Câncer do colo uterino: rastreamento, marcador biológico e polimorfismo genético

Existem fortes evidências de que os programas de rastreamento baseados em citologia resultaram em diminuição significativa da incidência e mortalidade por câncer do colo do útero, no entanto, um excesso substancial de tratamento de lesões intraepiteliais de baixo grau que dificilmente progrediriam para carcinoma cervical resulta da baixa especificidade do tradicional rastreio citológico. A detecção precoce das lesões através do rastreamento citológico e a avaliação do grau histológico em espécimes cervicais são fundamentais, entretanto não permitem identificar quais pacientes terão maior probabilidade de progressão para lesões de alto grau e carcinoma invasivo. A busca de potenciais marcadores de prognóstico; objetivando o entendimento da progressão das lesões intraepiteliais é de suma importância. Acredita-se que fatores imunoregulatórios, imunogenéticos e proteínas do ciclo celular estejam intimamente envolvidos no processo de carcinogênese. Considerando o exposto, a proposta do projeto foi inicialmente avaliar a eficácia da citologia oncológica no rastreamento do câncer cervical, foi investigado ainda o polimorfismo do gene do fator de transcrição FOXP3 e a expressão da proteína do ciclo celular P63 (P63) associados respectivamente a diagnóstico e prognóstico das lesões cervicais. Em um primeiro momento foi realizado estudo transversal que envolveu 3194 mulheres. As participantes foram submetidas à citologia e biópsia de colo dirigida por colposcopia e os resultados foram comparados para verificar-se a acurácia do teste de Papanicolaou na detecção de lesões intraepiteliais e câncer cervical. Posteriormente, realizou-se estudo comparativo do tipo observacional estratificado em três grupos: Grupo 1: 16 casos com diagnóstico histopatológico de metaplasia/cervicite, considerados normais, Grupo 2: 11 casos com lesão de baixo grau (LSIL) e Grupo 3: 15 casos com lesão de alto grau (HSIL) ou carcinoma epidermoide de colo. Um total de 42 participantes respondeu a um questionário epidemiológico padronizado sobre as características demográficas, hábitos pregressos, história reprodutiva e de comportamento sexual. Após exame colposcópico, foram coletados fragmentos de espécimes cervicais para a pesquisa da expressão proteica da P63 por imunohistoquímica. Amostras de sangue periférico foram coletadas para extração do DNA e detecção do polimorfismo do gene FOXP3. No primeiro estudo em que se avaliou a acurácia do teste de Papanicolaou, encontrou-se sensibilidade de 0,83, valor preditivo positivo (VPP) de 0,77 e especificidade de 0,23 no rastreamento das lesões cervicais e câncer de colo. viii Melhores resultados foram observados quando se avaliou a acurácia diagnóstica para lesões de alto grau e carcinoma com VPP de 0,99 e especificidade de 0,84.No estudo subsequente onde se comparou a expressão da proteína P63 observou-se maior número de núcleos marcados no grupo com lesões intraepiteliais de alto grau e câncer quando comparado ao grupo com biópsias negativas (p=0,0004). No último estudo pesquisou-se a associação do polimorfismo do gene FOXP3 com lesões intraepiteliais cervicais sendo evidenciada maior prevalência do genótipo heterozigoto, CT, no grupo com lesões de colo na histopatologia (p=0,027). Mulheres com lesões intraepiteliais de baixo ou alto grau e câncer de colo de útero apresentam maior expressão da proteína P63 e maior prevalência de genótipo heterozigoto do gene FOXP3 em comparação com as sem lesões cervicais. A associação da pesquisa da expressão da proteína e do polimorfismo do gene pode tornar os exames utilizados atualmente para a avaliação diagnóstica e prognóstica das lesões de colo uterino mais efetivos em detectar quais as mulheres com maior risco para progressão para câncer

Análise comparativa e teste empírico da validade dos modelos CAPM tradicional e condicional: o caso das ações da Petrobrás

ALVES, Janaína da Silva. Análise comparativa e teste empírico da validade dos modelos CAPM tradicional e condicional: o caso das ações da Petrobrás. Revista Ciências Administrativas, Fotaleza, v. 13, n. 1, p.147-157, ago. 2007.

