Uma proposição para o cálculo de mapas de disparidade de imagens estéreo usando um interpolador neural baseado em funções de base radial

This study aims to seek a more viable alternative for the calculation of differences in images of stereo vision, using a factor that reduces heel the amount of points that are considered on the captured image, and a network neural-based radial basis functions to interpolate the results. The objective to be achieved is to produce an approximate picture of disparities using algorithms with low computational cost, unlike the classical algorithms

Contribuição para o estudo do embarque de uma rede neural artificial em field programmable gate array (FPGA)

This study shows the implementation and the embedding of an Artificial Neural Network (ANN) in hardware, or in a programmable device, as a field programmable gate array (FPGA). This work allowed the exploration of different implementations, described in VHDL, of multilayer perceptrons ANN. Due to the parallelism inherent to ANNs, there are disadvantages in software implementations due to the sequential nature of the Von Neumann architectures. As an alternative to this problem, there is a hardware implementation that allows to exploit all the parallelism implicit in this model. Currently, there is an increase in use of FPGAs as a platform to implement neural networks in hardware, exploiting the high processing power, low cost, ease of programming and ability to reconfigure the circuit, allowing the network to adapt to different applications. Given this context, the aim is to develop arrays of neural networks in hardware, a flexible architecture, in which it is possible to add or remove neurons, and mainly, modify the network topology, in order to enable a modular network of fixed-point arithmetic in a FPGA. Five synthesis of VHDL descriptions were produced: two for the neuron with one or two entrances, and three different architectures of ANN. The descriptions of the used architectures became very modular, easily allowing the increase or decrease of the number of neurons. As a result, some complete neural networks were implemented in FPGA, in fixed-point arithmetic, with a high-capacity parallel processing

Técnicas inteligentes hídridas para o controle de sistemas não lineares

A neuro-fuzzy system consists of two or more control techniques in only one structure. The main characteristic of this structure is joining one or more good aspects from each technique to make a hybrid controller. This controller can be based in Fuzzy systems, artificial Neural Networks, Genetics Algorithms or rein forced learning techniques. Neuro-fuzzy systems have been shown as a promising technique in industrial applications. Two models of neuro-fuzzy systems were developed, an ANFIS model and a NEFCON model. Both models were applied to control a ball and beam system and they had their results and needed changes commented. Choose of inputs to controllers and the algorithms used to learning, among other information about the hybrid systems, were commented. The results show the changes in structure after learning and the conditions to use each one controller based on theirs characteristics

Contribuições para a análise de sinais neuronais e biomédicos

Following the new tendency of interdisciplinarity of modern science, a new field called neuroengineering has come to light in the last decades. After 2000, scientific journals and conferences all around the world have been created on this theme. The present work comprises three different subareas related to neuroengineering and electrical engineering: neural stimulation; theoretical and computational neuroscience; and neuronal signal processing; as well as biomedical engineering. The research can be divided in three parts: (i) A new method of neuronal photostimulation was developed based on the use of caged compounds. Using the inhibitory neurotransmitter GABA caged by a ruthenium complex it was possible to block neuronal population activity using a laser pulse. The obtained results were evaluated by Wavelet analysis and tested by non-parametric statistics. (ii) A mathematical method was created to identify neuronal assemblies. Neuronal assemblies were proposed as the basis of learning by Donald Hebb remain the most accepted theory for neuronal representation of external stimuli. Using the Marcenko-Pastur law of eigenvalue distribution it was possible to detect neuronal assemblies and to compute their activity with high temporal resolution. The application of the method in real electrophysiological data revealed that neurons from the neocortex and hippocampus can be part of the same assembly, and that neurons can participate in multiple assemblies. (iii) A new method of automatic classification of heart beats was developed, which does not rely on a data base for training and is not specialized in specific pathologies. The method is based on Wavelet decomposition and normality measures of random variables. Throughout, the results presented in the three fields of knowledge represent qualification in neural and biomedical engineering

Estimação da demanda de instalações elétricas de edificações com múltiplas unidades de consumo

