Search

Compressive sensing (CS) is a technique that enables the recovery of sparse signals using fewer measurements than traditional sampling methods. To address the computational challenges of CS reconstruction, our objective is to develop an interpretable and concise neural network model for reconstructing natural images using CS. We achieve this by mapping one step of the iterative shrinkage thresholding algorithm (ISTA) to a deep network block, representing one iteration of ISTA. To enhance learning ability and incorporate structural diversity, we integrate aggregated residual transformations (ResNeXt) and squeeze-and-excitation mechanisms into the ISTA block. This block serves as a deep equilibrium layer connected to a semi-tensor product network for convenient sampling and providing an initial reconstruction. The resulting model, called MsDC-DEQ-Net, exhibits competitive performance compared to state-of-the-art network-based methods. It significantly reduces storage requirements compared to deep unrolling methods, using only one iteration block instead of multiple iterations. Unlike deep unrolling models, MsDC-DEQ-Net can be iteratively used, gradually improving reconstruction accuracy while considering computation tradeoffs. Additionally, the model benefits from multiscale dilated convolutions, further enhancing performance. [ABSTRACT FROM AUTHOR]

A method for overlapping cell image segmentation is presented with a focus on multi‐layer image processing in a three‐phase scheme. In the first phase, a convolutional neural network is developed to provide a coarse cell segmentation with multiple output layers to identify cell cytoplasm, locations of cell nuclei, and the background, all as probabilistic image maps for the layer outputs. In the second phase, the probabilistic image maps from the convolutional neural network are used to identify locations of cell nuclei and cell cytoplasm. Then, multi‐layer random walker image segmentation is used with cell nuclei as hard initial seeds and the cytoplasm estimates as soft seeds in a diffusion graph‐based segmentation of the cells. With rough cell segmentation from both the trained convolutional neural network and the multi‐layer random walker graph‐based technique, a third phase combines and refines the cell segmentation using the Hungarian algorithm to optimise the assignment of individual pixel locations for the final cell segmentation. We evaluate the proposed method on cervical cell images generated from the International Symposium on Biomedical Imaging 2014 dataset with results that give a Dice similarity coefficient of 97.2% (compared to 93.2% for competitors) when trained on the generated dataset. [ABSTRACT FROM AUTHOR]

We present a new technique for separating two speech signals from a single recording. The proposed method bridges the gap between underdetermined blind source separation techniques and those techniques that model the human auditory system, that is, computational auditory scene analysis (CASA). For this purpose, we decompose the speech signal into the excitation signal and the vocal-tract-related filter and then estimate the components from the mixed speech using a hybrid model. We first express the probability density function (PDF) of the mixed speech's log spectral vectors in terms of the PDFs of the underlying speech signal's vocal-tract-related filters. Then, the mean vectors of PDFs of the vocal-tract-related filters are obtained using a maximum likelihood estimator given the mixed signal. Finally, the estimated vocal-tract-related filters along with the extracted fundamental frequencies are used to reconstruct estimates of the individual speech signals. The proposed technique effectively adds vocal-tract-related filter characteristics as a new cue to CASA models using a new grouping technique based on an underdetermined blind source separation. We compare our model with both an underdetermined blind source separation and a CASA method. The experimental results show that our model outperforms both techniques in terms of SNR improvement and the percentage of crosstalk suppression.

This paper derives the Cramér–Rao lower bound (CRLB) for a general multichannel spaceborne synthetic aperture radar system for ground moving-target indication and provides a theoretical analysis of across-track velocity estimation for RADARSAT-2 and a fictitious satellite. The signal model assumes a deterministic target signal in Gaussian clutter and noise. In estimation theory, the CRLB provides a lower bound on the achievable variance of any unbiased estimator. An estimator that achieves this bound is called efficient; however, there is no guarantee that an efficient estimator can be found. Nonetheless, the theoretical variance of the efficient estimator provides a good measure of the capability of the system and serves as a valuable system performance validation tool. Even if an efficient estimator cannot be found, for radar systems, the CRLB provides a necessary, but not sufficient design baseline for measurement parameters, such as the number of subapertures for transmit and receive, power levels, pulse-repetition frequency, and so on. CRLBs for a limited number of system configurations for RADARSAT-2 and TerraSAR-X are presented by Cerutti-Maori et al. and Ender et al.; however, the complete analytical form of CRLB for a general system, which can be readily applied to an arbitrary antenna switching configuration, has not been previously derived. [ABSTRACT FROM PUBLISHER]

