Modelo neuro-evolutivo de coordenação adaptativa em ambientes dinâmicos

Em ambientes dinâmicos e complexos, a política ótima de coordenação não pode ser derivada analiticamente, mas, deve ser aprendida através da interação direta com o ambiente. Geralmente, utiliza-se aprendizado por reforço para prover coordenação em tais ambientes. Atualmente, neuro-evolução é um dos métodos de aprendizado por reforço mais proeminentes. Em vista disto, neste trabalho, é proposto um modelo de coordenação baseado em neuro-evolução. Mais detalhadamente, desenvolveu-se uma extensão do método neuro-evolutivo conhecido como Enforced Subpopulations (ESP). Na extensão desenvolvida, a rede neural que define o comportamento de cada agente é totalmente conectada. Adicionalmente, é permitido que o algoritmo encontre, em tempo de treinamento, a quantidade de neurônios que deve estar presente na camada oculta da rede neural de cada agente. Esta alteração, além de oferecer flexibilidade na definição da topologia da rede de cada agente e diminuir o tempo necessário para treinamento, permite também a constituição de grupos de agentes heterogêneos. Um ambiente de simulação foi desenvolvido e uma série de experimentos realizados com o objetivo de avaliar o modelo proposto e identificar quais os melhores valores para os diversos parâmetros do modelo. O modelo proposto foi aplicado no domínio das tarefas de perseguição-evasão.

Modeling of optoelectronic devices through neuro-fuzzy architectures

The advantages offered by the electronic component LED (Light Emitting Diode) have caused a quick and wide application of this device in replacement of incandescent lights. However, in its combined application, the relationship between the design variables and the desired effect or result is very complex and it becomes difficult to model by conventional techniques. This work consists of the development of a technique, through comparative analysis of neuro-fuzzy architectures, to make possible to obtain the luminous intensity values of brake lights using LEDs from design data.

Weight and neuro-psycho-motor development in children discharged from neonatal intensive care unit

Background: Low birth weight affects child growth and development, requiring the intensive use of health services. There are conversely proportional associations between prematurity and academic performance around the world. In this study we evaluated factors involved in weight and neuropsychomotor profile in one and two years old discharged from Intensive Care Units (ICU).Methods/Design: We investigated 203 children from the ICU who were followed for 24 +/- 4 months. The research was conducted by collecting data from medical records of patients in a Follow-up program. We investigated the following variables: inadequate weight at one year old; inadequate weight at two years old and a severe neurological disorder at two years old.Results: We observed increase of almost 20% in the proportion of children which weighted between the 10th and 90th percentiles and decrease of around 40% of children below the 15th percentile, from one to two years old. In almost 60% of the cases neuropsychomotor development was normal at 2 years old, less than 15% of children presented abnormal development. Variables that remained influential for clinical outcome at 1 and 2 years old were related to birth weight and gestational age, except for hypoglycemia. Neurological examination was the most influential variable for severe neurological disturbance.Conclusion: Hypoglycemia was considered a new fact to explain inadequate weight. The results, new in Brazil and difficult in terms of comparison, could be used to identify risk factors and for a better approach of newborn discharged from ICUs.

Ação neuro-muscular do veneno crotálico: dados preliminares

Estudamos 6 pacientes, 2 cães e um coelho com intoxicação crotálica. Avaliamos a condução nervosa periférica sensitiva e motora, a transmissão neuromuscular e eletromiografias. As biópsias de músculo foram processadas por histoquímica. Os 6 pacientes apresentaram mononeuropatia sensitiva no nervo periférico adjacente ao local da inoculação do veneno e encontramos evidências histoquímicas de miopatia mitocondrial. Os defeitos da transmissão neuromuscular foram mínimos. A maioria dos autores admite que veneno crotálico determina síndrome miastênica. Nossos achados indicam que ptose palpebral, facies miastênico e fraqueza muscular observados após acidente crotálico, correspondem provavelmente a miopatia mitocondrial, muitas vezes transitória e reversível.

Genética e linguagem na síndrome de Williams-Beuren: uma condição neuro-cognitiva peculiar

TEMA: aspectos genéticos, cognitivos e de linguagem na Síndrome de Williams-Beuren (SWB). OBJETIVO: revisar a literatura sobre a SWB, destacando aspectos genéticos, cognitivos e de linguagem. CONCLUSÕES: a literatura mostrou que a etiologia da SWB é conhecida, embora o diagnóstico precoce pode ser difícil pela variabilidade de manifestações clínicas dessa condição. O fenótipo variável tem sido atribuído a deleção de vários genes na região 7q11.23. que inclui o gene da elastina. A deleção desse gene é identificada pelo estudo citogenético molecular denominado Hibridização in situ por Fluorescência (FISH). A freqüência populacional desta síndrome é de 1 em 20,000 nascimentos e é resultante de uma alteração genética de novo. O quadro da SWB é caracterizado principalmente por fácies típica conhecida como face de duende, alterações cardíacas, prejuízos cognitivos e aspectos comportamentais que incluem a linguagem. A característica falante e sociável associada as dificuldades viso-construtivas conferem a esta síndrome um quadro neuro-cognitivo peculiar. A deficiência mental é variável e pode ou não estar presente. Estudos que descreveram as habilidades de linguagem nesta síndrome destacaram que a habilidade sintática pode estar íntegra ou parcialmente íntegra, a produção verbal pode ser precisa e inteligível, mostrando a integridade do sistema fonológico. O vocabulário receptivo-auditivo é citado em alguns estudos como adequado e em outros como prejudicado para a idade mental. Pesquisas na área têm produzido, resultados incongruentes com respeito ao perfil de habilidades cognitivas e lingüísticas nos portadores dessa condição. A correlação entre as habilidades de linguagem e a cognição e a divergência de achados na literatura serão abordadas neste artigo.