This work aims to predict the total maximum demand of a transformer that will be used in power systems to attend a Multiple Unit Consumption (MUC) in design. In 1987, COSERN noted that calculation of maximum total demand for a building should be different from that which defines the scaling of the input protection extension in order to not overestimate the power of the transformer. Since then there have been many changes, both in consumption habits of the population, as in electrical appliances, so that this work will endeavor to improve the estimation of peak demand. For the survey, data were collected for identification and electrical projects in different MUCs located in Natal. In some of them, measurements were made of demand for 7 consecutive days and adjusted for an integration interval of 30 minutes. The estimation of the maximum demand was made through mathematical models that calculate the desired response from a set of information previously known of MUCs. The models tested were simple linear regressions, multiple linear regressions and artificial neural networks. The various calculated results over the study were compared, and ultimately, the best answer found was put into comparison with the previously proposed model

Análise de um controlador baseado no Jacobiano estimado da planta através de uma rede neural

This work presents an analysis of the control law based on an indirect hybrid scheme using neural network, initially proposed for O. Adetona, S. Sathanathan and L. H. Keel. Implementations of this control law, for a level plant of second order, was resulted an oscillatory behavior, even if the neural identifier has converged. Such results had motivated the investigation of the applicability of that law. Starting from that, had been made stability mathematical analysis and several implementations, with simulated plants and with real plants, for analyze the problem. The analysis has been showed the law was designed being despised some components of dynamic of the plant to be controlled. Thus, for plants that these components have a significant influence in its dynamic, the law tends to fail

Predição de promotores de Bacillus subtilis usando técnicas de aprendizado de máquina

One of the most important goals of bioinformatics is the ability to identify genes in uncharacterized DNA sequences on world wide database. Gene expression on prokaryotes initiates when the RNA-polymerase enzyme interacts with DNA regions called promoters. In these regions are located the main regulatory elements of the transcription process. Despite the improvement of in vitro techniques for molecular biology analysis, characterizing and identifying a great number of promoters on a genome is a complex task. Nevertheless, the main drawback is the absence of a large set of promoters to identify conserved patterns among the species. Hence, a in silico method to predict them on any species is a challenge. Improved promoter prediction methods can be one step towards developing more reliable ab initio gene prediction methods. In this work, we present an empirical comparison of Machine Learning (ML) techniques such as Na¨ýve Bayes, Decision Trees, Support Vector Machines and Neural Networks, Voted Perceptron, PART, k-NN and and ensemble approaches (Bagging and Boosting) to the task of predicting Bacillus subtilis. In order to do so, we first built two data set of promoter and nonpromoter sequences for B. subtilis and a hybrid one. In order to evaluate of ML methods a cross-validation procedure is applied. Good results were obtained with methods of ML like SVM and Naïve Bayes using B. subtilis. However, we have not reached good results on hybrid database

Aplicação de técnicas de aprendizado de máquina no reconhecimento de classes estruturais de proteínas

Nowadays, classifying proteins in structural classes, which concerns the inference of patterns in their 3D conformation, is one of the most important open problems in Molecular Biology. The main reason for this is that the function of a protein is intrinsically related to its spatial conformation. However, such conformations are very difficult to be obtained experimentally in laboratory. Thus, this problem has drawn the attention of many researchers in Bioinformatics. Considering the great difference between the number of protein sequences already known and the number of three-dimensional structures determined experimentally, the demand of automated techniques for structural classification of proteins is very high. In this context, computational tools, especially Machine Learning (ML) techniques, have become essential to deal with this problem. In this work, ML techniques are used in the recognition of protein structural classes: Decision Trees, k-Nearest Neighbor, Naive Bayes, Support Vector Machine and Neural Networks. These methods have been chosen because they represent different paradigms of learning and have been widely used in the Bioinfornmatics literature. Aiming to obtain an improvment in the performance of these techniques (individual classifiers), homogeneous (Bagging and Boosting) and heterogeneous (Voting, Stacking and StackingC) multiclassification systems are used. Moreover, since the protein database used in this work presents the problem of imbalanced classes, artificial techniques for class balance (Undersampling Random, Tomek Links, CNN, NCL and OSS) are used to minimize such a problem. In order to evaluate the ML methods, a cross-validation procedure is applied, where the accuracy of the classifiers is measured using the mean of classification error rate, on independent test sets. These means are compared, two by two, by the hypothesis test aiming to evaluate if there is, statistically, a significant difference between them. With respect to the results obtained with the individual classifiers, Support Vector Machine presented the best accuracy. In terms of the multi-classification systems (homogeneous and heterogeneous), they showed, in general, a superior or similar performance when compared to the one achieved by the individual classifiers used - especially Boosting with Decision Tree and the StackingC with Linear Regression as meta classifier. The Voting method, despite of its simplicity, has shown to be adequate for solving the problem presented in this work. The techniques for class balance, on the other hand, have not produced a significant improvement in the global classification error. Nevertheless, the use of such techniques did improve the classification error for the minority class. In this context, the NCL technique has shown to be more appropriated

