A new algorithm for separating mass spectra into individual substances for explosives detection is proposed. In the field of mass spectrometry, separation methods, such as principal-component analysis (PCA) and independent-component analysis (ICA), are widely used. All components, however, have no negative values, and the orthogonality condition imposed on components also does not necessarily hold in the case of mass spectra. Because these methods allow negative values and PCA imposes an orthogonality condition, they are not suitable for separation of mass spectra. The proposed algorithm is based on probabilistic latent-component analysis (PLCA). PLCA is a statistical formulation of non-negative matrix factorization (NMF) using KL divergence. Because PLCA imposes the constraint of non-negativity but not orthogonality, the algorithm is effective for separating components of mass spectra. In addition, to estimate the components more accurately, a sparsity constraint is applied to PLCA for explosives detection. The main contribution is industrial application of the algorithm into an explosives-detection system. Results of an experimental evaluation of the algorithm with data obtained in a real railway station demonstrate that the proposed algorithm outperforms PCA and ICA. Also, results of calculation time demonstrate that the algorithm can work in real time.

We propose a novel sparse representation-based direction-of-arrival (DOA) estimation method. In contrast to those that approximate l0-norm minimization by l1-norm minimization, our method designs a reweighted l1 norm to substitute the l0 norm. The capability of the reweighted l1 norm to bridge the gap between the l0- and l1-norm minimization is then justified. In addition, an array covariance vector without redundancy is utilized to extend the aperture. It is proved that the degree of freedom is increased as such. The simulation results show that the proposed method performs much better than l1-type methods when the signal-to-noise ratio (SNR) is low and when the number of snapshots is small.

We propose a novel algorithm for the recovery of non-sparse, but compressible signals from linear undersampled measurements. The algorithm proposed in this paper consists of two steps. The first step recovers the signal by the l1-norm minimization. Then, the second step decomposes the l1 reconstruction into major and minor components. By using the major components, measurements for the minor components of the target signal are estimated. The minor components are further estimated using the estimated measurements exploiting a maximum a posterior (MAP) estimation, which leads to a ridge regression with the regularization parameter determined using the error bound for the estimated measurements. After a slight modification to the major components, the final estimate is obtained by combining the two estimates. Computational cost of the proposed algorithm is mostly the same as the l1-nom minimization. Simulation results for one-dimensional computer generated signals show that the proposed algorithm gives 11.8% better results on average than the l1-norm minimization and the lasso estimator. Simulations using standard images also show that the proposed algorithm outperforms those conventional methods.

The sparse Fourier transform (SFT) seeks to recover k non-negligible Fourier coefficients from a k-sparse signal of length N (k«N). A single frequency signal can be recovered via the Chinese remainder theorem (CRT) with sub-sampled discrete Fourier transforms (DFTs). However, when there are multiple non-negligible coefficients, more of them may collide, and multiple stages of sub-sampled DFTs are needed to deal with such collisions. In this paper, we propose a combinatorial aliasing-based SFT (CASFT) algorithm that is robust to noise and greatly reduces the number of stages by iteratively recovering coefficients. First, CASFT detects collisions and recovers coefficients via the CRT in a single stage. These coefficients are then subtracted from each stage, and the process iterates through the other stages. With a computational complexity of O(klog klog 2N) and sample complexity of O(klog 2N), CASFT is a novel and efficient SFT algorithm.

Compressive sensing (CS)-based channel estimation considerably reduces pilot symbols usage by exploiting the sparsity of the propagation channel in the delay-Doppler domain. In this paper, we consider the application of Bayesian approaches to the sparse channel estimation in orthogonal frequency division multiplexing (OFDM) systems. Taking advantage of the block-sparse structure and statistical properties of time-frequency selective channels, the proposed Bayesian method provides a more efficient and accurate estimation of the channel status information (CSI) than do conventional CS-based methods. Moreover, our estimation scheme is not limited to the Gaussian scenario but is also available for channels that have non-Gaussian priors or unknown probability density functions. This characteristic is notably useful when the prior statistics of channel coefficients cannot be precisely estimated. We also design a combo pilot pattern to improve the performance of the proposed estimation scheme. Simulation results demonstrate that our method performs well at high Doppler frequencies.

Using a flash/no-flash image pair, we propose a novel white-balancing technique that can effectively correct the color balance of a complex scene under multiple light sources. In the proposed method, by using multiple images of the same scene taken under different lighting conditions, we estimate the reflectance component of the scene and the multiple shading components of each image. The reflectance component is a specific object color which does not depend on scene illumination and the shading component is a shading effect caused by the illumination lights. Then, we achieve white balancing by appropriately correcting the estimated shading components. The proposed method achieves better performance than conventional methods, especially under colored illumination and mixed lighting conditions.