Automação da drenagem no teste de produção convencional em tanque cilíndrico

This document aims to improve the quality of the production test in vertical tanks with free water drain pipes, through a device to control the draining system. This proposal consists of an interface detector close to the tank bottle and a control valve on the pipe-drain; they are attached to a remote supervisor system, which will be minimizing the human influence in the conclusion of the test result. And for more consciousness the work shows the importance of the wells production test in the attendance and diagnosis of the productive process, informing the large number of tests executed and problems of the procedure adopted in the field today. There are many possible sources of uncertainty in this kind of test as shown in the experiments realized in the field; the object prototype of this dissertation will be made in the field, based upon the definition of parameters and characteristics of the devices proposal. For a better definition of the draining process the action results of the assessment test are shown, especially changed some for the understand ing of the real process. It shows the proposal details and the configuration that will be used in the tank of Monte Alegre s field Production Station, explaining the interface detector kind and the control system. It is the base to a pilot project now in development, named as the new project classified in the status of the new technology and production improvement of PETROBRAS in Rio Grande do Norte and Ceará. This dissertation concludes that the automation of the conventional test with the draining system will bring benefits both economically as metrologically, because it reduces the uncertainty of the test procedures with free water draining, and also decreases the number of tests with problems

Avaliação do desenvolvimento neuropsicomotor em crianças na rede básica de saúde utilizando o teste de Denver II: identificação de fatores de risco materno

Alterations in the neuropsychomotor development of children are not rare and can manifest themselves with varying intensity at different stages of their development. In this context, maternal risk factors may contribute to the appearance of these alterations. A number of studies have reported that neuropsychomotor development diagnosis is not an easy task, especially in the basic public health network. Diagnosis requires effective, low-cost, and easy - to-apply procedures. The Denver Developmental Screening Test, first published in 1967, is currently used in several countries. It has been revised and renamed as the Denver II Test and meets the aforementioned criteria. Accordingly, the aim of this study was to apply the Denver II Test in order to verify the prevalence of suspected neuropsychomotor development delay in children between the ages of 0 and 12 months and correlate it with the following maternal risk factors: family income, schooling, age at pregnancy, drug use during pregnancy, gestational age, gestational problems, type of delivery and the desire to have children. For data collection, performed during the first 6 months of 2004, a clinical assessment was made of 398 children selected by pediatricians and the nursing team of each public health unit. Later, the parents or guardians were asked to complete a structured questionnaire to determine possible risk indicators of neuropsychomotor development delay. Finally the Denver II Developmental Screening Test (DDST) was applied. The data were analyzed together, using Statistical Package for Social Science (SPSS) software, version 6.1. The confidence interval was set at 95%. The Denver II Test yielded normal and questionable results. This suggests compromised neuropsychomotor development in the children examined and deserves further investigation. The correlation of the results with preestablished maternal risk variables (family income, mother s schooling, age at pregnancy, drug use during the pregnancy and gestational age) was strongly significant. The other maternal risk variables (gestational problems, type of delivery and desire to have children) were not significant. Using an adjusted logistic regression model, we obtained the estimate of the greater likelihood of a child having suspected neuropsychomotor development delay: a mother with _75 4 years of schooling, chronological age less than 20 years and a drug user during pregnancy. This study produced two manuscripts, one published in Acta Cirúrgica Brasileira , in which an analysis was performed of children with suspected neuropsychomotor development delay in the city of Natal, Brazil. The other paper (to be published) analyzed the magnitude of the independent variable maternal schooling associated to neuropsychomotor development delay, every 3 months during the first twelve months of life of the children selected.. The results of the present study reinforce the multifactorial characteristic of development and the cumulative effect of maternal risk factors, and show the need for a regional policy that promotes low-cost programs for the community, involving children at risk of neuropsychomotor development delay. Moreover, they suggest the need for better qualified health professionals in terms of monitoring child development. This was an inter- and multidisciplinary study with the integrated participation of doctors, nurses, nursing assistants and professionals from other areas, such as statisticians and information technology professionals, who met all the requirements of the Postgraduate Program in Health Sciences of the Federal University of Rio Grande do Norte

Sensibilidade da cinética do zinco e avaliação nutricional em crianças submetidas ao teste venoso de tolerância ao zinco

