Programa de Pós-graduação em Engenharia Elétrica e da Computação
URI Permanente desta comunidade
Navegar
Navegando Programa de Pós-graduação em Engenharia Elétrica e da Computação por Por Área do CNPQ "CNPQ::ENGENHARIAS"
Agora exibindo 1 - 14 de 14
Resultados por página
Opções de Ordenação
Item Descoberta automatizada de associações com o uso de algoritmo Apriori como técnica de mineração de dados(Universidade Federal de Goiás, 2011-02-25) ALMEIDA, Derciley Cunha de; BRITO, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900Nowadays, the use of modern information systems allows the storage and management of increasingly large amounts of data. On the other hand, the full analysis and the maximum extraction of useful information from this universe of available data present considerable challenges in view of inherent human limitations. This dissertation deals with the subject of data mining, which is the use of technology resources in order to extract information from databases in an automated way. One of the possibilities offered by data mining technologies is the automated search for possible associations within data. Information about such associations can be useful for understanding cause and effect relationships between the involved variables in data analysis for decision making. There are several data mining techniques and many of them can be used for discovering associations. The main goal of this work is to study a particular method for automated search of associations called Apriori , evaluating its capabilities and outcomes. The study focuses on the problem of improving the Apriori algorithm results, taking into consideration that the results of the data mining process might be improved if the data are prepared specifically for Apriori application. The conclusions are drawn from a case study in which the Apriori algorithm was applied to a database with information on drug distribution at a health institute. The results of two experiments are considered in order to evaluate the influence of data preprocessing on the Apriori algorithm's performance. It was found that the Apriori algorithm yields satisfactory results on the discovery of association in data; however, for best results, it is advisable that the data be prepared in advance, specifically for the Apriori application, otherwise many associations in the database might be left undiscovered.Item Análise de desempenho de plataformas de educação a distância com arquitetura cliente-servidor utilizando teoria de filas(Universidade Federal de Goiás, 2010-08-19) ALVES, Leonardo Antonio; VIEIRA, Flávio Henrique Teles; http://lattes.cnpq.br/0920629723928382In this work, we present an analytical model to predict the performance of the client-server system regarding an E-Learning platform. This approach is based on the queuing theory and can adequately describe the performance of an E-Learning platform and its parameters, such as the server response time. It is used a Poisson model to describe the traffic processes in the EaD system, comparing the output of the model to an E-Learning platform working at the MSD Education company. In this study, it was developed a precise tool for designing E-Learning platforms based on client-server model according to the increasing access demand.Item Detecção Automática de Ondas de Elliott em Mercado Acionário(Universidade Federal de Goiás, 2008-08-06) CALAÇA, Raul Wonsjuk; MARQUES, Thyago Carvalho; http://lattes.cnpq.br/1763926064124591; MARTINS, Weber; http://lattes.cnpq.br/3123848470517021The Elliott Wave analysis is a technique developed for the prediction of prices of financial assets (stocks, exchange rates etc.). This work introduces the basic concepts of the financial market, focusing mainly on the Elliott Wave principle, which differs from other techniques for providing direction and intensity of changes in shares / stocks prices in the financial market. The Elliott Wave detection usually employs manual methods, since automated systems present high costs and are apparently based on trial and error method associated with Statistics. Manual methods assess, following some rules, the waves prospected by trial and error, and requires specialized training and experience. To automatically detect the waves of Elliott, this work suggests, develops and tests a computational system based on Genetic Algorithms, an Artificial Intelligence technique inspired on Biology. Genetic Algorithms are used to evolve answers to problems by assessing candidates, which are coded as chromosomes. Tests of the system were performed based on BM&FBOVESPA stocks with high daily liquidity. Simulations have indicated that the detected waves are satisfactory, with error rate below 3% in each inflection point.Item Programação Genética Aplicada à Programação de Controladores Lógico Programáveis(Universidade Federal de Goiás, 2009-05-29) CARNEIRO, Marcos Lajovic; BRITO, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900This research proposes the application of an artificial intelligence technique called genetic programming (GP) to make easier the programming of programmable logical devices (PLC) by the automatic generation of Ladder and Instruction List programs. The system data input can be done by not-specialized people using scenarios composed by time lines. These time lines demonstrate graphically the sequencing details of the PLC input and output permitting the programming of systems that uses memory like inter-locking contacts and the use of timers. Since GP is great dependent of its initial simulation parameters, thousand of simulations have been done to determine the better kind of configuration of cross-over and mutationItem Programação Genética Aplicada no Processo de Descoberta de Conhecimento em Bases de Dados de Redes de Pesquisa.