic structure of the annual series of extreme daily rainfall (Preabs), available from the weather station of Ubatuba, State of São Paulo, Brazil (1935-2009), by using the general distribution of extreme value (GEV). The autocorrelation function, the Mann-Kendall test, and the wavelet analysis were used in order to evaluate the presence of serial correlations, trends, and periodical components. Considering the results obtained using these three statistical methods, it was possible to assume the hypothesis that this temporal series is free from persistence, trends, and periodicals components. Based on quantitative and qualitative adhesion tests, it was found that the GEV may be used in order to quantify the probabilities of the Preabs data. The best results of GEV were obtained when the parameters of this function were estimated using the method of maximum likelihood. The method of L-moments has also shown satisfactory results.

Capital Structure and Firm Growth: R&D Intensive Companies

The purpose of this study is to examine and explain firm`s growth impact on capital structure decision-making in research and development intensive companies. Many studies claim that R&D has a pivotal impact on capital structure decisions, but corporate finance theories have often failed to explain these observed patterns. As sales growth is an important concept and objective for R&D firms, it is logical to assume that it plays a vital role in capital structure decisions. This study applies nomothetic research approach. The theoretical part employs a formal conceptual analysis in order to develop the propositions that are tested with empirical data. The empirical part consists of the analysis of three companies; the data is obtained from the annual reports over the period 2003 – 2008. The companies operate in IT- or ICT-industry and are publicly listed. The method for analyzing the case data is based on the financial indicators, which are obtained from the financials of the case companies. These economic indicators describe the capital structure and the financial decision-making of the firms. The method relates to the quantitative studies. Yet, this study extends the analysis beyond the indicators. Specifically, this study addresses the question of what is behind the economic indicators, therefore combining aspects of quantitative and qualitative analysis. The firms examined in this study seem to prefer internal finance during growth. However, external finance seems to be a catalyst for sales growth. Firms strongly prefer equity financing. In growth, the use of equity per capital either increases or stays in a constant level. Over the period 2003 – 2008, the firms were often associated to equity related transactions and short-term debt. Short-term debt was used as a substitute of long-term debt and equity. The case firms also adjusted their capital structure – these adjustments were carried out with short-term debt or equity. The case data also provides implications for the growth signal theory that was developed in this study. Based on the econometric indicators, arguments can be made that equity investors are `attracted` to growing R&D firms. This is because growth helps investors perceive the true type of firm. The findings of this study are best explained by the trade-off theory and the pecking order theory. These corporate finance theories are considered as mainstream. Little support can be found to the implications of the signaling theory and market timing theory.

An experimental investigation of the effects of nozzle ellipticity on the flow structure of co-flow jet diffusion flames

The flow structure of cold and ignited jets issuing into a co-flowing air stream was experimentally studied using a laser Doppler velocimeter. Methane was employed as the jet fluid discharging from circular and elliptic nozzles with aspect ratios varying from 1.29 to 1.60. The diameter of the circular nozzle was 4.6 mm and the elliptic nozzles had approximately the same exit area as that of the circular nozzle. These non-circular nozzles were employed in order to increase the stability of attached jet diffusion flames. The time-averaged velocity and r.m.s. value of the velocity fluctuation in the streamwise and transverse directions were measured over the range of co-flowing stream velocities corresponding to different modes of flame blowout that are identified as either lifted or attached flames. On the basis of these measurements, attempts were made to explain the existence of an apparent optimum aspect ratio for the blowout of attached flames observed at higher values of co-flowing stream velocities. The insensitivity of the blowout limits of lifted flames to nozzle geometry observed in our previous work at low co-flowing stream velocities was also explained. Measurements of the fuel concentration at the jet centerline indicated that the mixing process was enhanced with the 1.38 aspect ratio jet compared with the 1.60 aspect ratio jet. On the basis of the obtained experimental data, it was suggested that the higher blowout limits of attached flames for an elliptic jet of 1.38 aspect ratio was due to higher entrainment rates.

The Use of Data Envelopment Analysis as Equity Portfolio Selection Criterion in the Finnish Stock Market

This thesis examines the application of data envelopment analysis as an equity portfolio selection criterion in the Finnish stock market during period 2001-2011. A sample of publicly traded firms in the Helsinki Stock Exchange is examined in this thesis. The sample covers the majority of the publicly traded firms in the Helsinki Stock Exchange. Data envelopment analysis is used to determine the efficiency of firms using a set of input and output financial parameters. The set of financial parameters consist of asset utilization, liquidity, capital structure, growth, valuation and profitability measures. The firms are divided into artificial industry categories, because of the industry-specific nature of the input and output parameters. Comparable portfolios are formed inside the industry category according to the efficiency scores given by the DEA and the performance of the portfolios is evaluated with several measures. The empirical evidence of this thesis suggests that with certain limitations, data envelopment analysis can successfully be used as portfolio selection criterion in the Finnish stock market when the portfolios are rebalanced at annual frequency according to the efficiency scores given by the data envelopment analysis. However, when the portfolios were rebalanced every two or three years, the results are mixed and inconclusive.

