In the literature, various Mobile Ad hoc NETwork (MANET) routing protocols proposed. Each performs the best under specific context conditions, for example under high mobility or less volatile topologies. In existing MANET, the degradation in the routing protocol performance is always associated with changes in the network context. To date, no MANET routing protocol is able to produce optimal performance under all possible conditions. The core aim of this thesis is to solve the routing problem in mobile Ad hoc networks by introducing an optimum system that is in charge of the selection of the running routing protocol at all times, the system proposed in this thesis aims to address the degradation mentioned above. This optimisation system is a novel approach that can cope with the network performance’s degradation problem by switching to other routing protocol. The optimisation system proposed for MANET in this thesis adaptively selects the best routing protocol using an Artificial Intelligence mechanism according to the network context. In this thesis, MANET modelling helps in understanding the network performance through different contexts, as well as the models’ support to the optimisation system. Therefore, one of the main contributions of this thesis is the utilisation and comparison of various modelling techniques to create representative MANET performance models. Moreover, the proposed system uses an optimisation method to select the optimal communication routing protocol for the network context. Therefore, to build the proposed system, different optimisation techniques were utilised and compared to identify the best optimisation technique for the MANET intelligent system, which is also an important contribution of this thesis. The parameters selected to describe the network context were the network size and average mobility. The proposed system then functions by varying the routing mechanism with the time to keep the network performance at the best level. The selected protocol has been shown to produce a combination of: higher throughput, lower delay, fewer retransmission attempts, less data drop, and lower load, and was thus chosen on this basis. Validation test results indicate that the identified protocol can achieve both a better network performance quality than other routing protocols and a minimum cost function of 4.4%. The Ad hoc On Demand Distance Vector (AODV) protocol comes in second with a cost minimisation function of 27.5%, and the Optimised Link State Routing (OLSR) algorithm comes in third with a cost minimisation function of 29.8%. Finally, The Dynamic Source Routing (DSR) algorithm comes in last with a cost minimisation function of 38.3%.

La résolution satisfaisante d'un problème d'optimisation difficile, qui comporte un grand nombre de solutions sous-optimales, justifie souvent le recours à une métaheuristique puissante. La majorité des algorithmes utilisés pour résoudre ces problèmes d'optimisation sont les métaheuristiques à population. Parmi celles-ci, nous intéressons à l'Optimisation par Essaim Particulaire (OEP, ou PSO en anglais) qui est apparue en 1995. PSO s'inspire de la dynamique d'animaux se déplaçant en groupes compacts (essaims d'abeilles, vols groupés d'oiseaux, bancs de poissons). Les particules d'un même essaim communiquent entre elles tout au long de la recherche pour construire une solution au problème posé, et ce en s'appuyant sur leur expérience collective. L'algorithme PSO, qui est simple à comprendre, à programmer et à utiliser, se révèle particulièrement efficace pour les problèmes d'optimisation à variables continues. Cependant, comme toutes les métaheuristiques, PSO possède des inconvénients, qui rebutent encore certains utilisateurs. Le problème de convergence prématurée, qui peut conduire les algorithmes de ce type à stagner dans un optimum local, est un de ces inconvénients. L'objectif de cette thèse est de proposer des mécanismes, incorporables à PSO, qui permettent de remédier à cet inconvénient et d'améliorer les performances et l'efficacité de PSO. Nous proposons dans cette thèse deux algorithmes, nommés PSO-2S et DEPSO-2S, pour remédier au problème de la convergence prématurée. Ces algorithmes utilisent des idées innovantes et se caractérisent par de nouvelles stratégies d'initialisation dans plusieurs zones, afin d'assurer une bonne couverture de l'espace de recherche par les particules. Toujours dans le cadre de l'amélioration de PSO, nous avons élaboré une nouvelle topologie de voisinage, nommée Dcluster, qui organise le réseau de communication entre les particules. Les résultats obtenus sur un jeu de fonctions de test montrent l'efficacité des stratégies mises en oeuvre par les différents algorithmes proposés. Enfin, PSO-2S est appliqué à des problèmes pratiques, en segmentation d'images et en électronique / The successful resolution of a difficult optimization problem, comprising a large number of sub optimal solutions, often justifies the use of powerful metaheuristics. A wide range of algorithms used to solve these combinatorial problems belong to the class of population metaheuristics. Among them, Particle Swarm Optimization (PSO), appeared in 1995, is inspired by the movement of individuals in a swarm, like a bee swarm, a bird flock or a fish school. The particles of the same swarm communicate with each other to build a solution to the given problem. This is done by relying on their collective experience. This algorithm, which is easy to understand and implement, is particularly effective for optimization problems with continuous variables. However, like several metaheuristics, PSO shows some drawbacks that make some users avoid it. The premature convergence problem, where the algorithm converges to some local optima and does not progress anymore in order to find better solutions, is one of them. This thesis aims at proposing alternative methods, that can be incorporated in PSO to overcome these problems, and to improve the performance and the efficiency of PSO. We propose two algorithms, called PSO-2S and DEPSO-2S, to cope with the premature convergence problem. Both algorithms use innovative ideas and are characterized by new initialization strategies in several areas to ensure good coverage of the search space by particles. To improve the PSO algorithm, we have also developed a new neighborhood topology, called Dcluster, which can be seen as the communication network between the particles. The obtained experimental results for some benchmark cases show the effectiveness of the strategies implemented in the proposed algorithms. Finally, PSO-2S is applied to real world problems in both image segmentation and electronics fields

