By Topic

Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on

Date July 31 2005-Aug. 4 2005

Go

Filter Results

Displaying Results 1 - 25 of 138
  • 2005 IEEE International Joint Conference on Neural Networks (IJCNN)

    Page(s): 0_1
    Save to Project icon | Request Permissions | PDF file iconPDF (264 KB)  
    Freely Available from IEEE
  • Proceedings of the International Joint Conference on Neural Networks (IJCNN) 2005

    Page(s): i
    Save to Project icon | Request Permissions | PDF file iconPDF (274 KB)  
    Freely Available from IEEE
  • Copyright

    Page(s): ii
    Save to Project icon | Request Permissions | PDF file iconPDF (79 KB)  
    Freely Available from IEEE
  • IJCNN 2005: Session Grid

    Page(s): iii - vii
    Save to Project icon | Request Permissions | PDF file iconPDF (5016 KB)  
    Freely Available from IEEE
  • Message from the General Chair

    Page(s): viii - x
    Save to Project icon | Request Permissions | PDF file iconPDF (1441 KB)  
    Freely Available from IEEE
  • Organizing Committee / International Program Committee

    Page(s): xi - xiii
    Save to Project icon | Request Permissions | PDF file iconPDF (375 KB)  
    Freely Available from IEEE
  • 2005 International Neural Network Society Officers

    Page(s): xiv
    Save to Project icon | Request Permissions | PDF file iconPDF (47 KB)  
    Freely Available from IEEE
  • The INNS President's Welcome

    Page(s): xv
    Save to Project icon | Request Permissions | PDF file iconPDF (133 KB)  
    Freely Available from IEEE
  • Conference topics

    Page(s): xvi
    Save to Project icon | Request Permissions | PDF file iconPDF (107 KB)  
    Freely Available from IEEE
  • IEEE - CIS (Excom - Adcom)

    Page(s): xvii
    Save to Project icon | Request Permissions | PDF file iconPDF (48 KB)  
    Freely Available from IEEE
  • Full text access may be available. Click article title to sign in or learn about subscription options.
  • General information

    Page(s): xx
    Save to Project icon | Request Permissions | PDF file iconPDF (450 KB)  
    Freely Available from IEEE
  • Registration

    Page(s): xxi
    Save to Project icon | Request Permissions | PDF file iconPDF (576 KB)  
    Freely Available from IEEE
  • Florida Institute of Technology

    Page(s): xxiv
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (507 KB)  

    First Page of the Article
    View full abstract»

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

    Page(s): xxv
    Save to Project icon | Request Permissions | PDF file iconPDF (446 KB)  
    Freely Available from IEEE
  • IJCNN 2005 Schedule-at-a-Glance

    Page(s): xxvi - xxvii
    Save to Project icon | Request Permissions | PDF file iconPDF (1435 KB)  
    Freely Available from IEEE
  • The IJCNN 2005 Post-Conference Workshops

    Page(s): xxviii
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (94 KB)  

    First Page of the Article
    View full abstract»

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

    Page(s): xxix - liv
    Save to Project icon | Request Permissions | PDF file iconPDF (3260 KB)  
    Freely Available from IEEE
  • Issues in designing automated minimal resource allocation neural networks

    Page(s): 2671 - 2673 vol. 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (452 KB) |  | HTML iconHTML  

    Artificial neural networks (ANNs) have a long record of generally promising results in hydrology. The earlier applications were mainly based on the back propagation feedforward method, which often used a lengthy trial-and-error method to determine the final network parameters. An attempt to overcome this shortcoming of the traditional applications is the minimal resource allocation network (MRAN). MRAN is online adaptive method which automatically configures the number of hidden nodes based on the input-output patterns presented to the network. Although MRAN demonstrated superior accuracy and more compact network, when compared with the traditional back propagation method, some additional questions need to be addressed. While the number of hidden nodes is estimated automatically, other user-defined parameters are selected arbitrarily, and adjusted through simulations. This research addresses determining the user-defined parameters prior to the model run. The research also compares MRAN results from two applications, and discusses a pathway towards designing a fully automated MRAN. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Wavelet networks: an alternative to classical neural networks

    Page(s): 2674 - 2679 vol. 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1808 KB) |  | HTML iconHTML  

