R. P. Landim, B. R. Menezes, S. Silva, W. Caminhas
{"title":"A neo-fuzzy-neuron with real time training applied to flux observer for an induction motor","authors":"R. P. Landim, B. R. Menezes, S. Silva, W. Caminhas","doi":"10.1109/SBRN.1998.730996","DOIUrl":"https://doi.org/10.1109/SBRN.1998.730996","url":null,"abstract":"Presents an alternative algorithm for induction machines rotor flux observation. The novel procedure is based on a neo-fuzzy-neuron (NFN) with real time training. The main characteristics of this novel observer are: quick and accurate convergence and adaptability to system dynamics, requiring only the stator current measurements. The fuzzy-neural network employed here does not require previous training. The NFN is described, as well as its application to a rotor flux observer of a three-phase induction machine. Network training and observer performance are assessed by simulations and experimental results.","PeriodicalId":401282,"journal":{"name":"Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132474136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A genetic algorithm approach to optimize the operation planning of hydrothermal system scheduling","authors":"A. Carneiro, P. Leite, A. Carvalho","doi":"10.1109/SBRN.1998.731041","DOIUrl":"https://doi.org/10.1109/SBRN.1998.731041","url":null,"abstract":"This article investigates the application of genetic algorithms to optimize large, nonlinear complex systems, particularly the optimization of the operation planning of hydrothermal system scheduling. Several of the current works to solve this kind of problems are based on nonlinear programming. However, this approach presents a number of deficiencies, like difficult convergence, oversimplification of the original problem or difficulties related to the approximation to the objective function. Aiming to find more efficient solutions for this class of problems, this paper proposes and investigates the use of a genetic approach. The authors believe that, due to their characteristics, like simplicity, parallelism and generality, genetic algorithms can provide an effective solution to the optimization of the operation planning of hydrothermal system scheduling. For such, this paper shows the application of this technique for the optimization of the operation planning for a system composed by three hydroelectric plants located in the Brazilian Southeast System.","PeriodicalId":401282,"journal":{"name":"Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209)","volume":"23 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123352130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A neural mapping for improving the performance of a high-energy calorimeter","authors":"J. Seixas, P. D. Silva, L. Calôba","doi":"10.1109/SBRN.1998.731029","DOIUrl":"https://doi.org/10.1109/SBRN.1998.731029","url":null,"abstract":"For a scintillating calorimeter, which is being designed to perform energy measurements in a next-generation high-energy collider experiment, a neural mapping is established to improve the overall detector performance. Training a neural network with energy vectors formed by the energy deposited on each cell of this granular detector, the original energy scale of the experimental particle beam is reconstructed and the linearity is significantly improved. In practice, the neural mapping corrects the nonlinearities that arise from the calorimeter design, and it may replace classical methods that use energy dependent multiparameter functions.","PeriodicalId":401282,"journal":{"name":"Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116121310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"CALIBRA for fuzzy concepts","authors":"M. Zanusso, A. L. Araújo","doi":"10.1109/SBRN.1998.731009","DOIUrl":"https://doi.org/10.1109/SBRN.1998.731009","url":null,"abstract":"This paper presents a system for calibration of the involved parameters in the classification and characterization process of fuzzy concepts that use t-norm differentiable and related membership families for the definition of characterizing functions. An empirical evaluation using the data set iris shows the comparability with the classical methods of classification. We also make a conjecture that relate any continuous membership function with the defined families.","PeriodicalId":401282,"journal":{"name":"Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123005526","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"RBF neural networks and MTI for text independent speaker identification","authors":"A. P. Timoszczuk, E. F. Cabral","doi":"10.1109/SBRN.1998.731007","DOIUrl":"https://doi.org/10.1109/SBRN.1998.731007","url":null,"abstract":"Artificial neural networks applied to speaker recognition tasks have being addressed by several researchers. This paper presents an investigation of the use of radial basis function (RBF) neural networks as classifiers applied to speaker identification tasks. A novel way to organize the speech frames in order to represent the speakers-the minimal temporal information (MTI)-is introduced and a comparison with the traditional multilayer perceptron (MLP) is presented. The results obtained indicate that the use of RBF neural networks are promising in speaker recognition and the MTI strategy to organize the speech frames are able to improve the