Back Propagation Neural Network Classifier Research Articles

Assessments of neural network classifier output codings using variability of Hamming distance

Influences of different output codings on the performance of a Back-Propagation Neural Network classifier were investigated. Experimental results obtained show that output codings with equal Hamming distance outperformed output codings with un-equal Hamming distance between the output states. Performances of the network classifiers are also shown to be closely associated to the variability of Hamming distance between states of the codings used.

Analysis of mammographic microcalcifications using gray-level image structure features

At present, mammography associated with clinical breast examination and breast self-examination is the only effective and viable method for mass breast screening. The presence of microcalcifications is one of the primary signs of breast cancer. It is, difficult however, to distinguish between benign and malignant microcalcifications associated with breast cancer. Here, the authors define a set of image structure features for classification of malignancy. Two categories of correlated gray-level image structure features are defined for classification of "difficult-to-diagnose" cases. The first category of features includes second-order histogram statistics-based features representing the global texture and the wavelet decomposition-based features representing the local texture of the microcalcification area of interest. The second category of features represents the first-order gray-level histogram-based statistics of the segmented microcalcification regions and the size, number, and distance features of the segmented microcalcification cluster. Various features in each category were correlated with the biopsy examination results of 191 "difficult-to-diagnose" cases for selection of the best set of features representing the complete gray-level image structure information. The selection of the best features was performed using the multivariate cluster analysis as well as a genetic algorithm (GA)-based search method. The selected features were used for classification using backpropagation neural network and parameteric statistical classifiers. Receiver operating characteristic (ROC) analysis was performed to compare the neural network-based classification with linear and k-nearest neighbor (KNN) classifiers. The neural network classifier yielded better results using the combined set of features selected through the GA-based search method for classification of "difficult-to-diagnose" microcalcifications.

A review and analysis of backpropagation neural networks for classification of remotely-sensed multi-spectral imagery

Abstract A literature survey and analysis of the use of neural networks for the classification of remotely-sensed multi-spectral imagery is presented. As part of a brief mathematical review, the backpropagation algorithm, which is the most common method of training multi-layer networks, is discussed with an emphasis on its application to pattern recognition. The analysis is divided into five aspects of neural network classification: (1) input data preprocessing, structure, and encoding, (2) output encoding and extraction of classes, (3) network architecture, (4) training algorithms, and (5) comparisons to conventional classifiers. The advantages of the neural network method over traditional classifiers are its nonparametric nature, arbitrary decision boundary capabilities, easy adaptation to different types of data and input structures, fuzzy output values that can enhance classification, and good generalization for use with multiple images. The disadvantages of the method are slow training time, inconsis...

Distributed coding for data representation of back-propagation neural network classifiers

A new distributed input coding is derived by distributing the feature variables over a number of input nodes based on the distribution of the training data. Using this coding method representation, the range of each input node will be fully optimised; this enables the network to converge at a higher rate during training. The coding method also enables the network to maintain the generalisation capability of conventional normalisation coding.

Distributed normalisation input coding to speed up training process of BP-neural network classifier

A coding method, distributed normalisation, is presented to speed up the training process of a back-propagation neural network classifier. In contrast to one-node normalisation coding, the values of the feature variables are distributed over a number of input nodes to increase the representation range of certain parts of each feature variable. A distinct advantage of this coding method is its ability to maintain the generalisation capability of one-node normalisation coding.

A detailed comparison of backpropagation neural network and maximum-likelihood classifiers for urban land use classification

A detailed comparison of the backpropagation neural network and maximum-likelihood classifiers for urban land use classification is presented. Landsat Thematic Mapper images of Tucson, Arizona, and Oakland, California, were used for this comparison. For the Tucson image, the percentage of matching pixels in the two classification maps was only 64.5%, while for the Oakland image it was 83.3%. Although the test site accuracies of the two Tucson maps were similar, the map produced by the neural network was visually more accurate; this difference is explained by examining class regions and density plots in the decision space and the continuous likelihood values produced by both classifiers. For the Oakland scene, the two maps were visually and numerically similar, although the neural network was superior in suppression of mixed pixel classification errors. From this analysis, the authors conclude that the neural network is more robust to training site heterogeneity and the use of class labels for land use that are mixtures of land cover spectral signatures. The differences between the two algorithms may be viewed, in part, as the differences between nonparametric (neural network) and parametric (maximum-likelihood) classifiers. Computationally, the backpropagation neural network is at a serious disadvantage to maximum-likelihood, taking nearly an order of magnitude more computing time when implemented on a serial workstation.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Data fusion with artificial neural networks for classification of earth surface from microwave satellite measurements

