By Topic

Proceedings of the IEEE

Issue 10 • Date Oct. 1996

Filter Results

Displaying Results 1 - 17 of 17
  • The Collected Papers of Claude E. Shannon [Book Reviews]

    Save to Project icon | Request Permissions | PDF file iconPDF (285 KB)  
    Freely Available from IEEE
  • Robust Control: Systems with Uncertain Physical Parameters [Book Reviews]

    Save to Project icon | Request Permissions | PDF file iconPDF (168 KB)  
    Freely Available from IEEE
  • The psychology of robots

    Page(s): 1553 - 1561
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (804 KB)  

    In recent years, neural networks have been proposed that portray many of the complexities of adaptive behavior. The networks describe how agents learn to predict future events by: 1) building models of the would, 2) inferring new predictions from past experiences, 3) combining elementary environmental stimuli into complex internal representations, 4) attending to stimuli associated with environmental novelty, and 5) attending to stimuli that are good predictors of other environmental events. When a predictive network is attached to a goal seeking system, the resulting architecture is able to describe spatial and maze navigation, as well as problem solving and planning. When the predictions of future events are based on the combination of environmental stimuli and the animal's own responses the networks provide the information necessary to choose between alternative behaviors. When the agent's own responses can be identified with the responses of other agents, the networks can describe learning by imitation. It is suggested that these principles might be applied to the design of adaptive, communicating autonomous robots View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • GRAIL: a multi-agent neural network system for gene identification

    Page(s): 1544 - 1552
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (924 KB)  

    Identifying genes within large regions of uncharacterized DNA is a difficult undertaking and is currently the focus of many research efforts. We describe a gene localization and modeling system, called GRAIL. GRAIL is a multiple sensor-neural network-based system. It localizes genes in anonymous DNA sequence by recognizing features related to protein-coding regions and the boundaries of coding regions, and then combines the recognized features using a neural network system. Localized coding regions are then “optimally” parsed into a gene model. Through years of extensive testing GRAIL consistently achieves about 90% of coding portions of test genes with a false positive rate of about 10% A number of genes for major genetic diseases have been located through the use of GRAIL, and over 1000 research laboratories worldwide use GRAIL on regular bases for localization of genes on their newly sequenced DNA View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Wavelet-based neural network with fuzzy-logic adaptivity for nuclear image restoration

    Page(s): 1458 - 1473
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1488 KB)  

    A novel wavelet-based neural network with fuzzy-logic adaptivity (WNNFA) is proposed for image restoration using a nuclear medicine gamma camera based on the measured system point spread function. The objective is to restore image degradation due to photon scattering and collimator photon penetration with the gamma camera and allow improved quantitative external measurements of radionuclides in vivo. The specific clinical model proposed is the imaging of bremsstrahlung radiation using 32 P and 90Y. The theoretical basis for four-channel multiresolution wavelet decomposition of the nuclear image into different subimages is developed with the objective of isolating the signal from noise. A fuzzy rule is generated to train a membership function using least mean squares to obtain an optimal balance between image restoration and the stability of the neural network, while maintaining a linear response for the camera to radioactivity dose. A multichannel modified Hopfield neural network architecture is then proposed for multichannel image restoration using the dominant signal subimages View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Applications of neurocomputing in traffic management of ATM networks

    Page(s): 1430 - 1441
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1312 KB)  

    In the near future, high speed integrated networks, employing asynchronous transfer mode (ATM) cell switching and multiplexing technique, will be used to provide new and diverse mixture of services and applications. Multimedia teleconferencing, video-on-demand, television broadcasting, and distant learning are some examples of these emerging services. The ATM technique is based on the principle of statistical multiplexing, which is flexible enough to support different types of traffic while providing efficient utilization of the network's resources. New classes of techniques such as neural networks and fuzzy logic have many adaptive, learning and computational capabilities that can be utilized to design effective traffic management algorithms. The subject of this paper is to demonstrate how such neurocomputing techniques can be used to address ATM traffic management issues such as traffic characterization, call admission control, usage parameters control and feedback congestion control View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On PAC learning of functions with smoothness properties using feedforward sigmoidal networks

    Page(s): 1562 - 1569
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (728 KB)  

