Electric load forecasting using a fuzzy ART&ARTMAP neural network

This work presents a neural network based on the ART architecture ( adaptive resonance theory), named fuzzy ART& ARTMAP neural network, applied to the electric load-forecasting problem. The neural networks based on the ARTarchitecture have two fundamental characteristics that are extremely important for the network performance ( stability and plasticity), which allow the implementation of continuous training. The fuzzy ART& ARTMAP neural network aims to reduce the imprecision of the forecasting results by a mechanism that separate the analog and binary data, processing them separately. Therefore, this represents a reduction on the processing time and improved quality of the results, when compared to the Back-Propagation neural network, and better to the classical forecasting techniques (ARIMA of Box and Jenkins methods). Finished the training, the fuzzy ART& ARTMAP neural network is capable to forecast electrical loads 24 h in advance. To validate the methodology, data from a Brazilian electric company is used. (C) 2004 Elsevier B.V. All rights reserved.

A fast electric load forecasting using neural networks

The objective of this work is the development of a methodology for electric load forecasting based on a neural network. Here, it is used Backpropagation algorithm with an adaptive process based on fuzzy logic. This methodology results in fast training, when compared to the conventional formulation of Backpropagation algorithm. Results are presented using data from a Brazilian Electric Company and the performance is very good for the proposal objective.

A fast electric load forecasting using adaptive neural networks

This work presents a procedure for electric load forecasting based on adaptive multilayer feedforward neural networks trained by the Backpropagation algorithm. The neural network architecture is formulated by two parameters, the scaling and translation of the postsynaptic functions at each node, and the use of the gradient-descendent method for the adjustment in an iterative way. Besides, the neural network also uses an adaptive process based on fuzzy logic to adjust the network training rate. This methodology provides an efficient modification of the neural network that results in faster convergence and more precise results, in comparison to the conventional formulation Backpropagation algorithm. The adapting of the training rate is effectuated using the information of the global error and global error variation. After finishing the training, the neural network is capable to forecast the electric load of 24 hours ahead. To illustrate the proposed methodology it is used data from a Brazilian Electric Company. © 2003 IEEE.

Electrical load forecasting formulation by a fast neural network

The objective of this work is to develop a methodology for electric load forecasting based on a neural network. Here, backpropagation algorithm is used with an adaptive process that based on fuzzy logic and using a decaying exponential function to avoid instability in the convergence process. This methodology results in fast training, when compared to the conventional formulation of backpropagation algorithm. The results are presented using data from a Brazilian Electric Company, and shows a very good performance for the proposal objective.

Comercialização de caju in natura na região noroeste do estado de São Paulo

Para estimar e analisar os custos de comercialização e identificar locais e formas de comercialização do caju, foram realizadas, durante o ano de 2000/01, entrevistas com produtores, técnicos da extensão rural, agentes intermediários e pesquisadores de órgãos públicos. Também foram levantadas informações na Companhia de Entrepostos e Armazéns Gerais de São Paulo (CEAGESP). Os custos agregados pelo segmento da comercialização devem-se, em grande parte, às despesas com o transporte até os grandes centros atacadistas, e também à comissão definida pelo atacadista. Para o produtor da região Noroeste do Estado de São Paulo, o ideal seria direcionar sua produção para os meses de janeiro a junho, garantindo assim melhores preços e com isso resultados mais satisfatórios.

Cauda equina syndrome after spinal tetracaine: Electromyographic evaluation-20 years follow-up

CAUDA equina syndrome (CES) has long been recognized as a rare complication of spinal anesthesia.(1) CES has been described after administration of spinal anesthetics with lidocaine(2) and bupivacaine.(3) In 1991,(4) CES was reported after continuous spinal anesthesia with 1% tetracaine. In 1980, at our university hospital, six adult female patients underwent perineal gynecologic surgery using a spinal anesthetic of 2 ml tetracaine, 1.2%, in 10% glucose. The concentration of the injected tetracaine was unknown by the anesthetists. In all cases, lumbar puncture was performed at the L3-L4 interspace with a disposable spinal needle while the patients were in the sitting position. CES was first diagnosed 72 h or later postoperatively; previous diagnosis was not possible because patients had an indwelling urethral catheter. The diagnosis of CES was confirmed in all patients. During the past year, after institutional approval and informed consent, clinical, magnetic resonance imaging, electromyographic examinations, and conduction studies were performed in three of the above patients. Examinations were not possible on the other three patients because one had recently died, another could not be located, and the third refused to participate. T1 and T2 magnetic resonance image readings were obtained with Gadolinium contrast from a 0.5 Tesla General Electric apparatus (General Electric, Tokyo, Japan). Bilateral sensory and motor conduction studies of the sciatic nerve branches were obtained using a two-channel Nihon-Kohden Neuropack 2 (Nihom-Kohden Corporation, Tokyo, Japan). Electromyography was performed in accordance with conventional techniques.(5,6)

Wetland projects developed in Brazil

The first studies with constructed wetlands undertaken in Brazil were the result of observations made from the Amazon flood plains. The first attempt to use this capacity to change the quality of the water, in the sense of purification performed in Brazil using constructed wetland systems, was made by Salati et al. After that, new technologies were developed in a focused attempt to increase the efficiency of the system and reduce investments. Over these 18 years, persuading the Brazilian scientific community as well as the environmental control agencies to give due attention to this kind of research has required endless efforts. Only in recent years have major institutions responsible for sewage treatment and potable water supply been concerned with this type of technology for solving real problems. These institutions are as follows: SABESP (Basic Sanitation Company of Sao Paulo State), SANEPAR (Sanitation Company of Parana State) and CESP (Electric Company of Sao Paulo State). One of the private institutions that has systematically worked in the design and projects of constructed wetlands is the Institute of Applied Ecology. This institution has enhanced and developed a water depuration system based on the purifying capacity of the soil. The wetlands with filtering soils are systems formed by overlapping layers of crushed stone, gravel and soil planted with rice. This technology has been used in sewage treatment and also in water supply systems.

