Your search

In the past fractal dimension has often been computed using a stochastic approach based on a random walk process, which has been found to be very time consuming. More recently, mathematical morphology has been used to compute the fractal dimension in a more timely fashion. This paper describes how the fractal dimension computed using mathematical morphology can be used in the texture analysis of ultrasonic imagery. The discriminatory ability of the fractal dimension as a pattern recognition feature is evaluated and compared to more traditional parameters. This analysis includes comparisons with statistical features in which each parameter is treated as an independent variable and in which interactions between those variables are evaluated. Pattern recognition techniques include Stepwise Discriminant Analysis, Linear Discriminant Analysis, and Nearest Neighbor Analyisis in addition to Backpropagation Neural Network Classifiers. Our results identify the fractal dimension as one of the most important parameters for distinguishing between normal and abnormal livers. In this study, consisting of 186 images, a significant statistical difference was found for both the mean and standard deviation of the fractal dimension between the normal and abnormal groups using parametric and nonparametric statistical techniques. © 1993 SPIE. All rights reserved.

Hybrid knowledge bases (HKBs), proposed by Nerode and Subrahmanian, provide a uniform theoretical framework for dealing with the mixed data types and multiple reasoning modes required for solving logical deployment problems. Algorithms based on mixed integer linear programming techniques have been developed for the syntactic subset of HKBs corresponding to function-free Prolog-like logic programs. In this study, we examine the ability of neural networks to solve a more comprehensive set of problems expressed within the hybrid knowledge base framework. The objective of this research is to design and implement a nonlinear optimization procedure for solving extended logic programs with neural networks. We focus upon two types of extensions which are typically required in the formulation of logical deployment problems. The first type of extension, which we shall refer to as a Type I extension, consists of embedding numerical and geometric constraints into logic programs. The second type of extension, which we shall call a Type II extension, consists of incorporating optimization problems into logic clauses. © 1993 SPIE. All rights reserved.

One of the major problems in the development of computer- A ssisted systems for geologic mapping is how to individualize the system to meet user needs. Ideally, the system should be responsive to specifications of desired types of output structures. Also the system should be able to incorporate the user's knowledge of regional characteristics into the feature extraction/selection and classification components. Automatic techniques for classification of remote sensing data typically require relatively large, labeled training sets which are well-organized with respect to the desired mapping between input and output patterns. The present paper focuses on the feature extraction/selection component of the system. Kohonen self-organizing feature maps in conjunction with image processing procedures for linear feature extraction are used for explorative data analysis, feature selection, and construction of exemplar patterns. The results of training Kohonen feature maps with different pattern sets and different feature combinations provide insight into the nature of pattern relationships which enables the user to develop sets of positive and negative training patterns for the classification component. © 1992 SPIE. All rights reserved.

A new multi-threshold Perceptron capable of handling both binary and analog input is presented and discussed. The modified Perceptron replaces the sigmoid function with sinusoidal function. A computer program has been developed to simulate behavior of a network utilizing the modified Perceptron. Both XOR and Parity Check problems were solved using a single-layer network utilizing this modified Perceptron. Based on the results obtained from the simulation the modified Perceptron is capable of solving problems (such as XOR) that can not be solved using a single-layer of the classical Perceptron. Also a network utilizing this modified Perceptron requires fewer number of iterations to converge to a solution than that of a multi-layer Perceptron network using back propagation. 1.

The purpose of this study was to compare the classification capabilities of the backpropagation algorithm and linear discriminant analysis for detecting liver metastisis using image texture features obtained from ultrasonic images of the liver. Twenty-one quantitative parameters were obtained from 134 regions of interest of equal size. The images were collected by the same radiologist on the same imager with the controls adjusted for variations in patient body size so as to produce images of consistent quality. Quantitative features were divided so that 13 were first-order statistics, 6 were second-order statistics, and 2 were image gradient parameters. The same features were processed by both the backpropagation algorithm and linear discriminant analysis using `jack-knife'' testing and the results of each computer- generated classification was compared to the supplied diagnosis in an effort to determine which method could best identify patterns. For this particular application, the backpropagation neural network was found to have slightly superior classification results (87) than linear discriminant analysis (83).

In this paper the ability of two common statistical discriminant analysis procedures are compared with two commercial neural network software packages. The major objective of this study was to determine which of the procedures could best discriminate between normal and abnormal ultrasonic liver textures. The same set of features were input into both statistical discriminant analysis procedures and both neural network models. Preliminary results have found the restricted Coulomb Energy (RCE) neural network model to have a testing accuracy of 90.6% which is approximately 10% better than any of the other techniques investigated. © 1991.

