A technique for block-loss restoration in block-based image and video coding, dubbed recovery of image blocks using the method of alternating projections (RIBMAP), is developed. The algorithm is based on orthogonal projections onto constraint sets in a Hilbert space. For the recovery of a linear dimension N size block, a total of 8N vectors are extracted from the surrounding area of an N x N missing block. These vectors form a library from which the best matching spatial information for the missing block is extracted. Recovery vectors, including both undamaged and restored damaged pixels, are introduced. The vectors are used to find highly correlated information relating to the lost pixels. To assure continuity with the surrounding undamaged area, three additional convex constraints are formulated. Adherance to these sets is imposed using alternating projections. Simulation results using orthogonal projections demonstrate that RIBMAP recovers spatial structure faithfully. Simulation comparisons with other procedures are presented: Ancis and Giusto's hybrid edge-based average-median interpolation technique, Sun and Kwok's projections onto convex sets-based method, Hemami and Meng's interblock correlation interpolation approach, Shirani et al.'s modified interblock correlation interpolation scheme, and Alkachouh and Bellanger's fast discrete cosine transformation-based spatial domain interpolation algorithm. Characteristic of the results are those of the "Lena" JPEG image when one fourth of periodically spaced blocks in the image have errors. The peak signal-to-noise ratio of the restored image is 28.68, 29.99, 31.86, 31.69, 31.57, and 34.65 dB using that of Ancis and Giusto, Sun and Kwok, Hemami and Meng, Shirani et al., Alkachouh and Bellanger, and RIPMAP, respectively.

Block loss and propagation error due to cell loss or missing packet information during the transmission over lossy networks can cause severe degradation of block and predictive-based video coding. Herein, new fast spatial and temporal methods are presented for block loss recovery. In the spatial algorithm, missing block recovery and edge extention are performed by pixel replacement based on range constraints imposed by surrounding neighborhood edge information and structure. In the temporal algorithm, an adaptive temporal correlation method is proposed for motion vector (MV) recovery. Parameters for the temporal correlation measurement are adaptively changed in accordance to surrounding edge information of a missing macroblock (MB). The temporal technique utilizes pixels in the reference frame as well as surrounding pixels of the lost block. Spatial motion compensation is applied after MV recovery when the reference frame does not have sufficient information for lost MB restoration. Simulations demonstrate that the proposed algorithms recover image information reliably using both spatial and temporal restoration. We compare the proposed algorithm with other procedures with consistently favorable results.

Equalization of satellite communication using complex-bilinear recurrent neural network (C-BLRNN) is proposed. Since the BLRNN is based on the bilinear polynomial, it can be used in modeling highly nonlinear systems with time-series characteristics more effectively than multilayer perceptron type neural networks (MLPNN). The BLRNN is first expanded to its complex value version (C-BLRNN) for dealing with the complex input values in the paper. C-BLRNN is then applied to equalization of a digital satellite communication channel for M-PSK and QAM, which has severe nonlinearity with memory due to traveling wave tube amplifier (TWTA). The proposed C-BLRNN equalizer for a channel model is compared with the currently used Volterra filter equalizer or decision feedback equalizer (DFE), and conventional complex-MLPNN equalizer. The results show that the proposed C-BLRNN equalizer gives very favorable results in both the MSE and BER criteria over Volterra filter equalizer, DFE, and complex-MLPNN equalizer.

An edge preserving image compression algorithm based on an unsupervised competitive neural network is proposed. The proposed neural network, the called weighted centroid neural network (WCNN), utilizes the characteristics of image blocks from edge areas. The mean/residual vector quantization (M/RVQ) scheme is utilized in this proposed approach as the framework of the proposed algorithm. The edge strength of image block data is utilized as a tool to allocate the proper code vectors in the proposed WCNN. The WCNN successfully allocates more code vectors to the image block data from edge area while it allocates less code vectors to the image black data from shade or non-edge area when compared to conventional neural networks based on VQ algorithm. As a result, a simple application of WCNN to an image compression problem gives improved edge characteristics in reconstructed images over conventional neural network based on VQ algorithms such as self-organizing map (SOM) and adaptive SOM.

An unsupervised competitive learning algorithm based on the classical -means clustering algorithm is proposed. The proposed learning algorithm called the centroid neural network (CNN) estimates centroids of the related cluster groups in training date. This paper also explains algorithmic relationships among the CNN and some of the conventional unsupervised competitive learning algorithms including Kohonen's self-organizing map (SOM) and Kosko's differential competitive learning (DCL) algorithm. The CNN algorithm requires neither a predetermined schedule for learning coefficient nor a total number of iterations for clustering. The simulation results on clustering problems and image compression problems show that CNN converges much faster than conventional algorithms with compatible clustering quality while other algorithms may give unstable results depending on the initial values of the learning coefficient and the total number of iterations.

A new image compression algorithm based on an unsupervised competitive neural network to prevent the edge degradation is proposed. The proposed unsupervised competitive neural network, called weighted centroid neural network (WCNN), utilizes the characteristics of image blocks from edge areas. The mean/residual VQ (M/R VQ)) scheme is utilized in this proposed approach as the frame work of the proposed algorithm. A novel measure for calculating edge strength is devised by using the residue of an image block data from the M/R scheme. The edge strength of an image block data is then utilized as a tool to allocate the proper code vectors in the proposed WCNN. The WCNN successfully allocates more code vectors to the image block data from edge area while it allocates less code vectors to the image block data from shade or non-edge area when compared to conventional the neural network based VQ algorithm. As a result, a simple application of WCNN to image compression problem gives improved edge characteristics in reproduced images over conventional neural network based VQ algorithms.

A training procedure that adapts the weights of a trained layered perceptron artificial neural network to training data originating from a slowly varying nonstationary process is proposed. The resulting adaptively trained neural network (ATNN), based on nonlinear programming techniques, is shown to adapt to new training data that are in conflict with earlier training data without affecting the neural networks' response to data elsewhere. The adaptive training procedure also allows for new data to be weighted in terms of its significance. The adaptive algorithm is applied to the problem of electric load forecasting and is shown to outperform the conventionally trained layered perceptron.

Multilayer perceptrons and trained classification trees are two very different techniques which have recently become popular. Giving enough data and time, both methods are capable of performing arbitrary nonlinear classification. The two techniques have not previously been compared on real-world problems. The authors first consider the important differences between multilayer perceptrons and classification trees and conclude that there is not enough theoretical basis for the clear-cut superiority of one technique over the other. They then present results of a number of empirical tests on quite different problems in power system load forecasting and speaker-independent vowel identification. They compare the performance for classification and prediction in terms of accuracy outside the training set. In all cases, even with various sizes of training sets, the multilayer perceptron performed as well as or better than the trained classification trees. The authors are confident that the univariate version of the trained classification trees do not perform as well as the multilayer perceptron. More studies are needed, however, on the comparative performance of the linear combination version of the classification trees.>