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

Comparative study between RBF and radial-PPS neural networks

The study of function approximation is motivated by the human limitation and inability to register and manipulate with exact precision the behavior variations of the physical nature of a phenomenon. These variations are referred to as signals or signal functions. Many real world problem can be formulated as function approximation problems and from the viewpoint of artificial neural networks these can be seen as the problem of searching for a mapping that establishes a relationship from an input space to an output space through a process of network learning. Several paradigms of artificial neural networks (ANN) exist. Here we will be investigated a comparative of the ANN study of RBF with radial Polynomial Power of Sigmoids (PPS) in function approximation problems. Radial PPS are functions generated by linear combination of powers of sigmoids functions. The main objective of this paper is to show the advantages of the use of the radial PPS functions in relationship traditional RBF, through adaptive training and ridge regression techniques.

A DOE based approach for the design of RBF artificial neural networks applied to prediction of surface roughness in AISI 52100 hardened Steel turning

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

RBF circuits based on folded cascode differential pairs

We propose new circuits for the implementation of Radial Basis Functions such as Gaussian and Gaussian-like functions. These RBFs are obtained by the subtraction of two differential pair output currents in a folded cascode configuration. We also propose a multidimensional version based on the unidimensional circuits. SPICE simulation results indicate good functionality. These circuits are intended to be applied in the implementation of radial basis function networks. One possible application of these networks is transducer signal conditioning in aircraft and spacecraft vehicles onboard telemetry systems. Copyright 2008 ACM.

Tracking of non-stationary time-series using resource allocating RBF networks

In this paper, we discuss some practical implications for implementing adaptable network algorithms applied to non-stationary time series problems. Using electricity load data and training with the extended Kalman filter, we demonstrate that the dynamic model-order increment procedure of the resource allocating RBF network (RAN) is highly sensitive to the parameters of the novelty criterion. We investigate the use of system noise and forgetting factors for increasing the plasticity of the Kalman filter training algorithm, and discuss the consequences for on-line model order selection. We also find that a recently-proposed alternative novelty criterion, found to be more robust in stationary environments, does not fare so well in the non-stationary case due to the need for filter adaptability during training.

Efficient training of RBF networks for classification.

Radial Basis Function networks with linear outputs are often used in regression problems because they can be substantially faster to train than Multi-layer Perceptrons. For classification problems, the use of linear outputs is less appropriate as the outputs are not guaranteed to represent probabilities. We show how RBFs with logistic and softmax outputs can be trained efficiently using the Fisher scoring algorithm. This approach can be used with any model which consists of a generalised linear output function applied to a model which is linear in its parameters. We compare this approach with standard non-linear optimisation algorithms on a number of datasets.

Efficient training of RBF networks for classification

Radial Basis Function networks with linear outputs are often used in regression problems because they can be substantially faster to train than Multi-layer Perceptrons. For classification problems, the use of linear outputs is less appropriate as the outputs are not guaranteed to represent probabilities. In this paper we show how RBFs with logistic and softmax outputs can be trained efficiently using algorithms derived from Generalised Linear Models. This approach is compared with standard non-linear optimisation algorithms on a number of datasets.

Simultaneous Control of Chaotic Systems Using RBF Networks

Chaos control is a concept that recently acquiring more attention among the research community, concerning the fields of engineering, physics, chemistry, biology and mathematic. This paper presents a method to simultaneous control of deterministic chaos in several nonlinear dynamical systems. A radial basis function networks (RBFNs) has been used to control chaotic trajectories in the equilibrium points. Such neural network improves results, avoiding those problems that appear in other control methods, being also efficient dealing with a relatively small random dynamical noise.

Pain Intensity And Cervical Range Of Motion In Women With Myofascial Pain Treated With Acupuncture And Electroacupuncture: A Double-blinded, Randomized Clinical Trial.

Acupuncture stimulates points on the body, influencing the perception of myofascial pain or altering physiologic functions. The aim was to evaluate the effect of electroacupuncture (EAC) and acupuncture (AC) for myofascial pain of the upper trapezius and cervical range of motion, using SHAM acupuncture as control. Sixty women presenting at least one trigger point at the upper trapezius and local or referred pain for more than six months were randomized into EAC, AC, and SHAM groups. Eight sessions were scheduled and a follow-up was conducted after 28 days. The Visual Analog Scale assessed the intensity of local and general pain. A fleximeter assessed cervical movements. Data were analyzed using paired t or Wilcoxon's tests, ANOVA or Friedman or Kruskal-Wallis tests and Pearson's correlation (α=0.05). There was reduction in general pain in the EAC and AC groups after eight sessions (P<0.001). A significant decrease in pain intensity occurred for the right trapezius in all groups and for the left trapezius in the EAC and AC groups. Intergroup comparisons showed improvement in general pain in the EAC and AC groups and in local pain intensity in the EAC group (P<0.05), which showed an increase in left rotation (P=0.049). The AC group showed increases in inclination (P=0.005) sustained until follow-up and rotation to the right (P=0.032). EAC and AC were effective in reducing the pain intensity compared with SHAM. EAC was better than AC for local pain relief. These treatments can assist in increasing cervical range of motion, albeit subtly.

