Scheduled System Maintenance
On Friday, October 20, IEEE Xplore will be unavailable from 9:00 PM-midnight ET. We apologize for the inconvenience.
Notice: There is currently an issue with the citation download feature. Learn more.

Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks

2000

Filter Results

Displaying Results 1 - 25 of 63
  • Web text mining using a hybrid system

    Publication Year: 2000, Page(s):131 - 136
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (372 KB)

    This paper presents the research of artificial intelligence techniques based on knowledge discovery in databases (KDD), knowledge discovery in texts, expert systems and artificial neural networks (ANN) applied for evaluation and selection of textual documents found on the World Wide Web. These techniques are useful because nowadays we have a explosive growth of the Web that provides a great amount... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks

    Publication Year: 2000
    Request permission for commercial reuse | PDF file iconPDF (247 KB)
    Freely Available from IEEE
  • Influence of training sample preprocessing in generalization accuracy of multilayer perceptron

    Publication Year: 2000
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (41 KB)

    Summary form only given. In this paper the behavior of multilayer perceptron (backpropagation algorithm) generalization accuracy using different pre-processing methods of training sample is investigated. In the experiments, diverse techniques were used. These were separated in two groups: the first one contains those that select a subset of the original sample; the second one clusters techniques w... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A comparative study of LBG and SOA codebooks concerning the computational complexity of the minimum distortion encoding for VQ

    Publication Year: 2000
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (107 KB)

    Summary form only given. Vector quantization (VQ),is a well-known compression technique which has been widely used in many speech and image coding systems. Techniques for codebook design attempt to produce a codebook that is optimum for a given source. To date, the most widely used technique for VQ codebook design is the LBG (Linde-Buzo-Gray) algorithm. Madeim et al. (1999) show that an unsupervis... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Constructing software autonomous agents to computer network management

    Publication Year: 2000
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (96 KB)

    Summary form only given. There are three important concepts in the computer network management area: managers, agents and managed objects. This work presents a methodology to develop autonomous agents for network management. There are two kinds of agents to develop: static or dynamic agents. The first one can be implemented, using heuristics obtained from an expert or the network administrator, th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Prediction of protein structures using a Hopfield network

    Publication Year: 2000
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (54 KB)

    Summary form only given. Under proper conditions, a globular protein adopts a unique 3D structure that is encoded in an amino acid sequence. The theoretical prediction of this structure, and the pathways followed during the folding process, are an important problem in structural molecular biology. Several works have explored the application of genetic algorithms and neural networks to the determin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hypermedia intelligent system

    Publication Year: 2000
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (33 KB)

    Summary form only given. In this article techniques are developed together for use of hypermedia systems with techniques of artificial intelligence. The hypermedia intelligent system (HIS) uses the language HTML and, consequently, such related systems as Java, JavaScript, VBScript, Shockwave, among others. A system servant can be used locally, in the Internet or in a intranet. This article present... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hierarchical neuro-fuzzy BSP model-HNFB

    Publication Year: 2000
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (80 KB)

    Summary form only given. This paper presents a new hybrid neuro-fuzzy model which is capable of learning structure and parameters by means of recursive binary space partitioning (BSP), and hence performing pattern classification. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fetal left atrium segmentation using Kohonen maps to measure the septum primum redundancy index

    Publication Year: 2000
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (98 KB)

    Summary form only given. Echocardiographic images are used by physicians in early detection of congenital heart diseases. Ultrasonic imaging has been the basis of noninvasive methods for early detection of fetal heart diseases. However, echocardiographic images are contaminated by speckle noise, and other imaging disturbances, making it difficult to visualize important heart structures. Usually th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of neural networks: a molecular geometry optimization study

    Publication Year: 2000
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (86 KB)

    Summary form only given. Optimization algorithms are iterative procedures that evolve from guessed starting points (SP) to the desired global minimum. Their performance can be greatly improved, if a neural network (NN) is created to select suitable SP. In this paper we consider the use of trained NN to select possible ground-state geometries for silicon clusters. A genetic algorithm is initial pop... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neuro-fuzzy networks for pattern classification and rule extraction

    Publication Year: 2000
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (108 KB)

    Summary form only given. An experimental evaluation of the neurofuzzy models NEFCLASS and FuNN is conducted in real world pattern recognition applications. The models are investigated with respect to classification performance and the number of rules generated and compared to the traditional MLP network trained with backpropagation. The models NEFCLASS and FuNN are examined in benchmarking problem... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Authors index

    Publication Year: 2000, Page(s):295 - 296
    Request permission for commercial reuse | PDF file iconPDF (106 KB)
    Freely Available from IEEE
  • A study of possible improvements to the Alopex training algorithm

    Publication Year: 2000, Page(s):125 - 130
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (428 KB)

    We studied the performance of the Alopex algorithm, and proposed modifications that improve the training time, and simplified the algorithm. We tested different variations of the algorithm. We describe the best cases and summarize the conclusions we arrived at. One of the proposed variations (99/B) performs slightly faster than the Alopex algorithm described by Unnikrishnan et al. (1994), showing ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A hierarchical neural model in short-term load forecasting

