O presente trabalho avalia a otimização de parâmetros concentrados de suspensão em veículos e considera a importância deste processo para minimizar a aceleração vertical rms transmitida para garantir conforto e segurança ao motorista. Dessa forma, o trabalho objetiva desenvolver uma modelagem capaz de representar o veículo completo para então otimizar os parâmetros de rigidez e amortecimento no domínio da frequência e identificar, em torno do ponto ótimo, quais desses parâmetros mais influenciam nessa minimização. Para atingir esses objetivos, dois modelos veiculares (com dois e oito graus de liberdade respectivamente) são propostos conforme as orientações das normas BS 6841 (1987), ISO 8608 (1995) e ISO 2631 (1997). Os modelos são analisados linearmente e otimizados por um algoritmo heurístico de enxame de partículas. Finalmente, os resultados de rigidez e amortecimento da suspensão são obtidos e reduzem em até 35,3% a aceleração vertical rms transmitida ao motorista. Por meio de uma análise de sensibilidade, as variáveis de projeto que mais contribuem para essa redução são identificadas. / The present work evaluates the optimization of lumped parameters of suspension on vehicles and considers the importance of this process to minimize the rms vertical acceleration transmitted to ensure comfort and safety to the driver. Thus, this work aims to develop a model able to represent the whole vehicle and, then, optimize the parameters of stiffness and damping in the frequency domain and identify, around the optimal point, those parameters which most influence in this minimization. To achieve these goals, two vehicle models (with two and eight degrees of freedom respectively) are proposed according to the guidelines of the standards BS 6841 (1987), ISO 8608 (1995) and ISO 2631 (1997). The models are linearly analyzed and optimized by a heuristic algorithm of particle swarm. Finally, the results of stiffness and damping of suspension are obtained and reduces up to 35,3% of rms vertical acceleration transmitted to the driver. Through a sensitivity analysis, the design variables that most contribute to this reduction are identified.

Context. Building autonomous racing car controllers is a growing field of computer science which has been receiving great attention lately. An approach named Artificial Potential Fields (APF) is used widely as a path finding and obstacle avoidance approach in robotics and vehicle motion controlling systems. The use of APF results in a collision free path, it can also be used to achieve other goals such as overtaking and maneuverability. Objectives. The aim of this thesis is to build an autonomous racing car controller that can achieve good performance in terms of speed, time, and damage level. To fulfill our aim we need to achieve optimality in the controller choices because racing requires the highest possible performance. Also, we need to build the controller using algorithms that does not result in high computational overhead. Methods. We used Particle Swarm Optimization (PSO) in combination with APF to achieve optimal car controlling. The Open Racing Car Simulator (TORCS) was used as a testbed for the proposed controller, we have conducted two experiments with different configuration each time to test the performance of our APF- PSO controller. Results. The obtained results showed that using the APF-PSO controller resulted in good performance compared to top performing controllers. Also, the results showed that the use of PSO proved to enhance the performance compared to using APF only. High performance has been proven in the solo driving and in racing competitions, with the exception of an increased level of damage, however, the level of damage was not very high and did not result in a controller shut down. Conclusions. Based on the obtained results we have concluded that the use of PSO with APF results in high performance while taking low computational cost.

The Ant Colony Optimization and Particle Swarm Optimization are two Swarm Intelligence algorithms often utilized for optimization. Swarm Intelligence relies on agents that possess fragmented knowledge, a concept not often utilized in games. The aim of this study is to research whether there are any benefits to using these Swarm Intelligence algorithms in comparison to standard algorithms such as A* for pathfinding in a game. Games often consist of dynamic environments with mobile agents, as such all experiments were conducted with dynamic destinations. Algorithms were measured on the length of their path and the time taken to calculate that path. The algorithms were implemented with minor modifications to allow them to better function in a grid based environment. The Ant Colony Optimization was modified in regards to how pheromone was distributed in the dynamic environment to better allow the algorithm to path towards a mobile target. Whereas the Particle Swarm Optimization was given set start positions and velocity in order to increase initial search space and modifications to increase particle diversity. The results obtained from the experimentation showcased that the Swarm Intelligence algorithms were capable of performing to great results in terms of calculation speed, they were however not able to obtain the same path optimality as A*. The algorithms' implementation can be improved but show potential to be useful in games.