In traditional speech emotion recognition systems, when the training and testing utterances are obtained from different corpora, the recognition rates will decrease dramatically. To tackle this problem, in this letter, inspired from the recent developments of sparse coding and transfer learning, a novel sparse transfer learning method is presented for speech emotion recognition. Firstly, a sparse coding algorithm is employed to learn a robust sparse representation of emotional features. Then, a novel sparse transfer learning approach is presented, where the distance between the feature distributions of source and target datasets is considered and used to regularize the objective function of sparse coding. The experimental results demonstrate that, compared with the automatic recognition approach, the proposed method achieves promising improvements on recognition rates and significantly outperforms the classic dimension reduction based transfer learning approach.

In this letter, we propose a new semantic parts learning approach to address the object detection problem with only the bounding boxes of object category labels. Our main observation is that even though the appearance and arrangement of object parts might have variations across the instances of different object categories, the constituent parts still maintain geometric consistency. Specifically, we propose a discriminative clustering method with sparse representation refinement to discover the mid-level semantic part set automatically. Then each semantic part detector is learned by the linear SVM in a one-vs-all manner. Finally, we utilize the learned part detectors to score the test image and integrate all the response maps of part detectors to obtain the detection result. The learned class-generic part detectors have the ability to capture the objects across different categories. Experimental results show that the performance of our approach can outperform some recent competing methods.

In this paper, we propose an efficient tracking method that is formulated as a multi-task reverse sparse representation problem. The proposed method learns the representation of all tasks jointly using a customized APG method within several iterations. In order to reduce the computational complexity, the proposed tracking algorithm starts from a feature selection scheme that chooses suitable number of features from the object and background in the dynamic environment. Based on the selected feature, multiple templates are constructed with a few candidates. The candidate that corresponds to the highest similarity to the object templates is considered as the final tracking result. In addition, we present a template update scheme to capture the appearance changes of the object. At the same time, we keep several earlier templates in the positive template set unchanged to alleviate the drifting problem. Both qualitative and quantitative evaluations demonstrate that the proposed tracking algorithm performs favorably against the state-of-the-art methods.

Face recognition across pose is generally tackled by either 2D based or 3D based approaches. The 2D-based often require a training set from which the cross-pose multi-view relationship can be learned and applied for recognition. The 3D based are mostly composed of 3D surface reconstruction of each gallery face, synthesis of 2D images of novel views using the reconstructed model, and match of the synthesized images to the probes. The depth information provides crucial information for arbitrary poses but more methods are yet to be developed. Extended from a latest face reconstruction method using a single 3D reference model and a frontal registered face, this study focuses on using the reconstructed 3D face for recognition. The recognition performance varies with poses, the closer to the front, the better. Several ways to improve the performance are attempted, including different numbers of fiducial points for alignment, multiple reference models considered in the reconstruction phase, and both frontal and profile poses available in the gallery. These attempts make this approach competitive to the state-of-the-art methods.

In this paper, we improve a width-3 joint sparse form proposed by Okeya, Katoh, and Nogami. After the improvement, the representation can attain an asymtotically optimal complexity found in our previous work. Although claimed as optimal by the authors, the average computation time of multi-scalar multiplication obtained by the representation is 563/1574n+o(n)≈0.3577n+o(n). That number is larger than the optimal complexity 281/786n+o(n)≈0.3575n+o(n) found in our previous work. To optimize the width-3 joint sparse form, we add more cases to the representation. After the addition, we can show that the complexity is updated to 281/786n+o(n)≈0.3575n+o(n), which implies that the modified representation is asymptotically optimal. Compared to our optimal algorithm in the previous work, the modified width-3 joint sparse form uses less dynamic memory, but it consumes more static memory.

In a patch-based super-resolution algorithm, a low-resolution patch is influenced by surrounding patches due to blurring. We propose to remove this boundary effect by subtracting the blur from the surrounding high-resolution patches, which enables more accurate sparse representation. We demonstrate improved performance through experimentation. The proposed algorithm can be applied to most of patch-based super-resolution algorithms to achieve additional improvement.

For robust visual tracking, the main challenges of a subspace representation model can be attributed to the difficulty in handling various appearances of the target object. Traditional subspace learning tracking algorithms neglected the discriminative correlation between different multi-view target samples and the effectiveness of sparse subspace learning. For learning a better subspace representation model, we designed a discriminative graph to model both the labeled target samples with various appearances and the updated foreground and background samples, which are selected using an incremental updating scheme. The proposed discriminative graph structure not only can explicitly capture multi-modal intraclass correlations within labeled samples but also can obtain a balance between within-class local manifold and global discriminative information from foreground and background samples. Based on the discriminative graph, we achieved a sparse embedding by using L2,1-norm, which is incorporated to select relevant features and learn transformation in a unified framework. In a tracking procedure, the subspace learning is embedded into a Bayesian inference framework using compound motion estimation and a discriminative observation model, which significantly makes localization effective and accurate. Experiments on several videos have demonstrated that the proposed algorithm is robust for dealing with various appearances, especially in dynamically changing and clutter situations, and has better performance than alternatives reported in the recent literature.