    Publication Year: 2000, Page(s):120 - 124
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (312 KB)

    This paper proposes a novel neural model for the short-term load forecasting problem. The neural model is made up of two self-organizing map nets-one on top of the other. It has been successfully applied to domains in which the context information given by former events plays a primary role. The model was trained and assessed on the load data extracted from a Brazilian electric utility. It was req... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Synthesis of analog circuits using evolutionary hardware

    Publication Year: 2000, Page(s):101 - 106
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (320 KB)

    The use of the genetic algorithm as a tool for the automatic synthesis of analog circuits is investigated. The advantages and modifications that can be introduced in the standard genetic algorithm, to improve its performance in this specific application, are discussed. The synthesis of an ideal active low pass filter is used as a test example to emphasize the characteristics and limitations of the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Monthly stream flow forecasting using an neural fuzzy network model

    Publication Year: 2000, Page(s):117 - 119
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (204 KB)

    This paper presents an fuzzy neural network model for inflow forecast for the Sobradinho hydroelectric power plant, part of the Chesf (Companhia Hidreletrica do Sao Francisco-Brazil) system. The model was implemented to forecast monthly average inflow on an one-step-ahead basis. The fuzzy neural network model is shown to provide better representation of the monthly average water inflow forecasting... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A dynamically coupled chaotic oscillatory correlation network

    Publication Year: 2000, Page(s):66 - 71
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (504 KB)

    In this paper, a network of dynamically coupled chaotic maps for scene segmentation is proposed. It is a two-dimensional array consisting of discrete chaotic elements. Time evolution of chaotic maps corresponding to an object in the given scene are synchronized and desynchronized with respect to time evolution of chaotic elements corresponding to different objects. As a continuous chaotic oscillat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Rule extraction from linear combinations of DIMLP neural networks

    Publication Year: 2000, Page(s):95 - 100
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (408 KB)

    The problem of rule extraction from neural networks is NP-hard. This work presents a new technique to extract If-Then-Else rules from linear combinations of discretised interpretable multilayer perceptron (DIMLP) neural networks. Rules are extracted in polynomial time with respect to the dimensionality of the problem, the number of examples, and the size of the resulting network. Further, the degr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network-based controllers for mobile robot

    Publication Year: 2000, Page(s):50 - 55
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (320 KB)

    A neural network-based control approach for mobile robot is proposed. The weight adaptation is made online, without previous learning. Several possible situations in robot navigation are considered,including uncertainties in the model and presence of disturbance. Weight adaptation laws are presented as well as simulation results View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Averaging spectra to improve the classification of the noise radiated by ships using neural networks

    Publication Year: 2000, Page(s):156 - 161
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (568 KB)

    The noise radiated from ships in the ocean contains information about their machinery, being normally used for detection and identification purposes. In this work we use a neural classifier to identify the radiated noise received by a hydrophone that was far from the ship. The classification is performed in the frequency domain using a feedforward neural network, which is trained using the backpro... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Elastic neural net algorithm for cluster analysis

    Publication Year: 2000, Page(s):191 - 195
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (352 KB)

    Proposes a method for data clustering in a n-dimensional space using the elastic net algorithm which is a variant of the Kohonen topographic map learning algorithm. The elastic net algorithm is a mechanical metaphor in which an elastic ring is attracted by points in a bi-dimensional space while their internal elastic forces try to shun the elastic expansion. The different weights associated with t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neural propositional reasoner that is goal-driven and works without pre-compiled knowledge

    Publication Year: 2000, Page(s):261 - 266
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (460 KB)

    This work presents the propositional version of a neural engine for finding proofs by refutation using the resolution principle. Such a neural architecture does not require special arrangements or different modules in order to do forward or backward reasoning, driven by the goal posed to it. Also, the neural engine is capable of performing monotonic reasoning with both complete and incomplete know... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural networks vs. PARMA modelling: case studies of river flow prediction

    Publication Year: 2000, Page(s):113 - 116
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (224 KB)

    This paper presents an constructive neural network model for seasonal stream flow forecasting. This surface water hydrology is basic to the design and operation of the reservoir. If information on the nature of the inflow is determinable in advance, then the reservoir can be operated by some decision rule to minimize downstream flood damage. For this reasons, several companies in the Brazilian Ele... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CDMA and TDMA based neural nets

    Publication Year: 2000, Page(s):78 - 83
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (328 KB)

    One of the main problems in neural nets implementation is how to take the information from the processing units where it is generated to other processing units, in order for the net to carry on the computation and eventually yield a result. This problem is significant enough to influence the whole physical design, thus we find a wide choice of solutions. This paper's two proposals come from the ri... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Extraction of statistically dependent sources with temporal structure

    Publication Year: 2000, Page(s):61 - 65
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (388 KB)

    In this work we develop a very simple batch learning algorithm for semi-blind extraction of a desired source signal with temporal structure from linear mixtures. Although we use the concept of sequential blind extraction of sources and independent component analysis (ICA), we do not carry out the extraction in a completely blind manner neither we assume that sources are statistically independent. ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.