This paper presents models that can be used in the design of microstrip antennas for mobile communications. The antennas can be triangular or rectangular. The presented models are compared with deterministic and empirical models based on artificial neural networks (ANN) presented in the literature. The models are based on Perceptron Multilayer (PML) and Radial Basis Function (RBF) ANN. RBF based models presented the best results. Also, the models can be embedded in CAD systems, in order to design microstrip antennas for mobile communications.
Neste artigo, os sinais de temperatura ambiente e de carregamento de transformadores de distribuição imersos em óleo são aplicados em uma arquitetura de redes neurais artificiais com o objetivo de estimar a temperatura interna destes transformadores. A arquitetura da rede neural utilizada nesta aplicação é do tipo perceptron multicamadas. O treinamento da rede foi realizado através do algoritmo de retropropagação denominado ''Resilient Propagation'' e foi baseado em dados de projeto e de ensaios de transformadores de distribuição imersos em óleo. Resultados de simulação da abordagem proposta indicam que esta metodologia pode ser utilizada eficientemente nos processos de proteção de transformadores, incrementando a seletividade, confiabilidade e o gerenciamento da rede de distribuição. In this paper, the ambient temperature values and load signals are applied in an architecture of artificial neural network with the objective of estimating the internal temperature of oil-immersed distribution transformers. The architecture of neural network used in this application is a multilayer perceptron. The training of the network was carried-out using the ''Resilient Propagation'' algorithm and it was based on design details and experimental data relative to the oil-immersed distribution transformers. Simulation results of the proposed approach indicate that this methodology can be efficiently used in the protection processes of transformers, increasing the selectivity, reliability and the management of the electric energy distribution system
The determination of The Radial Basis Function Network centers is an open problem. This work determines the cluster centers by a proposed gradient algorithm, using the information forces acting on each data point. These centers are applied to a Radial Basis Function Network for data classification. A threshold is established based on Information Potential to classify the outliers. The proposed algorithms are analysed based on databases considering the number of clusters, overlap of clusters, noise, and unbalance of cluster sizes. Combined, the threshold, and the centers determined by information forces, show good results in comparison to a similar Network with a k-means clustering algorithm.
Random maps can be constructed from a priori knowledge of the financial
assets. It is also addressed the reverse problem, i.e. from a function of an
empirical stationary probability density function we set up a random map
that naturally leads to an implied binomial tree, allowing the adjustment of
models, including the ability to incorporate jumps. An applica- tion related
to the options market is presented. It is emphasized that the quality of the
model to incorporate a priori knowledge of the financial asset may be
affected, for example, by the skewed vision of the analyst.
(Full article available in Portuguese only)
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.