By Topic

Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on

18-22 Nov. 2002

Go

Filter Results

Displaying Results 1 - 25 of 115
  • Sequential chaotic annealing neural network for CDMA multiuser detection

    Publication Year: 2002, Page(s):2176 - 2180 vol.5
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (453 KB) | HTML iconHTML

    The optimum multiuser detection problem in the presence of noise is a quadratic integer programming problem which has been shown to be NP-complete. In this paper, we propose a novel neural network based multiuser detector for a direct-sequence code division multiple access system. The proposed detector combines the paradigms of chaotic neural networks and methods from sequential unconstrained mini... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neural system design for CDF operations

    Publication Year: 2002, Page(s):2172 - 2175 vol.5
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (668 KB) | HTML iconHTML

    Conjugate directional filtering (CDF) is a method proposed by us recently. By using CDF, two direction-filtered results in conjugate directions can be merged into one image that shows the maximum linear features in the two conjugate directions. However, we only reported the CDF concepts and operations in our previous paper, without considerations in how to implement this method. In this paper, we ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hybrid HMM-NN for speech recognition and prior class probabilities

    Publication Year: 2002, Page(s):2391 - 2395 vol.5
    Cited by:  Papers (3)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (496 KB) | HTML iconHTML

    During the last years, speech recognition technologies have started their migration from research laboratories to real word applications gaining market shares. Although this shows that paradigms like Neural Networks have reached a high level of accuracy in modeling speech, it must be realized that there is still room for improving recognition performances exploiting the feedbacks coming from the a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stock price prediction using intraday and AHIPMI data

    Publication Year: 2002, Page(s):2167 - 2171 vol.5
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (553 KB) | HTML iconHTML

    Partitioned linear-nonlinear models are developed to improve in-sample precision and reduce sensitivity to out-sample modelling errors in stock price predictions. Such partitioned models are compared with linear regression models and nonlinear neural network models. The partitioned models demonstrate similar performance to the nonlinear models in both in-sample and out-sample predictions. Robust p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Speaker verification with a priori threshold determination using kernel-based probabilistic neural networks

    Publication Year: 2002, Page(s):2386 - 2390 vol.5
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (537 KB) | HTML iconHTML

    This paper compares kernel-based probabilistic neural networks for speaker verification. Experimental evaluations based on 138 speakers of the YOHO corpus using probabilistic decision-based neural networks (PDBNNs), Gaussian mixture models (GMMs) and elliptical basis function networks (EBFNs) as speaker models were conducted. The original PDBNN training algorithm was also modified to make PDBNNs a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Design of neuro-fuzzy network for image compression

    Publication Year: 2002, Page(s):2440 - 2443 vol.5
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (401 KB) | HTML iconHTML

    The main objective of this paper is to propose a Neuro-Fuzzy based algorithm for Image compression. The inputs to the network are original image data, while the outputs are reconstructed image data, which are close to the inputs. If the amount of data required to store the hidden unit values and the connection weights to the output layer is less than the original data, compression is achieved. The... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A recognition system that uses saccades to detect cars from real-time video streams

    Publication Year: 2002, Page(s):2162 - 2166 vol.5
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (530 KB) | HTML iconHTML

    In this work we present a system for detection of objects from video streams based on properties of human vision such as saccadic eye movements and selective attention. An object, in this application a car, is represented as a collection of features (horizontal and vertical edges) arranged at specific spatial locations with respect to the position of the fixation point. During the recognition proc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On detection of confused blood samples using self-organizing maps and genetic algorithm

    Publication Year: 2002, Page(s):2233 - 2238 vol.5
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (696 KB) | HTML iconHTML

    A SOM (self-organizing map)-based detection of confusion of blood test data referred to as CBC (complete blood count) data is proposed. Firstly, the method based on only SOM is shown. The learning data applied to SOMs are generated by subtracting the immediately anterior CBC data of subjects from the present CBC data. All the neurons in the second layer of SOM trained by applying the above learnin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The SOM-TSP method for the three-dimension city location problem

