By Topic

Neural Networks for Signal Processing X. Proceedings of the 2000 IEEE Signal Processing Society Workshop (Cat. No.00TH8501)

11-13 Dec. 2000

Go

Filter Results

Displaying Results 1 - 25 of 51
  • Neural Networks for Signal Processing X [front matter]

    Publication Year: 2000, Page(s):i - iv
    Request permission for commercial reuse | PDF file iconPDF (144 KB)
    Freely Available from IEEE
  • Index

    Publication Year: 2000, Page(s):945 - 947
    Request permission for commercial reuse | PDF file iconPDF (95 KB)
    Freely Available from IEEE
  • Using polynomial networks for speech recognition

    Publication Year: 2000, Page(s):795 - 803 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (360 KB)

    We consider the problem of using polynomial networks for speech recognition. Previous applications of polynomials to speech recognition have yielded systems which are difficult to train and have only moderate accuracy. We show that through a novel training algorithm, a probabilistic interpretation, and a novel scoring method, polynomial networks can be applied to speech recognition in a manner tha... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Lateral inhibition mechanism in computational auditory model and its application in robust speech recognition

    Publication Year: 2000, Page(s):785 - 794 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (580 KB)

    In the auditory neural system, the lateral inhibition mechanism is very common, such as in the cochlear nucleus, auditory cortex, etc. The function of this lateral inhibition is to sharpen the contrast of the temporal and spatial structures, thus prominent features of stimulation in spatial and temporal domains can be enhanced. In this paper, a new mathematical model based on lateral inhibition is... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy logic based microcalcification detection

    Publication Year: 2000, Page(s):662 - 671 vol.2
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (484 KB)

    A fuzzy method for detecting mammographic microcalcifications is proposed. The fuzzy detection algorithm examines the degree of membership in terms of brightness, distance and variance, and then assigns an output value which represents the likelihood of the pixel being a microcalcification. The microcalcification detection (MCD) algorithm is implemented using software and a hardware platform. The ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Hopfield neural network approach for the reconstruction of wide-bandwidth sonar data

    Publication Year: 2000, Page(s):876 - 885 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (536 KB)

    Sonar systems with small physical apertures are easier to mount on small vessels and remotely operated vehicles (ROVs). Such systems however are limited in terms of angular resolution. Although wide-bandwidth signals may be used to increase the range resolution of a sonar system, angular resolution is unaffected. Such limitations can be overcome if the region of interest in the underwater environm... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Support vector machines for speaker verification and identification

    Publication Year: 2000, Page(s):775 - 784 vol.2
    Cited by:  Papers (53)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (460 KB)

    The performance of the support vector machine (SVM) on a speaker verification task is assessed. Since speaker verification requires binary decisions, support vector machines seem to be a promising candidate to perform the task. A new technique for normalising the polynomial kernel is developed and used to achieve performance comparable to other classifiers on the YOHO database. We also present res... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Two dimensional phase retrieval using neural networks

    Publication Year: 2000, Page(s):652 - 661 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (428 KB)

    The object of the 2D phase retrieval problem is to reconstruct an image from its spectral magnitude alone. This problem emerges when the phase of the 2D signal is apparently lost or is impractical to measure. For 2D spatially-limited non-negative objects characterized by an analytic spectrum, the solution is unique. In this paper, we propose the use of a neural network for solving the 2D phase ret... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Arithmetic-unit and processor design for neural networks

    Publication Year: 2000, Page(s):935 - 944 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (572 KB)

    The last decade saw a proliferation of research into the design of neurocomputers, many of which did not get beyond the prototype stage. We argue that, on the whole, neurocomputers are no longer viable; like, say, database computers before them, their time has passed before they became a common reality. We consider the implementation of hardware neural networks, from the level of arithmetic to com... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognition of defects in high voltage transmission lines using the acoustic signal of corona effect

    Publication Year: 2000, Page(s):869 - 875 vol.2
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (368 KB)

    The paper deals with the analysis of the possible application of neural networks to the recognition of typical damage of UHV transmission lines. The acoustic signal generated as a result of corona effects is used as a damage symptom, as its intensity is usually increased after damage occurrence or after contamination of the surface of a conductor or an insulator string. The primary problem in the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive multidimensional spline neural network for digital equalization

    Publication Year: 2000, Page(s):729 - 735 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (268 KB)

    Presents a new neural architecture that is suitable for digital signal processing applications. The architecture, which is based on adaptable multidimensional activation functions, allows one to collect information from the previous network layer in aggregate form. In other words, the number of network connections (the structural complexity) can be very low with respect to the problem complexity. ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image processing using cellular neural networks based on multi-valued and universal binary neurons

    Publication Year: 2000, Page(s):557 - 566 vol.2
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (468 KB)

    Multi-valued neurons (MVNs) and universal binary neurons (UBNs) are neural processing elements with complex-valued weights and high functionality. It is possible to implement an arbitrary mapping described by a partially-defined multiple-valued function on a single MVN, and an arbitrary mapping described by a partially-defined or fully-defined Boolean function (which does not have to be a threshol... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Alertness monitor using neural networks for EEG analysis

    Publication Year: 2000, Page(s):814 - 820 vol.2
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (300 KB)

