This letter addresses the recovery of hierarchical sparse signals in a Bayesian framework. Hierarchical sparse signals exhibit two levels of sparsity, i.e., block-sparsity among different blocks and internal sparsity within each individual block. As in sparse Bayesian learning, each component of the coefficient vector is firstly modeled as a Gaussian distributed variable with zero mean. To enforce the two-level hierarchical sparsity, the variance is further modeled by two classes of hidden variables controlling the block-sparsity and the internal sparsity, respectively. Finally, variational Bayesian inference is used to recover the coefficient vector from the noise corrupted data. Numerical simulation and experimental results show that the proposed method outperforms those recently reported recovery methods.

This paper presents a novel inverse synthetic aperture radar (ISAR) imaging method by exploiting the inherent continuity of the scatterers on the target scene to obtain enhanced target images within a Bayesian framework. A simplified radar system is utilized by transmitting the sparse probing frequency signal, where the ISAR imaging problem can be converted to deal with underdetermined linear inverse scattering. Following the Bayesian compressive sensing (BCS) theory, a hierarchical Bayesian prior is employed to model the scatterers in the range-Doppler plane. In contrast to the independent prior on each scatterer in the conventional BCS, a correlated prior is proposed to statistically encourage the continuity structure of the scatterers in the target region. To overcome the intractability of the posterior distribution, the Gibbs sampling strategy is used for Bayesian inference. The parameters of the signal model are inferred efficiently from samples obtained by the Gibbs sampler. Because the proposed method is a data-driven learning process, the tedious parameter tuning process required by the convex optimization-based approaches can be avoided. Both the synthetic and the experimental results demonstrate that the proposed algorithm can achieve substantial improvements in the scenarios of limited measurements and low signal-to-noise ratio compared with other reported algorithms for ISAR imaging problems.

A new inverse synthetic aperture radar (ISAR) imaging approach is presented for application in situations where the maneuverability of noncooperative target is not too severe and the Doppler variation of subechoes from scatterers can be approximated as a first-order polynomial. The proposed algorithm is referred to as the range centroid Doppler (RCD) ISAR imaging technique and is based on the stretch Keystone-Wigner transform (SKWT). The SKWT introduces a stretch weight factor containing a range of chirp rate into the autocorrelation function of each cross-range profile and uses a 1-D interpolation of the phase history which we call stretch keystone formatting. The processing simultaneously eliminates the effects of linear frequency migration for all signal components regardless of their unknown chirp rate in time-frequency plane, but not for the noise or for the cross terms. By utilizing this novel technique, clear ISAR imaging can be achieved for maneuvering targets without an exhaustive search procedure for the motion parameters. Performance comparison is carried out to evaluate the improvement of the RCD technique versus other methods such as the conventional range Doppler (RD) technique, the range instantaneous Doppler (RID) technique, and adaptive joint time-frequency (AJTF) technique. Examples provided demonstrate the effectiveness of the RCD technique with both simulated and experimental ISAR data.

As shown in [9], for a state-space realization (A,B,C,d) of a digital filter there are no self-sustained oscillations (i.e., limit cycles) if there exists some diagonal matrix D ≫ 0 such that D-ATDA ≥ 0. Based on this result, we show that the optimal roundoff realizations are free of limit cycles. For any given realizations, a method is proposed to check the existence of such a D. A novel class of robust state-space realizations is derived and characterized, which are free of limit cycles and yield a minimal error propagation gain. The optimal realization problem for this class of realizations is formulated and solved analytically. Two examples are presented to test the efficiency of the proposed method and to demonstrate the behavior of the obtained optimal realization.

This comment letter points out that the essence of the "extreme learning machine (ELM)" recently appeared has been proposed earlier by Broomhead and Lowe and Pao , and discussed by other authors. Hence, it is not necessary to introduce a new name "ELM."

A novel beamspace inter-bit correlation 2D Rake receiver for DS-CDMA communication system is proposed in this paper. Although the proposed algorithm is a suboptimal solution, its performance is very close to the optimal space-time algorithm [1] and it can outperform the beamspace-frequency algorithm proposed in [2]. Another advantage is that the proposed algorithm is computationally more efficient when comparing with the beamspace-frequency algorithm.

In this paper, a novel blind space-time multiuser detector, called Space-Time Constrained Minimum Output Energy (ST-CMOE) detector, is proposed. The proposed ST-CMOE detector processes the received snapshot vector jointly in spatial and temporal domain and it can achieve the same performance as the training based space-time minimum mean square error (ST-MMSE) detector. An adaptive version of the proposed ST-CMOE detector is also presented. The computational load of this adaptive detector is comparable to Hu's method [1], while it does not require any initial training or channel estimation in the multipath environment. Simulation shows that, the adaptive ST-CMOE detector can work well in a dynamic multiple-access channel.

This letter derives a computationally efficient sequential Monte Carlo solution for blind detection of direct-sequence code-division multiple-access systems over multipath fading channels by decomposing the observed data into a number of signal components. Then the parameters of each component can be estimated by the sequential importance sampling and Kalman filtering. In comparison with other similar receivers, simulation results demonstrate that the proposed solution achieves the desirable performance with a significantly reduced computational complexity

Selection of significant genes via expression patterns is an important problem in microarray data processing. In this article, we propose and study a new method for selecting relevant genes obtained by spectral biclustering and based on similarity between genes and eigenvectors. The proposed algorithm can select a much smaller gene subset to make accurate predictions. The unsupervised gene selection method suggested in This work is demonstrated on two microarray cancer data sets, i.e., the lymphoma and the liver cancer data sets. In both examples, our method is able to identify two-gene combinations which can lead to prediction with very high accuracy.

The relevance feedback is proved to be an effective method in text information, image, and video retrieval. In this paper, we introduce this technique to carry out audio retrieval, in a hope not only to enhance the retrieval performance but also through this kind of user interaction to enhance the searching ability. Based on an initial searching result, a user can tag files with relevance or irrelevance according to one's judgment and preference. Then, the system updates the weights in similarity measurement and/or the query itself based on the feedback. Two relevance feedback algorithms have been proposed. One is a simplified technique used for feedback in image retrieval; another is based on constrained optimization concept. Experiments show that both approaches can yield similar performance improvements. Furthermore, the latter one can utilize negative feedback in a unified approach as well.

Nowadays, available audio corpora are rapidly increasing from fast growing Internet and digitized libraries. How to effectively classify and retrieve such huge databases is a challenging task. Content based technology is studied to automatically classify audio into hierarchy classes. Based on a small set of features selected by the sequential forward selection (SFS) method from 87 extracted ones, four classifiers, namely nearest neighbor (NN), modified k-nearest neighbor (k-NN), Gaussian mixture model (GMM), and probabilistic neural network (PNN) are compared. Experiments were conducted on a common database and a more comprehensive database built by the authors. Finally, the PNN classifier combined with Euclidean distance measurement was chosen for audio retrieval, using query by example.

DOA estimation is a difficult task in the wireless environment involving interference and multipath propagation. In this paper, an effective estimation method is proposed with low computation and high resolution. This scheme is based on using an antenna array receiver at the base station in CDMA systems. Perfect estimation of the time delay of multipath signals is assumed. The signal sub-space method is used at the output of the parallel matched filters to estimate each resolvable direction of multipath of the desired mobile user.