By enabling coordinated task execution and movement, robotic swarms can achieve efficient exploration or disaster site management. When utilizing Ultra-wideband (UWB) radio technology for ranging, the proposed relative localization sensor can be made lightweight and relatively indifferent to the ambient environment. Infrastructure dependency is eliminated by making the whole sensor fit on a swarm agent, while allowing for a certain amount of positional error. In this thesis, a novel algorithm is implemented in to constrained hardware and compared to a more traditional trilateration approach. Both algorithms utilize Particle Swarm Optimization (PSO) to be more robust towards noise and achieves similar accuracy, but the proposed algorithm can run up to ten times faster. The antenna array which forms the localization sensor weighs only 56g, and achieves around 0.5m RMSE with a 10Hz update rate. Experiments show that the accuracy can be further improved if the rotational bias observed in the UWB devices are compensated for.

The recent advent of bioinformatics has given rise to the central and recurrent problem of optimally aligning biological sequences. Many techniques have been proposed in an attempt to solve this complex problem with varying degrees of success. This thesis investigates the application of a computational intelligence technique known as particle swarm optimization (PSO) to the multiple sequence alignment (MSA) problem. Firstly, the performance of the standard PSO (S-PSO) and its characteristics are fully analyzed. Secondly, a scalability study is conducted that aims at expanding the S-PSO’s application to complex MSAs, as well as studying the behaviour of three other kinds of PSOs on the same problems. Experimental results show that the PSO is efficient in solving the MSA problem and compares positively with well-known CLUSTAL X and T-COFFEE. / Dissertation (MSc)--University of Pretoria, 2009. / Computer Science / Unrestricted

Non-rigid shapes are generally known as objects whose three dimensional geometry may deform by internal and/or external forces. Deformable shapes are all around us, ranging from protein molecules, to natural objects such as the trees in the forest or the fruits in our gardens, and even human bodies. Two deformable shapes may be related by isometry, which means their intrinsic geometries are preserved, even though their extrinsic geometries are dissimilar. An important problem in the analysis of the deformable shapes is to identify the three-dimensional correspondence between two isometric shapes, given that the two shapes may be deviated from isometry by intrinsic distortions. A major challenge is that non-rigid shapes have large degrees of freedom on how to deform. Nevertheless, irrespective of how they are deformed, they may be aligned such that the geodesic distance between two arbitrary points on two shapes are nearly equal. Such alignment may be expressed by a permutation matrix (a matrix with binary entries) that corresponds to every paired geodesic distance in between the two shapes. The alignment involves searching the space over all possible mappings (that is all the permutations) to locate the one that minimizes the amount of deviation from isometry. A brute-force search to locate the correspondence is not computationally feasible. This thesis introduces a novel approach created to locate such correspondences, in spite of the large solution space that encompasses all possible mappings and the presence of intrinsic distortion. In order to find correspondences between two shapes, the first step is to create a suitable descriptor to accurately describe the deformable shapes. To this end, we developed deformation-invariant metric descriptors. A descriptor constitutes pair-wise geodesic distances among arbitrary number of discrete points that represent the topology of the non-rigid shape. Our descriptor provides isometric-invariant representation of the shape irrespective of its circumstantial deformation. Two isometric-invariant descriptors, representing two candidate deformable shapes, are the input parameters to our optimization algorithm. We then proceed to locate the permutation matrix that aligns the two descriptors, that minimizes the deviation from isometry. Once we have developed such a descriptor, we turn our attention to finding correspondences between non deformable shapes. In this study, we investigate the use of both classical and quantum particle swarm optimization (PSO) algorithms for this task. To explore the merits of variants of PSO, integer optimization involving test functions with large dimensions were performed, and the results and the analysis suggest that quantum PSO is more effective optimization method than its classical PSO counterpart. Further, a scheme is proposed to structure the solution space, composed of permutation matrices, in lexicographic ordering. The search in the solution space is accordingly simplified to integer optimization to find the integer rank of the targeted permutation matrix. Empirical results suggest that this scheme improves the scalability of quantum PSO across large solution spaces. Yet, quantum PSO's global search capability requires assistance in order to more effectively manoeuvre through the local extrema prevalent in the large solution spaces. A mutation based genetic algorithm (GA) is employed to augment the search diversity of quantum PSO when/if the swarm stagnates among the local extrema. The mutation based GA instantly disengages the optimization engine from the local extrema in order to reorient the optimization energy to the trajectories that steer to the global extrema, or the targeted permutation matrix. Our resultant optimization algorithm combines quantum Particle Swarm Optimization (PSO) and mutation based Genetic Algorithm (GA). Empirical results show that the optimization method presented is scalable and efficient on standard hardware across different solution space sizes. The performance of the optimization method, in simulations and on various near-isometric shapes, is discussed. In all cases investigated, the method could successfully identify the correspondence among the non-rigid deformable shapes that were related by isometry.

