ALBERT

Beschreibung: Acoustic localization is an essential technique in speech capturing, speech enhancement, video conferencing, and human–robot interaction. However, in practical situations, localization has to be performed in abominable environments, where the presence of reverberation and noise degrades the performance of available position estimates. Besides, the designed systems should be adaptive to locomotion of targets with low computational complexity. In the context, this paper introduces a robust hierarchical acoustic localization method via time-delay compensation (TDC) and interaural matching filter (IMF). Firstly, interaural time-delay (ITD) and interaural level difference (ILD), which are cues involved in first two layers, respectively, are yielded by TDC all at once. Then, a novel feature named IMF, which can eliminate the difference between binaural signals, is proposed in the third layer. The final decision making is based on a Bayesian rule. The relationships among the three layers are that the former layer provides candidate directions for later ones such that the searching space becomes gradually smaller to reduce matching time. Experiments using both a public database and a real scenario verify that TDC and IMF are robust for acoustic localization, and hierarchical system has less consumption time.

Beschreibung: Canonical correlation analysis (CCA) is a widely used data analysis tool that allows to assess the correlation between two distinct sets of signals. It computes optimal linear combinations of the signals in both sets such that the resulting signals are maximally correlated. The weight vectors defining these optimal linear combinations are referred to as “principal CCA directions”. In addition to this particular type of data analysis, CCA is also often used as a blind source separation (BSS) technique, i.e., under certain assumptions, the principal CCA directions have certain demixing properties. In this paper, we propose a distributed CCA (DCCA) algorithm that can operate in wireless sensor networks (WSNs) with a fully connected or a tree topology. The algorithm estimates the $Q$ principal CCA directions from the sensor signal observations collected by the different nodes in the WSN and extracts the corresponding sources. These network-wide principal CCA directions are estimated in a time-recursive fashion without explicitly constructing the corresponding network-wide correlation matrices, i.e., without the need for data centralization. Instead, each node locally computes smaller CCA problems and only transmits compressed sensor signal observations (of dimension $Q$ ), which significantly reduces the bit rate over the wireless links of the WSN. We prove convergence and optimality of the DCCA algorithm, and we demonstrate its performance by means of numerical simulations in a blind source separation scenario.

Beschreibung: There has been much research on shrinkage methods for real-valued covariance matrices and their inverses (precision matrices). In spectral analysis of $p$ -vector-valued time series, complex-valued spectral matrices and precision matrices arise, and good shrinkage methods are often required, most notably when the estimated complex-valued spectral matrix is singular. As an improvement on the Ledoit-Wolf (LW) type of spectral matrix estimator we use random matrix theory to derive a Rao-Blackwell estimator for a spectral matrix, its inverse being a Rao–Blackwellized estimator for the spectral precision matrix. A random matrix method has previously been proposed for complex-valued precision matrices. It was implemented by very costly simulations. We formulate a fast, completely analytic approach. Moreover, we derive a way of selecting an important parameter using predictive risk methodology. We show that both the Rao–Blackwell estimator and the random matrix estimator of the precision matrix can substantially outperform the inverse of the LW estimator in a time series setting. Our new methodology is applied to EEG-derived time series data where it is seen to work well and deliver substantial improvements for precision matrix estimation.

Beschreibung: In this paper, the state estimation problem for discrete-time linear systems influenced by multiplicative and time-correlated additive measurement noises is considered where the multiplicative noises are zero-mean white noise sequences, and the time-correlated additive noise is described by a linear system model with white noise. An optimal linear estimator for the system under consideration is proposed, which does not require computing the inverse of state transition matrix. The proposed estimator has a recursive structure, and has time-independent computation and storage load. Computer simulations are carried out to demonstrate the performance of the proposed estimator. The simulation results show the superiority of the proposed estimator.

Beschreibung: In this paper, we start with the standard support vector machine (SVM) formulation and extend it by considering a general SVM formulation with normalized margin. This results in a unified convex framework that allows many different variations in the formulation with very diverse numerical performance. The proposed unified framework can capture the existing methods, i.e., standard soft-margin SVM, $ell_{1}$ -SVM, and SVMs with standardization, feature selection, scaling, and many more SVMs, as special cases. Furthermore, our proposed framework can not only provide us with more insights on different SVMs from the “energy” and “penalty” point of views, which help us understand the connections and differences between them in a unified way, but also enable us to propose more SVMs that outperform the existing ones under some scenarios.

Beschreibung: We consider multiple-antenna signal detection of primary user transmission signals by a secondary user receiver in cognitive radio networks. The optimal detector is analyzed for the scenario where the number of primary user signals is no less than the number of receive antennas at the secondary user. We first derive exact expressions for the moments of the generalized likelihood ratio test (GLRT) statistic, yielding approximations for the false alarm and detection probabilities. We then show that the normalized GLRT statistic converges in distribution to a Gaussian random variable when the number of antennas and observations grow large at the same rate. Further, using results from large random matrix theory, we derive expressions to compute the detection probability without explicit knowledge of the channel, and then particularize these expressions for two scenarios of practical interest: 1) a single primary user sending spatially multiplexed signals, and 2) multiple spatially distributed primary users. Our analytical results are finally used to obtain simple design rules for the signal detection threshold.

Beschreibung: This paper presents an optimized low-complexity and high-throughput MIMO signal detector core for detecting spatially multiplexed data streams. The core architecture supports various layer configurations up to 4, while achieving near-optimal performance, and configurable modulation constellations up to 256-QAM on each layer. The core is capable of operating as a soft-input soft-output log-likelihood ratio (LLR) MIMO detector which can be used in the context of iterative detection and decoding. High area-efficiency is achieved via algorithmic and architectural optimizations performed at two levels. First, distance computations and slicing operations for an optimal 2-layer maximum a posteriori MIMO detector are optimized to eliminate use of multipliers and reduce the overhead of slicing in the presence of soft-input LLRs. We show that distances can be easily computed using elementary addition operations, while optimal slicing is done via efficient comparisons with soft decision boundaries, resulting in a simple feed-forward pipelined architecture. Second, to support more layers, an efficient channel decomposition scheme is presented that reduces the detection of multiple layers into multiple 2-layer detection subproblems, which map onto the 2-layer core with a slight modification using a distance accumulation stage and a post-LLR processing stage. Various architectures are accordingly developed to achieve a desired detection throughput and run-time reconfigurability by time-multiplexing of one or more component cores. The proposed core is applied also to design an optimal multiuser MIMO detector for LTE. The core occupies an area of 1.58 MGE and achieves a throughput of 733 Mbps for 256-QAM when synthesized in 90-nm CMOS.

