Identificação não linear usando uma rede fuzzy wavelet neural network modificada

In last decades, neural networks have been established as a major tool for the identification of nonlinear systems. Among the various types of networks used in identification, one that can be highlighted is the wavelet neural network (WNN). This network combines the characteristics of wavelet multiresolution theory with learning ability and generalization of neural networks usually, providing more accurate models than those ones obtained by traditional networks. An extension of WNN networks is to combine the neuro-fuzzy ANFIS (Adaptive Network Based Fuzzy Inference System) structure with wavelets, leading to generate the Fuzzy Wavelet Neural Network - FWNN structure. This network is very similar to ANFIS networks, with the difference that traditional polynomials present in consequent of this network are replaced by WNN networks. This paper proposes the identification of nonlinear dynamical systems from a network FWNN modified. In the proposed structure, functions only wavelets are used in the consequent. Thus, it is possible to obtain a simplification of the structure, reducing the number of adjustable parameters of the network. To evaluate the performance of network FWNN with this modification, an analysis of network performance is made, verifying advantages, disadvantages and cost effectiveness when compared to other existing FWNN structures in literature. The evaluations are carried out via the identification of two simulated systems traditionally found in the literature and a real nonlinear system, consisting of a nonlinear multi section tank. Finally, the network is used to infer values of temperature and humidity inside of a neonatal incubator. The execution of such analyzes is based on various criteria, like: mean squared error, number of training epochs, number of adjustable parameters, the variation of the mean square error, among others. The results found show the generalization ability of the modified structure, despite the simplification performed

Análise estrutural e avaliação do efeito condroitim sulfato extraído de tilápia (Oreochromis niloticus) em modelo de peritonite aguda

Chondroitin sulfate (CS) is a naturally glycosaminoglycan found in the extracellular matrix of connective tissues and it may be extracted and purified those tissues. CS is involved in various biological functions, which may be related to the having structural variability, despite the simplicity of the linear chain structure from this molecule. Researches in biotechnology and pharmaceutical field with wastes from aquaculture has been developed in Brazil. In recent decades, tilapia (Oreochromis niloticus), native fish from Africa, has been one of the most cultivated species in various regions of the world, including Brazil. The tilapia farming is a cost-effective activity, however, it generates large amount of wastes that are discarded by producers. It is understood that waste from tilapia can be used in research as a source of molecules with important biotechnological applications, which also helps in reducing environmental impacts and promote the development of an ecofriendly activity. Thus, nile tilapia viscera were subjected to proteolysis, then the glycosaminoglycans were complexed with ion exchange resin (Lewatit), it was fractionated with increasing volumes of acetone and purified by ion exchange chromatography DEAE-Sephacel. Further, the fraction was analyzed by agarose gel electrophoresis and nuclear magnetic resonance (NMR). The electrophoretic profile of the compound together the analysis of 1H NMR spectra and the HSQC correlation allow to affirm that the compound corresponds to a molecule like chondroitin sulfate. MTT assay was used to assess cell viability in the presence of CS tilapia isolated and showed that the compound is not cytotoxic to normal cells such as cells from the mouse embryo fibroblast (3T3). Then, this compound was tested for the ability to reduce the influx of leukocytes in model of acute peritonitis (in vivo) induced by sodium thioglycolate. In this context, it was done total and differential leukocytes counting in the blood and peritoneal fluid collected respectively from vena cava and the peritoneal cavity of the animals subjected to the experiment. The chondroitin sulfate for the first time isolated from tilapia (CST ) was able to reduce the migration of leukocytes to the peritoneal cavity of inflamed mice until 80.4 per cent at a dose 10µg/kg. The results also show that there was a significant reduction (p<0.001) of the population of polymorphonuclear leukocytes from peritoneal cavity in the three tested doses (0.1µg/kg; 1µg/kg and 10µg/kg) when it was compared to the positive control (just thioglycolate). Therefore, since the CST structure and mechanism of action has been completely elucidated, this compound may have potential for therapeutic use in inflammatory diseases