(Universidade Federal de Goiás, 2010-12-20) DUARTE, Kedma Batista; BRITO, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900The Genetic Programming (GP) is a heuristic algorithm for Data Mining (DM), which can be applied to the classification task. This is a method of evolutionary computing inspired in the mechanisms of natural selection theory of Charles Darwin, declared in 1859 in his book "The Origin of Species." From an initial population, the method search over a number of generations to find solutions adapted to the environment of problem. The PG method was proposed in 1990 by John Koza, who demonstrated in one of its applications, the induction in formation of decision trees in the process of data classification. Within this context, the study developed in this work has as main objective the investigation of the concepts of PG and its application on a database of scientific collaboration networks, helping as a management tool in prospective studies of trends for the establishment of common axes in public policy of Science, Technology and Innovation (STI), focusing on regional development. The method is applied on a set of attributes, sorting them in order to identify similarity relationships between groups of researchers that comprise the network. The study involves the concepts of Knowledge Discovery in Databases (KDD) and Data Mining (DM). Networks of Scientific Collaboration, or Networks Research, are inserted in the context of small groups of social networks, the environment is dynamic due to the easy of information exchange and links between individuals, favoring the formation of new groups, which makes the growth of the network unlimited. "The combination of these groups, generated by the relationships between them, appears as a case of multi-criteria decision, granting the application of some complexity. In this sense, it is intended to apply the method of PG for generation of classification rules that lead to the discovery of groups of researchers with similar traits, which in a planned process could be induced to form groups strengthened and consolidated. The study helps to exploit the potential of genetic programming as a classifier algorithm, as well as use it as a method to build tools to support planning and decision making in STI.Item Previsão de Vazões Naturais Diárias Afluentes ao Reservatório da UHE Tucuruí Utilizando a Técnica de Redes Neurais Artificiais(Universidade Federal de Goiás, 2012-09-05) FERREIRA, Carlos da Costa; CRUZ JÚNIOR, Gélson da; http://lattes.cnpq.br/4370555454162131The forecast of natural flows to hydroelectric plant reservoirs is an essential input to the planning and programming of the SIN´s operation. Various computer models are used to determine these forecasts, including physical models, statistical models and the ones developed with the RNA´s techniques. Currently, the ONS performs daily forecasts of natural flows to the UHE Tucuruí based on the univariate stochastic model named PREVIVAZH, developed by Electric Energy Research Center - Eletrobras CEPEL. Throughout the last decade, several papers have shown evolution in the application of neural networks methodology in many areas, specially in the prediction of flows on a daily, weekly and monthly basis. The goal of this dissertation is to present and calibrate a model of natural flow forecast using the RNA´s methodology, more specifically the NSRBN (Non-Linear Sigmoidal Regression Blocks Networks) (VALENCA; LUDERMIR, 2001), on a time lapse from 1 to 12 days forward to the Tucuruí Hydroelectric Plant, considering the hydrometric stations data located upstream from it s reservoir. In addition, a comparative analysis of results found throughout the calibrated neural network and the ones released by ONS is performed. The results show the advantage of the methodology of artificial neural networks on autoregressive models. The Mean Absolute Percentage Error - MAPE values obtained were, on average, 48 % lower than those released by the ONS.Item Controle Inteligente de Tempo Livre em Tutoria Multissessão(Universidade Federal de Goiás, 2009-08-22) GOMES, Viviane Margarida; NALINI, Lauro Eugênio Guimarães; http://lattes.cnpq.br/7555089672749145; MARTINS, Weber; http://lattes.cnpq.br/3123848470517021Intelligent Tutoring Systems are softwares to provide customized instruction by using techniques of Computational Intelligence. This research proposes the intelligent control of free time (break interval) in multi-session tutoring. The teaching strategy employs tutoring modules with the following steps: 1) video class, 2) exercise, 3) practical suggestion, 4) free time, and 5) revision exercise. As part of the learning environment, free time (step 4) can contribute to increase the knowledge retention. Based on the student performance in exercises, the proposed system uses Reinforcement Learning to control free time durations. The intelligent agent decides according to the policy that has been indicated by the Softmax method. Among the relevant points of this algorithm, it can be highlighted the optimistic initial values, the incremental implementation and the temperature adjustment (Gibbs distribution parameter) to the selection of action. Two student groups have participated of data collection. The experimental group (with intelligent control) has been compared to the control group (where decisions belong to the student). In the groups, the intelligent agent or the student determines the action that will be followed or, in more detail, if free time will be shorter, longer or maintained. In comparison, statistical data analysis have shown significant and equivalent gains in knowledge retention. However, students from experimental group have realized more accurately the role of