Beschreibung: We study a tandem of agents who make decisions about an underlying binary hypothesis, where the distribution of the agent observations under each hypothesis comes from an uncertainty class defined by a 2-alternating capacity. We investigate both decentralized detection rules, where agents collaborate to minimize the error probability of the final agent, and social learning rules, where each agent minimizes its own local minimax error probability. We then extend our results to the infinite tandem network, and derive necessary and sufficient conditions on the uncertainty classes for the minimax error probability to converge to zero when agents know their positions in the tandem. On the other hand, when agents do not know their positions in the network, we study the cases where agents collaborate to minimize the asymptotic minimax error probability, and where agents seek to minimize their worst-case minimax error probability (over all possible positions in the tandem). We show that asymptotic learning of the true hypothesis is no longer possible in these cases, and derive characterizations for the minimax error performance.

Beschreibung: Various blind synchronization methods built on the maximum likelihood (ML) principle have been proposed, where the addressed scenarios include additive white Gaussian noise (AWGN), single-path fading, and multipath fading channels. We consider ML blind synchronization over wide-sense stationary uncorrelated scattering (WSSUS) channels. Different from existing studies, we exploit a more complete signal correlation function and find the carrier frequency offset estimate to be the solution of a quartic equation, rather than the phase angle of a complex number. As the truly ML synchronizer (dubbed MLE) is very complicated, we also derive a reduced-complexity alternative (dubbed RCE). It is found that the RCE yields indistinguishable performance from the MLE, at a somewhat lower complexity than an existing rival. We also present an in-depth theoretical analysis and comparison of the performance of various methods. Simulations show that the proposed methods yield rather robust performance in modeling errors of the fading rate and the channel power-delay profile (PDP).

Beschreibung: In this paper, the performance of cloud radio access networks (CRANs) where spatially distributed remote radio heads (RRHs) aid the macro base station (MBS) in transmission is analysed. In order to reflect a realistic scenario, the MBS and the RRHs are assumed to be equipped with multiple antennas and distributed according to a Poisson point process. Both, the MBS and the RRHs, are assumed to employ maximal ratio transmission (MRT) or transmit antenna selection (TAS). Considering downlink transmission, the outage performance of three schemes is studied; first is the selection transmission (ST) scheme, in which the MBS or the RRH with the best channel is selected for transmission. In the second scheme, all the RRHs participate (ARP) and transmit the signal to the user, whereas in the third scheme, a minimal number of RRHs, to attain a desired data-rate, participate in transmission (MRP). Exact closed-form expression for the outage probability is derived for the ST scheme. For the ARP and MRP schemes, analytical approximations of the outage probability are derived which are tight at high signal-to-noise ratios. In addition, for the MRP scheme, the minimal number of RRHs required to meet a target data rate is also calculated which can be useful in characterizing the system complexity. Furthermore, the derived expressions are validated through numerical simulation. It is shown that the average diversity gains of these schemes are independent of the intensity/number of RRHs and only depend on the number of antennas on the MBS. Furthermore, the ARP scheme outperforms the ST scheme when the MBS/RRHs transmit with maximum power. However, in case of a sum power constraint and equal power allocation, the ST scheme outperforms the ARP scheme.

Beschreibung: This paper proposes a dynamic resource allocation scheme to exploit the mixed timescale channel state information (CSI) knowledge structure in a multi-antenna base station-assisted device-to-device (D2D) network. The short-term multi-antenna beamforming control at each transmit device is adaptive to the local real-time CSI. The long-term routing and flow control is adaptive to the global topology and the long-term global CSI statistics of the D2D network. The design objective is to maximize a network utility function subject to the average transmit power constraint, the flow balance constraints and the instantaneous physical layer capacity constraints. The mixed timescale problem can be decomposed into a short-term beamforming control problem and a long-term flow and routing control problem. Using the stochastic cutting plane, we propose a low complexity, self-learning algorithm, which converges to the global optimal solution without explicit knowledge of the channel statistics. Simulation illustrates performance gains with several baselines.

Beschreibung: This paper considers the estimation of multi-scale multi-lag (MSML) channels. The MSML channel model is a good representation for wideband communication channels, such as underwater acoustic communication and radar. This model is characterized by a limited number of paths, each parameterized by a delay, Doppler scale, and attenuation factor. Herein, it is shown that an OFDM signal after passing through the MSML channel exhibits a low rank representation. This feature can be exploited to improve the channel estimation. By characterizing the received signal, it is shown that the MSML channel estimation problem can be adapted to a structured spectral estimation problem. The challenge is that the unknown frequencies are very close to each other due to the small values of Doppler scales. This feature can be employed to show that the data matrix is approximately low-rank. By exploiting structural features of the received signal, the Prony algorithm is modified to estimate the Doppler scales (close frequencies), delays and channel gains. Two strategies using convex and no-convex regularizers to remove noise from the corrupted signal are proposed. These algorithms are iterative based on the alternating direction method of multipliers. A bound on the reconstruction of the noiseless received signal provides guidance on the selection of the relaxation parameter in the optimizations. The performance of the proposed estimation strategies are investigated via numerical simulations, and it is shown that the proposed non-convex method offers up to 7 dB improvement in low SNR and the convex method offers up to 5 dB improvement in high SNR over prior methods for the MSML channel estimation.

Beschreibung: Distributed processing over networks relies on in-network processing and cooperation among neighboring agents. Cooperation is beneficial when agents share a common objective. However, in many applications, agents may belong to different clusters that pursue different objectives. Then, indiscriminate cooperation will lead to undesired results. In this paper, we propose an adaptive clustering and learning scheme that allows agents to learn which neighbors they should cooperate with and which other neighbors they should ignore. In doing so, the resulting algorithm enables the agents to identify their clusters and to attain improved learning and estimation accuracy over networks. We carry out a detailed mean-square analysis and assess the error probabilities of Types I and II, i.e., false alarm and misdetection, for the clustering mechanism. Among other results, we establish that these probabilities decay exponentially with the step-sizes so that the probability of correct clustering can be made arbitrarily close to one.