    Publication Year: 2002, Page(s):2552 - 2555 vol.5
    Cited by:  Papers (4)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (385 KB) | HTML iconHTML

    Up to now, shortening the installation time of electronic parts by chip-mounter has been researched by using the SOM-TSP method. This research aims to examine the effectiveness of the optimization ability of the SOM-TSP method when a multi-dimensional city is located. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy classification based identification of voltage sag via wavelets

    Publication Year: 2002, Page(s):2381 - 2385 vol.5
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (542 KB) | HTML iconHTML

    Increasing awareness of power quality issues, deregulation, use of consumer devices sensitive to power system disturbance and possibility of making up some of the inherent design limitations through monitoring based operational strategies have created a need for extensive monitoring of the power system operation. Voltage disturbance is a common phenomenon in electric power distribution system oper... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new kernel clustering algorithm

    Publication Year: 2002, Page(s):2527 - 2531 vol.5
    Cited by:  Papers (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (492 KB) | HTML iconHTML

    We propose a new kernel clustering algorithm. It estimates an in advance fixed number of vectors and margins in a feature space. Each pair of vector and margin defines a hyperplane in feature space and thus separates the data in two clusters. All the clusters together carry important information about the data set. The estimation in feature space is done implicitly by the use of a kernel. Therefor... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Combining fuzzy ART network clustering and sparse code shrinkage for image segmentation

    Publication Year: 2002, Page(s):2435 - 2439 vol.5
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (762 KB) | HTML iconHTML

    An autonomous segmentation process is one of the most difficult tasks of a visual system. Among the main aspects that can affect the results of this process is the presence of noise. In this paper, it is showed how a technique for denoising images can be combined with the Fuzzy ART clustering for improving the image segmentation results. A mobile robot application is used for testing the efficienc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Self organizing fuzzy neural network: an application to character recognition

    Publication Year: 2002, Page(s):2640 - 2644 vol.5
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (509 KB) | HTML iconHTML

    Character recognition is a very important field in DSP. Many different methods are used for this purpose. The ANN technique based on back propagation algorithm is very slow as its computational complexity is very high. On the other hand the Self-orthogonal ANN offers less computational complexity but it is not able to deal with the uncertainty associated with the input data sequence. Hence, fuzzy ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A contour character extraction approach in conjunction with a neural confidence fusion technique for the segmentation of handwriting recognition

    Publication Year: 2002, Page(s):2459 - 2463 vol.5
    Cited by:  Papers (4)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (612 KB) | HTML iconHTML

    The purpose of this paper is to present a novel neural network based algorithm to improve the segmentation process of cursive handwriting recognition and a detailed analysis of the performance of the algorithm on a benchmark database. The algorithm is based on a technique to fuse left character, center character and neural validation confidence values. A technique is proposed to extract a characte... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A comparison study on protein fold recognition

    Publication Year: 2002, Page(s):2492 - 2496 vol.5
    Cited by:  Papers (10)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (509 KB) | HTML iconHTML

    Although two proteins may be structurally similar, they may not have significant sequence similarity. The recognition of protein fold structures without relying on sequence similarity is a complex task. This work presents a comparison study on the recognition of 3-dimensional protein folds by Machine Learning models. Combinations of neural networks were trained by bagging and arcing with two datas... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network algorithm for solving ray-tracing problem

    Publication Year: 2002, Page(s):2665 - 2668 vol.5
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (419 KB) | HTML iconHTML

    This work is dedicated to the study of neural network method for solving of ray-tracing task, which appears in 3D visualization algorithms. Physical representation of the task is the problem of finding the nearest point of the "vision" ray crossing with the surfaces of the scene. Application: Real time 3D visualization, rendering of the complex scenes, containing semitransparent, reflecting, diffu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • SOMDS: multidimensional scaling through self organization map

    Publication Year: 2002, Page(s):2579 - 2581 vol.5
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (316 KB) | HTML iconHTML

    We propose SOMDS that is a combination of MDS (multidimensional scaling) and SOM. SOMDS is a special type of MDS that can learn locally and adaptively the structure of similarity data. SOMDS is a special type of SOM without neighborhood functions and whose inputs are similarities between objects. Convergence properties of the algorithm and some applications are presented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of neural network techniques for location predication in mobile networking