Objective: The purpose of this study was to investigate the kinetics of this micronutrient in schoolchildren between the ages of 6 and 9 years, of both sexes, and to verify its sensitivity in detecting alterations in body zinc status. Methods: Nutritional assessment was performed by body mass index. Food intake, venous zinc tolerance test and zinc kinetics were carried out before and after 3-month oral zinc supplementation. Results: Of the 42 children studied, 76.2% had healthy weight. Only energy, calcium and fiber intake were suboptimal before and after oral zinc supplementation. Serum zinc and total-body zinc clearance, although at normal levels, increased significantly after zinc supplementation. Conclusion: We concluded, therefore, that kinetics is a sensitive tool for detecting changes in body zinc status, even in children without a deficiency of this mineral. Furthermore, kinetics showed a positive response to supplementation and may be a sensitive parameter to evaluate the efficacy of this therapy

Elaboração e validade do teste de rastreio de doença da Alzheimer com provérbios (TRDAP) para indivíduos a partir de sessenta anos

A escassez de instrumentos para a avaliação e a triagem da doença de Alzheimer, (DA), notadamente denominados de rastreio, com características de padronização e validados para o Nordeste, motivou este Estudo. Visando à triagem de uma etapa mais leve da doença e encaminhamento precoce ao tratamento multidisciplinar foi elaborado o Teste de Rastreio da Doença de Alzheimer com Provérbios (TRDAP), a partir de um Jogo de Memória de Provérbios, construído como recurso terapêutico ocupacional. Está composto de três etapas conforme a função neuropsicológica avaliada, a A (memória de curto prazo), B (funções executivas e linguagem) e C (memória episódica), além do reconhecimento de provérbios. O Estudo foi realizado em uma amostra de conveniência, com 91 idosos (28 DA e 63 controles), a partir de 60 anos, com um ou mais anos de escolaridade. Foram controladas as variáveis, como doenças intercorrentes ou déficits sensoriais que pudessem comprometer o desempenho dos pacientes, nos testes. O protocolo constou de oito testes selecionados por especialistas: Miniexame do Estado Mental (para validade convergente), Escala de Depressão Geriátrica EDG (validade discriminante), Lista de Palavras, Fluência Verbal, Span de Dígitos, Figura Neuropsi, Teste do Relógio, Atividade de Vida Diária e Instrumental. Os resultados confirmaram a validade de construto convergente e discriminante, assim como a relação significativa (p<0,005) com todos os testes, exceto com o EDG. Quanto à validade concorrente, não houve discordância com o critério da avaliação médica observou-se consistência interna aceitável, conferindo confiabilidade no instrumento, o que não ocorreu com MEEM. Tais resultados permitem afirmar que o TRDAP possui características psicométricas, adequadas ao rastreio da fase leve da DA para população estudada