Previsão de cargas elétricas através de um modelo híbrido de regressão com redes neurais

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Regiões de procedência de abacaxi para a Ceagesp de São Paulo e análises qualitativa, comparativa e das causas da valoração dos frutos

Pós-graduação em Agronomia (Horticultura) - FCA

Avaliação das condições de uso de um equipamento de tomografia computadorizada e otimização de protocolos de crânio empregados na rotina do HCFMB-UNESP

Almost forty years computed tomography (CT) has been one of the most powerful tools in diagnostic imaging. However, this modality delivers relatively high doses to their patients. It is known that the inappropriate use and unnecessary radiation may be associated with a significant risk of cancer, especially in pediatric patients. Moreover, the quality assurance in CT, provided and required by Portaria 453/98 and the guide of the RE 1016/05, ensures that the images generated by computer tomography provide reliable diagnostic information with doses as low as reasonably achievable. This research aimed to make the quality control (QC) of CT equipment; establish a better relationship between dose and noise on the image to protocols of skull CT according to the study of optimization proposed in 2005 by Daros; and assess the dose distribution in different cranial organs for protocols of adult and pediatric use in the routine of the Department of Diagnostic Imaging of HCFMB-UNESP. The equipment used for testing QC, optimization and dosimetry was a third generation tomograph GE Sytec 3000i

Comparação entre metodologias de controle de qualidade em mamografia digital

The best way to detect breast cancer is by screening mammography. The mammography equipments are dedicated and require a rigorous quality control in order to have a good quality image and to early detect this disease. The digital equipment is relatively new in the market and there isn’t a national rule for quality control for several types of digital detectors. This study has proposed to compare two different tests manuals for quality control provided by the manufacturers of digital mammography equipments, and also compare them to the “European guidelines for quality assurance in breast cancer screening and diagnosis “(2006). The studied equipments were: Senographe 2000D from General Electric (GE) and the Hologic Selenia Lorad. Both were digital mammography equipments, the GE unit presents an indirect digital system and the other presents a direct digital system. Physical parameters of the image have been studied, such as spatial resolution, contrast resolution, noise, signal-tonoise ratio, contrast-to-noise ratio and modulation transfer function. After that, a study of the importance of quality control and the requirement to implement a Quality Assurance Program has been done. One data collection was done to compare those manual, it was done by checking which tests are indicated and the minimum frequency which they should be conducted in accordance with each manufacturer. The tests were performed by different methodologies and the results were compared. The examined tests were: the breast entrance skin dose, mean glandular dose, contrast-to-noise ratio, signal-to-noise ratio, automatic exposure control and automatic control of density, modulation transfer function, equipment resolution, homogeneity and ghost

Simultaneous observation of the magnetic and electric behavior in a correlated system near a metal-semiconductor transition: ESR in pellets of conducting polymers

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

DO INERTIAL ELECTRIC CHARGES RADIATE WITH RESPECT TO UNIFORMLY ACCELERATED OBSERVERS

We revisit the long standing problem of analyzing an inertial electric charge from the point of view of uniformly accelerated observers in the context of semi-classical gravity. We Choose a suitable set of accelerated observers with respect to which there is no photon emission coming from the inertial charge. We discuss this result against previous claims.

Investigation of the relationship between load and loss factors for a Brazilian electric utility

With the considerable increase of the losses in electric utilities of developing countries, such as Brazil, there is an investigation for loss calculation methodologies, considering both technical (inherent of the system) and non-technical (usually associated to the electricity theft) losses. In general, all distribution networks know the load factor, obtained by measuring parameters directly from the network. However, the loss factor, important for the energy loss cost calculation, can only be obtained in a laborious way. Consequently, several formulas have been developed for obtaining the loss factor. Generally, it is used the expression that relates both factors, through the use of a coefficient k. Last reviews introduce a range of factor k within 0.04 - 0.30. In this work, an analysis with real life load curves is presented, determining new values for the coefficient k in a Brazilian electric utility. © 2006 IEEE.

A statistical analysis of loss factor to determine the energy losses

Given that the total amount of losses in a distribution system is known, with a reliable methodology for the technical loss calculation, the non-technical losses can be obtained by subtraction. A usual method of calculation technical losses in the electric utilities uses two important factors: load factor and the loss factor. The load factor is usually obtained with energy and demand measurements, whereas, to compute the loss factor it is necessary the learning of demand and energy loss, which are not, in general, prone of direct measurements. In this work, a statistical analysis of this relationship using the curves of a sampling of consumers in a specific company is presented. These curves will be summarized in different bands of coefficient k. Then, it will be possible determine where each group of consumer has its major concentration of points. ©2008 IEEE.