Different medical imaging modalities provide complementary anatomical and functional information. One increasingly important use of such information is in the clinical management of cardiovascular disease. Multi-modality data is helping improve diagnosis accuracy, and individualize treatment. The Clinical Research Imaging Centre at the University of Edinburgh, has been involved in a number of cardiovascular clinical trials using longitudinal computed tomography (CT) and multi-parametric magnetic resonance (MR) imaging. The critical image processing technique that combines the information from all these different datasets is known as image registration, which is the topic of this thesis. Image registration, especially multi-modality and multi-parametric registration, remains a challenging field in medical image analysis. The new registration methods described in this work were all developed in response to genuine challenges in on-going clinical studies. These methods have been evaluated using data from these studies. In order to gain an insight into the building blocks of image registration methods, the thesis begins with a comprehensive literature review of state-of-the-art algorithms. This is followed by a description of the first registration method I developed to help track inflammation in aortic abdominal aneurysms. It registers multi-modality and multi-parametric images, with new contrast agents. The registration framework uses a semi-automatically generated region of interest around the aorta. The aorta is aligned based on a combination of the centres of the regions of interest and intensity matching. The method achieved sub-voxel accuracy. The second clinical study involved cardiac data. The first framework failed to register many of these datasets, because the cardiac data suffers from a common artefact of magnetic resonance images, namely intensity inhomogeneity. Thus I developed a new preprocessing technique that is able to correct the artefacts in the functional data using data from the anatomical scans. The registration framework, with this preprocessing step and new particle swarm optimizer, achieved significantly improved registration results on the cardiac data, and was validated quantitatively using neuro images from a clinical study of neonates. Although on average the new framework achieved accurate results, when processing data corrupted by severe artefacts and noise, premature convergence of the optimizer is still a common problem. To overcome this, I invented a new optimization method, that achieves more robust convergence by encoding prior knowledge of registration. The registration results from this new registration-oriented optimizer are more accurate than other general-purpose particle swarm optimization methods commonly applied to registration problems. In summary, this thesis describes a series of novel developments to an image registration framework, aimed to improve accuracy, robustness and speed. The resulting registration framework was applied to, and validated by, different types of images taken from several ongoing clinical trials. In the future, this framework could be extended to include more diverse transformation models, aided by new machine learning techniques. It may also be applied to the registration of other types and modalities of imaging data.

Dans l'état actuel des connaissances, il est impossible de poser correctement toute la physique permettant de modéliser les hydrosystèmes dans leur ensemble, notamment à cause de la dynamique très contrastée des différents compartiments. Les modèles systémiques simplifient la représentation des hydrosystèmes en ne considérant que leurs flux d’échange. L’objet de ce travail est de proposer un outil de modélisation systémique fournissant des informations sur le fonctionnement physique des hydrosystèmes, tout en étant simple et parcimonieux. Ce modèle nommé MASH (pour Modélisation des Hydrosystèmes par Approche Systémique) est basé sur l’utilisation de fonctions de transfert paramétriques choisies en fonction de leur faible paramétrisation, leur caractère général et leur interprétation physique. Il est versatile, dans le sens que son architecture est modulable et que le nombre d’entrées, le nombre de fonctions de transfert en série et le type de fonctions de transfert utilisé est laissée à la discrétion de l’utilisateur. Ce modèle est inversé en utilisant de récentes avancées en apprentissage automatique grâce à une famille d’heuristiques basée sur l’intelligence en essaim nommé « optimisation par essaim de particule » (ou PSO pour « Particle Swarm Optimization »). Le modèle et ses algorithmes d’inversion sont testés sur un cas d’école synthétique, puis sur un cas d’application réel. / In the light of current knowledge, hydrosystems cannot be modelled as a whole since underlying physical principles are not totally understood. Systemic models simplify hydrosystem representation by considering only water flows. The aim of this work is to provide a systemic modelling tool giving information about hydrosystem physical behavior while being simple and parsimonious. This model, called HMSA (for Hydrosystem Modelling with a Systemic Approach) is based on parametric transfer functions chose for their low parametrization, their general nature and their physical interpretation. It is versatile, since its architecture is modular, and the user can choose the number of inputs, outputs and transfer functions. Inversion is done with recent machine learning heuristic family, based on swarm intelligence called PSO (Particle Swarm Optimization). The model and its inversion algorithms are tested first with a textbook case, and then with a real-world case.