Estudos de algumas ferramentas de coleta e visualização de dados e desempenho de aplicações paralelas no ambiente MPI

The last years have presented an increase in the acceptance and adoption of the parallel processing, as much for scientific computation of high performance as for applications of general intention. This acceptance has been favored mainly for the development of environments with massive parallel processing (MPP - Massively Parallel Processing) and of the distributed computation. A common point between distributed systems and MPPs architectures is the notion of message exchange, that allows the communication between processes. An environment of message exchange consists basically of a communication library that, acting as an extension of the programming languages that allow to the elaboration of applications parallel, such as C, C++ and Fortran. In the development of applications parallel, a basic aspect is on to the analysis of performance of the same ones. Several can be the metric ones used in this analysis: time of execution, efficiency in the use of the processing elements, scalability of the application with respect to the increase in the number of processors or to the increase of the instance of the treat problem. The establishment of models or mechanisms that allow this analysis can be a task sufficiently complicated considering parameters and involved degrees of freedom in the implementation of the parallel application. An joined alternative has been the use of collection tools and visualization of performance data, that allow the user to identify to points of strangulation and sources of inefficiency in an application. For an efficient visualization one becomes necessary to identify and to collect given relative to the execution of the application, stage this called instrumentation. In this work it is presented, initially, a study of the main techniques used in the collection of the performance data, and after that a detailed analysis of the main available tools is made that can be used in architectures parallel of the type to cluster Beowulf with Linux on X86 platform being used libraries of communication based in applications MPI - Message Passing Interface, such as LAM and MPICH. This analysis is validated on applications parallel bars that deal with the problems of the training of neural nets of the type perceptrons using retro-propagation. The gotten conclusions show to the potentiality and easinesses of the analyzed tools.

Análise de desempenho da rede neural artificial do tipo multilayer perceptron na era multicore

Artificial neural networks are usually applied to solve complex problems. In problems with more complexity, by increasing the number of layers and neurons, it is possible to achieve greater functional efficiency. Nevertheless, this leads to a greater computational effort. The response time is an important factor in the decision to use neural networks in some systems. Many argue that the computational cost is higher in the training period. However, this phase is held only once. Once the network trained, it is necessary to use the existing computational resources efficiently. In the multicore era, the problem boils down to efficient use of all available processing cores. However, it is necessary to consider the overhead of parallel computing. In this sense, this paper proposes a modular structure that proved to be more suitable for parallel implementations. It is proposed to parallelize the feedforward process of an RNA-type MLP, implemented with OpenMP on a shared memory computer architecture. The research consistes on testing and analizing execution times. Speedup, efficiency and parallel scalability are analyzed. In the proposed approach, by reducing the number of connections between remote neurons, the response time of the network decreases and, consequently, so does the total execution time. The time required for communication and synchronization is directly linked to the number of remote neurons in the network, and so it is necessary to investigate which one is the best distribution of remote connections

Regulador automático de tensão robusto utilizando técnicas de controle adaptativo

The stability of synchronous generators connected to power grid has been the object of study and research for years. The interest in this matter is justified by the fact that much of the electricity produced worldwide is obtained with the use of synchronous generators. In this respect, studies have been proposed using conventional and unconventional control techniques such as fuzzy logic, neural networks, and adaptive controllers to increase the stabilitymargin of the systemduring sudden failures and transient disturbances. Thismaster thesis presents a robust unconventional control strategy for maintaining the stability of power systems and regulation of output voltage of synchronous generators connected to the grid. The proposed control strategy comprises the integration of a sliding surface with a linear controller. This control structure is designed to prevent the power system losing synchronism after a sudden failure and regulation of the terminal voltage of the generator after the fault. The feasibility of the proposed control strategy was experimentally tested in a salient pole synchronous generator of 5 kVA in a laboratory structure

Contribuições a técnicas de agrupamento e visualização de dados multivariados utilizando mapas auto-organizáveis

