In this paper, we present a novel iterative MPEG super-resolution method based on an embedded constraint version of Adaptive projected subgradient method [Yamada & Ogura 2003]. We propose an efficient operator that approximates convex projection onto a set characterizing framewise quantization, whereas a conventional method can only handle a convex projection defined for each DCT coefficient of a frame. By using the operator, the proposed method generates a sequence that efficiently approaches to a solution of super-resolution problem defined in terms of quantization error of MPEG compression.

This paper presents two novel blind set-theoretic adaptive filtering algorithms for suppressing "Multiple Access Interference (MAI)," which is one of the central burdens in DS/CDMA systems. We naturally formulate the problem of MAI suppression as an asymptotic minimization of a sequence of cost functions under some linear constraint defined by the desired user's signature. The proposed algorithms embed the constraint into the direction of update, and thus the adaptive filter moves toward the optimal filter without stepping away from the constraint set. In addition, using parallel processors, the proposed algorithms attain excellent performance with linear computational complexity. Geometric interpretation clarifies an advantage of the proposed methods over existing methods. Simulation results demonstrate that the proposed algorithms achieve (i) much higher speed of convergence with rather better bit error rate performance than other blind methods and (ii) much higher speed of convergence than the non-blind NLMS algorithm (indeed, the speed of convergence of the proposed algorithms is comparable to the non-blind RLS algorithm).

The purpose of this paper is to present the novel technique to solve the recognition errors in invariant range image multi-pose face recognition. The scale, center and pose error problems were solved by using the geometric transform. Range image face data (RIFD) was obtained from a laser range finder and was used in the model to generate multi-poses. Each pose data size was reduced by linear reduction. The reduced RIFD was transformed to the gradient face model for facial feature image extraction and also for matching using the Membership Matching Score model. Using this method, the results from the experiment are acceptable although the size of gradient face image data is quite small (659 elements). Three-Layer Matching Search was the algorithm designed to reduce the access timing to the most accurate and similar pose position. The proposed algorithm was tested using facial range images from 130 people with normal facial expressions and without eyeglasses. The results achieved the mean success rate of 95.67 percent of 12 degrees up/down and left/right (UDLR) and 88.35 percent of 24 degrees UDLR.

In this paper, we propose two adaptive filtering schemes for Stereophonic Acoustic Echo Cancellation (SAEC), which are based on the adaptive projected subgradient method (Yamada et al., 2003). To overcome the so-called non-uniqueness problem, the schemes utilize a certain preprocessing technique which generates two different states of input signals. The first one simultaneously uses, for fast convergence, data from two states of inputs, meanwhile the other selects, for stability, data based on a simple min-max criteria. In addition to the above difference, the proposed schemes commonly enjoy (i) robustness against noise by introducing the stochastic property sets, and (ii) only linear computational complexity, since it is free from solving systems of linear equations. Numerical examples demonstrate that the proposed schemes achieve, even in noisy situations, compared with the conventional technique, (i) much faster and more stable convergence in the learning process as well as (ii) lower level mis-identification of echo paths and higher level Echo Return Loss Enhancement (ERLE) around the steady state.

This paper presents a novel blind multiple access interference (MAI) suppression filter in DS/CDMA systems. The filter is adaptively updated by parallel projections onto a series of convex sets. These sets are defined based on the received signal as well as a priori knowledge about the desired user's signature. In order to achieve fast convergence and good performance at steady state, the adaptive projected subgradient method (Yamada et al., 2003) is applied. The proposed scheme also jointly estimates the desired signal amplitude and the filter coefficients based on an approximation of an EM type algorithm, following the original idea proposed by Park and Doherty, 1997. Simulation results highlight the fast convergence behavior and good performance at steady state of the proposed scheme.

This paper provides a novel signal processing for detecting defects based on the spatio-temporal gradient analysis over the Lamb-wave field. The proposed processing classifies the wave field through the rank of the covariance matrix which is defined by the four-dimensional vector with following components: a vertical displacement, its vertical velocity, and a pair of out-of-plane shearing strains. The covariance matrix provides the information about defects. Its determinant, therefore, is proposed as the inhomogeneity-index of the object surface. In this study, the physical meanings of the proposed index are shown, the computational process in the Lamb-wave field near the defects is discussed and their behaviors are investigated through FDTD-simulations and acoustic experiments.

Applying the formerly proposed classification framework for first order line search optimization techniques we introduce novel superlinear first order line search methods. Novelty of the methods lies in the line search subproblem. The presented line search subproblem features automatic step length and momentum adjustments at every iteration of the algorithms realizable in a single step calculation. This keeps the computational complexity of the algorithms linear and does not harm the stability and convergence of the methods. The algorithms have none or linear memory requirements and are shown to be convergent and capable of reaching the superlinear convergence rates. They were practically applied to artificial neural network training and compared to the relevant training methods within the same class. The simulation results show satisfactory performance of the introduced algorithms over the standard and previously proposed methods.