    The goal is to detect the instance at which a person has lost the level of alertness necessary to assure safe operation of a vehicle or display vigilance. A neural network is proposed to detect the onset of this signal characteristic. The input to this neural network system is a modified feature vector composed of the associated wavelet representations at different scales. The output of the neural... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The use of problem knowledge to improve the robustness of a fuzzy neural network

    Publication Year: 2000, Page(s):682 - 691 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (536 KB)

    Neural networks generally take a long time to train. This is because the network is initialized using random values for the weights. These random values have no relationship to the problem to be solved. The network is also more likely to converge to a non-optimal solution when initialized with random weights. This paper discusses how a fuzzy neural network can be initialized using problem knowledg... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiuser demodulators using adaptive polynomial perceptrons in CDMA systems

    Publication Year: 2000, Page(s):746 - 754 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (328 KB)

    The polynomial perceptron multiuser demodulator (PPMUD) and the bilinear recursive polynomial perceptron multiuser demodulator with decision feedback (BRPMUD) are applied to a digital communication system using spread spectrum. The proposed multiuser demodulators are compared with the conventional receiver, the multilayer perceptron multiuser demodulator (MLPMUD) and the radial basis function mult... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Implementation of channel repacking algorithms on Hopfield neural networks in cellular systems

    Publication Year: 2000, Page(s):765 - 774 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (396 KB)

    Channel repacking, the rearrangement of channels once a subscriber leaves a cellular mobile communication system, is one of many ways of increasing the capacity of the system. A channel repacking algorithm is proposed and implemented on a Hopfield neural network. Results based on simulations from two different cellular systems indicate that there is an improvement in capacity when channel repackin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feature grid neural networks for curve partitioning

    Publication Year: 2000, Page(s):642 - 651 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (464 KB)

    Presents a neural network method for partitioning image curves into perceptual entities called generic curve segments (GCSs). GCSs are perceptual classes of primitive curve objects, which are qualitative descriptors for grouping curve shapes. The success of GCS classification and curve grouping relies on correctly locating curve partitioning points (CPPs), i.e. points from where the curves are bro... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Color image segmentation using color space analysis and fuzzy clustering

    Publication Year: 2000, Page(s):624 - 633 vol.2
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (428 KB)

    This paper presents a new method using color space analysis to obtain a proper number of colors and a good initial estimate of center positions. Then fuzzy c-means algorithm is used to optimally cluster the color space data points projected from an input image. Hence, optimal color segmentation can be achieved View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fusion of multiple handwritten word recognition techniques

    Publication Year: 2000, Page(s):926 - 934 vol.2
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (376 KB)

    Fusion of multiple handwritten word recognition techniques is described. A novel borda count for fusion based on ranks and confidence values is proposed. Three techniques with two different conventional segmentation algorithms in conjunction with backpropagation and radial basis function neural networks have been used in this research. Development has taken place at the University of Missouri and ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An edge detection scheme using radial basis function networks

    Publication Year: 2000, Page(s):604 - 613 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (524 KB)

    A new edge detection scheme based on radial basis function networks is proposed. It is a two-tiered scheme where, in the first stage, each pixel in the input image is classified according to its potential for being part of an edge. The second stage then combines these pixels into true edges in the input image. Both stages use radial basis function networks. The scheme illustrates how the input spa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Off-line signature verification using HMMs and cross-validation

    Publication Year: 2000, Page(s):859 - 868 vol.2
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (508 KB)

    We propose an HMM-based approach for off-line signature verification. One of the novelty aspects of our method lies in the ability to dynamically and automatically derive the various author-dependent parameters, required to set an optimal decision rule for the verification process. In this context, the cross-validation principle is used to derive not only the best HMM models, but also an optimal a... View full abstract»

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

    Publication Year: 2000, Page(s):517 - 526 vol.2
    Cited by:  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (420 KB)

    Storage of fingerprint image databases needs allocation of huge secondary storage devices. To reduce the increasing demand on storage space, efficient data compression techniques are badly needed. In addition to that, the exchange of fingerprint images between governmental agencies could be done fast. The compression algorithm must also preserve the original information in the original image. This... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A modular signal processing model for permeability prediction in petroleum reservoir

    Publication Year: 2000, Page(s):906 - 915 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (364 KB)

    The use of the artificial neural network (ANN) especially the backpropagation neural network (BPNN) has been a promising tool for well log analysis in predicting permeability. However, due to the range of permeability data, it is normally converted using a logarithmic transform before being used for data analysis by the BPNN. This has an impact on the accuracy of permeability prediction. This pape... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Face recognition using a new distance metric

    Publication Year: 2000, Page(s):584 - 593 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (468 KB)

    Many classification techniques use a distance metric as a measure of the similarity between patterns, and their generalisation performance is often strongly related to the effectiveness of the measure. This paper introduces a distance metric based on the Mahalanobis distance function, which is statistically more reliable than some metrics but does not discard discriminating information, often rega... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimal feature selection using information maximisation: case of biomedical data

    Publication Year: 2000, Page(s):841 - 850 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (360 KB)

    The hybrid information maximisation (HIM) algorithm is derived. This algorithm is based on maximising the mutual information (MI) between the input and output of a network using the infomax principle, and between outputs of different network modules using the Imax algorithm. These two folds enable reducing the redundancy in output units in addition to selecting higher order features from input uni... View full abstract»

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