Algoritmo SOM com estrutura hierárquica e dinâmica aplicado a compressão de imagens

ln this work the implementation of the SOM (Self Organizing Maps) algorithm or Kohonen neural network is presented in the form of hierarchical structures, applied to the compression of images. The main objective of this approach is to develop an Hierarchical SOM algorithm with static structure and another one with dynamic structure to generate codebooks (books of codes) in the process of the image Vector Quantization (VQ), reducing the time of processing and obtaining a good rate of compression of images with a minimum degradation of the quality in relation to the original image. Both self-organizing neural networks developed here, were denominated HSOM, for static case, and DHSOM, for the dynamic case. ln the first form, the hierarchical structure is previously defined and in the later this structure grows in an automatic way in agreement with heuristic rules that explore the data of the training group without use of external parameters. For the network, the heuristic mIes determine the dynamics of growth, the pruning of ramifications criteria, the flexibility and the size of children maps. The LBO (Linde-Buzo-Oray) algorithm or K-means, one ofthe more used algorithms to develop codebook for Vector Quantization, was used together with the algorithm of Kohonen in its basic form, that is, not hierarchical, as a reference to compare the performance of the algorithms here proposed. A performance analysis between the two hierarchical structures is also accomplished in this work. The efficiency of the proposed processing is verified by the reduction in the complexity computational compared to the traditional algorithms, as well as, through the quantitative analysis of the images reconstructed in function of the parameters: (PSNR) peak signal-to-noise ratio and (MSE) medium squared error

Técnicas de computação natural para segmentação de imagens médicas

Image segmentation is one of the image processing problems that deserves special attention from the scientific community. This work studies unsupervised methods to clustering and pattern recognition applicable to medical image segmentation. Natural Computing based methods have shown very attractive in such tasks and are studied here as a way to verify it's applicability in medical image segmentation. This work treats to implement the following methods: GKA (Genetic K-means Algorithm), GFCMA (Genetic FCM Algorithm), PSOKA (PSO and K-means based Clustering Algorithm) and PSOFCM (PSO and FCM based Clustering Algorithm). Besides, as a way to evaluate the results given by the algorithms, clustering validity indexes are used as quantitative measure. Visual and qualitative evaluations are realized also, mainly using data given by the BrainWeb brain simulator as ground truth

Proposta de algoritmo para detecção de vazamentos em oleodutos utilizando análise freqüencial de sinais de pressão

Pipeline leak detection is a matter of great interest for companies who transport petroleum and its derivatives, in face of rising exigencies of environmental policies in industrialized and industrializing countries. However, existing technologies are not yet fully consolidated and many studies have been accomplished in order to achieve better levels of sensitivity and reliability for pipeline leak detection in a wide range of flowing conditions. In this sense, this study presents the results obtained from frequency spectrum analysis of pressure signals from pipelines in several flowing conditions like normal flowing, leakages, pump switching, etc. The results show that is possible to distinguish between the frequency spectra of those different flowing conditions, allowing recognition and announce of liquid pipeline leakages from pressure monitoring. Based upon these results, a pipeline leak detection algorithm employing frequency analysis of pressure signals is proposed, along with a methodology for its tuning and calibration. The proposed algorithm and its tuning methodology are evaluated with data obtained from real leakages accomplished in pipelines transferring crude oil and water, in order to evaluate its sensitivity, reliability and applicability to different flowing conditions

Separação cega de fontes lineares e não lineares usando algoritmo genético, redes neurais artificiais RBF e negentropia de Rényi como medida de independência

Conventional methods to solve the problem of blind source separation nonlinear, in general, using series of restrictions to obtain the solution, often leading to an imperfect separation of the original sources and high computational cost. In this paper, we propose an alternative measure of independence based on information theory and uses the tools of artificial intelligence to solve problems of blind source separation linear and nonlinear later. In the linear model applies genetic algorithms and Rényi of negentropy as a measure of independence to find a separation matrix from linear mixtures of signals using linear form of waves, audio and images. A comparison with two types of algorithms for Independent Component Analysis widespread in the literature. Subsequently, we use the same measure of independence, as the cost function in the genetic algorithm to recover source signals were mixed by nonlinear functions from an artificial neural network of radial base type. Genetic algorithms are powerful tools for global search, and therefore well suited for use in problems of blind source separation. Tests and analysis are through computer simulations