Structural learning algorithms are obtained by adding a penalty criterion (usually comes from the network structure) to the conventional criterion of the sum of squared errors and applying the backpropagation (BP) algorithm. This problem can be viewed as a constrained minimization problem. In this paper, we apply the Lagrangian differential gradient method to the structural learning based on the backpropagation-like algorithm. Computational experiments for both artificial and real data show that the improvement of generalization performance and the network optimization are obtained applying the proposed method.

This paper describes a VLSI-oriented motion estimation algorithm using a steepest descent method (SDM) applied to MPEG-4 visual communication with a mobile terminal. The SDM algorithm is optimized for QCIF or CIF resolution video and VLSI implementation. The SDM combined with a subblock search method is developed to enhance picture quality. Simulation results show that a mean PSNR drop of the SDM algorithm processing QCIF 15 fps resolution video in comparison with a full search algorithm is -0.17 dB. Power consumption of a VLSI based on the SDM algorithm assuming 0.18 µm CMOS technology is estimated at 2 mW. The VLSI attains higher picture quality than that based on the other fast motion estimation algorithm, and is applicable to mobile video applications.

In this letter, we propose a groupwise successive interference cancellation (GSIC) receiver with gradient descent search for multi-rate DS-CDMA system. Proposed receiver incorporates iterative gradient descent search algorithm into conventional GSIC receiver for multi-rate DS-CDMA system. It is shown that the receiver achieves significant performance improvement over the matched filter (MF) receiver, GSIC receiver, multi-stage parallel interference cacnellation (PIC) receiver, multi-stage partial PIC receiver, and GSIC receiver with PIC in a Rayleigh fading channel.

This paper presents a cost-effective CORDIC-based architecture for adaptive lattice filters. An implementation method for an ARMA lattice filter using the CORDIC algorithm has been proposed. The previously proposed method can provide a simple filter architecture; however, it has problems such as redundant structure and numerical inaccuracy. Therefore, by solving each problem we derive a new non-redundant filter architecture with improved numerical accuracy. The obtained filter architecture provides a low cost ARMA lattice filter in which high-precision data processing is feasible. In addition, the proposed architecture can be applied to AR-type lattice filters, so that it may have several applications in adaptive signal processing. The presented filter architecture is useful from a hardware point of view because it facilitates an effective VLSI design of various adaptive lattice filters.

Edge linking is a fundamental computer vision task, yet presents difficulties arising from the lack of information in the image. Viewed as a constrained optimization problem, it is NP hard-being isomorphic to the classical Traveling Salesman Problem. This paper proposes a gradient ascent learning algorithm of the elastic net approach for edge linking of images. The learning algorithm has two phases: an elastic net phase, and a gradient ascent phase. The elastic net phase minimizes the path through the edge points. The procedure is equivalent to gradient descent of an energy function, and leads to a local minimum of energy that represents a good solution to the problem. Once the elastic net gets stuck in local minima, the gradient ascent phase attempts to fill up the valley by modifying parameters in a gradient ascent direction of the energy function. Thus, these two phases are repeated until the elastic net gets out of local minima and produces the shortest or better contour through edge points. We test the algorithm on a set of artificial images devised with the aim of demonstrating the sort of features that may occur in real images. For all problems, the systems are shown to be capable of escaping from the elastic net local minima and producing more meaningful contours than the original elastic net.

Edge detection has been an essential step in image processing, and there has been much work undertaken to date. This paper inspects a fuzzy mathematical morphology in order to reach a higher-level of edge-image processing. The proposed scheme uses a fuzzy morphological gradient to detect object boundaries, when the boundaries are roughly defined as a curve or a surface separating homogeneous regions. The automatic edge detection algorithm consists of two major steps. First, a new version of anisotropic diffusion is proposed for edge detection and image restoration. All improvements of the new version use fuzzy mathematical morphology to preserve the edge accuracy and to restore the images to homogeneity. Second, the fuzzy morphological gradient operation detects the step edges between the homogeneous regions as object boundaries. This operation uses geometrical characteristics contained in the structuring element in order to extract the edge features in the set of edgeness, a set consisting of the quality values of the edge pixels. This set is prepared with fuzzy logic for decision and selection of authentic edge pixels. For experimental results, the proposed method has been tested successfully with both synthetic and real pictures.