Beschreibung: Robust Chinese remainder theorem (CRT) has been recently investigated for both integers and real numbers, where the folding integers are accurately recovered from erroneous remainders. In this paper, we consider the CRT problem for real numbers with noisy remainders that follow wrapped Gaussian distributions. We propose the maximum-likelihood estimation (MLE) based CRT when the remainder noises may not necessarily have the same variances. Furthermore, we present a fast algorithm for the MLE based CRT algorithm that only needs to search for the solution among $L$ elements, where $L$ is the number of remainders. Then, a necessary and sufficient condition on the remainder errors for the MLE CRT to be robust is obtained, which is weaker than the existing result. Finally, we compare the performances of the newly proposed algorithm and the existing algorithm in terms of both theoretical analysis and numerical simulations. The results demonstrate that the proposed algorithm not only has a better performance especially when the remainders have different error levels/variances, but also has a much lower computational complexity.

Beschreibung: Sparse signal restoration is usually formulated as the minimization of a quadratic cost function $Vert { mbi { y}} - { mbi { A}} { mbi { x}} Vert_{2}^{2}$ where $ { mbi { A}} $ is a dictionary and $ { mbi { x}} $ is an unknown sparse vector. It is well-known that imposing an $ell _{0}$ constraint leads to an NP-hard minimization problem. The convex relaxation approach has received considerable attention, where the $ell _{0}$ -norm is replaced by the $ell _{1}$ -norm. Among the many effective $ell _{1}$ solvers, the homotopy algorithm minimizes $Vert { mbi { y}} - { mbi { A}} { mbi { x}} Vert_{2}^{2}+lambda Vert { mbi { x}} Vert _{1}$ with respect to $ { mbi { x}} $ for a continuum of $lambda $ ’s. It is inspired by the piecewise regularity of the $ell _{1}$ -regularization path, also referred to as the homotopy path. In this paper, we address the minimization problem $Vert { mbi { y}} - { mbi { A}} { mbi { x}} Vert_{2}^{2}+lambda Vert { mbi { x}} Vert _{0}$ for a continuum of $lambda $ ’s and propose two heuristic search algorithms for $ell _{0}$ -homotopy. Continuation Single Best Replacement is a forward–backward greedy strategy extending the Single Best Replacement algorithm, previously proposed for $ell _{0}$ -minimization at a given $lambda $ . The adaptive search of the $lambda $ -values is inspired by $ell _{1}$ -homotopy. $ell _{0}$ Regularization Path Descent is a more complex algorithm exploiting the structural properties of the $ell _{0}$ -regularization path, which is piecewise constant with respect to $lambda $ . Both algorithms are empirically evaluated for difficult inverse problems involving ill-conditioned dictionaries. Finally, we show that they can be easily coupled with usual methods of model order selection.

Beschreibung: In recent work, robust Principal Components Analysis (PCA) has been posed as a problem of recovering a low-rank matrix ${bf L}$ and a sparse matrix ${bf S}$ from their sum, ${bf M}:= {bf L} + {bf S}$ and a provably exact convex optimization solution called PCP has been proposed. This work studies the following problem. Suppose that we have partial knowledge about the column space of the low rank matrix ${bf L}$ . Can we use this information to improve the PCP solution, i.e., allow recovery under weaker assumptions? We propose here a simple but useful modification of the PCP idea, called modified-PCP, that allows us to use this knowledge. We derive its correctness result which shows that, when the available subspace knowledge is accurate, modified-PCP indeed requires significantly weaker incoherence assumptions than PCP. Extensive simulations are also used to illustrate this. Comparisons with PCP and other existing work are shown for a stylized real application as well. Finally, we explain how this problem naturally occurs in many applications involving time series data, i.e., in what is called the online or recursive robust PCA problem. A corollary for this case is also given.

Beschreibung: Phased array is widely used in radar systems with its beam steering fixed in one direction for all ranges. Therefore, the range of a target cannot be determined within a single pulse when range ambiguity exists. In this paper, an unambiguous approach for joint range and angle estimation is devised for multiple-input multiple-output (MIMO) radar with frequency diverse array (FDA). Unlike the traditional phased array, FDA is capable of employing a small frequency increment across the array elements. Because of the frequency increment, the transmit steering vector of the FDA-MIMO radar is a function of both range and angle. As a result, the FDA-MIMO radar is able to utilize degrees-of-freedom in the range-angle domains to jointly determine the range and angle parameters of the target. In addition, the Cramér–Rao bounds for range and angle are derived, and the coupling between these two parameters is analyzed. Numerical results are presented to validate the effectiveness of the proposed approach.

Beschreibung: In this paper, we propose a novel single-group multicasting relay beamforming scheme. We assume a source that transmits common messages via multiple amplify-and-forward relays to multiple destinations. To increase the number of degrees of freedom in the beamforming design, the relays process two received signals jointly and transmit the Alamouti space-time block code over two different beams. Furthermore, in contrast to the existing relay multicasting scheme of the literature, we take into account the direct links from the source to the destinations. We aim to maximize the lowest received quality-of-service by choosing the proper relay weights and the ideal distribution of the power resources in the network. To solve the corresponding optimization problem, we propose an iterative algorithm which solves sequences of convex approximations of the original non-convex optimization problem. Simulation results demonstrate significant performance improvements of the proposed methods as compared with the existing relay multicasting scheme of the literature and an algorithm based on the popular semidefinite relaxation technique.

Beschreibung: In this paper, we propose a new class of iteratively re-weighted least squares (IRLS) for sparse recovery problems. The proposed methods are inspired by constrained maximum-likelihood estimation under a Gaussian scale mixture (GSM) distribution assumption. In the noise-free setting, we provide sufficient conditions ensuring the convergence of the sequences generated by these algorithms to the set of fixed points of the maps that rule their dynamics and derive conditions verifiable a posteriori for the convergence to a sparse solution. We further prove that these algorithms are quadratically fast in a neighborhood of a sparse solution. We show through numerical experiments that the proposed methods outperform classical IRLS for $ell_{tau}$ -minimization with $tauin(0,1]$ in terms of speed and of sparsity-undersampling tradeoff and are robust even in presence of noise. The simplicity and the theoretical guarantees provided in this paper make this class of algorithms an attractive solution for sparse recovery problems.

