This thesis explores the application of Radial Basis Functions (RBFs) to fluid dynamical problems. In particular, stationary Stokes and Navier-Stokes equations are solved using RBF collocation method. An existing approach from the literature, is enchanced by an additional polynomial basis and a new preconditioner. A faster method based on the partition of unity is introduced for stationary Stokes equations. Finally, a global method based on Picard linearization is introduced for stationary Navier-Stokes equations. / Denna avhandling utforskar tillämpningen av Radial Basis Functions (RBF) på dynamiska problem med vätskor. I synnerhet löses stationära Stokes och Navier-Stokes ekvationer lösas med hjälp av RBF-samlokaliseringsmetoden. En befintlig metod från litteraturen, förbättras genom en ytterligare polynombas och en ny förkonditionering. En snabbare metod baserad på enhetens partition introduceras för stationära Stokes-ekvationer. Slutligen introduceras en global metod baserad på Picard linjärisering för stationära Navier-Stokes ekvationer.

Species Distribution Modelling (SDM) plays a key role in a number of biological applications: assessment of temporal trends in distribution, environmental impact assessment and spatial conservation planning. From a statistical perspective, this thesis develops two methods for increasing the accuracy and reliability of maps of density surfaces and provides a solution to the problem of how to collate multiple density maps of the same region, obtained from differing sources. From a biological perspective, these statistical methods are used to analyse two marine mammal datasets to produce accurate maps for use in spatial conservation planning and temporal trend assessment. The first new method, Complex Region Spatial Smoother [CReSS; Scott-Hayward et al., 2013], improves smoothing in areas where the real distance an animal must travel (`as the animal swims') between two points may be greater than the straight line distance between them, a problem that occurs in complex domains with coastline or islands. CReSS uses estimates of the geodesic distance between points, model averaging and local radial smoothing. Simulation is used to compare its performance with other traditional and recently-developed smoothing techniques: Thin Plate Splines (TPS, Harder and Desmarais [1972]), Geodesic Low rank TPS (GLTPS; Wang and Ranalli [2007]) and the Soap lm smoother (SOAP; Wood et al. [2008]). GLTPS cannot be used in areas with islands and SOAP can be very hard to parametrise. CReSS outperforms all of the other methods on a range of simulations, based on their fit to the underlying function as measured by mean squared error, particularly for sparse data sets. Smoothing functions need to be flexible when they are used to model density surfaces that are highly heterogeneous, in order to avoid biases due to under- or over-fitting. This issue was addressed using an adaptation of a Spatially Adaptive Local Smoothing Algorithm (SALSA, Walker et al. [2010]) in combination with the CReSS method (CReSS-SALSA2D). Unlike traditional methods, such as Generalised Additive Modelling, the adaptive knot selection approach used in SALSA2D naturally accommodates local changes in the smoothness of the density surface that is being modelled. At the time of writing, there are no other methods available to deal with this issue in topographically complex regions. Simulation results show that CReSS-SALSA2D performs better than CReSS (based on MSE scores), except at very high noise levels where there is an issue with over-fitting. There is an increasing need for a facility to combine multiple density surface maps of individual species in order to make best use of meta-databases, to maintain existing maps, and to extend their geographical coverage. This thesis develops a framework and methods for combining species distribution maps as new information becomes available. The methods use Bayes Theorem to combine density surfaces, taking account of the levels of precision associated with the different sets of estimates, and kernel smoothing to alleviate artefacts that may be created where pairs of surfaces join. The methods were used as part of an algorithm (the Dynamic Cetacean Abundance Predictor) designed for BAE Systems to aid in risk mitigation for naval exercises. Two case studies show the capabilities of CReSS and CReSS-SALSA2D when applied to real ecological data. In the first case study, CReSS was used in a Generalised Estimating Equation framework to identify a candidate Marine Protected Area for the Southern Resident Killer Whale population to the south of San Juan Island, off the Pacific coast of the United States. In the second case study, changes in the spatial and temporal distribution of harbour porpoise and minke whale in north-western European waters over a period of 17 years (1994-2010) were modelled. CReSS and CReSS-SALSA2D performed well in a large, topographically complex study area. Based on simulation results, maps produced using these methods are more accurate than if a traditional GAM-based method is used. The resulting maps identified particularly high densities of both harbour porpoise and minke whale in an area off the west coast of Scotland in 2010, that might be a candidate for inclusion into the Scottish network of Nature Conservation Marine Protected Areas.