Estudo avaliativo de um algoritmo genético auto-organizável e multiobjetivo utilizando aprendizado de máquina para aplicações de telecomunicações

This paper presents an evaluative study about the effects of using a machine learning technique on the main features of a self-organizing and multiobjective genetic algorithm (GA). A typical GA can be seen as a search technique which is usually applied in problems involving no polynomial complexity. Originally, these algorithms were designed to create methods that seek acceptable solutions to problems where the global optimum is inaccessible or difficult to obtain. At first, the GAs considered only one evaluation function and a single objective optimization. Today, however, implementations that consider several optimization objectives simultaneously (multiobjective algorithms) are common, besides allowing the change of many components of the algorithm dynamically (self-organizing algorithms). At the same time, they are also common combinations of GAs with machine learning techniques to improve some of its characteristics of performance and use. In this work, a GA with a machine learning technique was analyzed and applied in a antenna design. We used a variant of bicubic interpolation technique, called 2D Spline, as machine learning technique to estimate the behavior of a dynamic fitness function, based on the knowledge obtained from a set of laboratory experiments. This fitness function is also called evaluation function and, it is responsible for determining the fitness degree of a candidate solution (individual), in relation to others in the same population. The algorithm can be applied in many areas, including in the field of telecommunications, as projects of antennas and frequency selective surfaces. In this particular work, the presented algorithm was developed to optimize the design of a microstrip antenna, usually used in wireless communication systems for application in Ultra-Wideband (UWB). The algorithm allowed the optimization of two variables of geometry antenna - the length (Ls) and width (Ws) a slit in the ground plane with respect to three objectives: radiated signal bandwidth, return loss and central frequency deviation. These two dimensions (Ws and Ls) are used as variables in three different interpolation functions, one Spline for each optimization objective, to compose a multiobjective and aggregate fitness function. The final result proposed by the algorithm was compared with the simulation program result and the measured result of a physical prototype of the antenna built in the laboratory. In the present study, the algorithm was analyzed with respect to their success degree in relation to four important characteristics of a self-organizing multiobjective GA: performance, flexibility, scalability and accuracy. At the end of the study, it was observed a time increase in algorithm execution in comparison to a common GA, due to the time required for the machine learning process. On the plus side, we notice a sensitive gain with respect to flexibility and accuracy of results, and a prosperous path that indicates directions to the algorithm to allow the optimization problems with "η" variables

Uma Aplicação do Algoritmo QT Clustering para Marcação Colaborativa de Pontos Perigosos em Vias Públicas

This work proposes a collaborative system for marking dangerous points in the transport routes and generation of alerts to drivers. It consisted of a proximity warning system for a danger point that is fed by the driver via a mobile device equipped with GPS. The system will consolidate data provided by several different drivers and generate a set of points common to be used in the warning system. Although the application is designed to protect drivers, the data generated by it can serve as inputs for the responsible to improve signage and recovery of public roads

Escalabilidade Paralela de um Algoritmo de Migração Reversa no Tempo (RTM) Pré-empilhamento

The seismic method is of extreme importance in geophysics. Mainly associated with oil exploration, this line of research focuses most of all investment in this area. The acquisition, processing and interpretation of seismic data are the parts that instantiate a seismic study. Seismic processing in particular is focused on the imaging that represents the geological structures in subsurface. Seismic processing has evolved significantly in recent decades due to the demands of the oil industry, and also due to the technological advances of hardware that achieved higher storage and digital information processing capabilities, which enabled the development of more sophisticated processing algorithms such as the ones that use of parallel architectures. One of the most important steps in seismic processing is imaging. Migration of seismic data is one of the techniques used for imaging, with the goal of obtaining a seismic section image that represents the geological structures the most accurately and faithfully as possible. The result of migration is a 2D or 3D image which it is possible to identify faults and salt domes among other structures of interest, such as potential hydrocarbon reservoirs. However, a migration fulfilled with quality and accuracy may be a long time consuming process, due to the mathematical algorithm heuristics and the extensive amount of data inputs and outputs involved in this process, which may take days, weeks and even months of uninterrupted execution on the supercomputers, representing large computational and financial costs, that could derail the implementation of these methods. Aiming at performance improvement, this work conducted the core parallelization of a Reverse Time Migration (RTM) algorithm, using the parallel programming model Open Multi-Processing (OpenMP), due to the large computational effort required by this migration technique. Furthermore, analyzes such as speedup, efficiency were performed, and ultimately, the identification of the algorithmic scalability degree with respect to the technological advancement expected by future processors