    Artificial neural networks (ANNs) are being widely used to predict and forecast highly nonlinear systems. Recently, Wavelet networks (WNs) have been shown to be a promising alternative to traditional neural networks. In this study, the robustness of WNs and ANNs in modeling two distinct time series is investigated. The first series represents a chaotic system (Henon map) and the second series represents a stochastic geophysical time series (streamflows). Monthly streamflow values of the English river between Umferville and Sioux Lookout, ON, Canada, are considered in this study. For the implementation of traditional ANNs, the weights and bias values are optimized using genetic algorithms (GAs). However, in WNs, along with weights and bias, the translation and dilation factors of wavelets are also optimized. Use of GAs to optimize the network parameters is to overcome the problem of convergence towards local optima. Results from the study indicate that, WNs are more suitable for modeling short time high frequency time series like Henon map. However, performance of WNs is comparable with that of ANNs in modeling low frequency time series like streamflows. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Streamflow forecasting with uncertainty estimate using Bayesian learning for ANN

    Page(s): 2680 - 2685 vol. 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (836 KB) |  | HTML iconHTML  

    Accurate site-specific streamflow forecasts along with uncertainty estimate are of particular importance for water resources planning and management. In the last decade, different types of artificial neural network (ANN) models have been shown as promising alternative methods for rainfall-runoff modeling. However, one of the critical issues with ANN based modeling remains the lack of confidence limits for the prediction results. Therefore, whatever the accuracy of the prediction values, there is a lack of reliability for practical applications. The Bayesian learning algorithm overcomes that limitation by providing uncertainty estimates of the predicted results. The present paper introduces a Bayesian learning approach for ANN modeling of daily streamflows implemented with a multilayer perceptron (MLP). The proposed model results are compared with those obtained from a multilayer perceptron trained with a 'scaled conjugate gradient' method. Overall, the model validation statistics and hydrograph comparison indicate that the Bayesian learning approach outperforms the conventional approach in almost all respects. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intelligent systems for meteorological events forecast

    Page(s): 2686 - 2688 vol. 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (961 KB) |  | HTML iconHTML  

    In this paper a committee of "intelligent systems" evaluates the occurrence of meteorological phenomena. Rain and fog are the events which are considered. The forecast system is based on a multinetwork approach which evaluates data coming from electronic sensors and from satellite observations. More data and more engines are used to increase the reliability of the event prediction. The increased complexity of the global system requires more data coming from different sources but gives a good reliability. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A multilayer perceptron approach for the retrieval of vertical temperature profiles from satellite radiation data

    Page(s): 2689 - 2693 vol. 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2204 KB) |  | HTML iconHTML  

    In this paper a multilayer perceptron neural network is used to retrieve vertical atmospheric temperature profiles from satellite radiation data. The training set consists of data provided by the direct model characterized by the radiative transfer equation (RTE) and by real radiation data from the NOAA-HIRS/2 (high resolution infrared radiation) sounder. The retrieved vertical temperature profiles are compared to radiosonde measured data. The neural network performance is compared to the results of the projects by J.C. Carvalho et al (1999) and by F.M. Ramos et al (1999) who used regularization techniques. Neural network approaches are especially advantageous due to the embed parallelism that may imply in faster vertical temperature profiles retrieving systems. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Machine learning in soil classification

    Page(s): 2694 - 2699 vol. 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2835 KB) |  | HTML iconHTML  

    In a number of engineering problems, e.g. in geotechnics, petroleum engineering, etc., intervals of measured series data (signals) are to be attributed a class maintaining the constraint of contiguity and standard classification methods could be inadequate. Classification in this case needs involvement of an expert who observes the magnitude and trends of the signals in addition to any a priori information that might be available. In this paper an approach for automating this classification procedure is presented. Firstly, a segmentation algorithm is applied to segment the measured signals. Secondly, the salient features of these segments are extracted using boundary energy method. Based on the measured data and extracted features classifiers to assign classes to the segments are built; they employ decision trees, ANNs and support vector machines. The methodology was tested for classifying subsurface soil using measured data from cone penetration testing and satisfactory results were obtained. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Estimation of prediction intervals for the model outputs using machine learning

    Page(s): 2700 - 2705 vol. 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2128 KB) |  | HTML iconHTML  

    A new method for estimating prediction intervals for a model output using machine learning is presented. In it, first the prediction intervals for in-sample data using clustering techniques to identify the distinguishable regions in input space with similar distributions of model errors are constructed. Then regression model is built for in-sample data using computed prediction intervals as targets, and, finally, this model is applied to estimate the prediction intervals for out-of-sample data. The method was tested on artificial and real hydrologic data sets using various machine learning techniques. Preliminary results show that the method is superior to other methods estimating the prediction intervals. A new method for evaluating performance for estimating prediction intervals is proposed as well. View full abstract»

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