Search

• This paper presents a family of normalized DSAs (NDSAs). • Low-order norm constraints are used to improve the performance for sparse system identification. • A variable step-size is derived for the family of DSAs to reduce steady-state misalignment. • Simulation results are provided to verify the effectiveness of the proposed algorithms. The classical sign algorithm (SA) has attracted much attention in many applications because of its low computational complexity and robustness against impulsive noise. However, its steady-state mean-square derivation (MSD) is large when a large step-size is used to guarantee a relatively fast convergence rate. To address this problem, the dual sign algorithm (DSA) was developed by using a piecewise cost function in the literature. In this paper a family of normalized DSAs (NDSAs) is proposed to further improve the performance of the DSA in terms of MSD. Specifically, two sparse NDSAs are firstly developed, by using the ℓ 1 -norm and ℓ 0 -norm constraints, respectively; on this basis, some variable step-size algorithms are then proposed based on mean-square a posteriori error minimization. Finally, simulation results are provided to show the superior performance of our proposed algorithms. [ABSTRACT FROM AUTHOR]

The multimodulus algorithm (MMA) is widely used to suppress inter-symbols interference (ISI) in communication systems because of its advantages that it can complete blind equalization and carrier phase recovery simultaneously. However, the slow convergence speed of MMA causes the equalizer to be unable to eliminate ISI effectively, which deteriorate the communication quality of the system. For that, we first present a momentum fractional order MMA (MFOMMA) to improve the performance of MMA for blind equalization in this paper. By optimizing MMA with the momentum term and the fractional order gradient information of the cost function, the proposed algorithm can get better ISI suppression performance. Then, the convergence performance of MFOMMA is analyzed to reveal the relationship between algorithm parameters and equalization ability. Moreover, in order to further enhance the ISI elimination capability of MFOMMA, we develop a variable fractional order scheme, which guarantee that the algorithm not only obtains a faster convergence speed but also a lower residual ISI. Finally, the effectiveness and superiorities of the proposed algorithm are demonstrated by some simulation experiments. [ABSTRACT FROM AUTHOR]

This paper proposes robust diffusion maximum versoria criterion algorithms to enhance the performance of the distributed estimation in a network of agents under impulsive noise environment. The diffusion maximum versoria criterion is a novel algorithm, under time-dependent constraint on the squared norm of the intermediate update at each node. To develop the robust version of the algorithm, the constraints are calculated by shared information which are collected from connected neighbors. The stability and steady-state performance of the proposed algorithms are also analyzed. We further exploit an altered dichotomous coordinate-descent (DCD) method to improve the performance and to reduce the complexity of the proposed algorithms in shifted-structure input regressors environment. Performance analysis and simulation results show the effectiveness and robustness of the proposed algorithms in various impulsive noise scenarios. [ABSTRACT FROM AUTHOR]

This paper presents a new adaptive algorithm for joint beamforming and antenna selection in mobile communication systems. Such an algorithm is of particular interest for massive multiple-input multiple-output (mMIMO) antenna systems along with limited number of available radio-frequency chains. The proposed algorithm is based on introducing an ℓ 0 -norm constraint to an established adaptive-projection beamforming optimization scheme. In doing so, a real-time beamforming optimization can be carried out, resulting in a beamforming vector that tends to be sparse. The higher-magnitude elements of such a vector point out to the antenna-array elements that have the largest contribution to the output signal-to-interference-plus-noise ratio (SINR). Consequently, an effective antenna selection can be achieved directly by considering the magnitude of the beamforming coefficients. Simulation results confirm the effectiveness of the proposed algorithm in enhancing the output SINR. • A new adaptive algorithm for joint beamforming and antenna selection is proposed. • The proposed algorithm is targeted for massive MIMO antenna systems. • A limited number of RF chains is considered. • An ℓ 0 -norm constraint is used for developing the proposed algorithm. • Simulation results show the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

This paper proposes a fast algorithm to compute arbitrary α -stable PDFs and CDFs. The procedure is based on off-line precomputations of α -stable values on a grid of points in the α – β parameter space, as well as in a set of abscissa points. The grid is built by defining two quality measures and assuring that minimum values for these measures are reached on those points. Results indicate that the method here proposed is substantially faster than directly evaluating the standard expressions proposed by Nolan [1] . The proposed algorithm makes it possible to efficiently use estimation methods based on the evaluation of the PDF, such as the Maximum Likelihood (ML) principle, which gives asymptotically unbiased and efficient estimates. To this end, an ML-based estimation algorithm is provided as well. [ABSTRACT FROM AUTHOR]

This paper focuses on the parameter estimation problems of output error autoregressive systems and output error autoregressive moving average systems (i.e., the Box–Jenkins systems). Two recursive least squares parameter estimation algorithms are proposed by using the data filtering technique and the auxiliary model identification idea. The key is to use a linear filter to filter the input–output data. The proposed algorithms can identify the parameters of the system models and the noise models interactively and can generate more accurate parameter estimates than the auxiliary model based recursive least squares algorithms. Two examples are given to test the proposed algorithms. [ABSTRACT FROM AUTHOR]

In this paper, we propose a fast local image inpainting algorithm based on the Allen–Cahn model. The proposed algorithm is applied only on the inpainting domain and has two features. The first feature is that the pixel values in the inpainting domain are obtained by curvature-driven diffusions and utilizing the image information from the outside of the inpainting region. The second feature is that the pixel values outside of the inpainting region are the same as those in the original input image since we do not compute the outside of the inpainting region. Thus the proposed method is computationally efficient. We split the governing equation into one linear equation and one nonlinear equation by using an operator splitting technique. The linear equation is discretized by using a fully implicit scheme and the nonlinear equation is solved analytically. We prove the unconditional stability of the proposed scheme. To demonstrate the robustness and accuracy of the proposed method, various numerical results on real and synthetic images are presented. [ABSTRACT FROM AUTHOR]