Myynti ja toimituskanavan valinta ulkomaan kaupassa, kohdemaa Venäjä

Parissa kymmenessä vuodessa on tapahtunut paljon muutoksia. Neuvostoliitto hajosi, Suomen talousrakenne muuttui, globalisaatio kiihtyy kasvavalla vauhdilla, viennin kuljetusmuotoihin on tullut muutoksia, mutta yritystoiminta edellyttää pysymistä ajan tasalla. Tässä diplomityössä tutkitaan myynti- ja toimituskanavien valintoja EU:sta Venäjälle tapahtuvissa viennissä. Työssä käytetään Venäjältä saatavaa tietoa, sillä suurimmat lopputulokseen vaikuttavat kuljetuskustannukset kuten kuljetus, tavaran käsittely ja välivarastointi syntyvät Venäjän puolella. Vienti EU:sta Venäjälle on kasvanut koko ajan tasaisella vauhdilla ja muodostanut samalla tavanomaisesta poikkeavia kuljetusmenetelmiä. Suomessa pk-yrityksillä ei ole resursseja perehtyä aiheeseen, mutta koko ajan yhä useammat yritykset harjoittavat kauppaa ohjaamalla tavaran valmistajalta suoraan vastaanottajalle. Silloin tavara on lähetettävä esimerkiksi eurooppalaiselta keskusvarastolta Venäjälle, jolloin säästytään turhista kuljetuksista Suomen kautta. Työssä tutkitaan yleisimpiä käytössä olevia kuljetusmuotoja, rautatiekuljetuksen potentiaalia ja maantiekuljetuksen mahdollisuuksia. Siinä analysoidaan logistisen teorian pääpiirteitä, yritystoiminnan logistisia prosesseja samoin kuin EU:n vientisäädöksiä ja EU:sta lähtevien vientikuljetuksien organisointiongelmia. Käytössäni on logististen prosessien rakenteen metodologia. Työssä suoritetaan vientiprosessin tutkimus ja esitetään suoritetun tutkimuksen tulokset. Tuloksien pohjalta tehdään päätökset.

Development, structure and distribution of colleters in Mandevilla illustris and M. velutina (Apocynaceae)

Colleters of Mandevilla illustris and M. velutina are present on the cotyledons, shoot apices, mature leaves and on the nodal region, where they are interpetiolar and intrapetiolar. In M. velutina there are two colleters on the adaxial basal part of the leaf blade, and in M. illustris, this number varies. The differentiation of the colleters occurs in the early stages of leaf development. When colleters are mature, they consist of a long head on a short stalk. The central core of the colleter is made up of parenchymatous cells that may exhibit phenolic compounds and is surrounded by radially elongated epithelial cells. The foliar and intrapetiolar colleters can exhibit vascularization. The colleters produce a translucient sticky substance that reacts positively to polysaccharides and, before senescence, they produce lipophilic substances. The Mandevilla colleters data can give support to the taxonomy and phylogeny of the Apocynaceae.

Structure and dynamics of a woody plant community of a tropical semi-deciduous seasonal forest in the "Estação Ecológica do Panga", municipality of Uberlândia, Minas Gerais, Brazil

Studies of plant community dynamics are essential in understanding the demographic patterns of species since changes in demographic rates can affect the floristic composition and future structure. The purpose of the present study was to analyze the changes in the community structure and floristic composition of woody plants in a tropical semi-deciduous forest in Uberlândia in central Brazil, during a 10-years period. The data were collected in 1989 and in 2000 in 50 quadrats (10 m x 10 m) where all trees with a minimum circumference at breast height of 10 cm were sampled. In 1989, 93 species and 1103 individuals were registered. Over a period of 10 years, seven new species were added to the community, although eight disappeared. The main change that occurred during this period in the floristic composition was the replacement of savannah species occurring in forest gaps by those from the forest understory.

Floristic and vegetation structure of a granitic grassland in Southern Brazil

A floristic and structural survey of a natural grassland community was conducted on Morro do Osso, a granitic hill in Porto Alegre, RS, Brazil. Structural data were surveyed in 39 one square meter plots placed over two major grassland areas. An accidental fire has occurred in one of the areas approximately one year prior to our survey, leading to further analysis of parameters differences between sites. The floristic list contains 282 species, whereas the structural survey has found 161 species. Families with highest accumulated importance values were Poaceae, Asteraceae and Fabaceae. The diversity and evenness indexes were 4.51 nats ind-1 and 0.86, respectively. Cluster analysis denoted two groups coinciding with the areas distinguished by the fire disturbance. A similarity analysis between our data and two other data sets from nearby granitic hills resulted in 28% to 35% similarity, with equivalent species-family distribution and many common dominant species, corroborating the concept of a continuous flora along the South Brazilian granitic hills.

