Hossam Osman

Fuzzy logic approach to data association

This paper proposes a new fuzzy logic approach for solving the data association problem typically encountered in the application of target tracking. A single massive target maneuvering in a heavily-cluttered underwater environment is considered. The proposed fuzzy data association (FDA) approach is combined with an interacting multiple model (IMM) filter. The resultant IMM-FDA tracking algorithm is applied to estimate the state of the maneuvering target, and its performance is compared to that of a combination of an IMM filter and the probabilistic data association (PDA) scheme. The obtained results indicate that the IMM-FDA significantly outperforms the IMM-PDA at the expense of requiring more computational cost and introducing a short processing lag.

Classification of ships in airborne SAR imagery using backpropagation neural networks

This paper proposes using a backpropagation (BP) neural network for the classification of ship targets in airborne synthetic aperture radar (SAR) imagery. The ship targets consisted of 2 destroyers, 2 cruisers, 2 aircraft carriers, a frigate and a supply ship. A SAR image simulator was employed to generate a training set, a validation set, and a test set for the BP classifier. The features required for classification were extracted from the SAR imagery using three different methods. The first method used a reduced resolution version of the whole SAR image as input to the BP classifier using simple averaging. The other two methods used the SAR image range profile either before or after a local-statistics noise filtering algorithm for speckle reduction. Performance on an extensive test set demonstrated the performance and computational advantages of applying the neural classification approach to targets in airborne SAR imagery. Improvements due to the use of multi-resolution features were also observed.

JPEG encoder for low-cost FPGAs

This paper presents the implementation of a JPEG encoder that exploits minimal usage of FPGA resources. The encoder compresses an image as a stream of 8times8 blocks with each element of the block applied and processed individually. The zigzag unit typically found in implementations of JPEG encoders is eliminated. The division operation of the quantization step is replaced by a combination of multiplication and shift operations. The encoder is implemented on Xilinx Spartan-3 FPGA and is benchmarked against two software implementations on four test images. It is demonstrated that it yields performance of similar quality while requiring very limited FPGA resources. A co-emulation technique is applied to reduce development time and to test and verify the encoder design.

On the discriminatory power of adaptive feed-forward layered networks

This correspondence expands the available theoretical framework that establishes a link between discriminant analysis and adaptive feed-forward layered linear-output networks used as mean-square classifiers. This has the advantages of providing more theoretical justification for the use of these nets in pattern classification and gaining a better insight into their behavior and about their use. The authors prove that, under reasonable assumptions, minimizing the mean-square error at the network output is equivalent to minimizing the following: 1) the difference between the optimum value of a familiar discriminant criterion and the value of this criterion evaluated in the space spanned 2) the outputs of the final hidden layer, and 3) the difference between the values of the same discriminant criterion evaluated in desired-output and actual-output subspaces. The authors also illustrate, under specific constraints, how to solve the following problem: given a feature extraction criterion, how the target coding scheme can be selected such that this criterion is maximized at the output of the network final hidden layer. Other properties for these networks are explored. >

Neural classifiers and statistical pattern recognition: applications for currently established links

Recent research has linked backpropagation (BP) and radial basis function (RBF) network classifiers, trained by minimizing the standard mean square error (MSE), to two main topics in statistical pattern recognition (SPR), namely the Bayes decision theory and discriminant analysis. However, so far, the establishment of these links has resulted in only a few practical applications for training, using, and evaluating these classifiers. The paper aims at providing more of these applications. It first illustrates that while training a linear output BP network, the explicit utilization of the network discriminant capability leads to an improvement in its classification performance. Then, for linear output BP and RBF networks, the paper defines a new generalization measure that provides information about the closeness of the network classification performance to the optimal performance. The estimation procedure of this measure is described and its use as an efficient criterion for terminating the learning algorithm and choosing the network topology is explained. The paper finally proposes an upper bound on the number of hidden units needed by an RBF network classifier to achieve an arbitrary value of the minimized MSE. Experimental results are presented to validate all proposed applications.