Estudo genético-clínico de mucopolissariodoses no estado do Ceará

As mucopolissacaridoses (MPS) são doenças genéticas raras decorrente da deficiência de enzimas lisossomais envolvidas no catabolismo de glicosaminoglicanos, resultando em um amplo espectro de manifestações clínicas, progressivas e multissistêmicas, exigindo tratamento por uma equipe multidisciplinar. Embora o Nordeste brasileiro seja uma região com grande taxa de consangüinidade e um efeito fundador envolvendo MPS, não há estudos caracterizando os pacientes dessa região. Nosso objetivo foi determinar o perfil epidemiológico, clínico e genético de casos não publicados com MPS provenientes do Ceará, identificando as diferenças entre outros estudos com MPS e possíveis problemas a serem enfrentados para a realização do diagnóstico precoce. O estudo foi seccional, descritivo, com amostra de pacientes com MPS em acompanhamento no Hospital Infantil Albert Sabin e Hospital Geral Cesar Cals no período de 2006-2013. Os dados foram obtidos a partir da avaliação clínica, revisão de prontuários médicos e entrevista com os pacientes e/ou familiares realizadas pelo investigador principal. Cinquenta e três pacientes foram incluídos no estudo (36 do sexo masculino), sendo 6 MPS I, 17 MPS II, 7 MPS III (3 MPSIII-A, 3 MPS III-B, 1 MPS III-C), 7 MPS IV-A, 16 de MPS VI. O óbito ocorreu em 16 casos (3 MPS I, MPS II 6, 1 MPS IIIA , IIIB 1MPS , 1 MPS IV , 4 MPS VI). A amostra foi composta principalmente por crianças. Houve elevada taxa de consangüinidade e recorrência familiar. Os tipos mais comuns foram MPS II e MPS VI. Exceto para macrossomia em MPS II, os dados de nascimento indicam que não houve risco para desenvolvimento de viii complicações perinatais. Os sintomas iniciaram em crianças com menos de 2 anos. As manifestações clínicas foram heterogêneas exceto para atraso no desenvolvimento neurológico em MPS III e manifestações esqueléticas em MPS IV. As principais características clínicas foram macrocefalia, baixa estatura, alterações odontológicas, respiratórias, cardíacas, hepatoesplenomegalia, hérnia umbilical, rigidez articular e anormalidades esqueléticas. A terapia de reposição enzimática foi instituída em 26 casos (4 MPS I, 10 MPS II, 12 MPS VI). Os problemas sócio-econômicos das famílias, o amplo espectro de sintomas e a gravidade da doença foram causas das dificuldades em realizar a avaliação periódica pela equipe multidisciplinar, além de exames complementares de maior custo para determinar as complicações da doença. Este foi o maior estudo transversal sobre MPS no Nordeste do Brasil. Em contraste com a maior incidência de MPS I na maioria das populações ocidentais, houve maior incidência de MPS II e VI. As alterações respiratórias foram um dos principais contribuintes para a mortalidade precoce, exceto nos casos de MPS I, em que a cardiomiopatia foi prevalente. A menor expectativa de vida ocorreu em MPS I. O envolvimento cognitivo foi comum em casos graves e o maior número de órgãos envolvidos representou maior risco de morrer. Para o diagnóstico precoce, deve-se buscar indivíduos afetados em famílias em que há parentes com MPS, além do maior reconhecimento de sinais e sintomas de MPS por profissionais de saúde

Aspectos de patogenicidade e relacionamento genético de isolados clínicos vaginas e anais de Candida albicans oriundos de pacientes com candidíase vulvovaginal

Vulvovaginal candidiasis (VVC) is one of the most common causes of vaginitis and affects about 75% of women of reproductive age. The majority of cases (80 to 90%) are due to C. albicans, the most virulent species of the genus Candida. Virulence attributes are scarcely investigated and the source of infection remains uncertain. Objective: This study aimed to evaluate the virulence factors and genotypes of clinical isolates of C. albicans sequentially obtained from the anus and vagina of patients with sporadic and recurrent VVC. Materials and methods: We analyzed 62 clinical isolates of C. albicans (36 vaginal and 26 anal strains). Direct examination of vaginal and anal samples and colony forming units (CFU) counts were performed. Yeasts were identified using the chromogenic media CHROMagar Candida® and by classical methodology, and phenotypically characterized regarding to virulence factors, including the ability to adhere to epithelial cells, proteinase activity, morphogenesis and biofilm formation. The genotypes of the strains were investigated with ABC genotyping, microsatellite genotyping with primer M13 and RAPD. Results: We found 100% agreement between direct examination and culture of vaginal samples. Filamentous forms were present in most of the samples of vaginal secretion, which presented CFU counts significantly higher than the samples of anal secretion. There was no statistically significant difference between virulence factors of infecting vaginal isolates and those presented by colonizing anal isolates; as well as for the comparison of the vaginal isolates from patients with different clinical conditions (sporadic or recurrent VVC). There was a decrease in the ability to adhere to HBEC, morphogenesis and biofilm formation of the vaginal isolates during the progress of infection. There was an association between the ability to express different virulence factors and the clinical manifestations presented by the patients. Genotype A was the most prevalent (93.6%), followed by genotype C (6.4%). We found maintenance of the same ABC genotype and greater prevalence of microevolution for the vaginal strains of C. albicans sequentially obtained. Vaginal and anal isolates of C. albicans obtained simultaneously from the same patient presented the same ABC genotype and high genetic relatedness. Conclusion: It is noteworthy that the proliferation of yeast and bud-to-hypha transition are important for the establishment of CVV. The expression of virulence factors is important for the pathogenesis of VVC, although it does not seem to be determinant in the transition from colonization to infection or to the installation of recurrent condition. Genotype A seems to be dominant over the others in both vaginal and anal isolates of patients with VVC. The most common scenario was microevolution of the strains of C. albicans in the vaginal environment. It is suggested that the anal reservoir constituted a possible source of vaginal infection, in most cases assessed

