Signal processing using cellular neural networks

The cellular neural network (CNN) architecture combines the best features from traditional fully-connected analog neural networks and digital cellular automata. The network can rapidly process continuous-valued (gray-scale) input signals (such as images) and perform many computation functions which traditionally were implemented in digital form. Here, we briefly introduce the the theory of CNN circuits, provide some examples of CNN applications to image processing, and discuss work toward a CNN implementation in custom CMOS VLSI. The role of analog computer-aided design (CAD) will be briefly presented as it relates to analog neural network implementation.This work is supported in part by the Office of Naval Research under Contract N00014-89-J1402, and the National Science Foundation under grant MIP-8912639.     

Efficient classification by neural networks using encoded patterns

The corners and the middle points, which are extracted as features from the line approximation of a given pattern, are overlaid on a radial grid to form the input array for training a backpropagation network for classification. The proposed method is shown to be simple and robust by extensive testing of its performance on patterns both with and without noise     

Application of neural networks to radar image classification

A number of methods have been developed to classify ground terrain types from fully polarimetric synthetic aperture radar (SAR) images, and these techniques are often grouped into supervised and unsupervised approaches. Supervised methods have yielded higher accuracy than unsupervised techniques, but suffer from the need for human interaction to determine classes and training regions. In contrast, unsupervised methods determine classes automatically, but generally show limited ability to accurately divide terrain into natural classes. In this paper, a new terrain classification technique is introduced to determine terrain classes in polarimetric SAR images, utilizing unsupervised neural networks to provide automatic classification, and employing an iterative algorithm to improve the performance. Several types of unsupervised neural networks are first applied to the classification of SAR images, and the results are compared to those of more conventional unsupervised methods. Results show that one neural network method-Learning Vector Quantization (LVQ)-outperforms the conventional unsupervised classifiers, but is still inferior to supervised methods. To overcome this poor accuracy, an iterative algorithm is proposed where the SAR image is reclassified using a maximum likelihood (ML) classifier. It is shown that this algorithm converges, and significantly improves classification accuracy     

Ideal observer approximation using Bayesian classification neural networks

It is well understood that the optimal classification decision variable is the likelihood ratio or any monotonic transformation of the likelihood ratio. An automated classifier which maps from an input space to one of the likelihood ratio family of decision variables is an optimal classifier or "ideal observer." Artificial neural networks (ANNs) are frequently used as classifiers for many problems. In the limit of large training sample sizes, an ANN approximates a mapping function which is a monotonic transformation of the likelihood ratio, i.e., it estimates an ideal observer decision variable. A principal disadvantage of conventional ANNs is the potential over-parameterization of the mapping function which results in a poor approximation of an optimal mapping function for smaller training samples. Recently, Bayesian methods have been applied to ANNs in order to regularize training to improve the robustness of the classifier. The goal of training a Bayesian ANN with finite sample sizes is, as with unlimited data, to approximate the ideal observer. We have evaluated the accuracy of Bayesian ANN models of ideal observer decision variables as a function of the number of hidden units used, the signal-to-noise ratio of the data and the number of features or dimensionality of the data. We show that when enough training data are present, excess hidden units do not substantially degrade the accuracy of Bayesian ANNs. However, the minimum number of hidden units required to best model the optimal mapping function varies with the complexity of the data.     

Waveform classification and information extraction from LIDAR databy neural networks

Two different neural network schemes for the classification of light detection and ranging (LIDAR) waveforms for the LARSEN 500 airborne system and for extraction of ocean information are proposed. The first method employs a single layer of linear neurons for classification of waveforms into various clusters. Both unsupervised and supervised learning algorithms have been employed to demonstrate the spatial distribution of milt in near-shore waters. In the second method, a new multistage multilayer feedforward architecture is used for the classification of the waveforms and for the extraction of various types of ocean information. The stage I networks work in a parallel fashion and map the input waveforms to a set of characteristics. The networks in stage II use these characteristics to assign a signature number to the waveform or extract other information. Both the schemes are used with real-world data collected by the LARSEN 500 system. The paper concludes with experimental results and comparisons     

Fast road classification and orientation estimation using omni-viewimages and neural networks

This paper presents the results of integrating omnidirectional view image analysis and a set of adaptive backpropagation networks to understand the outdoor road scene by a mobile robot. Both the road orientations used for robot heading and the road categories used for robot localization are determined by the integrated system, the road understanding neural networks (RUNN). Classification is performed before orientation estimation so that the system can deal with road images with different types effectively and efficiently. An omni-view image (OVI) sensor captures images with 360 degree view around the robot in real-time. The rotation-invariant image features are extracted by a series of image transformations, and serve as the inputs of a road classification network (RCN). Each road category has its own road orientation network (RON), and the classification result (the road category) activates the corresponding RON to estimate the road orientation of the input image. Several design issues, including the network model, the selection of input data, the number of the hidden units, and learning problems are studied. The internal representations of the networks are carefully analyzed. Experimental results with real scene images show that the method is fast and robust.     