Implementação paralela escalável e eficiente do algoritmo simplex padrão em arquitetura multicore

This work presents a scalable and efficient parallel implementation of the Standard Simplex algorithm in the multicore architecture to solve large scale linear programming problems. We present a general scheme explaining how each step of the standard Simplex algorithm was parallelized, indicating some important points of the parallel implementation. Performance analysis were conducted by comparing the sequential time using the Simplex tableau and the Simplex of the CPLEXR IBM. The experiments were executed on a shared memory machine with 24 cores. The scalability analysis was performed with problems of different dimensions, finding evidence that our parallel standard Simplex algorithm has a better parallel efficiency for problems with more variables than constraints. In comparison with CPLEXR , the proposed parallel algorithm achieved a efficiency of up to 16 times better

Formação estelar desencadeada pela colisão entre nuvens moleculares magnetizadas

We use a finite diference eulerian numerical code, called ZEUS 3D, to do simulations involving the collision between two magnetized molecular clouds, aiming to evaluate the rate of star formation triggered by the collision and to analyse how that rate varies depending on the relative orientations between the cloud magnetic fields before the shock. The ZEUS 3D code is not an easy code to handle. We had to create two subroutines, one to study the cloud-cloud collision and the other for the data output. ZEUS is a modular code. Its hierarchical way of working is explained as well as the way our subroutines work. We adopt two sets of different initial values for density, temperature and magnetic field of the clouds and of the external medium in order to study the collision between two molecular clouds. For each set, we analyse in detail six cases with different directions and orientations of the cloud magnetic field relative to direction of motion of the clouds. The analysis of these twelve cases allowed us to conform analytical-theoretical proposals found in the literature, and to obtain several original results. Previous works indicate that, if the cloud magnetic fields before the collision are orthogonal to the direction of motion, then a strong inhibition of star formation will occur during a cloud-cloud shock, whereas if those magnetic fields are parallel to the direction of motion, star formation will be stimulated. Our treatment of the problem confirmed numerically those results, and further allowed us to quantify the relative star forming efficiencies in each case. Moreover, we propose and analyse an intermediate case where the field of one of the clouds is orthogonal to the motion and the field of the other one is parallel to the motion. We conclude that, in this case, the rate at which the star formation occurs has a value also intermediate between the two extreme cases we mentioned above. Besides that we study the case in which the fields are orthogonal to the direction of the motion but, instead of being parallel to each other, they are anti-parallel, and we obtained for this case the corresponding variation of the star formation rate due to this alteration of the field configuration. This last case has not been studied in the literature before. Our study allows us to obtain, from the simulations, the rate of star formation in each case, as well as the temporal dependence of that rate as each collision evolves, what we do in detail for one of the cases in particular. The values we obtain for the rate of star formation are in accordance with those expected from the presently existing observational data

Formação estelar desencadeada pela colisão entre nuvens moleculares magnetizadas

Conselho Nacional de Desenvolvimento Científico e Tecnológico

Aplicaçaõ das técnicas Path-relinking e Vocabulary buiding na melhoria de performance do algoritmo memético para o problema do caixeiro viajante assimétrico

The present essay shows strategies of improvement in a well succeded evolutionary metaheuristic to solve the Asymmetric Traveling Salesman Problem. Such steps consist in a Memetic Algorithm projected mainly to this problem. Basically this improvement applied optimizing techniques known as Path-Relinking and Vocabulary Building. Furthermore, this last one has being used in two different ways, in order to evaluate the effects of the improvement on the evolutionary metaheuristic. These methods were implemented in C++ code and the experiments were done under instances at TSPLIB library, being possible to observe that the procedures purposed reached success on the tests done

Percepção de fala dos deficientes auditivos usando aparelho de amplificação com algoritmo de redução de ruído