Sensitivity and specificity of machine learning classifiers for glaucoma diagnosis using Spectral Domain OCT and standard automated perimetry

PURPOSE: To evaluate the sensitivity and specificity of machine learning classifiers (MLCs) for glaucoma diagnosis using Spectral Domain OCT (SD-OCT) and standard automated perimetry (SAP). METHODS: Observational cross-sectional study. Sixty two glaucoma patients and 48 healthy individuals were included. All patients underwent a complete ophthalmologic examination, achromatic standard automated perimetry (SAP) and retinal nerve fiber layer (RNFL) imaging with SD-OCT (Cirrus HD-OCT; Carl Zeiss Meditec Inc., Dublin, California). Receiver operating characteristic (ROC) curves were obtained for all SD-OCT parameters and global indices of SAP. Subsequently, the following MLCs were tested using parameters from the SD-OCT and SAP: Bagging (BAG), Naive-Bayes (NB), Multilayer Perceptron (MLP), Radial Basis Function (RBF), Random Forest (RAN), Ensemble Selection (ENS), Classification Tree (CTREE), Ada Boost M1(ADA),Support Vector Machine Linear (SVML) and Support Vector Machine Gaussian (SVMG). Areas under the receiver operating characteristic curves (aROC) obtained for isolated SAP and OCT parameters were compared with MLCs using OCT+SAP data. RESULTS: Combining OCT and SAP data, MLCs' aROCs varied from 0.777(CTREE) to 0.946 (RAN).The best OCT+SAP aROC obtained with RAN (0.946) was significantly larger the best single OCT parameter (p<0.05), but was not significantly different from the aROC obtained with the best single SAP parameter (p=0.19). CONCLUSION: Machine learning classifiers trained on OCT and SAP data can successfully discriminate between healthy and glaucomatous eyes. The combination of OCT and SAP measurements improved the diagnostic accuracy compared with OCT data alone.

Avaliação da influência de substâncias fenólicas e carotenoides na anomalia do epicarpo da goiaba, "anelamento"

A anomalia do epicarpo da goiaba, comumente relatada por agricultores e técnicos como o "anelamento juvenil da goiaba", tem causado preocupação devido à desinformação sobre o assunto. O objetivo deste estudo foi analisar quimicamente as concentrações de substâncias fenólicas e carotenoides na região do epicarpo de goiabas afetadas pelo "anelamento", visando a caracterizar essa anomalia previamente relatada. Foram analisadas substâncias fenólicas (taninos, flavonas/flavonóis, antocianinas e fenóis totais) e carotenoides em epicarpos de frutos verdes e maduros de goiabeiras cv. Paluma, com e sem anomalia. O delineamento experimental adotado foi o inteiramente casualizado, sendo estabelecidos seis tratamentos com o epicarpo dos frutos maduro sem anomalia na região inferior (FMSI); frutos maduros sem injuria na região superior (FMSS); frutos verdes sem anomalia na região inferior (FVSI); frutos verdes sem anomalia na região superior (FVSS); frutos verdes com anomalia na região inferior (FVCI); frutos verdes com anomalia na região superior (FVCS). Dentre as substâncias analisadas, os carotenoides, os taninos e os fenóis totais mostram indicativos para a caracterização do anelamento. Tanto substâncias fenólicas quanto carotenoides apresentam propriedades antioxidantes e, dessa forma, poderiam estar relacionadas à defesa antioxidante causada por um fator de estresse ainda desconhecido, que promove o "anelamento" característico apresentado pelas goiabas.