Beschreibung: We consider the problem of approximating optimal in the Minimum Mean Squared Error (MMSE) sense nonlinear filters in a discrete time setting, exploiting properties of stochastically convergent state process approximations. More specifically, we consider a class of nonlinear, partially observable stochastic systems, comprised by a (possibly nonstationary) hidden stochastic process (the state), observed through another conditionally Gaussian stochastic process (the observations). Under general assumptions, we show that, given an approximating process which, for each time step, is stochastically convergent to the state process, an approximate filtering operator can be defined, which converges to the true optimal nonlinear filter of the state in a strong and well defined sense. In particular, the convergence is compact in time and uniform in a completely characterized set of probability measure almost unity. The results presented in this paper can form a common basis for the analysis and characterization of a number of popular but heuristic approaches for approximating optimal nonlinear filters, such as approximate grid based techniques.

Beschreibung: A standard assumption for consistent estimation in the errors-in-variables setting is persistency of excitation of the noise-free input signal. We relax this assumption by considering data from multiple experiments. Consistency is obtained asymptotically as the number of experiments tends to infinity. The main theoretical and algorithmic difficulties are related to the growing number of to-be-estimated initial conditions. The method proposed in the paper is based on analytic elimination of the initial conditions and optimization over the remaining parameters. The resulting estimator is consistent; however, achieving asymptotically efficiency is an open problem.

Beschreibung: Bayesian filtering aims at estimating sequentially a hidden process from an observed one. In particular, sequential Monte Carlo (SMC) techniques propagate in time weighted trajectories which represent the posterior probability density function (pdf) of the hidden process given the available observations. On the other hand, conditional Monte Carlo (CMC) is a variance reduction technique which replaces the estimator of a moment of interest by its conditional expectation given another variable. In this paper, we show that up to some adaptations, one can make use of the time recursive nature of SMC algorithms in order to propose natural temporal CMC estimators of some point estimates of the hidden process, which outperform the associated crude Monte Carlo (MC) estimator whatever the number of samples. We next show that our Bayesian CMC estimators can be computed exactly, or approximated efficiently, in some hidden Markov chain (HMC) models; in some jump Markov state-space systems (JMSS); as well as in multitarget filtering. Finally our algorithms are validated via simulations.

Beschreibung: In this paper, cooperative sensor localization using asynchronous time-of-arrival measurements is investigated. It is well known that localization performance in wireless networks using time-based ranging or pseudo-ranging methods is greatly affected by the accuracy of the timing synchronization between the nodes involved in the estimation. Commonly, the original estimation problem is broken down into two subproblems, the synchronization problem and the localization problem, in what is known as a two-step approach. However, in this paper, the joint synchronization and localization problem is considered and examined for use in cooperative networks. It is discussed that the cooperation between the source nodes eliminates the need for high anchor node densities and improves localization performance significantly. Furthermore, the Cramér-Rao lower bounds (CRLB) and the maximum likelihood (ML) estimator are derived. It is shown that the ML estimator is highly nonlinear and nonconvex and must, therefore, be solved by using computationally complex algorithms. In order to reduce the complexity of the estimation, a novel semidefinite programming (SDP) relaxation method is developed by relaxing the original nonconvex ML problem, in such a way as to reformulate the estimation problem as a convex problem. The performance of the proposed SDP method is shown through computer simulations to nearly equal that of the ML estimator. The approach is also applied to the noncooperative case where it is found to be superior in performance than the previously proposed suboptimal estimators. Finally, complexity analyses are included for the estimators under consideration.

Beschreibung: In this paper, we consider the problem of parameter estimation over sensor networks in the presence of quantized data and directed communication links. We propose a two-stage distributed algorithm aiming at achieving the centralized sample mean estimate in a distributed manner. Different from the existing algorithms, a running average technique is utilized in the proposed algorithm to smear out the randomness caused by the probabilistic quantization scheme. With the running average technique, it is shown that the centralized sample mean estimate can be achieved both in the mean square and almost sure senses, which is not observed in the standard consensus algorithms. In addition, the rates of convergence are given to quantify the mean square and almost sure performances. Finally, simulation results are presented to illustrate the effectiveness of the proposed algorithm and highlight the improvements by using running average technique.

Beschreibung: This paper studies a pilot-assisted physical layer data fusion technique known as Distributed Co-Phasing (DCP). In this two-phase scheme, the sensors first estimate the channel to the fusion center (FC) using pilots sent by the latter; and then they simultaneously transmit their common data by pre-rotating them by the estimated channel phase, thereby achieving physical layer data fusion. First, by analyzing the symmetric mutual information of the system, it is shown that the use of higher order constellations (HOC) can improve the throughput of DCP compared to the binary signaling considered heretofore. Using an HOC in the DCP setting requires the estimation of the composite DCP channel at the FC for data decoding. To this end, two blind algorithms are proposed: 1) power method, and 2) modified $K$ -means algorithm. The latter algorithm is shown to be computationally efficient and converges significantly faster than the conventional $K$ -means algorithm. Analytical expressions for the probability of error are derived, and it is found that even at moderate to low SNRs, the modified $K$ -means algorithm achieves a probability of error comparable to that achievable with a perfect channel estimate at the FC, while requiring no pilot symbols to be transmitted from the sensor nodes. Also, the problem of signal corruption due to imperfect DCP is investigated, and constellation shaping to minimize the probability of signal corruption is proposed and analyzed. The analysis is validated, and the promising performance of DCP for energy-efficient physical layer data fusion is illustrated, using Monte Carlo simulations.

Beschreibung: In this paper we propose a fast and efficient Jacobi-like approach named JET (Joint Eigenvalue decomposition based on Triangular matrices) for the Joint EigenValue Decomposition (JEVD) of a set of real or complex non-defective matrices based on the LU factorization of the matrix of eigenvectors. Contrarily to classical Jacobi-like JEVD methods, the iterative procedure of the JET approach can be reduced to the search for only one of the two triangular matrices involved in the factorization of the matrix of eigenvectors, hence decreasing the numerical complexity. Two variants of the JET technique, namely JET-U and JET-O, which correspond to the optimization of two different cost functions are described in detail and these are extended to the complex case. Numerical simulations show that in many practical cases the JET approach provides more accurate estimation of the matrix of eigenvectors than its competitors and that the lowest numerical complexity is consistently achieved by the JET-U algorithm. In addition, we illustrate in the ICA context the interest of being able to solve efficiently the (non-orthogonal) JEVD problem. More particularly, based on our JET-U algorithm, we propose a more robust version of an existing ICA method, named MICAR-U. The identifiability of the latter is studied and proved under some conditions. Computer results given in the context of brain interfaces show the better ability of MICAR-U to denoise simulated electrocortical data compared to classical ICA techniques for low signal to noise ratio values.