Frequentemente, os indivíduos com perda auditiva têm dificuldade de entender a fala no ambiente ruidoso. OBJETIVO: O objetivo deste estudo foi avaliar clinicamente o desempenho dos indivíduos adultos com deficiência auditiva neurossensorial, com relação à percepção da fala, utilizando o aparelho de amplificação sonora individual digital com o algoritmo de redução de ruído denominado Speech Sensitive Processing, ativado e desativado na presença de um ruído. MATERIAL E MÉTODO: Este estudo de casos foi realizado em 32 indivíduos com deficiência auditiva neurossensorial de graus leve, moderado ou leve a moderado. Foi realizada a avaliação por meio de um teste de percepção de fala, onde se pesquisou o reconhecimento de sentenças na presença de um ruído, para obter a relação sinal/ruído, utilizando o aparelho auditivo digital. RESULTADOS: O algoritmo pôde proporcionar benefício para a maioria dos indivíduos deficientes auditivos, na pesquisa da relação sinal/ruído e os resultados apontaram diferença estatisticamente significante na condição em que o algoritmo encontrava-se ativado, comparado quando o algoritmo não se encontrava ativado. CONCLUSÃO: O uso do algoritmo de redução de ruído deve ser pensado como alternativa clínica, pois observamos a eficácia desse sistema na redução do ruído, melhorando a percepção da fala.

Estados estacionários de partículas sem spin em potenciais quadrados

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Partículas inteligentes de poli (nisopropilacrilamida), quitosana e poli (ácido acrílico): efeito da temperatura e do pH sobre suas propriedades em suspensões aquosas

The present study describes the stability and rheological behavior of suspensions of poly (N-isopropylacrylamide) (PNIPAM), poly (N-isopropylacrylamide)-chitosan (PNIPAMCS), and poly (N-isopropylacrylamide)-chitosan-poly (acrylic acid) (PNIPAM-CS-PAA) crosslinked particles sensitive to pH and temperature. These dual-sensitive materials were simply obtained by one-pot method, via free-radical precipitation copolymerization with potassium persulfate, using N,N -methylenebisacrylamide (MBA) as a crosslinking agent. Incorporation of the precursor materials into the chemical networks was confirmed by elementary analysis and infrared spectroscopy. The influence of external stimuli such as pH and temperature, or both, on particle behavior was investigated through rheological measurements, visual stability tests and analytical centrifugation. The PNIPAM-CS particles showed higher stability in acid and neutral media, whereas PNIPAM-CS-PAA particles were more stable in neutral and alkaline media, both below and above the LCST of poly (Nisopropylacrylamide) (stability data). This is due to different interparticle interactions, as well as those between the particles and the medium (also evidenced by rheological data), which were also influenced by the pH and temperature of the medium. Based on the results obtained, we found that the introduction of pH-sensitive polymers to crosslinked poly (Nisopropylacrylamide) particles not only produced dual-sensitive materials, but allowed particle stability to be adjusted, making phase separation faster or slower, depending on the desired application. Thus, it is possible to adapt the material to different media

Estudos de adsorção de tetraciclina e cromoglicato em partículas de quitosana

Among the polymers that stand out most in recent decades, chitosan, a biopolymer with physico-chemical and biological promising properties has been the subject of a broad field of research. Chitosan comes as a great choice in the field of adsorption, due to their adsorbents properties, low cost and abundance. The presence of amino groups in its chain govern the majority of their properties and define which application a sample of chitosan may be used, so it is essential to determine their average degree of deacetylation. In this work we developed kinetic and equilibrium studies to monitor and characterize the adsorption process of two drugs, tetracycline hydrochloride and sodium cromoglycate, in chitosan particles. Kinetic models and the adsorption isotherms were applied to the experimental data. For both studies, the zeta potential analyzes were also performed. The adsorption of each drug showed distinct aspects. Through the studies developed in this work was possible to describe a kinetic model for the adsorption of tetracycline on chitosan particles, thus demonstrating that it can be described by two kinetics of adsorption, one for protonated tetracycline and another one for unprotonated tetracycline. In the adsorption of sodium cromoglycate on chitosan particles, equilibrium studies were developed at different temperatures, allowing the determination of thermodynamic parameters