Backpropagation neural networks have been developed for detection of geological lineaments in the Landsat Thematic Mapper (TM) imagery of the Canadian Shield using edge images as input and digitized lineament maps as the desired output. Lineament detection is a challenging problem for traditional image processing and pattern recognition techniques. Many linear features observable in geological image data do not represent lineaments, and the presence and extent of lineaments must be inferred from contextual information. In order to compare the ability of neural networks and conventional classifiers to recognize lineaments prior to performing edge/line element grouping operations, various gradient and curvature features are extracted from the image data set. Selected features from this group formed the inputs to backpropagation neural networks, linear discriminant classifiers, and nearest-neighbor classifiers. The neural network results were compared with the results obtained using conventional classifiers for sample training and test sets. The trained neural network was then applied to the edge image to mask out those edge points which had been classified as non- lineament points.

The primary objective of this research is the development and testing of neural network models for two fundamental computer vision tasks: edge/line detection and texture analysis. In order to test the ability of the neural network models to detect patterns in images we used both remote sensing data and medical imagery. Neural network models for edge and line detection were used to detect geological lineaments in Landsat data. Neural network models for the analysis of image texture variations were used on ultrasonic images to distinguish patients with normal liver scans from patients with diffuse liver disease. 1.

In scientific imaging, it is crucial to obtain precise images to facilitate accurate observations for the given application. However, often times the imaging equipment used to acquire such images introduces error into the observed image. Therefore, there is a fundamental need to remove the error associated with these images in order to facilitate accurate observations. This study investigates the effectiveness of an image processing technique utilizing an iterative deconvolution algorithm to remove error from micro-CT images. This technique is applied to several sets of in-vivo micro CT scans of mice, and its effectiveness is evaluated by qualitative comparison of the resultant thresholded binary images to thresholded binary images produced by more conventional image processing techniques; namely Gaussian filtering and straight thresholding. Results for this study suggest that iterative deconvolution as a pre-processing step produces superior qualitative results as compared to the more conventional methods tested. The groundwork for future quantitative verification is motivated. ©2005 IEEE.

The primary goal of this research was to provide image processing support to aid in the identification of those subjects most affected by bone loss when exposed to weightlessness and provide insight into the causes for large variability. Past research has demonstrated that genetically distinct strains of mice exhibit different degrees of bone loss when subjected to simulated weightlessness. Bone loss is quantified by in vivo computed tomography (CT) imaging. The first step in evaluating bone density is to segment gray scale images into separate regions of bone and background. Two of the most common methods for implementing image segmentation are thresholding and edge detection. Thresholding is generally considered the simplest segmentation process which can be obtained by having a user visually select a threshold using a sliding scale. This is a highly subjective process with great potential for variation from one observer to another. One way to reduce inter-observer variability is to have several users independently set the threshold and average their results but this is a very time consuming process. A better approach is to apply an objective adaptive technique such as the Riddler / Calvard method. In our study we have concluded that thresholding was better than edge detection and pre-processing these images with an iterative deconvolution algorithm prior to adaptive thresholding yields superior visualization when compared with images that have not been pre-processed or images that have been pre-processed with a filter.

The problem of characterizing the relationship between packet size and network delay has received little attention in the field. Research in that area has been limited to either simulation studies or empirical observations that are detached from analytic traffic modeling. From a queueing viewpoint, it is simple to show that these three variables are inter-related, which necessitates a more careful study. We present a traffic model of a router fed by ON/OFF-type sources with heavy-tailed burst sizes. The traffic model considered is consistent with the evidence that Web traffic is heavy-tailed. The analysis cases that are considered establish a quantitative characterization of the complex relationship among packet payload and header sizes, traffic burstiness, and router queueing delay. © 2004 IEEE.

We present a genetic algorithm for heuristically solving a cost minimization problem applied to communication networks with threshold based discounting. The network model assumes that every two nodes can communicate and offers incentives to combine flow from different sources. Namely, there is a prescribed threshold on every link, and if the total flow on a link is greater than the threshold, the cost of this flow is discounted by a factor α. A heuristic algorithm based on genetic strategy is developed and applied to a benchmark set of problems. The results are compared with former branch and bound results using the CPLEX® solver. For larger data instances we were able to obtain improved solutions using less CPU time, confirming the effectiveness of our heuristic approach. Copyright© 2003, Lawrence Erlbaum Associates, Inc.