When using convex probability sets (or, equivalently, lower previsions) as uncertainty models, identifying extreme points can help simplifying various computations or the use of some algorithms. In general, sets induced by specific models such as possibility distributions, linear vacuous mixtures or 2-monotone measures may have extreme points easier to compute than generic convex sets. In this paper, we study extreme points of another specific model: comparative probability orderings between the singletons of a finite space. We characterize these extreme points by means of a graphical representation of the comparative model, and use them to study the properties of the lower probability induced by this set. By doing so, we show that 2-monotone capacities are not informative enough to handle this type of comparisons without a loss of information. In addition, we connect comparative probabilities with other uncertainty models, such as imprecise probability masses. [ABSTRACT FROM AUTHOR]

Demosaicking is an important step in generating a full-color image from a color filter array image captured by a single-sensor digital camera. In this paper, we propose a new demosaicking algorithm which uses Taylor series and an adaptive fusion strategy. For generating directional predictors, we present a new interpolator based on Taylor series. The directional predictors are used together with spatial and spectral correlations. Using these predictors and the adaptive fusion strategy improves the green channel interpolation, in turn helping to reconstruct the red and blue channel interpolations. Experiments comparing the proposed algorithm to some other demosaicking algorithms show that the proposed algorithm provides superior performance in terms of both objective and subjective image quality. [ABSTRACT FROM AUTHOR]

This paper proposes a novel single-image super-resolution algorithm based on linear Bayesian maximum a posteriori (MAP) estimation and sparse representation. Starting from constructing several probability distribution priors in representation vector, we develop a linear Bayesian MAP estimator to acquire the most probable high-resolution (HR) image behind the low-resolution (LR) observation. Our new algorithm involves three main steps: (1) obtaining an initial estimate of the HR image via bi-cubic interpolation algorithm, (2) performing sparse coding on the initial estimate to get the representation vector and its support, (3) using the MAP estimator to restore the desired representation vector and then reconstructing the HR output. Simulated results show that the proposed method can achieve a more competitive performance both in subjective visual quality and in peak-signal-to-noise ratio (PSNR) and structural similarity (SSIM) measures, compared with other state-of-the-art super-resolution methods. [ABSTRACT FROM AUTHOR]

Wireless Body area networks (WBANs) consist of sensors that continuously monitor and transmit real time vital signals to a nearby coordinator and then to a remote terminal via the Internet. One of the most important signals for monitoring in WBANs is the electrocardiography (ECG) signal. The design of an accurate and energy efficient ECG telemonitoring system can be achieved by: i) reducing the amount of data that should be transmitted ii) minimizing the computational operations executed at any transmitter/receiver in a WBAN. To this end, compressed sensing (CS) approaches can offer a viable solution. In this paper, we propose two novel CS based ECG reconstruction algorithms that minimize the samples that are required to be transmitted for an accurate reconstruction, by exploiting the block structure of the ECG in the time domain (TD) and in an uncorrelated domain (UD). The proposed schemes require the solutions of second-order cone programming (SOCP) problems that are usually tackled by computational demanding interior point (IP) methods. To solve these problems efficiently, we develop a path-wise coordinate descent based scheme. The reconstruction accuracy is evaluated by the percentage root-mean-square difference (PRD) metric. A reconstructed signal is acceptable if and only if PRD < 9 % . Simulation studies carried out with real electrocardiographic (ECG) data, show that the proposed schemes, operating in both the TD and in the UD as compared to the conventional CS techniques, reduce the Compression Ratio (CR) by 20 % and 44 % respectively, offering at the same time significantly low computational complexity. [ABSTRACT FROM AUTHOR]

Several techniques have been proposed in the literature to accelerate the convergence of adaptive algorithms for the identification of sparse impulse responses (i.e., with energy concentrated in a few coefficients). Among these techniques, the improved µ-law proportionate normalized least mean squares (IMPNLMS) algorithm is one of the most effective. This paper presents an accurate transient analysis of this algorithm and derives an estimate of its steady-state MSE, without requiring the assumption of white Gaussian input signals. [ABSTRACT FROM AUTHOR]

This paper proposes a minor component analysis-based neural learning algorithm for designing linear-phase finite impulse response digital filters. The objective function to be minimized in the least-squares design can be formulated as the eigenvalue problem for solving an appropriate real, symmetric, and positive-definite matrix. To achieve the eigenfilter design, an alternative neural learning rule based on the minor component analysis algorithm is exploited. The optimal filter coefficients corresponding to the eigenvector of the smallest eigenvalue of the positive-definite matrix can be achieved in an iterative manner, avoiding the complex computation of eigenvalue decomposition. Furthermore, the learning step parameter that affects the convergence performance is investigated empirically. The simulation results indicate that the proposed neural-based approach can be applied to eigenfilter design and yields a lower computational complexity compared with traditional matrix algebraic-based approaches. [ABSTRACT FROM AUTHOR]

Principal Component Analysis (PCA) is a simple non-parametric method for extracting relevant information from high-dimensional data sets. In this paper, we analyze the data collected from the Indian MST (Mesosphere, Stratosphere, Troposphere) radar at Gadanki (13.5°N, 79.2°E) using PCA. We tested the PCA for various simulated signals like narrowband, wideband and exponential signals which may contain more than one frequency both in absence and presence of noise. For the simulated data, it is observed that PCA works for low SNR, i.e. it successfully detects the frequency in the highly noise-corrupted signal also. Finally, we applied PCA to the radar data for estimating the power spectrum and thus in turn estimating the Doppler frequency components. We estimate the zonal (U), meridional (V), wind speed (W) etc. from the Doppler frequencies. Compared with existing algorithms, PCA works well at higher altitudes and results have been validated using the GPS sonde data. [ABSTRACT FROM AUTHOR]