Uso sustentável da Copernicia prunifera (Miller) H. E Moore no semiárido potiguar: valorização de saberes e conservação dos recursos genéticos

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior

Acurácia do teste de labirinto no rastreamento de déficits cognitivos em idosos

This study intended to evaluate the maze test accuracy in cognitive deficit screening in elderly with or without neuropsychological pathology. The sample included 40 healthy young (18-25 years old; mean- 21 ± 1.6), 40 healthy old (60-77 years old; mean- 67 ± 5.1) and 18 patients with probable diagnosis of Alzheimer s disease initial stage (52-90 years old; mean- 78 ± 9.2). Data analysis was made using Anova with Tukey s post hoc, multiple linear regression analysis and ROC curve analysis. According to Tukey s test Alzheimer patients spent more time (46843 ± 37926 ms) to execute the test than healthy young (5482 ± 2873 ms; p= 0.0001) and elderly (17978 ± 13700; p= 0.0001); healthy young executed test n lower time (p= 0.035). According to the regression analysis of age, education level and cognitive performance of the three groups, the cognitive performance was the predictor of the execution time. When analyzing young and elderly only age was the predictor and the cognitive performance was the only factor to influence the test of old aged healthy and patients. The ROC curve analysis indicated 72% accuracy for young and elderly and 36% for healthy and elderly patients. The maze execution time represented a better balance between sensibility (75%) and the specificity (61%) was near 13575 ms, indicating that those subjects that execute the maze in a time higher to this value may show cognitive deficit related to the executive function. According to the results it is suggested that the maze test used in this study shows a good accuracy in the cognitive deficit tracking and may discriminate age changes

Busca heurística através de algoritmo genético e memético com construção de vocábulos para o problema de atribuição de localidades a anéis Sonet

Telecommunications play a key role in contemporary society. However, as new technologies are put into the market, it also grows the demanding for new products and services that depend on the offered infrastructure, making the problems of planning telecommunications networks, despite the advances in technology, increasingly larger and complex. However, many of these problems can be formulated as models of combinatorial optimization, and the use of heuristic algorithms can help solving these issues in the planning phase. In this project it was developed two pure metaheuristic implementations Genetic algorithm (GA) and Memetic Algorithm (MA) plus a third hybrid implementation Memetic Algorithm with Vocabulary Building (MA+VB) for a problem in telecommunications that is known in the literature as Problem SONET Ring Assignment Problem or SRAP. The SRAP arises during the planning stage of the physical network and it consists in the selection of connections between a number of locations (customers) in order to meet a series of restrictions on the lowest possible cost. This problem is NP-hard, so efficient exact algorithms (in polynomial complexity ) are not known and may, indeed, even exist

Algoritmo Q-learning como estratégia de exploração e/ou explotação para metaheurísticas GRASP e algoritmo genético

Techniques of optimization known as metaheuristics have achieved success in the resolution of many problems classified as NP-Hard. These methods use non deterministic approaches that reach very good solutions which, however, don t guarantee the determination of the global optimum. Beyond the inherent difficulties related to the complexity that characterizes the optimization problems, the metaheuristics still face the dilemma of xploration/exploitation, which consists of choosing between a greedy search and a wider exploration of the solution space. A way to guide such algorithms during the searching of better solutions is supplying them with more knowledge of the problem through the use of a intelligent agent, able to recognize promising regions and also identify when they should diversify the direction of the search. This way, this work proposes the use of Reinforcement Learning technique - Q-learning Algorithm - as exploration/exploitation strategy for the metaheuristics GRASP (Greedy Randomized Adaptive Search Procedure) and Genetic Algorithm. The GRASP metaheuristic uses Q-learning instead of the traditional greedy-random algorithm in the construction phase. This replacement has the purpose of improving the quality of the initial solutions that are used in the local search phase of the GRASP, and also provides for the metaheuristic an adaptive memory mechanism that allows the reuse of good previous decisions and also avoids the repetition of bad decisions. In the Genetic Algorithm, the Q-learning algorithm was used to generate an initial population of high fitness, and after a determined number of generations, where the rate of diversity of the population is less than a certain limit L, it also was applied to supply one of the parents to be used in the genetic crossover operator. Another significant change in the hybrid genetic algorithm is the proposal of a mutually interactive cooperation process between the genetic operators and the Q-learning algorithm. In this interactive/cooperative process, the Q-learning algorithm receives an additional update in the matrix of Q-values based on the current best solution of the Genetic Algorithm. The computational experiments presented in this thesis compares the results obtained with the implementation of traditional versions of GRASP metaheuristic and Genetic Algorithm, with those obtained using the proposed hybrid methods. Both algorithms had been applied successfully to the symmetrical Traveling Salesman Problem, which was modeled as a Markov decision process