Beschreibung: A new design for successive interference cancellation (SIC) detection for multiple-input multiple-output systems is introduced, and it is developed on the basis of the method of normal equations commonly used to solve the linear least squares problem. On the basis of this design, optimal-ordered and suboptimal-ordered SIC detection algorithms are derived. It is shown that the proposed optimal-ordered SIC detection algorithm offers a complexity reduction ratio of 1.11–1.25 compared to the fastest known optimal-ordered SIC detection algorithm for intermediate and large numbers of antennas and in terms of the average complexity. On the other hand, the proposed suboptimal-ordered SIC detection algorithm requires a lower complexity than the proposed optimal-ordered one and provides a bit-error-rate performance close to that of the optimal-ordered one and better than those of the other suboptimal-ordered SIC detection algorithms.

Beschreibung: We consider the problem of signal recovery on graphs. Graphs model data with complex structure as signals on a graph. Graph signal recovery recovers one or multiple smooth graph signals from noisy, corrupted, or incomplete measurements. We formulate graph signal recovery as an optimization problem, for which we provide a general solution through the alternating direction methods of multipliers. We show how signal inpainting, matrix completion, robust principal component analysis, and anomaly detection all relate to graph signal recovery and provide corresponding specific solutions and theoretical analysis. We validate the proposed methods on real-world recovery problems, including online blog classification, bridge condition identification, temperature estimation, recommender system for jokes, and expert opinion combination of online blog classification.

Beschreibung: In this paper, we investigate the network power minimization problem for the multicast cloud radio access network (Cloud-RAN) with imperfect channel state information (CSI). The key observation is that network power minimization can be achieved by adaptively selecting active remote radio heads (RRHs) via controlling the group-sparsity structure of the beamforming vector. However, this yields a non-convex combinatorial optimization problem, for which we propose a three-stage robust group sparse beamforming algorithm. In the first stage, a quadratic variational formulation of the weighted mixed $ell_1/ell_2$ -norm is proposed to induce the group-sparsity structure in the aggregated beamforming vector, which indicates those RRHs that can be switched off. A perturbed alternating optimization algorithm is then proposed to solve the resultant non-convex group-sparsity inducing optimization problem by exploiting its convex substructures. In the second stage, we propose a PhaseLift technique based algorithm to solve the feasibility problem with a given active RRH set, which helps determine the active RRHs. Finally, the semidefinite relaxation (SDR) technique is adopted to determine the robust multicast beamformers. Simulation results will demonstrate the convergence of the perturbed alternating optimization algorithm, as well as, the effectiveness of the proposed algorithm to minimize the network power consumption for multicast Cloud-RAN.

Beschreibung: Many machine learning frameworks, such as resource-allocating networks, kernel-based methods, Gaussian processes, and radial-basis-function networks, require a sparsification scheme in order to address the online learning paradigm. For this purpose, several online sparsification criteria have been proposed to restrict the model definition on a subset of samples. The most known criterion is the (linear) approximation criterion, which discards any sample that can be well represented by the already contributing samples, an operation with excessive computational complexity. Several computationally efficient sparsification criteria have been introduced in the literature with the distance and the coherence criteria. This paper provides a unified framework that connects these sparsification criteria in terms of approximating samples, by establishing theoretical bounds on the approximation errors. Furthermore, the error of approximating any pattern is investigated, by proposing upper bounds on the approximation error for each of the aforementioned sparsification criteria. Two classes of fundamental patterns are described in detail, the centroid (i.e., empirical mean) and the principal axes in the kernel principal component analysis. Experimental results show the relevance of the theoretical results established in this paper.

Beschreibung: The radix- $2^{k}$ algorithm plays a crucial role in the pipelined implementation of fast Fourier transform (FFT). This paper presents a fixed-point analysis and hardware evaluation of radix- $2^{k}$ FFT under the framework of the single-path delay feedback (SDF) and multi-path delay commutator (MDC) pipelined structure. The investigation is carried out with variable operating word-lengths to ensure the generality. Furthermore, the main streams to fulfill FFT coefficients weighting, namely, the approach using complex multipliers and the one adopting memoryless CORDIC units, are both considered in the analysis. Based on these derivations, a joint optimization of radix- $2^{k}$ algorithm and operating word-length is discussed to achieve a reasonable trade-off between computational accuracy and hardware expenditure. Simulations and experiments indicates that the derived SQNR is reliable to unfold the quantization effects of fixed-point radix- $2^{k}$ FFT. In addition, the proposed joint optimization strategy is capable of providing better solutions to implement the radix- $2^{k}$ FFT processor efficiently.

Beschreibung: In this paper, the quickest change detection problem is studied in two-state hidden Markov models (HMM), where the vector parameter $theta$ of the HMM changes from $theta_{0}$ to $theta_{1}$ at some unknown time, and one wants to detect the true change as quickly as possible while controlling the false alarm rate. It turns out that the generalized likelihood ratio (GLR) scheme, while theoretically straightforward, is generally computationally infeasible for the HMM. To develop efficient but computationally simple schemes for the HMM, we first discuss a subtlety in the recursive form of the generalized likelihood ratio (GLR) scheme for the HMM. Then we show that the recursive CUSUM scheme proposed in Fuh (Ann. Statist., 2003) can be regarded as a quasi-GLR scheme for pseudo post-change hypotheses with certain dependence structure between pre- and postchange observations. Next, we extend the quasi-GLR idea to propose recursive score schemes in the scenario when the postchange parameter $theta_{1}$ of the HMM involves a real-valued nuisance parameter. Finally, the Kullback-Leibler (KL) divergence plays an essential role in the quickest change detection problem and many other fields, however it is rather challenging to numerically compute it in HMMs. Here we develop a non-Monte Carlo method that computes the KL divergence of two-state HMMs via the underlying invariant probability measure, which is characterized by the Fredholm integral equation. Numerical study demonstrates an unusual property of the KL divergence for HMM that implies the severe effects of misspecifying the postchange parameter for the HMM.