In this master thesis I recapitulated several methods for clustering input data. Two well known clustering algorithms, concretely K-means algorithm and Fuzzy C-means (FCM) algorithm, were described in the submitted work. I presented several methods, which could help estimate the optimal number of clusters. Further, I described Kohonen maps and two models of Kohonen's maps with dynamically changing structure, namely Kohonen map with growing grid and the model of growing neural gas. At last I described quite new model of radial basis function neural networks. I presented several learning algorithms for this model of neural networks. In the end of this work I made some clustering experiments with real data. This data describes the international trade among states of the whole world.

Weather radar imagery is important for several remote sensing applications including tracking of storm fronts and radar echo classification. In particular, tracking of precipitation events is useful for both forecasting and classification of rain/non-rain events since non-rain events usually appear to be static compared to rain events. Recent weather radar imaging-based forecasting approaches [3] consider that precipitation events can be modeled as a combination of localized functions using Radial Basis Function Neural Networks (RBFNNs). Tracking of rain events can be performed by tracking the parameters of these localized functions. The RBFNN-based techniques used in forecasting are not only computationally expensive, but also moderately effective in modeling small size precipitation events. In this thesis, an existing RBFNN technique [3] was implemented to verify its computational efficiency and forecasting effectiveness. The feasibility of modeling precipitation events using RBFNN effectively was evaluated, and several modifications to the existing technique have been proposed.

Construire une surface lisse d'un objet 3D est un problème important dans de nombreuses applications graphiques. En particulier, les méthodes de subdivision permettent de passer facilement d'un maillage discret à une surface continue. Un problème général résultant de la subdivision de deux maillages initialement connectés le long d'un bord est l'apparition de fissures ou de trous entre eux. Ces fissures produisent non seulement des formes indésirables, mais induisent aussi des difficultés pour les traitements ultérieurs. Il faut donc réparer ces défauts de sorte que la surface obtenue soit lisse et puisse être subdivisée ou modifiée. Nous proposons de nouvelles méthodes pour relier deux maillages avec des résolutions différentes en utilisant une transformée en ondelettes B-splines et une approximation locale ou une interpolation locale à l'aide de fonctions de base radiales (RBF). Ces procédés génèrent un maillage de connexion où la continuité est contrôlée. La résolution du maillage est ajustable pour respecter le changement de résolution entre les zones grossières et fines. En outre, nous présentons des méthodes pour combler les trous à n-côtés, et le raffinement des maillages grâce à un schéma de subdivision adaptative. Nous avons conçu, implémenté et testé les algorithmes en MatLab pour illustrer nos méthodes et montrer des résultats expérimentaux. Ces algorithmes sont mis en oeuvre sur de nombreux modèles d'objets 3D avec des formes complexes. En outre, nous avons fourni des approches différentes pour chaque problème. Ainsi, les résultats des différentes approches sont comparés et évalués afin d'exploiter les avantages et les inconvénients de ces approches. / Constructing a smooth surface of a 3D object is an important problem in many graphical applications. In particular, subdivision methods permit to pass easily from a discrete mesh to a continuous surface. A generic problem arising from subdividing two meshes initially connected along a common boundary is the occurrence of cracks or holes between them. These cracks not only produce undesired shapes, but also bring serious trouble for further mesh processing. They must be removed or filled so that the produced surface is smooth and can be further subdivided or edited. In order to remove cracks, we propose new methods for joining two meshes with different resolutions using a Lifted B-spline wavelet transform and a local approximation or radial basis function (RBF) local interpolation. These methods generate a connecting mesh where continuity is controlled from one boundary to the other and the connecting mesh can change gradually in resolution between coarse and fine areas. Additionally, we introduce methods for filling n-sided holes, and refining meshes with an adaptive subdivision scheme. We have designed, implemented, and tested the algorithms in MatLab to illustrate our proposed methods and show experimental results. These algorithms are implemented on many 3D object models with complex shapes. Additionally, we have provided some different approaches for each problem. Thus, results from the different approaches are compared and evaluated to exploit the advantages and disadvantages of these approaches.