Um sistema para estimação da vazão de gás de poços produzindo por Plunger Lift para vaso separador de teste em plataformas de petróleo

This work intends to analyze the behavior of the gas flow of plunger lift wells producing to well testing separators in offshore production platforms to aim a technical procedure to estimate the gas flow during the slug production period. The motivation for this work appeared from the expectation of some wells equipped with plunger lift method by PETROBRAS in Ubarana sea field located at Rio Grande do Norte State coast where the produced fluids measurement is made in well testing separators at the platform. The oil artificial lift method called plunger lift is used when the available energy of the reservoir is not high enough to overcome all the necessary load losses to lift the oil from the bottom of the well to the surface continuously. This method consists, basically, in one free piston acting as a mechanical interface between the formation gas and the produced liquids, greatly increasing the well s lifting efficiency. A pneumatic control valve is mounted at the flow line to control the cycles. When this valve opens, the plunger starts to move from the bottom to the surface of the well lifting all the oil and gas that are above it until to reach the well test separator where the fluids are measured. The well test separator is used to measure all the volumes produced by the well during a certain period of time called production test. In most cases, the separators are designed to measure stabilized flow, in other words, reasonably constant flow by the use of level and pressure electronic controllers (PLC) and by assumption of a steady pressure inside the separator. With plunger lift wells the liquid and gas flow at the surface are cyclical and unstable what causes the appearance of slugs inside the separator, mainly in the gas phase, because introduce significant errors in the measurement system (e.g.: overrange error). The flow gas analysis proposed in this work is based on two mathematical models used together: i) a plunger lift well model proposed by Baruzzi [1] with later modifications made by Bolonhini [2] to built a plunger lift simulator; ii) a two-phase separator model (gas + liquid) based from a three-phase separator model (gas + oil + water) proposed by Nunes [3]. Based on the models above and with field data collected from the well test separator of PUB-02 platform (Ubarana sea field) it was possible to demonstrate that the output gas flow of the separator can be estimate, with a reasonable precision, from the control signal of the Pressure Control Valve (PCV). Several models of the System Identification Toolbox from MATLAB® were analyzed to evaluate which one better fit to the data collected from the field. For validation of the models, it was used the AIC criterion, as well as a variant of the cross validation criterion. The ARX model performance was the best one to fit to the data and, this way, we decided to evaluate a recursive algorithm (RARX) also with real time data. The results were quite promising that indicating the viability to estimate the output gas flow rate from a plunger lift well producing to a well test separator, with the built-in information of the control signal to the PCV

Análise comparativa do desempenho de um Controlador Fuzzy acoplado a um PID Neural sintonizado por um Algoritmo Genético com Controladores Inteligentes Convencionais

On this paper, it is made a comparative analysis among a controller fuzzy coupled to a PID neural adjusted by an AGwith several traditional control techniques, all of them applied in a system of tanks (I model of 2nd order non lineal). With the objective of making possible the techniques involved in the comparative analysis and to validate the control to be compared, simulations were accomplished of some control techniques (conventional PID adjusted by GA, Neural PID (PIDN) adjusted by GA, Fuzzy PI, two Fuzzy attached to a PID Neural adjusted by GA and Fuzzy MISO (3 inputs) attached to a PIDN adjusted by GA) to have some comparative effects with the considered controller. After doing, all the tests, some control structures were elected from all the tested techniques on the simulating stage (conventional PID adjusted by GA, Fuzzy PI, two Fuzzy attached to a PIDN adjusted by GA and Fuzzy MISO (3 inputs) attached to a PIDN adjusted by GA), to be implemented at the real system of tanks. These two kinds of operation, both the simulated and the real, were very important to achieve a solid basement in order to establish the comparisons and the possible validations show by the results

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