Beschreibung: Convex optimization is a powerful tool for resource allocation and signal processing in wireless networks. As the network density is expected to drastically increase in order to accommodate the exponentially growing mobile data traffic, performance optimization problems are entering a new era characterized by a high dimension and/or a large number of constraints, which poses significant design and computational challenges. In this paper, we present a novel two-stage approach to solve large-scale convex optimization problems for dense wireless cooperative networks, which can effectively detect infeasibility and enjoy modeling flexibility. In the proposed approach, the original large-scale convex problem is transformed into a standard cone programming form in the first stage via matrix stuffing, which only needs to copy the problem parameters such as channel state information (CSI) and quality-of-service (QoS) requirements to the prestored structure of the standard form. The capability of yielding infeasibility certificates and enabling parallel computing is achieved by solving the homogeneous self-dual embedding of the primal-dual pair of the standard form. In the solving stage, the operator splitting method, namely, the alternating direction method of multipliers (ADMM), is adopted to solve the large-scale homogeneous self-dual embedding. Compared with second-order methods, ADMM can solve large-scale problems in parallel with modest accuracy within a reasonable amount of time. Simulation results will demonstrate the speedup, scalability, and reliability of the proposed framework compared with the state-of-the-art modeling frameworks and solvers.

Beschreibung: The discrete cosine transform (DCT) is known to be asymptotically equivalent to the Karhunen-Loève transform (KLT) of Gaussian first-order auto-regressive (AR(1)) processes. Since being uncorrelated under the Gaussian hypothesis is synonymous with independence, it also yields an independent-component analysis (ICA) of such signals. In this paper, we present a constructive non-Gaussian generalization of this result: the characterization of the optimal orthogonal transform (ICA) for the family of symmetric- $alpha$ -stable AR(1) processes. The degree of sparsity of these processes is controlled by the stability parameter $0 〈 alphaleq2$ with the only non-sparse member of the family being the classical Gaussian AR(1) process with $alpha=2$ . Specifically, we prove that, for $alpha 〈 2$ , a fixed family of operator-like wavelet bases systematically outperforms the DCT in terms of compression and denoising ability. The effect is quantified with the help of two performance criteria (one based on the Kullback-Leibler divergence, and the other on Stein’s formula for the minimum estimation error) that can also be viewed as statistical measures of independence. Finally, we observe that, for the sparser kind of processes with $0 〈 alphaleq 1$ , the operator-like wavelet basis, as dictated by linear system theory, is undistinguishable from the ICA solution obtained through numerical optimization. Our framework offers a unified view that encompasses sinusoidal transforms such as the DCT and a family of orthogonal Haar-like wavelets that is linked analytically to the underlying signal model.

Beschreibung: MUSIC is a popular algorithm for estimating the direction of arrival (DOA) in array signal processing applications. In this paper, we analyze the performance of the MUSIC algorithm for a single source system, in the presence of noisy and missing data (when only a random subset of the entries in the data matrix are observed). We prove consistency of the DOA estimate when signal from a single source is impinging on low coherence arrays, and derive an analytic expression for the mean-squared-error (MSE) performance of MUSIC for the case of uniform linear arrays, in the large array and relatively large sample setting. Our analysis is mathematically justified in both the sample rich and deficient regimes. The expression for the MSE is a simple function of array geometry, signal-to-noise ratio (SNR), the fraction of entries observed, and the ratio of the number of sensors to number of snapshots. We derive a phase transition threshold which separates a regime where MUSIC is consistent from a regime where MUSIC is inconsistent. This threshold depends upon the SNR, the probability of observing entries in the data matrix, and number of sensors and snapshots in a simple manner which we make explicit.

Beschreibung: Phase retrieval problems involve solving linear equations, but with missing sign (or phase, for complex numbers) information. More than four decades after it was first proposed, the seminal error reduction algorithm of Gerchberg and Saxton and Fienup is still the popular choice for solving many variants of this problem. The algorithm is based on alternating minimization; i.e., it alternates between estimating the missing phase information, and the candidate solution. Despite its wide usage in practice, no global convergence guarantees for this algorithm are known. In this paper, we show that a (resampling) variant of this approach converges geometrically to the solution of one such problem—finding a vector $bf x$ from ${bf y}, {bf A}$ , where ${bf y} = vert {bf A}^T{bf x}vert$ and $vert{bf z}vert$ denotes a vector of element-wise magnitudes of ${bf z}$ —under the assumption that $ {bf A}$ is Gaussian. Empirically, we demonstrate that alternating minimization performs similar to recently proposed convex techniques for this problem (which are based on “lifting” to a convex matrix problem) in sample complexity and robustness to noise. However, it is much more efficient and can scale to large problems. Analytically, for a resampling version of alternating minimization, we show geometric convergence to the solution, and sample complexity that is off by log factors from obvious lower bounds. We also establish close to optimal scaling for the case when the unknown vector is sparse. Our work represents the first theoretical guarantee for al- ernating minimization (albeit with resampling) for any variant of phase retrieval problems in the non-convex setting.

Beschreibung: We consider Bayesian blind deconvolution (BD) of an unknown sparse sequence convolved with an unknown pulse. Our goal is to detect the positions where the sparse input sequence is nonzero and to estimate the corresponding amplitudes as well as the pulse shape. For this task, we propose a novel evolution of the single most likely replacement (SMLR) algorithm. Our method uses a modified Bernoulli-Gaussian prior that incorporates a minimum temporal distance constraint. This prior simultaneously induces sparsity and enforces a prescribed minimum distance between the pulse centers. The minimum distance constraint provides an effective way to avoid overfitting (i.e., spurious detected pulses) and improve resolution. The proposed BD method overcomes certain weaknesses of the traditional SMLR-based BD method, which is verified experimentally to result in improved detection/estimation performance and reduced computational complexity. Our simulation results also demonstrate performance and complexity advantages relative to the iterated window maximization (IWM) algorithm and a recently proposed partially collapsed Gibbs sampler method.

Beschreibung: We address the problem of super-resolution frequency recovery using prior knowledge of the structure of a spectrally sparse, undersampled signal. In many applications of interest, some structure information about the signal spectrum is often known. The prior information might be simply knowing precisely some signal frequencies or the likelihood of a particular frequency component in the signal. We devise a general semidefinite program to recover these frequencies using theories of positive trigonometric polynomials. Our theoretical analysis shows that, given sufficient prior information, perfect signal reconstruction is possible using signal samples no more than thrice the number of signal frequencies. Numerical experiments demonstrate great performance enhancements using our method. We show that the nominal resolution necessary for the grid-free results can be improved if prior information is suitably employed.