Em Computação Gráfica, campos vetoriais possuem diversas aplicações desde a síntese e mapeamento de texturas à animações de fluidos, produzindo efeitos amplamente utilizados na indústria do entretenimento. Para produzir tais campos, é preferível o uso de ferramentas de design em vez de simulações numéricas não só devido ao menor custo computacional mas, principalmente, por prover liberdade ao artista ao sintetizar o campo de acordo com a sua necessidade. Atualmente, na literatura, existem bons métodos de design de campos vetoriais em superfícies de objetos tridimensionais porém, o design no interior desses objetos ainda é pouco estudado, principalmente quando o campo de interesse possui propriedades específicas. O objetivo deste trabalho é desenvolver uma técnica para sintetizar campos vetoriais, com características do movimento de fluidos incompressíveis, no interior de domínios. Em uma primeira etapa, o método consiste na interpolação dos vetores de controle, com uma certa propriedade desejada, em todo o domínio. Posteriormente, o campo obtido é modificado para respeitar a geometria do contorno. / Vector fields are important to an wide range of applications on the field of Computer Graphics, from the synthesis and mapping of textures to fluid animation, producing effects widely used on the entertainment industry. To produce such fields, design tools are prefered over numerical simulations not only for its lower computational cost, but mainly by providing freedom to the artist in the creation process. Nowadays, good methods of vector field design over surfaces exist in literature, however there is only a few studies on the synthesis of vector fields of the interior of objects and even fewer when specific properties of the field are required. This work presents a technique to synthesize vector fields with properties of imcompressible fluids motion in the interior of objects. On a first step, the method consists in interpolating control vectors with a certain desired property throughout the whole domain and later the resulting field is modified to properly fit the boundary geometry of the object.

Made available in DSpace on 2016-12-23T14:08:09Z (GMT). No. of bitstreams: 1 Parte Inicial.pdf: 580643 bytes, checksum: 1783483d80317ac5307ad55e7cbdb752 (MD5) Previous issue date: 2013-03-25 / O propósito da pesquisa aqui elaborada é mostrar a viabilidade da aplicação de Funções de Base Radial de Suporte Compacto (FBRSC) no processo de aproximação direta do núcleo da ação de domínio através de integração de contorno. Essa formulação utilizada no tratamento da integral de domínio é denominada como (Método dos Elementos de Contorno com Integração Direta de Contorno) MECIC. Com o intuito de se avaliar a efetividade das FBRSC como funções de interpolação, serão realizados diversos testes numéricos, onde se deseja calcular o volume de superfícies. Então, serão realizados testes bidimensionais de aproximação, variando-se o suporte das FBRSCs, a fim de analisar o comportamento dessas funções. Depois de verificar a efetividade e a precisão das FBRSCs no processo de interpolação, desenvolvem-se programas, no ambiente do Método dos Elementos de Contorno (MEC), para a solução de problemas governados pela Equação de Poisson com a Formulação MECIC associada ao conceito de interpolação com FBRSC com suporte devidamente otimizados. A aferição das soluções numéricas obtidas se dá a partir da comparação com as suas respectivas soluções analíticas, facilmente encontradas na literatura especializada. Assim, possibilita-se estimar o erro relativo e então a eficácia da Formulação MECIC com FBRSC. Uma vez comprovado a sua eficácia, a Formulação MECIC com FBRSC é testada também com o esquema de interpolação com ajuste de pontos. Durante todo o desenvolvimento, atenta-se para a importância do custo computacional da formulação, a partir da geração de tabelas com o tempo de processamento dos programas implementados no MEC. Dessa forma, avalia-se qualitativamente o desempenho das FBRSC na Formulação MECIC, visando futuras aplicações na área de propagação de ondas sísmicas / The purpose of this research is to show the viability of application of Compactly Supported Radial Basis Function (CSRBF) in the process of direct approximation of the core of the domain action through boundary integration. This formulation is termed as (Boundary Elements Method with Directs Boundary Integration) MECIC, and is used in the treatment of the domain integration. By evaluating the effectiveness of CSRBF as interpolation functions, it performed several numerical tests to calculate the volume of surfaces. Also; by varying the support of CSRBFs, it performed two-dimensional approximation tests to examine the behavior of these functions. After verifying the effectiveness and accuracy of CSRBFs in the interpolation process, it developed computational programs to solve physical problems using the MECIC formulation, which is governed by Poisson s Equation. That formulation is associated with the concept of CSRBF in which the support is properly optimized. The calibration of the numerical solutions is given by the confrontation with their respective analytical solutions, easily found in the specialized literature. In this way, it is possible to estimate the relative error and the effectiveness of the MECIC formulation in association with the CSRBF concept. It is tested also with the curve fitting interpolation scheme. Owing the importance of the computational cost of that formulation, it is generated several time tables showing the processing time of those Boundary Elements Method computational programs. Therefore; aiming future applications in the seismic propagation wave area, it was finally evaluated the qualitative performance of the CSRBF in MECIC s formulation