Most speech enhancement methods based on short-time spectral modification are generally expressed as a spectral gain depending on the estimate of the local signal-to-noise ratio (SNR) on each frequency bin. Several studies have analyzed the performance of a priori SNR estimation algorithms to improve speech quality and to reduce speech distortions. In this paper, we concentrate on the analysis of over- and under estimation of the a priori SNR in speech enhancement and noise reduction systems. We first show that conventional approaches such as the decision-directed approach proposed by Ephraïm and Malah lead to a biased estimator for the a priori SNR. To reduce this bias, our strategy relies on the introduction of a correction term in the a priori SNR estimate depending on the current state of both the available a posteriori SNR and the estimated a priori one. The proposed solution leads to a bias-compensated a priori SNR estimate, and allows to finely estimating the output speech signal to be very close to the original one on each frequency bin. Such refinement procedure in the a priori SNR estimate can be inserted in any type of spectral gain function to improve the output speech quality. Objective tests under various environments in terms of the Normalized Covariance Metric (NCM) criterion, the Coherence Speech Intelligibility Index (CSII) criterion, the segmental SNR criterion and the Perceptual Evaluation of Speech Quality (PESQ) measure are presented showing the superiority of the proposed method compared to competitive algorithms. [ABSTRACT FROM AUTHOR]

To mitigate the leakage signal that obstructs the target information extraction in miniatured frequency modulated continuous wave (FMCW) radar system, an adaptive leakage signal cancellation algorithm is proposed in this paper. Without any help of the additional auxiliary path, all the processing for the intermediate frequency (IF) signal can be conducted in the digital domain. The basic principle to cancel leakage signal is to produce a cancelling signal, which has the same amplitude and anti-phase with the leakage signal. Differently, in this paper, the input phase parameter of the proposed method can be arbitrary and it can be modified by the corresponding corrected function. Besides, to acquire the phase noise in the leakage signal conveniently when generating cancelling signal, the information geometry theory is applied to transform the complex phase noise model into statistical characteristics calculation of the input signal. The effectiveness of the model and the proposed algorithm is verified by simulated results. Furthermore, a real FMCW system is designed to collect the practice echo signals. The resulting data denotes that the leakage signal in the received signal is greatly suppressed and the leakage signal power drops by −15.92 dB. [ABSTRACT FROM AUTHOR]

In this paper, a robust watermarking algorithm in integer wavelet domain using downsampling is proposed. The innovations of this paper can be summarized as follows. First, after downsampling both the host image and watermark, each sub-watermark is embedded into the corresponding sub-host image. Second, four sub-watermarks are encrypted by pixel scrambling and fractional random transform, and the right principal component of watermark is embedded in the host image to avoid false positive problem. Third, two-level singular value decomposition and block cosine transform are performed on host image and watermark respectively, and the dual embedding of watermark is realized. Fourth, guided dynamic particle swarm optimization is used to optimize the embedding factors. The simulation results show that the proposed watermarking algorithm satisfies the requirements of robust watermarking very well. It has large capacity and strong robustness to common attacks. Moreover, compared with the existing related algorithms, this algorithm has obvious advantages. • Embed each sub-watermark obtained by downsampling into corresponding sub-host image. • Encrypt four sub-watermarks by pixel scrambling and DFRNT to enhance its security. • Embed the right principal component of watermark into the host image to avoid FPP. • Apply two-level SVD to host image and achieve the double embedding of watermark. • Optimize the embedding factors by GDPSO to balance the invisibility and robustness. [ABSTRACT FROM AUTHOR]

Sparse Recovery (SR) algorithms have been widely used for direction of arrival (DOA) estimation. At low values of signal to noise ratio (SNR) i.e. beyond -10 dB and with adequate number of sensors [1] , their estimates are incorrect. The magnitude spectrum-based Re-weighted sparse recovery (RWSR) algorithms improve the robustness by re-weighting the sparse estimates. But their efficiency degrades significantly with a fewer number of sensors. The significance of phase spectrum in the form of Group delays for robust DOA estimation using RWSR algorithms for spatially contiguous sources is explored in this paper. An optimal re-weighting methodology based on simultaneously minimizing average root mean square error (ARMSE) and maximizing the probability of separation is proposed. The simulations are carried for Gaussian and Laplacian noise to demonstrate the superior performance of the proposed method with a few sensors at low values of SNR. [ABSTRACT FROM AUTHOR]

• Evaluate the properties of Lncosh function and apply it to the research of impulsive noise problem. • Derivate the Least Lncosh algorithm and firstly use it for DOA estimation. • Propose the variable-parameter least Lncosh algorithm for DOA estimation. • Derivation, simulations and experimental data confirm the effectiveness of the proposed algorithm. The Lncosh function, a natural logarithm function that composes of hyperbolic cosine function, is thought of a compromise distribution between mean–absolute-error (MAE) and mean-square-error (MSE) via a regularization factor r (r > 0), which will provide potential superior performance in both Gaussian and impulsive noise environments. In this paper, a new DOA estimation algorithm is developed based on adaptive nulling technology and variable-parameter adaptive algorithm that is realized to reconstruct Lncosh function to modify least Lncosh (LL) algorithm to implement efficient DOAs for a wider range of applications. In the proposed algorithm, variable r -parameter and variable step-size schemes are devised to improve the LL algorithm. The DOA estimation capacity, root-mean-square error and mean stability for the proposed improved LL algorithm are analyzed under various noises including impulsive noise. The behavior of the devised variable LL algorithm is verified and discussed using simulations and experiments. [ABSTRACT FROM AUTHOR]

A new signal decomposition algorithm is developed in this paper. The goal of signal decomposition is to decompose a complex and nonstationary signal into a set of basic functions, usually called intrinsic mode functions (IMFs). In the proposed algorithm, it is assumed that each IMF has a limited bandwidth, and the frequency bands of various IMFs are disjoint. Based on this assumption, it is suggested to estimate the IMFs using a set of ideal filters designed in the frequency domain. The ideal filter bank is estimated in the proposed algorithm using penalized least-squares, where the weighted ℓ 0 -norm is utilized as the penalty term. In addition, the weighting parameters (used with the weighted ℓ 0 -norm) and the regularization parameter are calculated using techniques based on energy detection over short windows. It was found that the optimum value of the regularization parameter depends on the noise variance and the size of the windows over which the energy is calculated. To maintain the adaptivity of the proposed algorithm, two techniques are suggested for estimating the values of these two parameters from the analyzed signals. The numerical results on simulated and real data show that the proposed algorithm is fast, robust against noise, and outperforms some state-of-the-art signal decomposition algorithms. [ABSTRACT FROM AUTHOR]