A data fusion system with artificial neural networks (ANN) is used for fast and accurate classification of five earth surface conditions and surface changes, based on seven Special Sensor Microwave Imager (SSMI) multichannel microwave satellite measurements. The measurements include brightness temperatures at 19, 22, 37, and 85 GHz at both horizontal and vertical polarizations (only vertical at 22 GHz). The seven channel measurements are processed through a convolution computation such that all measurements are located at same grid. Five surface classes including nonscattering surface, precipitation over land, over ocean, snow, and desert are identified from ground-truth observations. The system processes sensory data in three consecutive phases: (a) preprocessing to extract feature vectors and enhance separability among detected classes; (b) preliminary classification of Earth surface patterns using two separate and parallel-acting classifiers: back-propagation neural network and binary decision tree classifiers; and (c) data fusion of results from preliminary classifiers to obtain the optimal performance in over-all classification. Both the binary decision tree classifier and the fusion processing centers are implemented by neural network architectures. The fusion system configuration is a hierarchical neural network architecture, in which each functional neural net will handle different processing phases in a pipelined fashion. There is a total of around 13,500 samples for this analysis, of which 4% are used as the training set and 96% as the testing set. After training, this classification system is able to bring up the detection accuracy to 94% compared with 88% for back-propagation artificial neural networks and 80% for binary decision tree classifiers. The neural network data fusion classification is currently under progress to be integrated in an image processing system at NOAA and to be implemented in a prototype of a massively parallel and dynamically reconfigurable Modular Neural Ring (MNR).

Correction of intensity variations in MR images for computer-aided tissue classification

A number of supervised and unsupervised pattern recognition techniques have been proposed in recent years for the segmentation and the quantitative analysis of MR images. However, the efficacy of these techniques is affected by acquisition artifacts such as inter-slice, intra-slice, and inter-patient intensity variations. Here a new approach to the correction of intra-slice intensity variations is presented. Results demonstrate that the correction process enhances the performance of backpropagation neural network classifiers designed for the segmentation of the images. Two slightly different versions of the method are presented. The first version fits an intensity correction surface directly to reference points selected by the user in the images. The second version fits the surface to reference points obtained by an intermediate classification operation. Qualitative and quantitative evaluation of both methods reveals that the first one leads to a better correction of the images than the second but that it is more sensitive to operator errors.

THE USE OF NEURAL NETWORK CLASSIFIERS FOR HIGGS SEARCHES

Neural Network Classifiers are used to separate the signal from the background in a High-Energy Physics problem. The basic principles of Multidimensional Analysis by means of Back-Propagation Neural Network Classifiers and the application to the Higgs search are discussed. A search for the Minimal Standard Model Higgs boson, through the reaction [Formula: see text], using the data collected in 1990 by the DELPHI detector at LEP is made. The technique used allows to reach good detection efficiencies and no evidence of the Minimal Standard Model Higgs boson with mass less than 37 GeV is found. The use of Neural Network Classifiers proves to be a very powerful classification method. A comparison of the method with standard analysis techniques is presented.

A two-stage classification scheme with backpropagation neural network classifiers

Abstract This paper introduces backpropagation neural network as a classifier with some practical considerations, and proposes a two-stage classification scheme based on this classifier. A preliminary experiment with a large set of Hangul (Korean script) confirms the superiority relative to a single large neural network classifier.

Classification of multispectral remote sensing data using a back-propagation neural network

The suitability of a back-propagation neural network for classification of multispectral image data is explored. A methodology is developed for selection of both training parameters and data sets for the training phase. A new technique is also developed to accelerate the learning phase. To benchmark the network, the results are compared to those obtained using three other algorithms: a statistical contextual technique, a supervised piecewise linear classifier, and an unsupervised multispectral clustering algorithm. All three techniques were applied to simulated and real satellite imagery. Results from the classification of both Monte Carlo simulation and real imagery are summarized. >