Temporal and spatial analysis was applied to a sequence of cloud top pressure (CTP) images and cloud optical thickness (TAU) images, and a storm tracking algorithm was proposed. A sequence of storm tracks from the satellite images was developed from the satellite images. Composite images were created by projecting ahead in time and substituting the first valid pixel for missing data, and a variety of CTP and TAU cut-off values were used to identify regions of interest. The region correspondences were determined from one time frame to another which yielded the storm center coordinates. The obtained tracks were compared to the storm tracks computed from sea level pressure data by matching the results first in time and then in spatial distance.

The objective of this study is to compare geometric-based and evolutionary techniques for tracking storm systems from sequences of satellite images. Analysis was applied to the International Satellite Cloud Climatology Project low resolution D1 database for selected storm systems during the month of September, 1988. During this time period there were two exceptionally long tracks of major hurricane systems, Hurricanes Gilbert and Helene. Cloud top pressure and cloud optical thickness were used to identify storm systems. The ability of the geometric-based and evolutionary techniques to generate tracks through storm regions was assessed. Differences in final tracking results between the two techniques resulted not only from the differences in methodology but also form differences in the type of preprocessed input used by each of the techniques. Tracking results were compared to results disseminated by the Colorado State/Tropical Prediction Center and maintained by the National Hurricane Center in Miami, Florida. For the hurricanes investigated in this study, both techniques were able to generate tracks which followed either most or some of the portions of the hurricanes. The evolutionary algorithm was in general able to maintain good continuity along the tracks but, with no knowledge of overall region movement, was unable to discern which of two possible directions would be best to pursue in cases where there were tow or more equally close storm systems components. The geometric method was able to maintain a smooth track close to the course of the hurricane except for confusion primarily at the beginning and/or end of tracks.

Several working or experimental management systems use expert systems techniques for fault management purposes. Although the effort in the area is still growing, most of the expert fault management systems developed were built in an ad-hoc and unstructured basis simply transferring the knowledge of the human expert into an automated system. However, to meet future challenges, a theoretical foundation for fault management must be established aiming to bridge the gap between the working systems and research, and to provide a general structured model easily expandable to future networks. In this paper an algorithm is proposed to simplify the set of clustered alarms. This algorithm is based on the techniques widely used in the Logic Design field to simplify switching functions. The performance of the proposed algorithm is analyzed and the results are compared to those of a traditional algorithm.

A quality assurance system is essential for the credibility and structured growth of anaesthesiology-based transoesophageal echocardiography (TEE) programmes. We have developed software (Q/A Kappa), involving a 400- line source code, capable of directly reporting kappa correlation coefficient values, using external reviewer interpretations as the 'gold standard', and thereby allowing systematic assessment of the validity of intraoperative echocardiographic interpretation. This paper presents assessment of the validity of 240 intraoperative anaesthesiologists' echocardiographic interpretations, and, in addition, the results of field testing of this prototypical software. Data, derived from consecutive cardiac surgery patients, consisted of standardized two-dimensional transoesophageal echocardiographic, colour flow and Doppler imaging sequences. Intraoperative and off-line 'gold standard' TEE interpretations were compared for 19 fields or variables using the Q/A Kappa program. The kappa correlation coefficients were highly variable and dependent on the examination field, ranging from 0.08 for apical regional wall motion scores to 1.00 for tricuspid regurgitation grade, left atrial measurement, aortic valve anatomy and left ventricular long axis and short axis global function. The correlation coefficients were also operator dependent. These data (480 interpretations) were also manually integrated into the equation required for calculation of values of the variable kappa correlation coefficient. The relationship between Q/A Kappa-derived values and manually calculated values was highly significant (p < 0.001; r = 1.0). The implications and possible explanations of the results for particular examination fields are discussed. This study also demonstrates successful seamless functioning of this software program from data entry, segmentation into tables and valid statistical analysis. These findings suggest that it is practical to provide sophisticated continuous quality improvement TEE data on a routine basis.

During the software lifecycle, the software structure is subject to many changes in order to fulfill the customer's requirements. In Distributed Object Oriented systems, software engineers face many challenges to solve the software-hardware mismatch problem in which the software structure does not match the customer's underlying hardware. A major design problem of Object Oriented software systems is the efficient distribution of software classes among the different nodes in the system while maintaining two features: low-coupling and high software quality. In this paper, we present a new methodology for efficiently restructuring Distributed Object Oriented software systems to improve the overall system performance and to solve the softwarehardware mismatch problem. Our method has two main phases. In the first phase, we use the hierarchical clustering method to restructure the target software application. As a result, all the possible clustering solutions that could be applied to the target software application are generated. In the second phase, we decide on the best-fit clustering solution according to the customer hardware organization.