In compressive sensing (CS), the restricted isometry property (RIP) is an important condition on measurement matrices which guarantees the recovery of sparse signals with undersampled measurements. It has been proved in the prior works that both random (e.g., i.i.d. Gaussian, Bernoulli, \ldots) and Toeplitz matrices satisfy the RIP with high probability. However, structured matrices, such as banded Toeplitz matrices have drawn more attention since their structures have the advantage of fast matrix multiplication which may decrease the computational complexity of recovery algorithms. In this paper, we show that banded block Toeplitz matrices satisfy the RIP condition with high probability. Banded block Toeplitz matrices can be used in the sparse multi-channel source separation. The banded block Toeplitz matrices decrease the computational complexity while they have fewer number of non-zero entries in comparison to the same dimensional banded Toeplitz matrices. Furthermore, our simulation results show that banded block Toeplitz matrices outperform banded Toeplitz matrices in signal estimation. The analytical RIP bound for banded block Toeplitz matrices is provided in this paper and the RIP bound of sparse Gaussian matrices is also obtained as an upper bound for banded block Toeplitz matrices. Our simulation and analytical results show that sparse Gaussian random matrices do satisfy the RIP condition with high probability. The probability of satisfying the RIP depends on the probability of zero entries. [ABSTRACT FROM PUBLISHER]

In this letter, an efficient and reliable nonlinearity measure for quantifying the nonlinear distortion (NLD) is formulated. In order to achieve such a formulation, the bit error rate (BER) performance of the downlink of direct sequence-code division multiple access, in presence of NLD caused by a predistorter-high power amplifier (PD-HPA) is investigated. Exponential curve fitting is used to develop an approximate expression for the BER performance, through which the nonlinearity measure is formulated. The proposed measure is characterized by having a direct link with the BER performance in addition of being dependent of the input back-off level. [ABSTRACT FROM PUBLISHER]

In this paper, we present a multiple description video coding algorithm based on error-resilient and error concealment set partitioning in hierarchical trees (ERC-SPIHT). In this proposed approach, additional redundancy is generated by wavelet decomposing the spatial root subband and such redundancy is then intentionally inserted into the substreams. As a result, the novelty of the proposed approach is that the root subband coefficients lost during transmission in any substream can be reconstructed by exploiting both inherent redundancy and inserted redundancy. This reconstruction procedure is implemented in two steps, first by using existing 2-D error concealment techniques, and second with the proposed root subband recovery approach. The former step is used to estimate the missing coefficients in the spatial root and high frequency subbands by exploiting the inherent redundancy, while the latter attempts to utilize the inserted redundancy to further improve the precision in the estimation of the missing spatial root subband coefficients. The proposed root subband recovery method can be iteratively applied and accuracy of the reconstruction can be gradually increased with each iteration. Experimental results on different video sequences show that the proposed method maintains error-resilience with high coding efficiency. In particular, our results demonstrate that the proposed algorithm achieves a significant improvement on video quality by up to 2.5753 dB in the presence of a substream loss compared to ERC-SPIHT. [ABSTRACT FROM AUTHOR]

We present an image registration model for image sets with arbitrarily shaped local illumination variations between images. Any nongeometric variations tend to degrade the geometric registration precision and impact subsequent processing. Traditional image registration approaches do not typically account for changes and movement of light sources, which result in interimage illumination differences with arbitrary shape. In addition, these approaches typically use a least-square estimator that is sensitive to outliers, where interimage illumination variations are often large enough to act as outliers. In this paper, we propose an image registration approach that compensates for arbitrarily shaped interimage illumination variations, which are processed using robust M-estimators tuned to that region. Each M-estimator for each illumination region has a distinct cost function by which small and large interimage residuals are unevenly penalized. Since the segmentation of the interimage illumination variations may not be perfect, a segmentation confidence weighting is also imposed to reduce the negative effect of mis-segmentation around illumination region boundaries. The proposed approach is cast in an iterative coarse-to-fine framework, which allows a convergence rate similar to competing intensity-based image registration approaches. The overall proposed approach is presented in a general framework, but experimental results use the bisquare M-estimator with region segmentation confidence weighting. A nearly tenfold improvement in subpixel registration precision is seen with the proposed technique when convergence is attained, as compared with competing techniques using both simulated and real data sets with interimage illumination variations. [ABSTRACT FROM AUTHOR]