A novel traffic identification approach based on multifractal analysis and combined neural network

An accurate identification of Internet traffic of different applications is highly relevant for a broad range of network management and measurement tasks, including traffic engineering, service differentiation, performance monitoring, and security. Traditional traffic identification approaches have become increasingly inaccurate due to restrictions of port numbers, protocol signatures, traffic encryption, and etc. In this paper, a new traffic identification approach based on multifractal analysis of wavelet energy spectrum and classification of combined neural network models is proposed. The proposed approach is able to achieve the identification of different Internet application traffic by performing classification over the wavelet energy spectrum coefficients that were inferred from the original traffic. Without using any payload information, the proposed approach has more advantages over traditional methods. The experiment results illustrate that the proposed approach has satisfactory identification results.     

The use of wavelet packet transform and artificial neural networks in analysis and classification of dysphonic voices

This paper presents a dysphonic voice classification system using the wavelet packet transform and the best basis algorithm (BBA) as dimensionality reductor and 06 artificial neural networks (ANN) acting as specialist systems. Each ANN was a 03-layer multilayer perceptron with 64 input nodes, 01 output node and in the intermediary layer the number of neurons depends on the related training pathology group. The dysphonic voice database was separated in five pathology groups and one healthy control group. Each ANN was trained and associated with one of the 06 groups, and fed by the best base tree (BBT) nodes' entropy values, using the multiple cross validation (MCV) method and the leave-one-out (LOO) variation technique and success rates obtained were 87.5%, 95.31%, 87.5%, 100%, 96.87% and 89.06% for the groups 01 to 06, respectively.     

Terrain classification in SAR images using principal componentsanalysis and neural networks

The development of a neural-network-based classifier for classifying three distinct scenes (urban, park, and water) from several polarized SAR images of the San Francisco Bay area is discussed. The principal components (PC) scheme or Karhunen-Loeve transform is used to extract the salient features of the input data, and to reduce the dimensionality of the feature space prior to the application to the neural networks. Using the PC scheme along with the polarized images used in the present study led to substantial improvements in the classification rates when compared with previous studies. When a combined polarization architecture was used, the classification rate for water, urban, and park areas improved to 100%, 98.7%, and 96.1%, respectively     

Satellite image analysis using neural networks

The tremendous backlog of unanalyzed satellite data necessitates the development of improved methods for data cataloging and analysis. Ford Aerospace has developed an image analysis system, Satellite Image Analysis using Neural Networks (SIANN), that integrates the technologies necessary to satisfy NASA's science data analysis requirements for the next generation of satellites. SIANN will enable scientists to train a neural network to recognize image data containing scenes of interest and then rapidly search data archives for all such images. The approach combines conventional image processing technology with recent advances in neural networks to provide improved classification capabilities. SIANN allows users to proceed through a four-step process of image classification: filtering and enhancement, creation of neural network training data via application of feature extraction algorithms, configuring and training a neural network model, and classification of images by application of the trained neural network. A prototype experimentation testbed has been completed and applied to climatological data.     

Design of neural networks for classification of remotely sensed imagery

As currently planned, future Earth remote sensing platforms (i.e., Earth Observing System [EOS]) will be capable of generating data at a rate of over 50 Megabits per second. To address this issue the Intelligent Data Management (IDM) project at NASA/GSFC has prototyped an Intelligent Information Fusion System (IIFS) that uses backpropagation neural networks for the classification of remotely sensed imagery. This is part of the IDM strategy of providing archived data to a researcher through a variety of discipline-specific indices. In this paper we discuss classification accuracies of a backpropagation neural network and compare it with a maximum likelihood classifier (MLC) with multivariate normal class models. We have found that, because of its nonparametric nature, the neural network outperforms the MLC in this area. In addition, we discuss techniques for constructing optimal neural nets on parallel hardware like the MasPar MP-1 currently at NASA/GSFC. Other important discussions are centered around training and classification times of the two methods, and sensitivity to the training data. Finally we discuss future work in the area of classification and neural nets.     

Equilibrium analysis of cellular neural networks

Cellular neural networks (CNNs) are dynamical systems, described by a large set of coupled nonlinear differential equations. The equilibrium-point analysis is an important step for understanding the global dynamics and for providing design rules. We yield a set of sufficient conditions (and a simple algorithm for checking them) ensuring the existence of at least one stable equilibrium point. Such conditions give rise to simple constraints, that extend the class of CNNs, for which the existence of a stable equilibrium point is rigorously proved. In addition, they are suitable for design and easy to check, because they are directly expressed in term of the template elements.     