Caracterização físico-química de polpas de frutos da Amazônia e sua correlação com a atividade anti-radical livre

Características físico-químicas (cor, pH, acidez total titulável, sólidos solúveis totais, conteúdo de lipídios e umidade) e níveis de compostos bioativos (ácido ascórbico, fenólicos totais) foram determinados em quinze amostras de polpas de frutos procedentes da região Amazônica (abiu, acerola, açaí, araçá-boi, bacaba, bacuri, buriti, cajá, cajarana, caju, cupuaçu, graviola, murici, noni e tamarindo). A atividade de radicais livres foi avaliada pelo método de ABTS. Algumas polpas apresentaram alta potencialidade antioxidante, associada com a atividade antirradicais livres obtida e os conteúdos dos componentes bioativos como compostos fenólicos e ácido ascórbico, destacando-se acerola e acaí. O conteúdo total de compostos fenólicos foi correlacionado à capacidade antioxidante das polpas.

Utilização de técnicas estatísticas em duas revistas de fruticultura

Neste trabalho são descritas as técnicas de análise estatística utilizadas e a acessibilidade estatística em uma amostra dos artigos originais publicados no período 1996-2006 em duas revistas de pesquisa na área de fruticultura: a Revista Brasileira de Fruticultura (RBF) e a revista francesa Fruits. No total foram classificados 986 artigos em 16 categorias de análise estatística, ordenadas em grau ascendente de complexidade. No período analisado, foi constatado um aumento no uso de análises mais sofisticadas ao longo do tempo em ambos as revistas. Os trabalhos publicados pela RBF aplicaram com maior freqüência técnicas estatísticas mais complexas, com maior utilização de delineamentos em blocos aleatorizados, arranjos fatoriais, parcelas subdivididas e modelos hierárquicos, e do teste de Tukey para comparações múltiplas de médias. Nos trabalhos publicados pela revista Fruits, predominou o uso de outros testes paramétricos e do teste de Duncan. O pacote estatístico SAS foi o mais utilizado nos artigos publicados em ambas as revistas. Os leitores da revista RBF precisaram de um nível de conhecimento estatístico mais elevado para ter acesso à maior parte dos artigos publicados no período, em comparação com os leitores da revista francesa.

Influence of respiratory biofeedback associated to re-expansive ventilation patterns in individuals with functional mouth breathing

Objectives: Assess the effect of re-expansive respiratory patterns associated to respiratory biofeedback (RBF) on pulmonary function, respiratory muscle strength and habits in individuals with functional mouth breathing (FMB). Methods: Sixty children with FMB were divided into experimental and control groups. The experimental group was submitted to 15 sessions of re-expansive respiratory patterns associated to RBF (biofeedback pletsmovent; MICROHARD (R) V1.0), which provided biofeedback of the thoracic and abdominal movements. The control group was submitted to 15 sessions using biofeedback alone. Spirometry, maximum static respiratory pressure measurements and questions regarding habits (answered by parents/guardians) were carried out before and after therapy. The Student`s t-test for paired data and non-parametric tests were employed for statistical analysis at a 5% Level of significance. Results: Significant changes were found in forced vital. capacity, Tiffeneau index scores, maximum expiratory pressure, maximum inspiratory pressure and habits assessed in FMB with the use of RBF associated to the re-expansive patterns. No significant differences were found comparing the experimental and control groups. Conclusions: The results allow the conclusion that RBF associated to re-expansive patterns improves forced vital capacity, Tiffeneau index scores, respiratory muscle strength and habits in FMB and can therefore be used as a form of therapy for such individuals. (C) 2008 Elsevier Ireland Ltd. All rights reserved.

Effects of Nicotine Exposure on Renal Function of Normal and Hypercholesterolemic Rats

Background/Aims: Renal risks of nicotine exposure associated with hypercholesterolemia are still unknown. Methods: Thus, hypercholesterolemic rats (HC) and their control (C) were evaluated by inulin clearance (InCl) measured at baseline and during nicotine infusion (100 mu g/kg b.w.). Five groups were studied: (i) C; (ii) DEN (C submitted to a renal denervation); (iii) C + L-arginine (0.25% in drinking water); (iv) HC, and (v) HC + L-arginine (0.25% in drinking water). Furthermore, C and HC had their renal blood flow (RBF) measured and they have also been chronically treated with nicotine (12.5 mu g/ml in drinking water) to assess InCl on the 8th day. Results: Nicotine increased blood pressure in C, DEN and HC and reduced InCl only in C. L-Arginine treatment blunted nicotine effects on blood pressure and increased InCl only in C. Moreover, nicotine did not change RBF in C but elicited in HC, whereas renal vascular resistance was increased in C and unchanged in HC. Indeed, chronic nicotine exposure has also reduced InCl in C. Conclusion: Nicotine acted on the adrenergic system and nitric oxide counteracted this action in C, but the same may not be applied to HC. An impairment in renal autoregulation may explain why InCl was unchanged in HC. Copyright (C) 2009 S. Karger AG, Basel