This paper presents a stochastic model of the least-mean-square for bilinear forms (LMS-BF) algorithm in which the bilinear term is defined with respect to the temporal and spatial impulse responses of a multiple-input/single-output (MISO) spatiotemporal system. Specifically, taking into account uncorrelated and correlated Gaussian input data, an analytical stochastic model is derived describing the behavior of the temporal and spatial (and, consequently, spatiotemporal) adaptive filters for both transient and steady-state phases. Based on the proposed model, some interesting insights about convergence and steady-state characteristics of the algorithm are discussed, thereby providing useful design guidelines. Moreover, an analytical relationship is established between the LMS and the LMS-BF algorithms, which makes it possible to obtain appropriate performance comparisons confirming the improved convergence characteristics achieved by the latter. Through simulation results, the accuracy of the proposed model as well as some features of the algorithm are verified under different operating scenarios. [ABSTRACT FROM AUTHOR]

• The steady-state complementary mean square deviation of the WL-RLS algorithm is analyzed. • The Lyapunov stability analysis of the WL-RLS algorithm for time-invariant system and noise-free output is performed. • Numerical stability analysis has been conducted, illustrating that the WL-RLS algorithm is numerically stable for λ < 1. The widely linear recursive least squares (WL-RLS) algorithm is useful for dealing with noncircular signals. In this paper, we focus on the theoretical prediction and stability of the WL-RLS algorithm. First, the steady-state complementary mean square deviation (CMSD) behavior under a time-varying system is analyzed, which is different from the traditional standard mean square analysis that takes the form of real-valued evolution. Second, the Lyapunov stability and numerical stability are taken into account to provide an in-depth understanding of the stability issue. Specifically, by employing the Lyapunov stability theory (LST) approach, we perform the stability analysis of the WL-RLS algorithm for time-invariant system and noise-free output, illustrating that the WL-RLS algorithm is exponentially convergent in the sense of Lyapunov. Moreover, the numerical stability is analyzed by considering the finite word-length effects, and it is shown that the WL-RLS algorithm is numerically stable when the forgetting factor λ < 1. Numerical simulations for system identification scenarios verify the accuracy of the steady-state theoretical prediction. [ABSTRACT FROM AUTHOR]

The application of fuzzy clustering in image segmentation is a research hotspot nowadays. Existing robust fuzzy clustering have some problems such as the inability to adaptively select spatial constraint parameters, the inability to accurately segment images corrupted by high noise, and the inability to achieve a balance between noise suppression and detail preservation. In the fuzzy clustering based on objective function optimization, the choice of distance measure is very important. Gaussian kernel function is defined by Euclidean distance and has been widely used in many fields such as pattern recognition, machine learning, etc. However, Euclidean distance in fuzzy clustering is very sensitive to outliers or noise, it is difficult to obtain satisfactory results for some special data sets, which will affect the performance of clustering algorithm. In this paper, a non local information self-integration optimization algorithm based on kernel-based fuzzy local information clustering algorithm is proposed. The algorithm uses the self-integration method on the basis of the local information of the image and introduces non-local information at the same time, which solves the common problems of current clustering algorithm. Firstly, the self-integrating method solves the problem of selecting spatial constraint parameters, and the algorithm continues self-learning and iteratively calculates the parameter values; secondly, the distance measure uses Gaussian kernel induced distance to further enhance the robustness against noise and the adaptability of processing data sets; Finally, the local and non-local information are integrated at the same time to achieve a segmentation effect, which can effectively suppress most of the noise and retain the details of original image. Experimental results show that the proposed algorithm is superior to existing state-of-the-art fuzzy clustering-related algorithm in the presence of high noise. [ABSTRACT FROM AUTHOR]

In this paper, a high-precision two-dimensional (2D) direction of arrival (DOA) estimation algorithm by three parallel uniform linear arrays (ULAs) is proposed. Both the internal spacing of each sub-array and the spacing between two adjacent sub-arrays can exceed the half-wavelength of incident signal. An extended propagator method (PM) algorithm is introduced to obtain a multiple extended propagator matrix by processing the covariance matrix of received signals. Then, by using the extended propagator matrix, unambiguous and high-precision 2D DOA estimation can be obtained without extra pairing process. For the proposed array construction, mutual coupling effect can be ignored as long as the element interval is large enough. The extended PM algorithm based on the proposed array has far higher precision than the existing similar algorithms, which can be proved by some simulation experiments. [ABSTRACT FROM AUTHOR]

This paper discusses beamspace target height estimation for bistatic multiple-input multiple-output (MIMO) radars. Beamspace super-resolution algorithms for target height estimation have attracted significant attention due to low data transmission, storage, and computation. However, current literature has not yet considered beamspace target height estimation for a bistatic MIMO radar. Although target height estimation algorithms can be directly applied to a bistatic MIMO radar after minor modifications, such a direct application does not afford optimum performance. Therefore, we develop a three-dimensional beamspace maximum likelihood data fusion (3D-BMLF) algorithm appropriate for the target height estimation algorithm of a bistatic MIMO radar. The 3D-BMLF algorithm first converts target signals from the element space to the 3D beamspace, separates the transmitter and the receiver signals, and obtains two closed-form solutions of target height using the beamspace ML algorithm. Finally, the proposed method fuses the two closed-form solutions by minimizing the mean square error (MSE) of estimation. As a result, the 3D-BMLF algorithm has a very low computational burden and good estimation accuracy. Our computational complexity analysis and simulation results demonstrate the suitability of the 3D-BMLF algorithm for engineering applications. [ABSTRACT FROM AUTHOR]