Baltic Sea ice SAR segmentation and classification using modified pulse-coupled neural networks

A method for segmentation and classification of Baltic Sea ice synthetic aperture radar (SAR) images, based on pulse-coupled neural networks (PCNNs), is presented. Also, automated training, which is based on decomposing the total pixel value distribution into a mixture of class distributions, is presented and discussed. The algorithms have been trained and tested using logarithmic scale Radarsat-1 ScanSAR Wide mode images over the Baltic Sea ice. Before the decomposition into mixture of class distributions, an incidence angle correction, specifically designed for these Baltic Sea ice SAR images, is applied. Because the data distributions in the uniform areas of these images are very close to Gaussian distributions, the data are decomposed into a mixture of Gaussian distributions, using the Expectation-Maximazation algorithm. Only uniform image areas are used in the decomposition phase. The mixture of distributions is compared to the distributions of the Baltic Sea ice classes, based on earlier scatterometer measurements and visual video interpretations of the sea ice classes. The parameter values for the PCNN segmentation are defined based on this mixture of distributions. The PCNN segmentation results are also compared to the operational sea ice information of digitized ice charts and to visual interpretation of the sea ice class.     

Elman和BP神经网络在模式分类领域内的对比研究

为了研究Elman神经网络和标准BPNN中何种网络类型更适合于解决模式分类问题,分别构建了基于Elman神经网络的分类模型和基于标准BPNN的分类模型。以平面上二维向量模式的分类为例,对2种分类模型进行训练和泛化能力测试。仿真结果表明,在训练样本数量相等且中小规模网络的条件下,Elman网络模型比BP网络模型具有更高的分类精度,更快的收敛速度,更适合于解决模式分类问题。     

Cognitive radio signal classification based on subspace decomposition and RBF neural networks

Spectrum sensing is one of the major challenges for commercial development of cognitive radio systems, since the detection of the presence of a primary user is a complex task that requires high reliability. This work proposes a signal classifier capable of detecting and identifying a primary user signal on a given channel of the radio spectrum. The proposed approach combines eigen-decomposition techniques and neural networks not only to decide about the presence of a primary user, but also to identify the primary user signal type, a feature that is not encountered in the current approaches proposed in literature. Besides the advantage of identifying the primary user type, the proposed method also considerably reduces the computational cost of the detection process. The proposed classification method has been applied to the development of five primary user signal Classification Modules, which includes wireless microphone, orthogonal frequency-division multiplexing and Digital Video Broadcasting-Terrestrial signals. The results show that the proposed classifier correctly detects and identifies the primary users, even under low signal to noise ratio and multipath scenarios.     

Application of neural networks for sea ice classification inpolarimetric SAR images

Several automatic methods have been developed to classify sea ice types from fully polarimetric synthetic aperture radar (SAR) images, and these techniques are generally grouped into supervised and unsupervised approaches. In previous work, supervised methods have been shown to yield higher accuracy than unsupervised techniques, but suffer from the need for human interaction to determine classes and training regions. In contrast, unsupervised methods determine classes automatically, but generally show limited ability to accurately divide terrain into natural classes. In this paper, a new classification technique is applied to determine sea ice types in polarimetric and multifrequency SAR images, utilizing an unsupervised neural network to provide automatic classification, and employing an iterative algorithm to improve the performance. The learning vector quantization (LVQ) is first applied to the unsupervised classification of SAR images, and the results are compared with those of a conventional technique, the migrating means method. Results show that LVQ outperforms the migrating means method, but performance is still poor. An iterative algorithm is then applied where the SAR image is reclassified using the maximum likelihood (ML) classifier. It is shown that this algorithm converges, and significantly improves classification accuracy. The new algorithm successfully identifies first-year and multiyear sea ice regions in the images at three frequencies. The results show that L- and P-band images have similar characteristics, while the C-band image is substantially different. Classification based on single features is also carried out using LVQ and the iterative ML method. It is found that the fully polarimetric classification provides a higher accuracy than those based on a single feature. The significance of multilook classification is demonstrated by comparing the results obtained using four-look and single-look classifications     

中立型时滞BAM神经网络的稳定性分析

文章介绍了中立型时滞BAM神经网络,并重点分析其稳定性,给出了中立型时滞BAM神经网络的平衡点唯一和全局指数稳定性的判据,同时举例说明判据的正确性和结果的有效性。     

Improved image classification with neural networks by fusing multispectral signatures with topographical data

Automated schemes are needed to classify multispectral remotely sensed data. Human intelligence is often required to correctly interpret images from satellites and aircraft. Humans succeed because they use various types of cues about a scene to accurately define the contents of the image. Consequently, it follows that computer techniques that integrate and use different types of information would perform better than single source approaches. This research illustrated that multispectral signatures and topographical information could be used in concert. Significantly, this dual source tactic classified a remotely sensed image better than the multispectral classification alone. These classifications were accomplished by fusing spectral signatures with topographical information using neural network technology. A neural network was trained to classify Landsat multispectral images of the Black Hills. Bands 4, 5, 6, and 7 were used to generate four classifications based on the spectral signatures. A file of georeferenced ground truth classifications was used as the training criterion. The network was trained to classify urban, agricultural, range, and forest with a 65.7% correctness. Another neural network was programmed and trained to fuse these multispectral signature results with a file of georeferenced altitude data. This topographical file contained 10 levels of elevations. When this nonspectral elevation information was fused with the spectral signatures, the classifications were improved to 73.7% and 75.7%.