Beschreibung: This paper addresses the behavior of a classical multiantenna GLRT test that allows to detect the presence of a known signal corrupted by a multipath propagation channel and by an additive temporally white Gaussian noise with unknown spatial covariance matrix. The paper is focused on the case where the number of sensors $M$ is large, and of the same order of magnitude as the sample size $N$ , a context which is modeled by the large system asymptotic regime $M rightarrow +infty $ , $N rightarrow +infty $ in such a way that $M/N rightarrow c$ for $c in (0,+infty )$ . The purpose of this paper is to study the behaviour of a GLRT statistics in this regime, and to show that the corresponding theoretical analysis allows to accurately predict the performance of the test when $M$ and $N$ are of the same order of magnitude.

Beschreibung: This paper derives an asymptotic generalized likelihood ratio test (GLRT) and an asymptotic locally most powerful invariant test (LMPIT) for two hypothesis testing problems: 1) Is a vector-valued random process cyclostationary (CS) or is it wide-sense stationary (WSS)? 2) Is a vector-valued random process CS or is it nonstationary? Our approach uses the relationship between a scalar-valued CS time series and a vector-valued WSS time series for which the knowledge of the cycle period is required. This relationship allows us to formulate the problem as a test for the covariance structure of the observations. The covariance matrix of the observations has a block-Toeplitz structure for CS and WSS processes. By considering the asymptotic case where the covariance matrix becomes block-circulant we are able to derive its maximum likelihood (ML) estimate and thus an asymptotic GLRT. Moreover, using Wijsman’s theorem, we also obtain an asymptotic LMPIT. These detectors may be expressed in terms of the Loève spectrum, the cyclic spectrum, and the power spectral density, establishing how to fuse the information in these spectra for an asymptotic GLRT and LMPIT. This goes beyond the state-of-the-art, where it is common practice to build detectors of cyclostationarity from ad-hoc functions of these spectra.

Beschreibung: The impulse response of wireless channels between the $N_t$ transmit and $N_r$ receive antennas of a MIMO-OFDM system are group approximately sparse (ga-sparse), i.e., the $N_tN_r$ channels have a small number of significant paths relative to the channel delay spread and the time-lags of the significant paths between transmit and receive antenna pairs coincide. Often, wireless channels are also group approximately cluster-sparse (gac-sparse), i.e., every ga-sparse channel consists of clusters, where a few clusters have all strong components while most clusters have all weak components. In this paper, we cast the problem of estimating the ga-sparse and gac-sparse block-fading and time-varying channels in the sparse Bayesian learning (SBL) framework and propose a bouquet of novel algorithms for pilot-based channel estimation, and joint channel estimation and data detection, in MIMO-OFDM systems. The proposed algorithms are capable of estimating the sparse wireless channels even when the measurement matrix is only partially known. Further, we employ a first-order autoregressive modeling of the temporal variation of the ga-sparse and gac-sparse channels and propose a recursive Kalman filtering and smoothing (KFS) technique for joint channel estimation, tracking, and data detection. We also propose novel, parallel-implementation based, low-complexity techniques for estimating gac-sparse channels. Monte Carlo simulations illustrate the benefit of exploiting the gac-sparse structure in the wireless channel in terms of the mean square error (MSE) and coded bit error rate (BER) performance.

Beschreibung: One-dimensional (1-D) and two-dimensional (2-D) frequency estimation for a single complex sinusoid in white Gaussian noise is a classic signal processing problem with numerous applications. It is revisited here through a new unitary principal-singular-vector utilization modal analysis (PUMA) approach, which is realized in terms of real-valued computations. The 2-D unitary PUMA is first formulated as an iteratively weighted least squares optimization problem. Recognizing that only one iteration is sufficient when 2-D unitary PUMA is initialized using least squares, a computationally attractive closed-form solution is then obtained. A variant of 2-D unitary PUMA is also developed for the 1-D case. Due to the real-valued computations and closed-form expression for the frequency estimate, the unitary PUMA is more computationally efficient than a number of state-of-the-art methods. Furthermore, the asymptotic variances of 1-D and 2-D unitary PUMA estimators are theoretically derived, and numerical results are included to demonstrate the effectiveness of the proposed methods.

Beschreibung: Distributed estimation over sensor networks has received a lot of attention due to its great promise for broad applicability. In many cases, sensors have constraints on the range of data they can measure. This may cause that the measurements or observations are censored, and hence the value of a measurement or observation could be only partially known. This paper focuses on distributed censored regression over networks and develops a diffusion-based algorithm for the censored regression. The proposed algorithm first adopts an adaptive bias-corrected estimator based on a probit regression model to reduce the adverse effect of censoring on estimation results, and afterwards carries out the least squares procedure to find the estimate of the parameter of interest in a collaborative manner between every node and its neighbors. The theoretical study of convergence in the mean and mean-square sense reveals that the proposed algorithm is asymptotically unbiased and stable under some conditions. Moreover, simulation results show the effectiveness of the proposed algorithm.

Beschreibung: Computational load remains a major concern when processing signals by means of sliding transforms. In this paper, we present an efficient algorithm for the fast computation of one-dimensional and two-dimensional sliding discrete Tchebichef moments. To do so, we first establish the relationships that exist between the Tchebichef moments of two neighboring windows taking advantage of Tchebichef polynomials’ properties. We then propose an original way to fast compute the moments of one window by utilizing the moment values of its previous window. We further theoretically establish the complexity of our fast algorithm and illustrate its interest within the framework of digital forensics and more precisely the detection of duplicated regions in an audio signal or an image. Our algorithm is used to extract local features of such a signal tampering. Experimental results show that its complexity is independent of the window size, validating the theory. They also exhibit that our algorithm is suitable to digital forensics and beyond to any applications based on sliding Tchebichef moments.