RBF recognition rate.","PeriodicalId":401282,"journal":{"name":"Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132527333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Context and scale influencing clustering through unsupervised neural networks","authors":"A. S. Henriques, A. Araujo","doi":"10.1109/SBRN.1998.731037","DOIUrl":"https://doi.org/10.1109/SBRN.1998.731037","url":null,"abstract":"This work aims at proposing a neural network model for clustering in which no information about the desired output is given, and influences due to context and scale are considered. Two models of unsupervised neural networks are described. The first is a winner-take-all (WTA) algorithm with pre-established lateral inhibition, the second is a model with Hebbian and anti-Hebbian learning. Both models have the same architecture but the second one has adaptable lateral inhibitory links. The proposed models are used in two different domains: classification of the iris and classification of animals. In the first, the patterns are formed by continuous inputs, while in the second, the inputs are mainly binary. The proposed models are evaluated according to their capacity of generalization, ability to classify nonlinearly separable patterns and robustness when clustering noisy patterns.","PeriodicalId":401282,"journal":{"name":"Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133316992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An adaptive neural fuzzy network model for seasonal stream flow forecasting","authors":"R. Ballini, S. Soares, M. Andrade","doi":"10.1109/SBRN.1998.731032","DOIUrl":"https://doi.org/10.1109/SBRN.1998.731032","url":null,"abstract":"This paper presents an adaptive neural fuzzy network model for seasonal stream flow forecasting. The model is based on a constructive learning method that adds neurons to the network structure whenever new knowledge is necessary so that it learns the fuzzy rules and membership functions essential for modeling a fuzzy system. The model was implemented to forecast monthly average inflow on an one-step-ahead basis. It was tested on three hydroelectric plants located in different river basins in Brazil. When the results were compared with those of a multilayer feedforward neural network model, the present model revealed at least a 50% decrease in the forecasting error.","PeriodicalId":401282,"journal":{"name":"Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131866631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Design of radial basis function network as classifier in face recognition using eigenfaces","authors":"C. Thomaz, R. Feitosa, Alvaro Veiga","doi":"10.1109/SBRN.1998.731006","DOIUrl":"https://doi.org/10.1109/SBRN.1998.731006","url":null,"abstract":"In this paper we investigate alternative designs of a radial basis function network acting as classifier in a face recognition system. The inputs to the RBF network are the projections of a face image over the principal components. A database of 250 facial images of 25 persons is used for training and evaluation. Two RBF designs are studied: the forward selection and the Gaussian mixture model. Both designs are also compared to the conventional Euclidean and Mahalanobis classifiers. A set of experiments evaluates the recognition rate of each method as a function of the number of principal components used to characterize the image samples. The results of the experiments indicate that the Gaussian mixture model RBF achieves the best performance while allowing less neurons in the hidden layer. The Gaussian mixture model approach shows also to be less sensitive to the choice of the training set.","PeriodicalId":401282,"journal":{"name":"Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114779604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Factor semantics for document retrieval","authors":"R. Calvo","doi":"10.1109/SBRN.1998.731028","DOIUrl":"https://doi.org/10.1109/SBRN.1998.731028","url":null,"abstract":"Principal component analysis is a useful technique for reducing the dimensionality of datasets, a paramount need in high dimensional term spaces. We study three neural networks with Hebbian-like learning that approximately produce the principal components of a document database. The explained variance of the solutions shows how much information the reduced space retains. In this database the first factor is strongly described by words that are usually included in a stop-word list, other factors show high loadings in content specific terms; this indicates that the networks are learning the semantic space. The retrieval performance on the reduced space is compared with other methods.","PeriodicalId":401282,"journal":{"name":"Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116444759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Convergence in a sparse distributed memory","authors":"G. Sjodin","doi":"10.1109/SBRN.1998.731019","DOIUrl":"https://doi.org/10.1109/SBRN.1998.731019","url":null,"abstract":"A method for converging in the sparse distribution memory, utilizing the Jaeckel activation mechanism, is presented. This is done by identifying the possible errors in the address.","PeriodicalId":401282,"journal":{"name":"Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121183564","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}