The requirements and needs of global data usage in product lifecycle management

This study was done for ABB Ltd. Motors and Generators business unit in Helsinki. In this study, global data movement in large businesses is examined from a product data management (PDM) and enterprise resource planning (ERP) point-of-view. The purpose of this study was to understand and map out how a large global business handles its data in a multiple site structure and how it can be applied in practice. This was done by doing an empirical interview study on five different global businesses with design locations in multiple countries. Their master data management (MDM) solutions were inspected and analyzed to understand which solution would best benefit a large global architecture with many design locations. One working solution is a transactional hub which negates the effects of multisite transfers and reduces lead times. Also, the requirements and limitations of the current MDM architecture were analyzed and possible reform ideas given.  

Efficient Optimization Algorithms for Nonlinear Data Analysis

Identification of low-dimensional structures and main sources of variation from multivariate data are fundamental tasks in data analysis. Many methods aimed at these tasks involve solution of an optimization problem. Thus, the objective of this thesis is to develop computationally efficient and theoretically justified methods for solving such problems. Most of the thesis is based on a statistical model, where ridges of the density estimated from the data are considered as relevant features. Finding ridges, that are generalized maxima, necessitates development of advanced optimization methods. An efficient and convergent trust region Newton method for projecting a point onto a ridge of the underlying density is developed for this purpose. The method is utilized in a differential equation-based approach for tracing ridges and computing projection coordinates along them. The density estimation is done nonparametrically by using Gaussian kernels. This allows application of ridge-based methods with only mild assumptions on the underlying structure of the data. The statistical model and the ridge finding methods are adapted to two different applications. The first one is extraction of curvilinear structures from noisy data mixed with background clutter. The second one is a novel nonlinear generalization of principal component analysis (PCA) and its extension to time series data. The methods have a wide range of potential applications, where most of the earlier approaches are inadequate. Examples include identification of faults from seismic data and identification of filaments from cosmological data. Applicability of the nonlinear PCA to climate analysis and reconstruction of periodic patterns from noisy time series data are also demonstrated. Other contributions of the thesis include development of an efficient semidefinite optimization method for embedding graphs into the Euclidean space. The method produces structure-preserving embeddings that maximize interpoint distances. It is primarily developed for dimensionality reduction, but has also potential applications in graph theory and various areas of physics, chemistry and engineering. Asymptotic behaviour of ridges and maxima of Gaussian kernel densities is also investigated when the kernel bandwidth approaches infinity. The results are applied to the nonlinear PCA and to finding significant maxima of such densities, which is a typical problem in visual object tracking.

Effect of race, genetic population structure, and genetic models in two-locus association studies: clustering of functional renin-angiotensin system gene variants in hypertension association studies

Previous genetic association studies have overlooked the potential for biased results when analyzing different population structures in ethnically diverse populations. The purpose of the present study was to quantify this bias in two-locus association studies conducted on an admixtured urban population. We studied the genetic structure distribution of angiotensin-converting enzyme insertion/deletion (ACE I/D) and angiotensinogen methionine/threonine (M/T) polymorphisms in 382 subjects from three subgroups in a highly admixtured urban population. Group I included 150 white subjects; group II, 142 mulatto subjects, and group III, 90 black subjects. We conducted sample size simulation studies using these data in different genetic models of gene action and interaction and used genetic distance calculation algorithms to help determine the population structure for the studied loci. Our results showed a statistically different population structure distribution of both ACE I/D (P = 0.02, OR = 1.56, 95% CI = 1.05-2.33 for the D allele, white versus black subgroup) and angiotensinogen M/T polymorphism (P = 0.007, OR = 1.71, 95% CI = 1.14-2.58 for the T allele, white versus black subgroup). Different sample sizes are predicted to be determinant of the power to detect a given genotypic association with a particular phenotype when conducting two-locus association studies in admixtured populations. In addition, the postulated genetic model is also a major determinant of the power to detect any association in a given sample size. The present simulation study helped to demonstrate the complex interrelation among ethnicity, power of the association, and the postulated genetic model of action of a particular allele in the context of clustering studies. This information is essential for the correct planning and interpretation of future association studies conducted on this population.

Factor structure of Bech's version of the Brief Psychiatric Rating Scale in Brazilian patients

The objective of the present study was to evaluate the factor structure of Bech's version of the Brief Psychiatric Rating Scale (BPRS), translated into Portuguese. The BPRS was administered to a heterogeneous group of psychiatric inpatients (N = 98) and outpatients (N = 62) in a University Hospital. Each patient was evaluated from one to eight times. The interval between consecutive interviews was one week for the inpatients and one month for the outpatients. The results were submitted to factorial analysis. The internal consistency of the total scale and of each factor was also estimated. Factorial analysis followed by normalized orthogonal rotation (Varimax) yielded four factors: Withdrawal-Retardation, Thinking Disorder, Anxious-Depression and Activation. Internal consistency measured by Cronbach's alpha coefficient ranged from 0.766 to 0.879. The data show that the factor structure of the present instrument is similar to that of the American version of the BPRS which contains 18 items, except for the absence of the fifth factor of the latter scale, Hostile-Suspiciousness.