Layout optimization of offshore wind farms seeks to automate the design of the wind farm and the placement of wind turbines such that the proposed wind farm maximizes its potential. The optimization of an offshore wind farm layout therefore seeks to minimize the costs of the wind farm while maximizing the energy extraction while considering the effects of wakes on the resource; the electrical infrastructure required to collect the energy generated; the cost variation across the site; and all technical and consenting constraints that the wind farm developer must adhere to. As wakes, electrical losses, and costs are non-linear, this produces a complex optimization problem. This thesis describes the design, development, validation, and initial application of a new framework for the optimization of offshore wind farm layouts using either a genetic algorithm or a particle swarm optimizer. The developed methodology and analysis tool have been developed such that individual components can either be used to analyze a particular wind farm layout or used in conjunction with the optimization algorithms to design and optimize wind farm layouts. To accomplish this, separate modules have been developed and validated for the design and optimization of the necessary electrical infrastructure, the assessment of the energy production considering energy losses, and the estimation of the project costs. By including site-dependent parameters and project specific constraints, the framework is capable of exploring the influence the wind farm layout has on the levelized cost of energy of the project. Deploying the integrated framework using two common engineering metaheuristic algorithms to hypothetical, existing, and future wind farms highlights the advantages of this holistic layout optimization framework over the industry standard approaches commonly deployed in offshore wind farm design leading to a reduction in LCOE. Application of the tool to a UK Round 3 site recently under development has also highlighted how the use of this tool can aid in the development of future regulations by considering various constraints on the placement of wind turbines within the site and exploring how these impact the levelized cost of energy.

presente trabalho consolida um estudo para o planejamento de trajetória livre de colisão para um robô pneumático com 5 graus de liberdade aplicando três algoritmos metaheurísticos: algoritmos metaheurísticos por vagalumes, algoritmos metaheurísticos por enxames de partículas e algoritmos genéticos. No que se refere à aplicação de algoritmos metaheurísticos ao estudo de planejamento de trajetória de robôs manipuladores na presença de obstáculos, existem diferentes tipos de técnicas para evitar colisões que consideram os efeitos cinemáticos e dinâmicos na obtenção de trajetórias com o menor tempo, torque, etc. Neste estudo, são propostas contribuições à aplicação dessas técnicas especificamente a robôs manipuladores pneumáticos, sobretudo, no que diz respeito às características específicas dos servoposicionadores pneumáticos, como, por exemplo, a modelagem do atrito desses sistemas, o cálculo da massa equivalente, etc. A metodologia utilizada é definida em duas etapas. A primeira delas consiste na obtenção de pontos intermediários, adquiridos considerando a menor distância entre os mesmos e o ponto final, gerados considerando a presença de obstáculos (cilindros, cubos e esferas) Esses obstáculos são mapeados em regiões de colisão, que constituem restrições para o problema de otimização. A segunda etapa baseia-se no estudo do planejamento de trajetórias: aplicam-se b-splines de 5º e 7º grau na interpolação dos pontos intermediários, com vistas à obtenção de trajetórias que considerem, de um lado, a menor força dos atuadores associada à dinâmica do manipulador em estudo e, de outro, restrições cinemáticas e dinâmicas, determinadas por meio das características operacionais dos servoposicionadores pneumáticos. Os resultados mostram que a metodologia proposta é adequada para tarefas de manipulação de peças na presença de obstáculos, uma vez que os pontos intermediários situam-se fora da região de colisão nos três casos aqui apresentados. Além disso, quanto à segunda etapa, observou-se que as trajetórias de 5º e 7º grau apresentaram resultados similares, de maneira que os erros obtidos poderiam ser melhorados analisando aspectos associados ao controlador do robô em estudo. / The thesis presents a study for collision-free trajectory planning for a pneumatic robot with 5 degrees of freedom applying three metaheuristic algorithms: firefly metaheuristic algorithm, particle swarm optimization and genetic algorithms. As regards the application of metaheuristic algorithms to the study of the trajectory planning of manipulating robots in the presence of obstacles, there are different types of techniques to avoid collisions that consider the kinematic and dynamic effects, obtaining trajectories with the optimal time, torque, etc. In this study, contributions are made to the application of these techniques specifically to pneumatic manipulator robots, particularly with regard to the specific characteristics of pneumatic servo-actuators, such as friction modeling of these systems, calculation of equivalent mass, etc. The methodology used is defined in two steps. The first one consists of obtaining intermediate points, acquired considering the smallest distance between the intermediate points and the final point, generated considering the presence of obstacles (cylinders, cubes and spheres) These obstacles are mapped in collision regions, which are constraints to the optimization problem. The second step is based on the study of the trajectory planning: 5th and 7th degree b-splines are applied in the interpolation of the intermediate points, in order to obtain trajectories that consider the smallest actuator force associated to the dynamics of the manipulator and the kinematic and dynamic constraints, determined by the operational characteristics of pneumatic servo-positioners. The results show that the proposed methodology is suitable for tasks of manipulating parts in the presence of obstacles because the intermediate points are outside the collision region in the three cases presented here. In addition, it was observed that the trajectories of 5th and 7th degree presented similar results, so that the errors obtained could be improved by analyzing aspects associated to the controller of the robot.