We present an approach for separating two speech signals when only one single recording of their linear mixture is available. For this purpose, we derive a filter, which we call the soft mask filter, using minimum mean square error (MMSE) estimation of the log spectral vectors of sources given the mixture's log spectral vectors. The soft mask filter's parameters are estimated using the mean and variance of the underlying sources which are modeled using the Gaussian composite source modeling (CSM) approach. It is also shown that the binary mask filter which has been empirically and extensively used in single-channel speech separation techniques is, in fact, a simplified form of the soft mask filter. The soft mask filtering technique is compared with the binary mask and Wiener filtering approaches when the input consists of male+male, female+female, and male+female mixtures. The experimental results in terms of signal-to-noise ratio (SNR) and segmental SNR show that soft mask filtering outperforms binary mask and Wiener filtering. [ABSTRACT FROM AUTHOR]

We present a new technique for separating two speech signals from a single recording. The proposed method bridges the gap between underdetermined blind source separation techniques and those techniques that model the human auditory system, that is, computational auditory scene analysis (CASA). For this purpose, we decompose the speech signal into the excitation signal and the vocal-tract-related filter and then estimate the components from the mixed speech using a hybrid model. We first express the probability density function (PDF) of the mixed speech's log spectral vectors in terms of the PDFs of the underlying speech signal's vocal-tract-related filters. Then, the mean vectors of PDFs of the vocal-tract-related filters are obtained using a maximum likelihood estimator given the mixed signal. Finally, the estimated vocal-tract-related filters along with the extracted fundamental frequencies are used to reconstruct estimates of the individual speech signals. The proposed technique effectively adds vocaltract- related filter characteristics as a new cue to CASA models using a new grouping technique based on an underdetermined blind source separation. We compare our model with both an underdetermined blind source separation and a CASA method. The experimental results show that our model outperforms both techniques in terms of SNR improvement and the percentage of crosstalk suppression. [ABSTRACT FROM AUTHOR]

This paper proposes a new method for performing joint audio-video talker localization that explores the reliability of the individual localization estimates such as audio, motion detection, and skin-color detection. The reliability information is estimated from the audio and video data separately. The proposed method then uses this reliability information in conjunction with a simple summing voter to dynamically discriminate erroneous outputs from the localizers while performing fusion on the localization results. Based on the voter output, a majority rule is then used to make the final decision of the active talker's current location. The results show that adding the reliability information during fusion improves localization performance when compared to audio only, motion detection only, skin-color detection only, and joint audio-video using straight summing fusion localization methods. The computational complexity of the proposed method is comparable to the existing ones. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a novel power spectrum-based method for fractal analysis of surface electromyography signals. This method, named the bi-phase power spectrum method, provides a bi-phase power-law which represents a multi-scale statistically self-affine signal. This form of statistical self-affinity provides an accurate approximation for stochastic signals originating from a strong non-linear combination of a number of similar distributions, such as surface electromyography signals which are formed by the summation of a number of single muscle fiber action potentials. This power-law is characterized by a set of spectral indicators, which are related to distributional and geometrical characteristics of the electromyography signal’s interference pattern. These novel spectral indicators are capable of sensing the effects of motor units’ recruitment and shape separately by exploiting the geometry of the interference pattern. The bi-phase power spectrum method is compared to geometrical techniques and the 1/f α approach for fractal analysis of electromyography signals. The extracted indicators using the bi-phase power spectrum method are evaluated in the context of force and joint angle and the results of a human study are presented. Results demonstrate that the bi-phase power spectrum method provides reliable information, consisting of components capable of sensing force and joint angle effects separately, which could be used as complementary information for confounded conventional measures. [Copyright &y& Elsevier]

Image reconstruction for positron emission tomography (PET) can be challenging and the resulting image typically has high noise. The kernel-based reconstruction method [1], incorporates prior anatomic information in the reconstruction algorithm to reduce noise while preserving resolution. Prior information is incorporated in the reconstruction algorithm by means of spatial kernels originally used in machine learning. In this paper, the kernel-based method is used to reconstruct PET images of sympathetic innervation in the heart. The resulting images are compared with standard Ordered Subset Expectation Maximization (OSEM) reconstructed images qualitatively and quantitatively using data from 6 human subjects. The kernel-based method demonstrated superior SNR with preserved contrast and accuracy compared to OSEM.

In this paper we investigate the effect of force and joint angle on myoelectric signal parameters. In recent years, methods that have been previously used to analyze nonlinear chaotic dynamical systems have been applied to myoelectric signals. Nonlinear myoelectric signal parameters that have been used include the fractal dimension, estimated using the Katz method and Box-Counting methods, and the spectral slopes. Previous research has only examined effects of contractile force, whereas this research also includes joint angle effects. Results of this research suggest that the Katz and Box-Counting approaches used to estimate fractal dimension are not well suited for time functions, such as myoelectric signals. Results from the spectral slope parameters suggest that these parameters can track joint angle effects. A generalized model approach building upon the spectral slope method is proposed for future work.