free time as a component of the teaching strategyItem Ambiente virtual para reabilitação de membros superiores utilizando visão computacional(Universidade Federal de Goiás, 2012-05-02) GOMIDE, Renato de Sousa; VIEIRA, Marcus Fraga; http://lattes.cnpq.br/4153462617460766The use of computing devices used in virtual reality has been exploited to provide solutions in healthcare, specifically in functional rehabilitation. There are studies that indicate that immersion caused by the use of virtual environments in rehabilitation presents positive results on the evolution of a patient in therapy. From this information, there was motivation for this study, which aims at developing a low cost solution consisting in a virtual environment for upper limbs rehabilitation. This work describes the internal elements of the computing device and also the development of the virtual environment. The user interacts with the virtual environment through computer vision techniques, having a webcam as a data input device. Acquired images by the webcam are processed so that an object of interest may be in evidence by algorithms of image segmentation. There were analyzed five techniques of image segmentation in RGB and HSV color spaces. By the results obtained in the development environment, it wasn't possible to classify the best method of segmentation, and the performance of the methods varies according to the color of the object of interest and lighting of the external environment. The virtual environment was modeled after technical visits made in rehabilitation center supported by physiotherapists and occupational therapists. The virtual environment was tested only in research environment. Therefore it is necessary to employ the system in rehabilitation clinic in partnership with health professionals so that there is a validation of the virtual environment developed in this project in the area of rehabilitation.Item Estudo de Técnicas de Otimização de Sistemas Hidrotérmicos por Enxame de Partículas(Universidade Federal de Goiás, 2012-06-21) GOMIDES, Lauro Ramon; CRUZ JÚNIOR, Gélson da; http://lattes.cnpq.br/4370555454162131Particle Swarm Optimization has been widely used to solve real-world problems, including the operation planning of hydrothermal generation systems, where the main goal is to achieve rational strategies of operation. This can be accomplished by minimizing the high-cost thermoelectric generation, while maximizing the low-cost hydroelectric generation. The optimization process must consider a set of complex constrains. This work presents the application of some recently proposed Particle Swarm Optimizers for a group of hydroelectric power plants of the Brazilian interconnected system, using real data from existing plants. There were performed some tests by using the standard PSO, PSO-TVAC, Clan PSO, Clan PSO with migration, Center PSO, and one approach proposed in this work, called Center Clan PSO, over three different mid-term periods. All PSO approaches were compared to the results achieved by a Non-linear Programming algorithm (NLP). Furthermore, another approach was proposed, based on Center PSO, named Extended Center PSO. It was observed that the PSO approaches presented as promising solutions to the problem, even better than NLP in some cases.Item Proposta de um sistema de gerência de redes PLC utilizando SNMPv3(Universidade Federal de Goiás, 2009-08-20) OLIVEIRA, Diogo Nunes de; DEUS JÚNIOR, Getúlio Antero de; http://lattes.cnpq.br/8531659368461322; VIEIRA, Flávio Henrique Teles; http://lattes.cnpq.br/0920629723928382ACCESS technologies for data transmission, such as xDSL, Wi-¯ and cable modem are widely used because they support high data transmission rates at low cost. Among these technologies, Power Line Communications, known as PLC, is a promising solution. PLC technology transmits data over power network, which presents high capilarity, due to the fact that it is present in 99% of residences. Since most of its structure already exists, power supply concessionaries started investing in this solution to stop being only a power supply concessionary and to be also a telecommunication company. In order to obtain control over a technology it is necessary to use management techniques that permits the maximum extraction of information from technology and involved devices. One of the goals of this work is to present the management solution developed to PLC networks. This solution di®ers from network management solutions used on other data transmission technologies due to the transmission media utilized. The management software used as base of the management system implemented is a free and no cost software. The concept of free code was adopted to the solutions implemented to the management system. The other goal of this work is to present the proposal and implementation of an embedded system based on PIC microcontroller that performs conversion of versions of SNMP protocol, which is the default management protcol in TCP/IP based networks. This converter device brings security to PLC networks management, since PLC devices only support version 2c of SNMP protocol, which is faulty regarding security. Since SNMPv3 supports authentication and privacy al gorithms, the designed converter device is capable of providing security, due to its capacity of coding a SNMPv2c packet into a SNMPv3 packet, and vice-versa.Item Modelagem multifractal aplicada à estimação de probabilidade de perda de dados e ao controle de fluxos de tráfego em redes(Universidade Federal de Goiás, 2011-03-29) ROCHA, Flávio Geraldo Coelho; VIEIRA, Flávio Henrique Teles; http://lattes.cnpq.br/0920629723928382In this dissertation, the multifractal analysis is used in the context of traffic modeling of communications networks by proposing