Self-organizing maps (SOM) are artificial neural networks widely used in the data mining field, mainly because they constitute a dimensionality reduction technique given the fixed grid of neurons associated with the network. In order to properly the partition and visualize the SOM network, the various methods available in the literature must be applied in a post-processing stage, that consists of inferring, through its neurons, relevant characteristics of the data set. In general, such processing applied to the network neurons, instead of the entire database, reduces the computational costs due to vector quantization. This work proposes a post-processing of the SOM neurons in the input and output spaces, combining visualization techniques with algorithms based on gravitational forces and the search for the shortest path with the greatest reward. Such methods take into account the connection strength between neighbouring neurons and characteristics of pattern density and distances among neurons, both associated with the position that the neurons occupy in the data space after training the network. Thus, the goal consists of defining more clearly the arrangement of the clusters present in the data. Experiments were carried out so as to evaluate the proposed methods using various artificially generated data sets, as well as real world data sets. The results obtained were compared with those from a number of well-known methods existent in the literature

Equalização neural aplicada a sistemas com modulação bidimensional em fibra óptica

Nowadays, optic fiber is one of the most used communication methods, mainly due to the fact that the data transmission rates of those systems exceed all of the other means of digital communication. Despite the great advantage, there are problems that prevent full utilization of the optical channel: by increasing the transmission speed and the distances involved, the data is subjected to non-linear inter symbolic interference caused by the dispersion phenomena in the fiber. Adaptive equalizers can be used to solve this problem, they compensate non-ideal responses of the channel in order to restore the signal that was transmitted. This work proposes an equalizer based on artificial neural networks and evaluates its performance in optical communication systems. The proposal is validated through a simulated optic channel and the comparison with other adaptive equalization techniques

Medição da densidade óssea através de ondas eletromagnéticas e classificação por MVS

This work holds the purpose of presenting an auxiliary way of bone density measurement through the attenuation of electromagnetic waves. In order to do so, an arrangement of two microstrip antennas with rectangular configuration has been used, operating in a frequency of 2,49 GHz, and fed by a microstrip line on a substrate of fiberglass with permissiveness of 4.4 and height of 0,9 cm. Simulations were done with silica, bone meal, silica and gypsum blocks samples to prove the variation on the attenuation level of different combinations. Because of their good reproduction of the human beings anomaly aspects, samples of bovine bone were used. They were subjected to weighing, measurement and microwave radiation. The samples had their masses altered after mischaracterization and the process was repeated. The obtained data were inserted in a neural network and its training was proceeded with the best results gathered by correct classification on 100% of the samples. It comes to the conclusion that through only one non-ionizing wave in the 2,49 GHz zone it is possible to evaluate the attenuation level in the bone tissue, and that with the appliance of neural network fed with obtained characteristics in the experiment it is possible to classify a sample as having low or high bone density

Extração do óleo e caracterização dos resíduos da borra de petróleo para fins de reuso

The petroleum industry, in consequence of an intense activity of exploration and production, is responsible by great part of the generation of residues, which are considered toxic and pollutants to the environment. Among these, the oil sludge is found produced during the production, transportation and refine phases. This work had the purpose to develop a process to recovery the oil present in oil sludge, in order to use the recovered oil as fuel or return it to the refining plant. From the preliminary tests, were identified the most important independent variables, like: temperature, contact time, solvents and acid volumes. Initially, a series of parameters to characterize the oil sludge was determined to characterize its. A special extractor was projected to work with oily waste. Two experimental designs were applied: fractional factorial and Doehlert. The tests were carried out in batch process to the conditions of the experimental designs applied. The efficiency obtained in the oil extraction process was 70%, in average. Oil sludge is composed of 36,2% of oil, 16,8% of ash, 40% of water and 7% of volatile constituents. However, the statistical analysis showed that the quadratic model was not well fitted to the process with a relative low determination coefficient (60,6%). This occurred due to the complexity of the oil sludge. To obtain a model able to represent the experiments, the mathematical model was used, the so called artificial neural networks (RNA), which was generated, initially, with 2, 4, 5, 6, 7 and 8 neurons in the hidden layer, 64 experimental results and 10000 presentations (interactions). Lesser dispersions were verified between the experimental and calculated values using 4 neurons, regarding the proportion of experimental points and estimated parameters. The analysis of the average deviations of the test divided by the respective training showed up that 2150 presentations resulted in the best value parameters. For the new model, the determination coefficient was 87,5%, which is quite satisfactory for the studied system