Production scheduling is one of the most important issues in the planning and operation of manufacturing systems. Customers increasingly expect to receive the right product at the right price at the right time. Various problems experienced in manufacturing, for example low machine utilization and excessive work-in-process, can be attributed directly to inadequate scheduling. In this dissertation a production scheduling algorithm is developed for Optimatix, a South African-based company specializing in supply chain optimization. To address the complex requirements of the customer, the problem was modeled as a flexible job shop scheduling problem with sequence-dependent set-up times, auxiliary resources and production down time. The algorithm development process focused on investigating the application of both particle swarm optimization (PSO) and differential evolution (DE) to production scheduling environments characterized by multiple machines and multiple objectives. Alternative problem representations, algorithm variations and multi-objective optimization strategies were evaluated to obtain an algorithm which performs well against both existing rule-based algorithms and an existing complex flexible job shop scheduling solution strategy. Finally, the generality of the priority-based algorithm was evaluated by applying it to the scheduling of production and maintenance activities at Centurion Ice Cream and Sweets. The production environment was modeled as a multi-objective uniform parallel machine shop problem with sequence-dependent set-up times and unavailability intervals. A self-adaptive modified vector evaluated DE algorithm was developed and compared to classical PSO and DE vector evaluated algorithms. Promising results were obtained with respect to the suitability of the algorithms for solving a range of multi-objective multiple machine scheduling problems. Copyright / Dissertation (MEng)--University of Pretoria, 2009. / Industrial and Systems Engineering / unrestricted

Temporal data is common in real-world datasets. Analysis of such data, for example by means of clustering algorithms, can be difficult due to its dynamic behaviour. There are various types of changes that may occur to clusters in a dataset. Firstly, data patterns can migrate between clusters, shrinking or expanding the clusters. Additionally, entire clusters may move around the search space. Lastly, clusters can split and merge. Data clustering, which is the process of grouping similar objects, is one approach to determine relationships among data patterns, but data clustering approaches can face limitations when applied to temporal data, such as difficulty tracking the moving clusters. This research aims to analyse the ability of particle swarm optimisation (PSO) and differential evolution (DE) algorithms to cluster temporal data. These algorithms experience two weaknesses when applied to temporal data. The first weakness is the loss of diversity, which refers to the fact that the population of the algorithm converges, becoming less diverse and, therefore, limiting the algorithm’s exploration capabilities. The second weakness, outdated memory, is only experienced by the PSO and refers to the previous personal best solutions found by the particles becoming obsolete as the environment changes. A data clustering algorithm that addresses these two weaknesses is necessary to cluster temporal data. This research describes various adaptations of PSO and DE algorithms for the purpose of clustering temporal data. The algorithms proposed aim to address the loss of diversity and outdated memory problems experienced by PSO and DE algorithms. These problems are addressed by combining approaches previously used for the purpose of dealing with temporal or dynamic data, such as repulsion and anti-convergence, with PSO and DE approaches used to cluster data. Six PSO algorithms are introduced in this research, namely the data clustering particle swarm optimisation (DCPSO), reinitialising data clustering particle swarm optimisation (RDCPSO), cooperative data clustering particle swarm optimisation (CDCPSO), multi-swarm data clustering particle swarm optimisation (MDCPSO), cooperative multi-swarm data clustering particle swarm optimisation (CMDCPSO), and elitist cooperative multi-swarm data clustering particle swarm optimisation (eCMDCPSO). Additionally, four DE algorithms are introduced, namely the data clustering differential evolution (DCDE), re-initialising data clustering differential evolution (RDCDE), dynamic data clustering differential evolution (DCDynDE), and cooperative dynamic data clustering differential evolution (CDCDynDE). The PSO and DE algorithms introduced require prior knowledge of the total number of clusters in the dataset. The total number of clusters in a real-world dataset, however, is not always known. For this reason, the best performing PSO and best performing DE are compared. The CDCDynDE is selected as the winning algorithm, which is then adapted to determine the optimal number of clusters dynamically. The resulting algorithm is the k-independent cooperative data clustering differential evolution (KCDCDynDE) algorithm, which was compared against the local network neighbourhood artificial immune system (LNNAIS) algorithm, which is an artificial immune system (AIS) designed to cluster temporal data and determine the total number of clusters dynamically. It was determined that the KCDCDynDE performed the clustering task well for problems with frequently changing data, high-dimensions, and pattern and cluster data migration types. / Dissertation (MSc)--University of Pretoria, 2015. / Computer Science / Unrestricted