    We consider the problem of learning functions based on finite samples by using feedforward sigmoidal networks. The unknown function f is chosen from a family that has either bounded modulus of smoothness and/or bounded capacity. The sample is given by (X1, f(X1)), (X2, f(X2)), ...(Xn, f(Xn)). Where X1, X2, ..., Xn, are independently and identically distributed according to an unknown distribution PX. General results guarantee the existence of a neural network, fw*, that best approximates f in terms of expected error. However, since both f and PX are unknown, computing fw* is impossible in general. We propose to compute probability and approximately correct (PAC) approximations to fw*, based on alternative estimators, namely: 1) the nearest neighbor rule, 2) local averaging, and 3) Nadaraya-Watson estimators, all computed using the Haar system. We show that given a sufficiently large sample, each of these estimators guarantees a performance as close as desired to that of fw*. The practical importance of this result sterns from the fact that, unlike neural networks, the three estimators above are linear-time computable in terms of the sample size View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Engineering applications of the self-organizing map

    Page(s): 1358 - 1384
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4280 KB)  

    The self-organizing map (SOM) method is a new, powerful software tool for the visualization of high-dimensional data. It converts complex, nonlinear statistical relationships between high-dimensional data into simple geometric relationships on a low-dimensional display. As it thereby compresses information while preserving the most important topological and metric relationships of the primary data elements on the display, it may also be thought to produce some kind of abstractions. The term self-organizing map signifies a class of mappings defined by error-theoretic considerations. In practice they result in certain unsupervised, competitive learning processes, computed by simple-looking SOM algorithms. Many industries have found the SOM-based software tools useful. The most important property of the SOM, orderliness of the input-output mapping, can be utilized for many tasks: reduction of the amount of training data, speeding up learning nonlinear interpolation and extrapolation, generalization, and effective compression of information for its transmission View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fingerprint classification through self-organizing feature maps modified to treat uncertainties

    Page(s): 1497 - 1512
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1928 KB)  

    In this paper, a neural network structure based on self organizing feature maps (SOFM) is proposed for fingerprint classification. In order to be able to deal with fingerprint images having distorted regions, the SOFM learning and classification algorithms are modified. For this purpose, the concept of “certainty” is introduced and used in the modified algorithms. This fingerprint classifier together with a fingerprint identifier, constitute subsystems of an automated fingerprint identification system, named HALafis. Our results show that a network that is trained with a sufficiently large and representative set of samples can be used as an indexing mechanism for a fingerprint database, so that it does not need to be retrained for each fingerprint added to the database View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural networks applied to traffic management in telephone networks

    Page(s): 1421 - 1429
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (700 KB)  

    In this paper the application of neural networks to some of the network management tasks carried out in a regional Bell telephone company is described. Network managers monitor the telephone network for abnormal conditions and have the ability to place controls in the network to improve traffic flow. Conclusions are drawn regarding the utility and effectiveness of the neural networks in automating the network management tasks View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network methods for volumetric magnetic resonance imaging of the human brain

    Page(s): 1488 - 1496
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1848 KB)  

    Brain magnetic resonance (MR) images contain massive information requiring lengthy and complex interpretation (as in the identification of significant portions of the image), quantitative evaluation (as in the determination of the size of certain significant regions), and sophisticated interpretation (as in determining any image portions which indicate signs of lesions or of disease). In this paper we first survey the clinical and research needs for brain imaging. We present the state-of-the-art in relevant image analysis techniques. We then discuss our recent work on the use of novel artificial neural networks which have a recurrent structure to extract precise morphometric information from MRI scans of the human brain. Finally, experimental data using our novel approach is presented and suggestions are made for future research View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network optimization for multi-target multi-sensor passive tracking

    Page(s): 1442 - 1457
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1600 KB)  

    In this paper, we review a number of neural network approaches to combinatorial optimization. We specifically address the difficult problem of localizing multiple targets using only passive sensors, i.e. the sensors detect only bearing angles. Thus, target positions must be found through triangulation. An efficient solution to this problem has been of particular interest in air defence applications. In this paper, we describe two different neural network based approaches for solving this passive tracking problem. In particular, we demonstrate the use of a Hopfield neural network to preface the subsequent development of the multiple elastic modules (MEM) model. The MEM model is presented as a significant extension to current self-organizing neural networks. We describe the unique features of the MEM model, including nonhomogeneous adaptive temperature field for escaping from poor local optima, and locking and expectation features used for dealing with dynamic real-world problems. Applications of the MEM model to other areas including computer vision, are also briefly described View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Low bit-rate video compression with neural networks and temporal subsampling