Abstract: We propose a new method to incorporate priors on the solution of nonnegative matrix factorization (NMF). The NMF solution is guided to follow the minimum mean square error (MMSE) estimates of the weight combinations under a Gaussian mixture model (GMM) prior. The proposed algorithm can be used for denoising or single-channel source separation (SCSS) applications. NMF is used in SCSS in two main stages, the training stage and the separation stage. In the training stage, NMF is used to decompose the training data spectrogram for each source into a multiplication of a trained basis and gains matrices. In the separation stage, the mixed signal spectrogram is decomposed as a weighted linear combination of the trained basis matrices for the source signals. In this work, to improve the separation performance of NMF, the trained gains matrices are used to guide the solution of the NMF weights during the separation stage. The trained gains matrix is used to train a prior GMM that captures the statistics of the valid weight combinations that the columns of the basis matrix can receive for a given source signal. In the separation stage, the prior GMMs are used to guide the NMF solution of the gains/weights matrices using MMSE estimation. The NMF decomposition weights matrix is treated as a distorted image by a distortion operator, which is learned directly from the observed signals. The MMSE estimate of the weights matrix under the trained GMM prior and log-normal distribution for the distortion is then found to improve the NMF decomposition results. The MMSE estimate is embedded within the optimization objective to form a novel regularized NMF cost function. The corresponding update rules for the new objectives are derived in this paper. The proposed MMSE estimates based regularization avoids the problem of computing the hyper-parameters and the regularization parameters. MMSE also provides a better estimate for the valid gains matrix. Experimental results show that the proposed regularized NMF algorithm improves the source separation performance compared with using NMF without a prior or with other prior models. [Copyright &y& Elsevier]

Abstract: A kind of weighted orthogonal constrained independent component analysis (ICA) algorithms with weighted orthogonalization for achieving this constraint is proposed recently. It has been proved in the literature that weighted orthogonal constrained ICA algorithms keep the equivariance property and have much better convergence speed, separation ability and steady state misadjustment, but the convergence is not yet analyzed in the published literature. The goal of this paper is to fill this gap. Firstly, a characterization of the stationary points corresponding to these algorithms using symmetric Minimum Distance Weighted Unitary Mapping (MDWUM) for achieving the weighted orthogonalization is obtained. Secondly, the monotonic convergence of the weighted orthogonal constrained fixed point ICA algorithms using symmetric MDWUM for convex contrast function is proved, which is further extended to nonconvex contrast functions case by adding a weighted orthogonal constraint term onto the contrast function. Together with the boundedness of contrast function, the convergence of fixed point ICA algorithms with weighted orthogonal constraint using symmetric MDWUM is implied. Simulation experiments results show that the adaptive ICA algorithms using symmetric MDWUM are better in terms of accuracy than the ones with pre-whitening, and the fixed-point ICA algorithms using symmetric MDWUM converge monotonically. [Copyright &y& Elsevier]

Abstract: It is recently shown that algorithms derived from random matrix theory (RMT) can provide superior performance for spectrum sensing, which corresponds to the task of detecting the presence of primary users in cognitive radio. The essence of the RMT-based methods is to utilize the distribution of extremal eigenvalues of the received signal sample covariance matrix (SCM), namely, the Tracy–Widom (TW) distribution. Although the TW distribution is quite useful in spectrum sensing, computationally demanding numerical evaluation is required because it does not have an explicit closed-form expression. In this paper, we devise two novel volume-based detectors by exploiting the determinant of the SCM or volume to distinguish between the signal-presence and signal-absence cases. With the use of RMT, we accurately produce the theoretical decision threshold for one of the detectors under the Gaussian noise assumption. Simulation results are included to illustrate the effectiveness of the volume-based detectors. [Copyright &y& Elsevier]

Abstract: The accuracy of a source location estimate is very sensitive to the presence of the random noise in the known sensor positions. This paper investigates the use of calibration sensors, each of which is capable of broadcasting calibration signals to other sensors as well as receiving the signals from the source and other calibration sensors, to reduce the loss in the source localization accuracy due to uncertainties in sensor positions. We begin the study with deriving the Cramer–Rao lower bound (CRLB) for source localization using time difference of arrival (TDOA) and frequency difference of arrival (FDOA) measurements when a single calibration sensor is available. The obtained CRLB result is then extended to the more general case with multiple calibration sensors. The performance improvement due to the use of calibration sensors is established analytically. We then propose a closed-form algorithm that can explore efficiently the calibration sensors to improve the source localization accuracy when the sensor positions are subject to random errors. We prove analytically that the newly developed localization method attains the CRLB accuracy under some mild approximations. Simulations verify the theoretical developments. [Copyright &y& Elsevier]

Abstract: The new Mersenne number transform (NMNT) has proved to be an important number theoretic transform (NTT) used for error-free calculation of convolutions and correlations. Its main feature is that for a suitable Mersenne prime number (p), the allowed power-of-two transform lengths can be very large. In this paper, efficient radix-22 decimation-in-time and in-frequency algorithms for fast calculation of the NMNT are developed by deriving the appropriate mathematical relations in finite field and applying principles of the twiddle factor unscrambling technique. The proposed algorithms achieve both the regularity of radix-2 algorithm and the efficiency of radix-4 algorithm and can be applied to any powers of two transform lengths with simple bit reversing for ordering the output sequence. Consequently, the proposed algorithms possess the desirable properties such as simplicity and in-place computation. The validity of the proposed algorithms has been verified through examples involving large integer multiplication and digital filtering applications, using both the NMNT and the developed algorithms. [Copyright &y& Elsevier]

Abstract: In LTE downlink systems with a high frequency reuse factor, inter-cell interference has been viewed as a predominant factor limiting system performance. Therefore, we develop an iterative interference suppression receiver to mitigate inter-cell interference for LTE downlink systems in this paper. The key challenge here is how to accurately estimate the channel state information and spatial interference covariance matrix by using limited available pilots to improve the interference suppression capability and the successful probability of signal detection. To overcome the challenge, an iterative receiver making full use of the time–frequency correlation of channel is proposed. Simulation results show that the proposed iterative receiver can obtain a lower packet-error ratio compared with the existing algorithms. [Copyright &y& Elsevier]