Submitted by Luiza Maria Pereira de Oliveira (luiza.oliveira@ufpe.br) on 2017-07-12T14:35:17Z No. of bitstreams: 2 license_rdf: 811 bytes, checksum: e39d27027a6cc9cb039ad269a5db8e34 (MD5) DISSERTAÇÃO Diogo da Silva Severo.pdf: 871898 bytes, checksum: d5d7499d1a7c7d0838db7f6fc9dd682b (MD5) / Made available in DSpace on 2017-07-12T14:35:17Z (GMT). No. of bitstreams: 2 license_rdf: 811 bytes, checksum: e39d27027a6cc9cb039ad269a5db8e34 (MD5) DISSERTAÇÃO Diogo da Silva Severo.pdf: 871898 bytes, checksum: d5d7499d1a7c7d0838db7f6fc9dd682b (MD5) Previous issue date: 2013-08-15 / Redes Neurais Artificiais foram inspiradas nas redes neurais biológicas e as principais semelhanças compartilhadas por ambas são: capacidade de processamento de informação de forma paralela e distribuída, presença de unidades de processamento simples e capacidade de aprendizado através de exemplos. Entretanto, as redes neurais artificiais não apresentam uma característica inerente às redes neurais biológicas: modularização. Em contraste com as redes neurais artificiais, nosso cérebro apresenta áreas especializadas distintas responsáveis por tarefas específicas como visão, audição e fala, por exemplo. Com o intuito de aproximar ainda mais as redes neurais artificiais das redes neurais biológicas, foram propostas as redes neurais modulares. Tais redes tiram proveito da modularização para superar as redes neurais simples quando lidam com problemas complexos. Um conceito crucial relacionado ao uso de redes neurais modulares é a decomposição. A decomposição trata da divisão do problema original em vários subproblemas, menores e mais simples de serem resolvidos. Cada subproblema é tratado por um especialista (rede neural simples) específico. Ao solucionar seus respectivos subproblemas, cada módulo faz uso de todo o conjunto original de características para treinar seus especialistas. Entretanto, é esperado que diferentes módulos requeiram diferentes características para realizar suas tarefas. Dessa forma, é importante escolher quais características melhor preservam a informação discriminatória entre classes necessária à tarefa de classificação de cada módulo. Este trabalho propõe uma arquitetura de rede neural modular que seleciona um conjunto específico de características por módulo, sendo este um tópico pouco explorado na literatura uma vez que, em sua maioria, os trabalhos envolvendo redes neurais modulares não realizam seleção de características para cada módulo específico. O procedimento de seleção de características é um método de otimização global baseado no PSO binário. Outra contribuição do presente trabalho é um método híbrido de seleção e ponderação de características baseado no PSO binário. Foram realizados experimentos com bases de dados públicas e os resultados mostraram que a arquitetura proposta obteve melhores taxas de classificação ou taxas iguais, porém, fazendo uso de menos características quando comparadas a redes neurais modulares que não realizam a seleção de características por módulo. Os experimentos realizados com o método híbrido de seleção e ponderação de características baseado em otimização por enxame de partículas mostraram taxas de classificação superiores às taxas obtidas pelos métodos que serviram de comparação. / Artificial Neural Networks were inspired by biological neural networks and the major similarities shared by both are: the ability to process information in a parallel and istributed way, the presence of simple processing units and the ability for learning through examples. However, artificial neural networks do not present an inherent characteristic of biological neural networks: modularization. In contrast to artifical neural networks, our brain has distinct specialized areas for specific tasks such as vision, hearing and speech, for example. With the aim of bringing even more artificial neural networks to biological neural networks, modular neural networks were proposed. Such networks take advantage of modularization to outperform the simple neural networks when dealing with complex problems. A crucial concept related to the use of neural networks is the task decomposition. The task decomposition divides the original problem into several subproblems, smaller and simpler to resolve. Each subproblem is handled by a specific expert (simple neural network). To solve their subproblems, each module makes use of the whole set of features to train its expert. Nevertheless, it is expected that different modules require different features to perform their tasks. Thus, it is important to choose which features better preserve the discriminant information among classes for each module. This work proposes a modular neural network architecture that selects a specific set of features per module. This approach is a topic little explored in literature since in most cases research involving modular neural networks do not perform feature selection for each particular module. The feature selection procedure is an optimization method based on the binary particle swarm optimization. Another contribution of this work is a hybrid feature selection and weighting method based on binary PSO. Experiments were carried out on public datasets and the results show that the proposed architecture achieved better accuracy rates or equal rates, however, using less features when compared to modular neural networks that do not select features per module. Experiments with the hybrid feature selection and weighting method based on optimization particle swarm show better accuracy rates when compared to other hybrids methods used in this work as comparison methods.

No description available.