This paper proposes a new approach to fuzzy inference system for modeling nonlinear systems based on measured input and output data. In the suggested fuzzy inference system, the number of fuzzy rules and parameter values of membership functions are automatically decided by using the extended kernel method. The extended kernel method individually performs linear transformation and kernel mapping. Linear transformation projects input space into linearly transformed input space. Kernel mapping projects linearly transformed input space into high dimensional feature space. Especially, the process of linear transformation is needed in order to solve difficulty determining the type of kernel function which presents the nonlinear mapping in according to nonlinear system. The structure of the proposed fuzzy inference system is equal to a Takagi-Sugeno fuzzy model whose input variables are weighted linear combinations of input variables. In addition, the number of fuzzy rules can be reduced under the condition of optimizing a given criterion by adjusting linear transformation matrix and parameter values of kernel functions using the gradient descent method. Once a structure is selected, coefficients in consequent part are determined by the least square method. Simulated results of the proposed technique are illustrated by examples involving benchmark nonlinear systems.

A reduced complexity multiple-input multiple-output (MIMO) equalizer with ordered successive interference cancellation (OSIC) is proposed for combating intersymbol interference (ISI) and cochannel interference (CCI) over frequency-selective multipath channels. It is developed as a reduced-rank realization of the conventional MMSE decision feedback equalizer (DFE). In particular, the MMSE weight vectors at each stage of OSIC are computed based on the generalized sidelobe canceller (GSC) technique and reduced-rank processing is incorporated by using the conjugate gradient (CG) algorithm for reduced complexity implementation. The CG algorithm leads to a best low-rank representation of the GSC blocking matrix via an iterative procedure, which in turn gives a reduced-rank equalizer weight vector achieving the best compromise between ISI and CCI suppression. With the dominating interference successfully cancelled at each stage of OSIC, the number of iterations required for the convergence of the CG algorithm decreases accordingly for the desired signal. Computer simulations demonstrate that the proposed reduced-rank MIMO DFE can achieve nearly the same performance as the full-rank MIMO MMSE DFE with an effective rank much lower than the dimension of the signal-plus-interference subspace.

A robust adaptive filtering algorithm was established recently (I. Yamada, K. Slavakis, K. Yamada 2002) based on the interactive use of statistical noise information and the ideas developed originally for efficient algorithmic solutions to the convex feasibility problems. The algorithm is computationally efficient and robust to noise because it requires only an iterative parallel projection onto a series of closed half spaces highly expected to contain the unknown system to be identified and is free from the computational load of solving a system of linear equations. In this letter, we show the potential applicability of the adaptive algorithm to the identification problem for the second order Volterra systems. The numerical examples demonstrate that a straightforward application of the algorithm to the problem soundly realizes fast and stable convergence for highly colored excited speech like input signals in possibly noisy environments.

This paper describes two methods to construct fuzzy inference rules by the simplified fuzzy reasoning. The present methods have a construction mechanism of the rule unit that is applicable in two parameters: the central value and the width of the membership function in the antecedent part. The first approach is to create a rule unit near the selected rule which has the nearest position from the central input space for the central value. The second is to create a rule unit near the selected rule which has the minimum width for the width. Experimental results are presented in order to show that the proposed methods are effective in difference on the inference error and the number of learning iterations.

This paper describes an ultra low power, motion estimation (ME) processor for MPEG2 HDTV resolution video. It adopts a Gradient Descent Search (GDS) algorithm that drastically reduces required computational power to 6 GOPS. A SIMD datapath architecture optimized for the GDS algorithm decreases the clock frequency and operating voltage. A low power 3-port SRAM with a write-disturb-free cell array arrangement is newly designed for image data caches of the processor. The proposed ME processor contains 7-M transistors, integrated in 4.50 mm 3.35 mm area using 0.13 µm CMOS technology. Estimated power consumption is less than 100 mW at 81 MHz@1.0 V. The processor is applicable to a portable HDTV system.

This paper proposes a gradient ascent learning algorithm for the elastic net approach to the Traveling Salesman Problem (TSP). The learning model has two phases: an elastic net phase, and a gradient ascent phase. The elastic net phase is equivalent to gradient descent of an energy function, and leads to a local minimum of energy that represents a good solution to the problem. Once the elastic net gets stuck in local minima, the gradient ascent phase attempts to fill up the valley by modifying parameters in a gradient ascent direction of the energy function. Thus, these two phases are iterated until the elastic net gets out of local minima. We test the algorithm on many randomly generated travel salesman problems up to 100 cities. For all problems, the systems are shown to be capable of escaping from the elastic net local minima and generating shorter tour than the original elastic net.

The density gradient (DG) model is tested for its ability to describe tunneling currents through thin insulating barriers. Simulations of single barriers (MOS diodes, MOSFETs) and double barriers (RTDs) show the limitations of the DG model. For comparison, direct tunneling currents are calculated with the Schrodinger-Bardeen method and used as benchmark. The negative differential resistance (NDR) observed in simulating tunneling currents with the DG model turns out to be an artifact related to large density differences in the semiconductor regions. Such spurious NDR occurs both for single and double barriers and vanishes, if all semiconductor regions are equally doped.