<div>The contribution of this research work can be divided into two main tasks: 1) implementing this Electronic Warfare Asset Allocation Problem (EWAAP) with the Genetic Algorithm (GA); 2) Comparing performance of Genetic Algorithm to Particle Swarm Optimization (PSO) algorithm. This research problem implemented Genetic Algorithm in C++ and used QT Data Visualization for displaying three-dimensional space, pheromone, and Terrain. The Genetic algorithm implementation maintained and preserved the coding style, data structure, and visualization from the PSO implementation. Although the Genetic Algorithm has higher fitness values and better global solutions for 3 or more receivers, it increases the running time. The Genetic Algorithm is around (15-30%) more accurate for asset counts from 3 to 6 but requires (26-82%) more computational time. When the allocation problem complexity increases by adding 3D space, pheromones and complex terrains, the accuracy of GA is 3.71% better but the speed of GA is 121% slower than PSO. In summary, the Genetic Algorithm gives a better global solution in some cases but the computational time is higher for the Genetic Algorithm with than Particle Swarm Optimization.</div>

This thesis investigates the task of estimating the pose of a hand interacting with an object from a depth image. The main contribution of this thesis is the development of our discriminative one-shot hand-object pose estimation system. To the best of our knowledge, this is the first attempt at a one-shot hand-object pose estimation system. It is a two stage system consisting of convolutional neural networks. The first stage segments the object out of the hand from the depth image. This hand-minus-object depth image is combined with the original input depth image to form a 2-channel image for use in the second stage, pose estimation. We show that using this 2-channel image produces better pose estimation performance than a single stage pose estimation system taking just the input depth map as input. We also believe that we are amongst the first to research hand-object segmentation. We use fully convolutional neural networks to perform hand-object segmentation from a depth image. We show that this is a superior approach to random decision forests for this task. Datasets were created to train our hand-object pose estimator stage and hand-object segmentation stage. The hand-object pose labels were estimated semi-automatically with a combined manual annotation and generative approach. The segmentation labels were inferred automatically with colour thresholding. To the best of our knowledge, there were no public datasets for these two tasks when we were developing our system. These datasets have been or are in the process of being publicly released.