    Page(s): 1529 - 1543
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2832 KB)  

    In this paper we describe a novel neural network technique for video compression, using a “point-process” type neural network model we have developed which is closer to biophysical reality and is mathematically much more tractable than standard models. Our algorithm uses an adaptive approach based upon the users' desired video quality Q, and achieves compression ratios of up to 500:1 for moving gray-scale images, based on a combination of motion detection, compression, and temporal subsampling of frames. This leads to a compression ratio of over 1000:1 for full-color video sequences with the addition of the standard 4:1:1 spatial subsampling ratios in the chrominance images. The signal-to-noise ratio ranges from 29 dB to over 34 dB. Compression is performed using a combination of motion detection, neural networks, and temporal subsampling of frames. A set of neural networks is used to adaptively select the desired compression of each picture block as a function of the reconstruction quality. The motion detection process separates out regions of the frame which need to be retransmitted. Temporal subsampling of frames, along with reconstruction techniques, lead to the high compression ratios View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural networks for control theory and practice

    Page(s): 1385 - 1406
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2052 KB)  

    The past five years have witnessed a great deal of progress in both the theory and the practice of control using neural net works. After a long period of experimentation and research neural network-based controllers are finally emerging in the marketplace and the benefits of such controllers are now being realized in a wide variety of fields. The practical applications are also calling for a better understanding of the theoretical principles involved. In this paper we review the current status of control practice using neural networks and the theory related to it and attempt to assess the advantages of neurocontrol for technology View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network architectures for vector prediction

    Page(s): 1513 - 1528
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4996 KB)  

    A vector predictor is an integral part of a predictive vector quantization coding scheme. The conventional techniques for designing a nonlinear predictor are extremely complex and suboptimal due to the absence of a suitable model for the source data. We investigated several neural network architectures that can be used to implement a nonlinear vector predictor, including the multilayer perceptron, the functional link network and the radial basis function network. We also evaluated and compared the performance of these neural network predictors with that of a linear vector predictor. Our experimental results show that a neural network predictor can predict the blocks containing edges with a higher accuracy than a linear predictor. However, the performance of a neural network predictor is comparable to that of a linear predictor for predicting the stationary and shade blocks View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network-assisted effective lossy compression of medical images

    Page(s): 1474 - 1487
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2792 KB)  

    A neural network architecture is proposed and shown to be very effective in performing lossy compression of medical images. A novel ROI-JPEG technique is introduced as the coding platform, in which the neural architecture adaptively selects regions of interest (ROI) in the images. By letting the selected ROI be coded with high quality, in contrast to the rest of image areas, high compression ratios are achieved, while retaining the significant (from medical point of view) image content. The performance of the method is illustrated by means of experimental results in real life problems taken from pathology and telemedicine applications View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic neural network methods applied to on-vehicle idle speed control

    Page(s): 1407 - 1420
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1484 KB)  

    The application of neural network techniques to the control of nonlinear dynamical systems has been the subject of substantial interest and research in recent years. In our own work, we have concentrated on extending the dynamic gradient formalism as established by Narendra and Parthasarathy (1990, 1991), and on employing it for applications in the control of nonlinear systems, with specific emphasis on automotive subsystems. The results we have reported to date, however, have been based exclusively upon simulation studies. In this paper, we establish that dynamic gradient training methods can be successfully used for synthesizing neural network controllers directly on instances of real systems. In particular we describe the application of dynamic gradient methods for training a time-lagged recurrent neural network feedback controller for the problem of engine idle speed control on an actual vehicle, discuss hardware and software issues, and provide representative experimental results View full abstract»

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

Aims & Scope

The most highly-cited general interest journal in electrical engineering and computer science, the Proceedings is the best way to stay informed on an exemplary range of topics.

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
H. Joel Trussell
North Carolina State University