Abstract: This paper introduces a smooth posterior density function for inferring shapes from silhouettes. Both the likelihood and the prior are modelled using kernel density functions and optimisation is performed using gradient ascent algorithms. Adding a prior allows for the recovery of concave areas of the shape that are usually lost when estimating the visual hull. This framework is also extended to use colour information when it is available in addition to the silhouettes. In these cases, the modelling not only allows for the shape to be recovered but also its colour information. Our new algorithms are assessed by reconstructing 2D shapes from 1D silhouettes and 3D faces from 2D silhouettes. Experimental results show that using the prior can assist in reconstructing concave areas and also illustrate the benefits of using colour information even when only small numbers of silhouettes are available. [Copyright &y& Elsevier]

Abstract: This paper shows a new algorithm to improve the performance of IQ demodulators and frequency converters exhibiting gain and phase imbalances between their branches. This algorithm does not require any input calibration signal and is independent of the input signal level. It exploits the spectral coherence (SC) concept using a monobit kernel to achieve optimization targets with minimum time to convergence, low computational load, and a wide range of input levels. Its effectiveness is shown through a low-IF receiver that improves its image rejection ratio (IRR) from 30 dB to 60 dB. [Copyright &y& Elsevier]

Abstract: The outputs of cascaded digital filters operating as accumulators are combined with a simplified Tchebichef polynomials to form Tchebichef moments (TMs). In this paper, we derive a simplified recurrence relationship to compute Tchebichef polynomials based on Z-transform properties. This paves the way for the implementation of second order digital filter to accelerate the computation of the Tchebichef polynomials. Then, some aspects of digital filter design for image reconstruction from TMs are addressed. The new proposed digital filter structure for reconstruction is based on the 2D convolution between the digital filter outputs used in the computation of the TMs and the impulse response of the proposed digital filter. They operate as difference operators and accordingly act on the transformed image moment sets to reconstruct the original image. Experimental results show that both the proposed algorithms to compute TMs and inverse Tchebichef moments (ITMs) perform better than existing methods in term of computation speed. [Copyright &y& Elsevier]

Abstract: This paper presents new algorithms that exploit uncorrelation between adjacent data samples produced by IFFT in ADSL systems. These algorithms update time-domain equalizer (TEQ) coefficients by adjacent lag autocorrelation minimization (ALAM) to shorten the channel. ALAM is an addition to the family of several existing autocorrelation-based algorithms that can achieve similar or better performance at lower complexity compared to other algorithms. The complexity reduction is achieved by designing a cost function without the sum-square, and further utilizing symmetrical TEQ property to reduce the complexity of the adaptation of TEQ to half of other existing algorithms. Furthermore, to avoid the limitations of lower bitrate after reaching the maximum bitrate and high complexity, an adaptive TEQ using equal-taps constraint (ETC) is introduced to maximize the bitrate along with achieving the lowest complexity. In addition, a simplified approach is used to calculate the expectation to reduce the computational complexity for ALAM and the other existing autocorrelation-based algorithms. Simulation results demonstrate that the proposed algorithms and modified existing algorithms achieve similar or better performance figures with reduced complexities. [Copyright &y& Elsevier]

Abstract: In this paper, the interaction and combination of Fuzzy Fading Memory (FFM) technique and Augmented Kalman Filtering (AUKF) method are presented for the state estimation of non-linear dynamic systems in presence of maneuver. It is shown that the AUKF method in conjunction with the FFM technique (FFM-AUKF) can estimate the target states appropriately since the FFM tunes the covariance matrix of the AUKF method in presence of unknown target accelerations by using a fuzzy system. In addition, the benefits of both FFM technique and AUKF method are employed in the scheme of well-known Interacting Multiple Model (IMM) algorithm. The proposed Fuzzy IMM (FIMM) algorithm does not need the predefinition and adjustment of sub-filters with respect to the target maneuver and reduces the number of required sub-filters to cover the wide range of unknown target accelerations. The Monte Carlo simulation analysis shows the effectiveness of the above-mentioned methods in maneuvering target tracking. [Copyright &y& Elsevier]

Abstract: In this paper, a novel algorithm is proposed to achieve robust high resolution detection in sparse multipath channels. Currently used sparse reconstruction techniques are not immediately applicable in multipath channel modeling. Performance of standard compressed sensing formulations based on discretization of the multipath channel parameter space degrade significantly when the actual channel parameters deviate from the assumed discrete set of values. To alleviate this off-grid problem, we make use of the particle swarm optimization (PSO) to perturb each grid point that reside in each multipath component cluster. Orthogonal matching pursuit (OMP) is used to reconstruct sparse multipath components in a greedy fashion. Extensive simulation results quantify the performance gain and robustness obtained by the proposed algorithm against the off-grid problem faced in sparse multipath channels. [Copyright &y& Elsevier]

Abstract: Blind source separation (BSS) has attained much attention in signal processing society due to its ‘blind’ property and wide applications. However, there are still some open problems, such as underdetermined BSS, noise BSS. In this paper, we propose a Bayesian approach to improve the separation performance of instantaneous mixtures with non-stationary sources by taking into account the internal organization of the non-stationary sources. Gaussian mixture model (GMM) is used to model the distribution of source signals and the continuous density hidden Markov model (CDHMM) is derived to track the non-stationarity inside the source signals. Source signals can switch between several states such that the separation performance can be significantly improved. An expectation-maximization (EM) algorithm is derived to estimate the mixing coefficients, the CDHMM parameters and the noise covariance. The source signals are recovered via maximum a posteriori (MAP) approach. To ensure the convergence of the proposed algorithm, the proper prior densities, conjugate prior densities, are assigned to estimation coefficients for incorporating the prior information. The initialization scheme for the estimates is also discussed. Systematic simulations are used to illustrate the performance of the proposed algorithm. Simulation results show that the proposed algorithm has more robust separation performance in terms of similarity score in noise environments in comparison with the classical BSS algorithms in determined mixture case. Additionally, since the mixing matrix and the sources are estimated jointly, the proposed EM algorithm also works well in underdetermined case. Furthermore, the proposed algorithm converges quickly with proper initialization. [Copyright &y& Elsevier]