FundaÃÃo Cearense de Apoio ao Desenvolvimento Cientifico e TecnolÃgico / The infrastructure expansion planning in cellular networks, so called Base Station Placement (BSP) problem, is a challenging task that must consider a large set of aspects, and which cannot be expressed as a linear optimization function. The BSP is known to be a NP-hard problem unable to be solved by any deterministic method. Based on some fundamental assumptions of Long Term Evolution - Advanced (LTE-A) networks, this work proceeds to investigate the use of two methods for BSP optimization task: the Particle Swarm Optimization (PSO) and the Differential Evolution (DE), which were adapted for placement of many new network nodes simultaneously. The optimization process follows two multi-objective functions used as fitness criteria for measuring the performance of each node and of the network. The optimization process is performed in three scenarios where one of them presents actual data collected from a real city. For each scenario, the fitness performance of both methods as well as the optimized points found by each technique are presented. / O planejamento de expansÃo de infraestrutura em redes celulares à uma desafio que exige considerar diversos aspectos que nÃo podem ser separados em uma funÃÃo de otimizaÃÃo linear. Tal problema de posicionamento de estaÃÃes base à conhecido por ser do tipo NP-hard, que nÃo pode ser resolvido por qualquer mÃtodo determinÃstico. Assumindo caracterÃsticas bÃsicas da tecnologia Long Term Evolution (LTE)-Advanced (LTE-A), este trabalho procede à investigaÃÃo do uso de dois mÃtodos para otimizaÃÃo de posicionamento de estaÃÃes base: OtimizaÃÃo por Enxame de PartÃculas â Particle Swarm Optimization (PSO) â e EvoluÃÃo Diferencial â Differential Evolution (DE) â adaptados para posicionamento de mÃltiplas estaÃÃes base simultaneamente. O processo de otimizaÃÃo à orientado por dois tipos de funÃÃes custo com multiobjetivos, que medem o desempenho dos novos nÃs individualmente e de toda a rede coletivamente. A otimizaÃÃo à realizada em trÃs cenÃrios, dos quais um deles apresenta dados reais coletados de uma cidade. Para cada cenÃrio, sÃo exibidos o desempenho dos dois algoritmos em termos da melhoria na funÃÃo objetivo e os pontos encontrados no processo de otimizaÃÃo por cada uma das tÃcnicas

Submitted by Rosivalda Pereira (mrs.pereira@ufma.br) on 2017-08-11T19:29:47Z No. of bitstreams: 1 SidneyCerqueiraJunior.pdf: 2395617 bytes, checksum: cbf8e82ed5431d78b69640d4a6b7d511 (MD5) / Made available in DSpace on 2017-08-11T19:29:47Z (GMT). No. of bitstreams: 1 SidneyCerqueiraJunior.pdf: 2395617 bytes, checksum: cbf8e82ed5431d78b69640d4a6b7d511 (MD5) Previous issue date: 2012-06-01 / In the last years, the process of restructuring of the electricity market, brought several changes in the operational e regulatory aspects. The main idea was the separation of the generation, transmission and distribution activities in order to insert the competition among them, aimed to increase the e ciency, safety and quality of supply of electrical energy. The hourly schedule, usually called a Unit Commitment has as objective the de - nition of which generators should be online/o ine and their respective operation points. In some markets based on this new model, the determination of the optimal scheduling of generators (thermal and hydro) is made by the Agent Generator, which is largely responsible for the allocation of your portfolio. Given this, the aim of this work is to nd the operational policy that will maximize the pro t of Agent Generator, based on forecast price and respecting the thermal, hydro and market constrictions assigned to the problem. Thus, the optimal schedule found is an important factor in developing strategies to o ers of bids to auctions in which the Genco will participate. For the case study technique Particle Swarm Optimization is applied to solve the problem in plants belonging to the Brazilian electric system, which are also analyzed the in uence of the start-up cost to the optimal schedule. / Nos últimos anos, o processo de reestruturação da indústria da eletricidade, trouxe diversas mudanças nos aspectos operacionais e regulatórios. A ideia principal foi a separação das atividades de geração, transmissão e distribuição, de modo a inserir competição entre esses, visando o aumento da e ficiência, segurança e qualidade no fornecimento da energia elétrica. A programação horária, usualmente denominada de Pré-Despacho de Potência, tem como objetivo a defi nição de quais unidades devem estar ligadas/desligadas e seus respectivos pontos de operação. Em alguns mercados baseado neste novo modelo, a determinação da programação ótima dos geradores (termelétricas e hidrelétricas) é feita pelo próprio Agente Gerador, sendo este o maior responsável pela alocação de seu portfólio. Diante disto, o objetivo deste trabalho é encontrar a política operativa que irá maximizar o lucro desse Agente Gerador, baseado na previsão de preço horário e respeitando as restrições térmicas, hidráulicas e de mercado atribuídas ao problema. Assim, a programação ótima encontrada é um importante fator para elaboração das estratégias de ofertas de lances a leilões em que o Agente Gerador irá participar. Para estudo de caso, a técnica Otimização por Enxame de Partículas é aplicada para solucionar o problema em usinas que pertencem ao sistema elétrico brasileiro, onde é analisado também a influência do custo de partida na programação ótima horária.