algorithms and techniques for improving the performance of these networks. Thus, in order to better describe traffic networks, a model based on multifractal multiplicative cascade that uses autoregressive processes for multipliers modeling is proposed, the model is called CMAM (Multifractal Cascade with Multipliers Autoregressive Modeling). Simulations are carried out to evaluate the model performance on describing real video traffic traces and wired and wireless real network traffic traces. In addition, considering data loss probability as an important quality of service measure, a mathematical expression for estimating loss probability that takes into account wavelet coefficients associated to the traffic process is proposed. The expression is evaluated, among other ways, through simulations in a wireless network scenario based on OFDM / TDMA technologies. Then, an admission control scheme for network flows which is based on the proposed loss probability estimation is presented and applied to the scenario considered. Simulations show efficiency of the proposed scheme in comparison to other approaches found in the literature. In addition, an adaptive transmission rate allocation scheme that considers the characteristics of multifractal network traffic is proposed, which one is compared to an approach that considers the monofractal traffic properties. Finally, using CMAM for video traffic modeling, a rate control algorithm for video traffic in the source is presented based on exponential modeling of the scale function associated with the quantization parameter Q of the video encoder.Item Redução da complexidade computacional do método de estimação de ângulos de incidência através da diferença entre os valores singulares da matriz de covariância espacial(Universidade Federal de Goiás, 2009-03-13) SILVA, Hugo Vinícius Leão e; LEMOS, Rodrigo Pinto; http://lattes.cnpq.br/3333000136853156This work is concerned with the estimation of Direction-Of-Arrival (DOA) angles of plane waves impinging on a sensor array. Among all methods of estimation found in litera-ture, MODEX (MODE with eXtra roots) outstands for its performance and computational complexity. However, recently, a method called SEAD (SEArch of Direction by differential spectrum) was proposed. It has shown better estimation performance against noise than MODEX has. However, its computational complexity is prohibitive for real-time applications. In order to reduce it s computational complexity, a new estimate selection procedure on SEAD is proposed, that yields to significantly less candidate angles than before. Additionally, the introduction of iterative refinements on estimates has allowed improving resolution as well as complexity reductionItem Estimação de vazão baseada em modelagem e simulação do controle de acesso ao meio em redes PLC(Universidade Federal de Goiás, 2010-08-18) VASQUES, Thiago Lara; ARAÚJO, Sérgio Granato de; http://lattes.cnpq.br/3634204499080969; VIEIRA, Flávio Henrique Teles; http://lattes.cnpq.br/0920629723928382We carried out a study on throughput estimation based on analysis and modeling of the medium access control in HomePlug 1.0 standard based PLC networks. The data communication using electrical energy wires has advantages such as presenting characteristics of ubiquity due to the existent infrastructure, but faces significant obstacles as fading and noise. The main standard of this kind of home network is the HomePlug, which defines a protocol based on the method of multiple access with collision avoidance (CSMA/CA). The HomePlug adds to the CSMA/CA a technique called deferral counter (DC) that adapts the contention of the nodes in accessing the medium according to network load. The objective of this work is todo a comparative study of the throughput, which is the ratio of the packet payload, i.e., the amount of data that is inserted into the body of the datagram, and the frame transmission time. To this end, we evaluate what is the theoretical maximum throughput of the PLC channel, we developed a simulator for the CSMA/CA and we propose a simple probabilistic model to describe the throughput on the network PLC. Finally, we make a comparison between the results obtained with the simulator and the probabilistic model to those observed from a real PLC network, proving that the results of the theoretical maximum throughput and the simulation results are close and that the probability model becomes a tool for calculating throughput in PLC networks.Item Análise e Comparação de Modelos de Previsão de Vazões para o Planejamento Energético, Utilizando Séries Temporais(Universidade Federal de Goiás, 2009-01-02) XAVIER, Priscila Branquinho; CRUZ JÚNIOR, Gélson da; http://lattes.cnpq.br/4370555454162131n the planning of the energetic operation, analysis and forecasts of the flow are very important. A huge difficulty in the forecast of flow is the seasonality presence, due to drought and flood periods in the year. Many scientists, with different methodologies, have been concerned with finding a best model, compared with the utilized by Brazil s system - Markovian Model. The Makovian Model, or selfregressive with order 1, is a Box & Jenkins methodology, and requires data handling to treat non-stationarity, or the use of regular models, requiring a hardly theoretical formulation for the statistical procedures. Therefore, the statistical models, autoregressive model with seasonality and Holt-Winters model, of treatment of temporal series are presented and, carried out the flow s analysis and forecast for three study groups, in two different (historical) horizons. The performance of the models was compared and the results showed that the proposed models presents better adjust than the model adopted by Brazilian system