In this master thesis I recapitulated several methods for data clustering. Two well known clustering algorithms, concretely K-means algorithm and Fuzzy C-means (FCM) algorithm, were described in the submitted work. I presented several methods, which could help estimate the optimal number of clusters. Further, I described Kohonen maps and two models of Kohonen's maps with dynamically changing structure, namely Kohonen map with growing grid and the model of growing neural gas. At last I described quite new model of radial basis function neural networks. I presented several learning algorithms for this model of neural networks, RAN, RANKEF, MRAN, EMRAN and GAP. In the end of this work I made some clustering experiments with real data. This data describes the international trade among states of the whole world.

Neste trabalho é proposta uma plataforma robótica móvel, concebida de maneira modular e hierárquica, visando o estudo de diversos aspectos aplicados à navegação, tanto autônoma quanto semi-autônoma, em ambientes internos. O sistema proposto possibilita a implementação de arquiteturas reativas e híbridas com aprendizagem, sendo a importância e limitações desta última discutidas. Utilizando a plataforma desenvolvida, uma aplicação de navegação robótica com aprendizagem supervisionada é realizada, usando sensores de ultra-som e através de tele-operação. O objetivo é fazer com que o agente associe, em tempo real, suas próprias respostas sensoriais com as ações motoras realizadas pelo tele-operador, permitindo que a tarefa seja repetida autonomamente com alguma generalização. Para realizar tal mapeamento, uma rede de função de base radial (RBF), usando um algoritmo de aprendizado seqüencial, é apresentada e utilizada. / This work presents a mobile robotic platform, built as a modular and hierarchical approach, aiming at the study of several aspects of indoor navigation. The proposed system allows the implementation of reactive and hybrid architectures with learning, for autonomous or semi-autonomous navigation. The importance and limitations of the learning characteristics are discussed. An application of robotic navigation with supervised learning is implemented using ultrasonic sensors and teleoperation. The aim is the agent to associate, in real time, its own sensorial perception to the motor actions realized by a teleoperator, allowing the task to be repeated in an autonomous way, with some generalization. To make the corresponding mapping, a radial basis function network (RBF), trained by a sequential learning algorithm, is presented and used.

Because blades in jet engine compressors are subject to dynamic loads based on the engine's speed, it is essential that the blades are properly "tuned" to avoid resonance at those frequencies to ensure safe operation of the engine. The tuning process can be time consuming for designers because there are many parameters controlling the geometry of the blade and, therefore, its resonance frequencies. Humans cannot easily optimize design spaces consisting of multiple variables, but optimization algorithms can effectively optimize a design space with any number of design variables. Automated blade tuning can reduce design time while increasing the fidelity and robustness of the design. Using surrogate modeling techniques and gradient-free optimization algorithms, this thesis presents a method for automating the tuning process of an airfoil. Surrogate models are generated to relate airfoil geometry to the modal frequencies of the airfoil. These surrogates enable rapid exploration of the entire design space. The optimization algorithm uses a novel objective function that accounts for the contribution of every mode's value at a specific operating speed on a Campbell diagram. When the optimization converges on a solution, the new blade parameters are output to the designer for review. This optimization guarantees a feasible solution for tuning of a blade. With 21 geometric parameters controlling the shape of the blade, the geometry for an optimally tuned blade can be determined within 20 minutes.