Abstract: Traditional minimum spanning tree-based clustering algorithms only make use of information about edges contained in the tree to partition a data set. As a result, with limited information about the structure underlying a data set, these algorithms are vulnerable to outliers. To address this issue, this paper presents a simple while efficient MST-inspired clustering algorithm. It works by finding a local density factor for each data point during the construction of an MST and discarding outliers, i.e., those whose local density factor is larger than a threshold, to increase the separation between clusters. This algorithm is easy to implement, requiring an implementation of iDistance as the only k-nearest neighbor search structure. Experiments performed on both small low-dimensional data sets and large high-dimensional data sets demonstrate the efficacy of our method. [Copyright &y& Elsevier]

Abstract: This paper presents a new video super resolution technique, based on the motion and static areas of the low resolution video frames. In order to separate the motion and static blocks, a block motion estimation method is performed between a reference and its neighboring frames. Among the motion blocks, the occluded blocks are identified using an adaptive threshold applied on each block individually. Structure-adaptive normalized convolution (SANC) reconstruction method is used to generate the high resolution static and motion blocks where discrete wavelet transform (DWT) based interpolation is used to produce the high resolution occluded blocks. The static and motion blocks are combined into a high resolution frame. Finally, a sharpening process is performed on the high resolution frame in order to generate the super resolved high resolution output frame. The experimental results show that the proposed technique provides significantly better qualitative visual results as well as quantitative higher PSNR than the state of the art video super resolution algorithms. [Copyright &y& Elsevier]

Abstract: In this paper, we introduce a novel image adaptive technique for high capacity watermarking scheme using accurate and fast radial harmonic Fourier moments (RHFMs). The high embedding capacity is achieved by improving the hiding ratio after reducing inaccuracies in the computation of RHFMs. The binary watermark is embedded by performing the conditional quantization of selected RHFMs magnitudes to minimize the spatial distortion added to the host image. In addition, fast algorithms based on 8-way symmetry/anti-symmetry properties and recursive relations for the computation of sinusoidal kernel functions are adopted to enhance the speed of RHFMs-based watermarking process. Experimental studies show that the proposed watermarking scheme provides higher embedding capacity, good visual imperceptibility, better robustness to geometric distortions and common signal processing transformations, and lower computational complexity compared to the existing Zernike and pseudo-Zernike moments (ZMs/PZMs)-based watermarking schemes. [Copyright &y& Elsevier]

Abstract: In this paper, a local weighted interpolation method for intra-field deinterlacing is proposed as an improved version of the DCS (deinterlacing with awareness of closeness and similarity) algorithm. The original DCS method is derived from bilateral filter which takes the local spatial closeness and pixel similarity into account when calculating the weight of interpolation. The proposed algorithm achieves three improvements: 1) instead of the line average, a more accurate interpolation filter is used to estimate the center missing pixel; 2) the center-independent interpolation method is proposed to replace the center-dependent interpolation strategy; 3) the adaptive weighted interpolation method is used to improve the accuracy of interpolation. Experimental results show that the proposed algorithm provides superior performance in terms of both objective and subjective image qualities when compared with other conventional benchmarks, including DCS algorithms with low complexity. [Copyright &y& Elsevier]

Abstract: In this paper, the problem of despeckling SAR images when the input data is either an intensity or an amplitude signal is revisited. State-of-the-art despeckling methods based on Bayesian estimators in the wavelet domain, recently proposed in the literature, are taken into consideration. First, how these methods proposed for one format (e.g., intensity) can be adapted to the other format (e.g., amplitude) is investigated. Second, the performance of such algorithms in both cases is analyzed. Experimental results carried out on simulated speckled images and on true SAR data are presented and discussed in order to assess the best strategy. From these results, it can be observed that filtering in the amplitude domain yields better performances in terms of objective quality indexes, such as preservation of structural details, as well as in terms of visual inspection of the filtered SAR data. [Copyright &y& Elsevier]

Passive localization and classification algorithms for mixed near-field and far-field sources have mainly been investigated for antenna arrays with regular or symmetrical geometry. However, these algorithms may not be applicable to wireless sensor networks, where spatially distributed sensor nodes form an array of random geometry. This paper proposes squared error norm of residual fitting error matrix (SRFEM) cost function for mixed source localization, which does not place any constraint on the geometry of antenna array. The proposed cost function is optimized using computationally simple swarm intelligence (SI) algorithms. Convergence performance of three SI algorithms, i.e., particle swarm optimization, Whale optimization, and Grey Wolf optimization is investigated to obtain estimates of the source location parameters with a minimal number of iterations or computational complexity. In order to provide robustness for the SRFEM cost function, this paper proposes an impulse denoising technique based on the long-short term memory recurrent neural network (LSTM-RNN). Simulation results confirm that, in the presence of AWGN, the proposed SRFEM cost function outperforms existing techniques based on the uniform linear array and approaches the theoretical Cramer-Rao lower bound even for a fewer number of snapshots. Further, simulation analysis also reveals that LSTM-RNN provides better mixed localization performance under impulse noise as compared to the bounded noise covariance approach at high signal-to-noise values. [ABSTRACT FROM AUTHOR]

In order to solve the Direction of Arrival (DOA) estimation of fast-moving targets in a strong noisy environment, an auto-paired two-dimensional (2D) DOA estimation algorithm architecture based on the sparse recovery of acoustic vector sensor arrays is proposed. The structure of the array signal autocorrelation operator is similar to the 2D compressed sampling model. Based on the structure of the autocorrelation operator, a 2D DOA estimation sparse recovery model for the Uniform Line Array (ULA) of the acoustic vector sensors is proposed. Meanwhile, the modified Compressive Sampling Matching Pursuit (CoSaMP) algorithm is used to realize the auto-paired 2D DOA estimation. The simulation results show that the method proposed in this paper can effectively suppress noise, and can be used to realize 2D DOA estimation of acoustic vector sensor ULA under a low Signal-to-Noise Ratio (SNR) and small snapshots. [ABSTRACT FROM AUTHOR]