    Publication Year: 2002, Page(s):2157 - 2161 vol.5
    Cited by:  Papers (3)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (450 KB) | HTML iconHTML

    Over the last few years, the worldwide cellular communication market has undergone exponential growth. This can be attributed to several factors like decreasing prices, improved radio coverage, lightweight and compact terminals. In order to accommodate higher subscriber densities, the standard technique used is to reduce the radio cell size. However, reduction in cell size increases signaling for ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Clustering gene data via Associative Clustering Neural Network

    Publication Year: 2002, Page(s):2228 - 2232 vol.5
    Cited by:  Papers (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (431 KB) | HTML iconHTML

    We describe a new approach to the analysis of gene expression data using Associative Clustering Neural Network (ACNN). ACNN dynamically evaluates similarity between any two gene samples through the interactions of a group of gene samples. It has feasibility to more robust performance than those similarities evaluated by direct distances. The clustering performance of ACNN has been tested on the Le... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Speech adaptation using neural networks for connected digit recognition

    Publication Year: 2002, Page(s):2401 - 2404 vol.5
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (466 KB) | HTML iconHTML

    The performance of speech recognizers is usually degraded when used in different environments due to varied channels, speech rate and so on. Retraining the recognizers demands a large amount of new data recorded under new environments. On the contrary adaptation can fit the characteristics of the new environments by using only a small amount of data. In this paper a neural network based adaptation... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Growing hierarchical self organising map (GHSOM) toolbox: visualisations and enhancements

    Publication Year: 2002, Page(s):2537 - 2541 vol.5
    Cited by:  Papers (9)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (640 KB) | HTML iconHTML

    The Growing Hierarchical Self Organising Map (GHSOM) presents a method of dynamically modeling the data set that is presented. To a certain extent the GHSOM provides a solution to determine the size of the SOM needed, which is done through a growing fashion of neurons. In our development of the GHSOM Toolbox for Matlab presented in this paper, we have discovered that the GHSOM algorithm also provi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmentation of pathological features in MRI brain datasets

    Publication Year: 2002, Page(s):2673 - 2677 vol.5
    Cited by:  Papers (2)  |  Patents (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (670 KB) | HTML iconHTML

    One of the major clinical applications of magnetic resonance imaging (MRI) is to detect pathological features in human body parts. While results are available in a digital format, their evaluation is performed by a trained human observer, which is still considered as the "gold standard". However, providing additional quantitative figures (e.g., lesion size or count) is tedious for a human and may ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intra-feature metric matrices for nominal data pattern classification

    Publication Year: 2002, Page(s):2587 - 2591 vol.5
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (434 KB) | HTML iconHTML

    In machine learning problems, similarity measures (e.g. using metrics) are widely utilized in nearest neighbor, support vector machines and neural network algorithms. However, when there is one or more non-ordinal data in feature vector, metric evaluation is difficult. Although non-metric methods such as decision trees with ID3, C4.5 or CART can be employed to process such problems, many other ele... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • DevLex: a self-organizing neural network model of the development of lexicon

    Publication Year: 2002, Page(s):2546 - 2551 vol.5
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (586 KB) | HTML iconHTML

    In this paper we present the DevLex model of language acquisition. DevLex consists of two self-organizing maps (a growing semantic map and a phonological map) that are connected via associative links. It simulates the early stages of lexical development in children, in particular, word confusion as evidenced in naming errors. The simulation results indicate that the rate of word confusion is modul... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A modified FIR network for time series prediction

    Publication Year: 2002, Page(s):2597 - 2600 vol.5
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (412 KB) | HTML iconHTML

    In this paper, we present a modified FIR (Finite Impulse Response) network model for improving the capability of time series prediction system. The model has interval arithmetic capability as well as the time series prediction capability of the Finite Impulse Response (FIR) network. The proposed model exhibits some advantageous features, as follows. Since the interval values can be generated as in... View full abstract»

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