Probabilistic winner-take-all learning algorithm for radial-basis-function neural classifiers

This paper proposes a new adaptive competitive learning algorithm called the probabilistic winner-take-all. The algorithm is based on a learning scheme developed by Agrawala within the statistical pattern recognition literature (Agrawala 1970). Its name stems from the fact that for a given input pattern once each competitor computes the probability of being the one that generated this pattern, the computed probabilities are utilized to probabilistically choose a winner. Then, only this winner is permitted to learn. The learning rule of the algorithm is derived for three different cases. Its properties are discussed and compared to those of two other competitive learning algorithms, namely the standard winner-take-all and the maximum-likelihood soft competition. Experimental comparison is also given. When all three algorithms are used to train the hidden layer of radial-basis-function classifiers, experiments indicate that classifiers trained with the probabilistic winner-take-all outperform those trained with the other two algorithms.

Enhanced SVM versus Several Approaches in SAR Target Recognition

This paper presents a comparative study between different automatic target recognition (ATR) approaches in the application of synthetic aperture radar (SAR) target recognition. Four different categories of approaches are investigated and compared. The first is distribution-based where a statistical data model is assumed for the SAR image data. The second category contains one approach that is based upon principal component analysis (PCA). The third category employs different neural network architectures. The last category utilizes support vector machines (SVM). It contains the classical SVM implementation and an enhanced implementation proposed elsewhere by the authors in which the traditional Euclidean kernel is replaced by a new one that is more suitable for the application in question. Experimental results are presented. It is shown that the enhanced SVM approach outperforms all other investigated approaches in both the classification performance and the confuser rejection

New fuzzy-based indoor positioning scheme using ZigBee wireless protocol

This paper proposes new fuzzy-based scheme providing position information vital for smart home applications. The scheme runs efficiently on the economical wireless ZigBee nodes and uses the link quality indicator (LQI) measured without the need for any additional hardware. It uses fuzzy logic to represent measure noise and surrounding environmental impacts. Position estimation is based upon the fuzzy information provided by all available ZigBee nodes and the surrounding environment is modeled by assembling a set of representative fuzzy vectors. Fuzzy levels are determined by applying the K-means algorithm given the LQI distribution as input. The scheme performance is compared to two popular schemes, the I3BM and the Environment Adaptive. The three are implemented using the Jennic JN5148 ZigBee PRO kit. It is demonstrated that for regular motion the proposed scheme significantly outperforms the other two without high computational cost, slow response, or large memory requirement.

Novel Multiclass SVM-Based Binary Decision Tree Classifier

This paper proposes a novel algorithm for constructing multiclass SVM-based binary decision tree classifiers. The basic strategy of the proposed algorithm is to set the target values for the training patterns such that linear separability is always achieved and thus a linear SVM can be constructed at each non-leaf node. It is argued that replacing complex, nonlinear SVMs by a larger number of linear SVMs remarkably reduces training and classification times as well as classifier size without compromising classification performance. This is experimentally demonstrated through a comparative analysis involving the most efficient existing multiclass SVM classifiers, namely the one-against-rest and the one-against-one.

New Spatial FCM Approach with Application to SAR Target Clustering

This paper develops a new fuzzy clustering approach that is suitable for image processing applications. The developed approach is based upon the classical fuzzy c-means (FCM) and referred to as the spatial FCM (SFCM). Its effectiveness is due to two mechanisms. The first is the replacement of the Euclidean distance traditionally used to measure similarity between input images and clusters prototypes by a novel similarity measure that considers spatial relationships between image pixels and thus becomes less sensitive to image perturbations. The second SFCM mechanism for effectiveness is the addition of a similarity penalty term to FCMs objective function. The aim is to encourage clustering similar images into same clusters. The SFCM is compared to the FCM and some of its variants in the difficult application of synthetic aperture radar (SAR) target clustering. It is shown that the SFCM consistently yields better performance