In a synthetic aperture radar system, long-time coherent integration for ground moving targets suffers from the complex range migrations (RMs) and Doppler frequency migration (DFM), which lead to a serious degradation of the target detection. To address these problems and obtain the motion parameters of the moving target, a new algorithm based on modified location rotation transform (MLRT) and improved discrete chirp Fourier transform (IDCFT), i.e., MLRT-IDCFT, is proposed in this paper. More concretely, the matched filtering function is first utilized to remove the range curvature (RC) for improving the computational efficiency. After that, the MLRT-IDCFT corrects the residual linear range migration (LRM) through rotating coordinate locations of the echo trajectory and achieves the coherent integration as well as the motion parameter estimation via the IDCFT. The IDCFT exploits the prior information to adaptively adjust the parameter estimation range, which not only improves the parameter resolution but also guarantees the validity of the parameter estimation. Due to the linear transform property, the proposed method can work well under the low signal-to-noise ratio (SNR) environment. Additionally, it has a relatively low computational complexity since the exhaustive searching for acceleration is avoided. Several simulations are provided to demonstrate the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

• A novel image deblocking methodology within a graph framework is proposed. • We transform the expression of an image from the image topology to graph topology. • Two graph topology learning methods are carried out. • Graph PCA is studied to replace the low-rank constrain in the CONCOLOR model. • Twelve standard images are used to test the performance of the improved models. Since JPEG compression is achieved via independent and coarse quantization of discrete cosine transformation coefficients in each block, its results generally exhibit visually annoying blocking artifacts and Gibbs phenomena at low bitrates. Moreover, the existing image deblocking algorithms are basically processed under the classical image topology structure. In this paper, we present a novel image blocking artifact-free methodology within a graph framework. A graph is a compatible tool. Most of the existing image deblocking models can be improved by transforming images or image patches into graph signals. To verify this viewpoint, we focus on improving the existing mainstream total-variation-based and constrained non-convex low-rank image deblocking models. Furthermore, we provide numerical algorithms and the corresponding fast workarounds. The introduction of a graph renders the pixel representation more flexible and adaptive, and can improve the computational efficiency of the constrained non-convex low-rank image deblocking approach. In addition, twelve standard images are used to test the performance of the proposed models. The experiments show that in comparison to several existing famous models, our models achieve competitive results in terms of deblocking and calculation speed. [ABSTRACT FROM AUTHOR]

• DOA estimation method based on gridless idea is provided for sparse linear array with gain-phase errors. • A novel atomic norm for the received signal of difference coarray is defined by introducing error parameters. • The process of DOA estimation is described as a dual formulation of constrained ANM approach. • A rigorous derivation and proof on how to convert dual problem into an SDP problem is given. Sparse arrays have attracted great attention in the field of direction-of-arrival (DOA) estimation due to the extended degrees of freedom (DOFs). Nevertheless, the traditional DOA estimation methods for sparse arrays suffer from degraded performance when sensor elements are uncalibrated. This paper presents a novel atomic norm-based algorithm for source localization with arbitrary sparse linear array (SLA) in the scenario with gain-phase uncertainties. Our proposed approach defines a new atomic norm for second order virtual signal by taking model errors into consideration. Then, the dual problem corresponding to original optimization problem is formulated to recover the DOAs by defining the dual atomic norm. We further present the corresponding semidefinite program characteristic that can be solved. The proposed method avoids iterations and restrictions on array configuration. It makes full use of all the DOFs provided by difference coarray of arbitrary SLA to estimate more sources and to provide high accuracy. Besides, compared with the existing coarray-based calibrated algorithms, the proposed algorithm does not need discretization on spatial domain. Computer simulations are carried out to demonstrate the superiority of the proposed algorithm. [ABSTRACT FROM AUTHOR]

In nature and engineering world, the acquired signals are usually affected by multiple complicated factors and appear as multicomponent nonstationary modes. In such and many other situations, it is necessary to separate these signals into a finite number of monocomponents to represent the intrinsic modes and underlying dynamics implicated in the source signals. In this paper, we consider the mode retrieval of a multicomponent signal which has crossing instantaneous frequencies (IFs), meaning that some of the components of the signal overlap in the time-frequency domain. We use the chirplet transform (CT) to represent a multicomponent signal in the three-dimensional space of time, frequency and chirp rate and introduce a CT-based signal separation scheme (CT3S) to retrieve modes. In addition, we analyze the error bounds for IF estimation and component recovery with this scheme. We also propose a matched-filter along certain specific time-frequency lines with respect to the chirp rate to make nonstationary signals be further separated and more concentrated in the three-dimensional space of CT. Furthermore, based on the approximation of source signals with linear chirps at any local time, we propose an innovative signal reconstruction algorithm, called the group filter-matched CT3S (GFCT3S), which also takes a group of components into consideration simultaneously. GFCT3S is suitable for signals with crossing IFs. It also decreases component recovery errors when the IFs curves of different components are not crossover, but fast-varying and close to each other. Numerical experiments on synthetic and real signals show our method is more accurate and consistent in signal separation than the empirical mode decomposition, synchrosqueezing transform, and other approaches. [ABSTRACT FROM AUTHOR]

In this paper, we proposed a novel online kernel-adaptive learning algorithm under the reproducing-kernel-Hilbert space (RKHS), which is called kernel q-Rényi (KqR) algorithm. The KqR algorithm is derived via constructing a q-Rényi kernel function as a cost function into kernel adaptive filtering algorithm (KAF). The vector-quantization (VQ) method is wildly used in the KAF algorithms, which is called quantized KAF. The quantized kernel q-Rényi (QKqR) algorithm is also proposed to significantly reduce computational cost via quantizing input space to curb the size of neural networks growth. The mean-square-convergence analysis of the QKqR algorithm is established, and the theoretical-value of the excess-mean-square-error (EMSE) are presented. The performance of the KqR and QKqR algorithms are investigated and demonstrated via tracking the Mackey-Glass (MG) time-series-prediction and the nonlinear channel equalization (NCE) under the non-Gaussian background interferences. [ABSTRACT FROM AUTHOR]