The dynamic routing and wavelength assignment (RWA) problem in wavelength division multiplexing (WDM) optical networks with sparse wavelength conversion has been a hot research topic in recent years. An optimized algorithm based on a multiple-layered interconnected graphic model (MIG) for the dynamic RWA is presented in this paper. The MIG is constructed to reflect the actual WDM network topology. Based on the MIG, the link cost is given by the conditions of available lightpath to calculate an initial solution set of optimal paths, and by combination with path length, the optimized solution using objective function is determined. This approach simultaneously solves the route selection and wavelength assignment problem. Simulation results demonstrate the proposed MIG-based algorithm is effective in reducing blocking probability and boosting wavelength resource utilization compared with other RWA methods.

The concept of sparse representation is gaining momentum in image processing applications, especially in image compression, from last one decade. Sparse coding algorithms represent signals as a sparse linear combination of atoms of an overcomplete dictionary. Earlier works shows that sparse coding of images using learned dictionaries outperforms the JPEG standard for image compression. The conventional method of image compression based on sparse coding, though successful, does not adapting the compression rate based on the image local block characteristics. Here, we have proposed a new framework in which the image is classified into three classes by measuring the block activities followed by sparse coding each of the classes using dictionaries learned specific to each class. K-SVD algorithm has been used for dictionary learning. The sparse coefficients for each class are Huffman encoded and combined to form a single bit stream. The model imparts some rate-distortion attributes to compression as there is provision for setting a different constraint for each class depending on its characteristics. We analyse and compare this model with the conventional model. The outcomes are encouraging and the model makes way for an efficient sparse representation based image compression.

Computation in the brain is realized in complicated, heterogeneous, and extremely large-scale network of neurons. About a hundred billion neurons communicate with each other by action potentials called “spike firings” that are delivered to thousands of other neurons from each. Repeated integration and networking of these spike trains in the network finally form the substance of our cognition, perception, planning, and motor control. Beyond conventional views of neural network mechanisms, recent rapid advances in both experimental and theoretical neuroscience unveil that the brain is a dynamical system to actively treat environmental information rather passively process it. The brain utilizes internal dynamics to realize our resilient and efficient perception and behavior. In this paper, by considering similarities and differences of the brain and information networks, we discuss a possibility of information networks with brain-like continuing internal dynamics. We expect that the proposed networks efficiently realize context-dependent in-network processing. By introducing recent findings of neuroscience about dynamics of the brain, we argue validity and clues for implementation of the proposal.

Recently, design of sparse finite impulse response (FIR) digital filters has attracted much attention due to its ability to reduce the implementation cost. However, finding a filter with the fewest number of nonzero coefficients subject to prescribed frequency domain constraints is a rather difficult problem because of its non-convexity. In this paper, an algorithm based on binary particle swarm optimization (BPSO) is proposed, which successively thins the filter coefficients until no sparser solution can be obtained. The proposed algorithm is evaluated on a set of examples, and better results can be achieved than other existing algorithms.

In consideration of the image noise captured by photoelectric cameras at nighttime, a robust motion detection algorithm based on sparse representation is proposed in this study. A universal dictionary for arbitrary scenes is presented. Realistic and synthetic experiments demonstrate the robustness of the proposed approach.

Chronic liver disease is a major worldwide health problem. Diagnosis and staging of chronic liver diseases is an important issue. In this paper, we propose a quantitative method of analyzing local morphological changes for accurate and practical computer-aided diagnosis of cirrhosis. Our method is based on sparse and low-rank matrix decomposition, since the matrix of the liver shapes can be decomposed into two parts: a low-rank matrix, which can be considered similar to that of a normal liver, and a sparse error term that represents the local deformation. Compared with the previous global morphological analysis strategy based on the statistical shape model (SSM), our proposed method improves the accuracy of both normal and abnormal classifications. We also propose using the norm of the sparse error term as a simple measure for classification as normal or abnormal. The experimental results of the proposed method are better than those of the state-of-the-art SSM-based methods.

Post-Silicon Tunable (PST) buffers are widely adopted in high-performance integrated circuits to fix timing violations introduced by process variations. In typical optimization procedures, the statistical timing analysis of the circuits with PST clock buffers will be executed more than 2000 times for large scale circuits. Therefore, the efficiency of the statistical timing analysis is crucial to the PST clock buffer optimization algorithms. In this paper, we propose a stochastic collocation based efficient statistical timing analysis method for circuits with PST buffers. In the proposed method, we employ the Howard algorithm to calculate the clock periods of the circuits on less than 100 deterministic sparse-grid collocation points. Afterwards, we use these obtained clock periods to derive the yield of the circuits according to the stochastic collocation theory. Compared with the state-of-the-art statistical timing analysis method for the circuits with PST clock buffers, the proposed method achieves up to 22X speedup with comparable accuracy.