Design of a simplified neuro-fuzzy system based on CMAC Architectures

This work presents the design of a fuzzy controller with simplified architecture that use an artificial neural network working as the aggregation operator for several active fuzzy rules. The simplified architecture of the fuzzy controller is used to minimize the time processing used in the closed loop system operation, the basic procedures of fuzzification are simplified to maximum while all the inference procedures are computed in a private way. As consequence, this simplified architecture allows a fast and easy configuration of the simplified fuzzy controller. The structuring of the fuzzy rules that define the control actions is previously computed using an artificial neural network based on CMAC Cerebellar Model Articulation Controller. The operational limits are standardized and all the control actions are previously calculated and stored in memory. For applications, results and conclusions several configurations of this fuzzy controller are considered.

Multivalued adaptive neuro-fuzzy controller for robot vehicle - art. no. 1406

Robotic vehicle navigation in unstructured and uncertain environments is still a challenge. This paper presents the implementation of a multivalued neurofuzzy controller for autonomous ground vehicle (AGVs) in indoor environments. The control system consists of a hierarchy of mobile robot using multivalued adaptive neuro-fuzzy inference system behaviors.

Adenocarcinoma de cólon com diferenciação neuro-endócrina e escamosa. Relato de caso.

A tubular adenocarcinoma of the colon with solid area composed by small cells that was found by immunohistochemistry study using antibody to neuron-specific enolase (NSE) to possess neuroendocrine differentiation is related. In another areas of the tumor were visualized keratinizing squamous cells. The presence of neuro-endocrine and squamous cells features provide further evidence that neoplastic colonic cells have the capacity for multi-directional differentiation. The implications of this combination in relation to theories of tumor origin and differentiation and the prognostic significance of neuro-endocrine cells in malignant neoplasms of the gastrointestinal tract are discussed.

Applying a genetic neuro-model reference adaptive controller in drilling optimization

Motivated by rising drilling operation costs, the oil industry has shown a trend toward real-time measurements and control. In this scenario, drilling control becomes a challenging problem for the industry, especially due to the difficulty associated with parameters modeling. One of the drillbit performance evaluators, the Rate Of Penetration (ROP), has been used as a drilling control parameter. However, relationships between operational variables affecting the ROP are complex and not easily modeled. This work presents a neuro-genetic adaptive controller to treat this problem. It is based on an auto-regressive with extra input signals, or ARX model and on a Genetic Algorithm (GA) to control the ROP. © [2006] IEEE.

A genetic neuro-model reference adaptive controller for petroleum wells drilling operations

Motivated by rising drilling operation costs, the oil industry has shown a trend towards real-time measurements and control. In this scenario, drilling control becomes a challenging problem for the industry, especially due to the difficulty associated to parameters modeling. One of the drill-bit performance evaluators, the Rate of Penetration (ROP), has been used in the literature as a drilling control parameter. However, the relationships between the operational variables affecting the ROP are complex and not easily modeled. This work presents a neuro-genetic adaptive controller to treat this problem. It is based on the Auto-Regressive with Extra Input Signals model, or ARX model, to accomplish the system identification and on a Genetic Algorithm (GA) to provide a robust control for the ROP. Results of simulations run over a real offshore oil field data, consisted of seven wells drilled with equal diameter bits, are provided. © 2006 IEEE.

Traffic flow breakdown prediction using feature reduction through Rough-Neuro fuzzy Networks

The prediction of the traffic behavior could help to make decision about the routing process, as well as enables gains on effectiveness and productivity on the physical distribution. This need motivated the search for technological improvements in the Routing performance in metropolitan areas. The purpose of this paper is to present computational evidences that Artificial Neural Network ANN could be use to predict the traffic behavior in a metropolitan area such So Paulo (around 16 million inhabitants). The proposed methodology involves the application of Rough-Fuzzy Sets to define inference morphology for insertion of the behavior of Dynamic Routing into a structured rule basis, without human expert aid. The dynamics of the traffic parameters are described through membership functions. Rough Sets Theory identifies the attributes that are important, and suggest Fuzzy relations to be inserted on a Rough Neuro Fuzzy Network (RNFN) type Multilayer Perceptron (MLP) and type Radial Basis Function (RBF), in order to get an optimal surface response. To measure the performance of the proposed RNFN, the responses of the unreduced rule basis are compared with the reduced rule one. The results show that by making use of the Feature Reduction through RNFN, it is possible to reduce the need for human expert in the construction of the Fuzzy inference mechanism in such flow process like traffic breakdown. © 2011 IEEE.

Rede Neuro-Fuzzy-Wavelet para detecção e classificação de anomalias de tensão em sistemas elétricos de potência

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Modelos computacionais fuzzy e neuro-fuzzy para avaliarem os efeitos da poluição do ar

Pós-graduação em Engenharia Mecânica - FEG