Beschreibung: In this paper, we describe a model for maximum likelihood estimation (MLE) of the relative abundances of different conformations of a protein in a heterogeneous mixture from small angle X-ray scattering (SAXS) intensities. To consider cases where the solution includes intermediate or unknown conformations, we develop a subset selection method based on k-means clustering and the Cramér-Rao bound on the mixture coefficient estimation error to find a sparse basis set that represents the space spanned by the measured SAXS intensities of the known conformations of a protein. Then, using the selected basis set and the assumptions on the model for the intensity measurements, we show that the MLE model can be expressed as a constrained convex optimization problem. Employing the adenylate kinase (ADK) protein and its known conformations as an example, and using Monte Carlo simulations, we demonstrate the performance of the proposed estimation scheme. Here, although we use 45 crystallographically determined experimental structures and we could generate many more using, for instance, molecular dynamics calculations, the clustering technique indicates that the data cannot support the determination of relative abundances for more than 5 conformations. The estimation of this maximum number of conformations is intrinsic to the methodology we have used here.

Beschreibung: Tensor factorization has proven useful in a wide range of applications, from sensor array processing to communications, speech and audio signal processing, and machine learning. With few recent exceptions, all tensor factorization algorithms were originally developed for centralized, in-memory computation on a single machine; and the few that break away from this mold do not easily incorporate practically important constraints, such as non-negativity. A new constrained tensor factorization framework is proposed in this paper, building upon the Alternating Direction Method of Multipliers (ADMoM). It is shown that this simplifies computations, bypassing the need to solve constrained optimization problems in each iteration; and it naturally leads to distributed algorithms suitable for parallel implementation. This opens the door for many emerging big data-enabled applications. The methodology is exemplified using non-negativity as a baseline constraint, but the proposed framework can incorporate many other types of constraints. Numerical experiments are encouraging, indicating that ADMoM-based non-negative tensor factorization (NTF) has high potential as an alternative to state-of-the-art approaches.

Beschreibung: A method for authorship attribution based on function word adjacency networks (WANs) is introduced. Function words are parts of speech that express grammatical relationships between other words but do not carry lexical meaning on their own. In the WANs in this paper, nodes are function words and directed edges from a source function word to a target function word stand in for the likelihood of finding the latter in the ordered vicinity of the former. WANs of different authors can be interpreted as transition probabilities of a Markov chain and are therefore compared in terms of their relative entropies. Optimal selection of WAN parameters is studied and attribution accuracy is benchmarked across a diverse pool of authors and varying text lengths. This analysis shows that, since function words are independent of content, their use tends to be specific to an author and that the relational data captured by function WANs is a good summary of stylometric fingerprints. Attribution accuracy is observed to exceed the one achieved by methods that rely on word frequencies alone. Further combining WANs with methods that rely on word frequencies, results in larger attribution accuracy, indicating that both sources of information encode different aspects of authorial styles.

Beschreibung: Greed is good. However, the tighter you squeeze, the less you have. In this paper, a less greedy algorithm for sparse signal reconstruction in compressive sensing, named orthogonal matching pursuit with thresholding is studied. Using the global 2-coherence, which provides a “bridge” between the well known mutual coherence and the restricted isometry constant, the performance of orthogonal matching pursuit with thresholding is analyzed and more general results for sparse signal reconstruction are obtained. It is also shown that given the same assumption on the coherence index and the restricted isometry constant as required for orthogonal matching pursuit, the thresholding variation gives exactly the same reconstruction performance with significantly less complexity.

Beschreibung: In multiobject inference, the multiobject probability density captures the uncertainty in the number and the states of the objects as well as the statistical dependence between the objects. Exact computation of the multiobject density is generally intractable and tractable implementations usually require statistical independence assumptions between objects. In this paper we propose a tractable multiobject density approximation that can capture statistical dependence between objects. In particular, we derive a tractable Generalized Labeled Multi-Bernoulli (GLMB) density that matches the cardinality distribution and the first moment of the labeled multiobject distribution of interest. It is also shown that the proposed approximation minimizes the Kullback–Leibler divergence over a special tractable class of GLMB densities. Based on the proposed GLMB approximation we further demonstrate a tractable multiobject tracking algorithm for generic measurement models. Simulation results for a multiobject Track-Before-Detect example using radar measurements in low signal-to-noise ratio (SNR) scenarios verify the applicability of the proposed approach.

Beschreibung: With bandwidths on the order of a gigahertz in emerging wireless systems, high-resolution analog-to-digital convertors (ADCs) become a power consumption bottleneck. One solution is to employ low resolution one-bit ADCs. In this paper, we analyze the flat fading multiple-input multiple-output (MIMO) channel with one-bit ADCs. Channel state information is assumed to be known at both the transmitter and receiver. For the multiple-input single-output channel, we derive the exact channel capacity. For the single-input multiple-output and MIMO channel, the capacity at infinite signal-to-noise ratio (SNR) is found. We also derive upper bound at finite SNR, which is tight when the channel has full row rank. In addition, we propose an efficient method to design the input symbols to approach the capacity achieving solution. We incorporate millimeter wave channel characteristics and find the bounds on the infinite SNR capacity. The results show how the number of paths and number of receive antennas impact the capacity.

Beschreibung: Based on the biorthogonal analysis approach, a multiwindow real-valued discrete Gabor transform (M-RDGT) for periodic sequences is presented to efficiently analyze the dynamic time-frequency content of a signal containing components with multiple and/or time-varying frequencies. The M-RDGT offers a computationally efficient implementation as well as a real-valued formulation of the multiwindow complex-valued discrete Gabor transform (M-CDGT). The completeness condition of the M-RDGT is proved to be equivalent to its biorthogonality constraint between analysis windows and synthesis windows. The M-RDGT can utilize the fast discrete Hartley transform algorithms for fast computation and has a simple relationship with the M-CDGT such that its coefficients can be directly computed from the M-RDGT coefficients. Therefore, the M-RDGT offers an efficient method to compute the M-CDGT. Since the analyzed sequence, analysis and synthesis windows in the existing M-CDGT must have an equal period, if the period of a sequence is very long, solving its windows requires a huge amount of computation and memory and could lead to numerical instability. To overcome this problem, a modified M-RDGT for long-periodic (or even infinite) sequences is presented and its corresponding biorthogonality constraint between analysis windows and synthesis windows is modified, in which the period of the analysis and synthesis windows is independent of the period of a analyzed sequence so that one can apply short windows to process any long-periodic (or even in finite) sequence. Finally, the multirate-based parallel implementation of the M-RDGT is presented, which has shown to be effective and fast for time-frequency analysis.

Beschreibung: In this paper, we present a Bayesian approach for spectral unmixing of multispectral Lidar (MSL) data associated with surface reflection from targeted surfaces composed of several known materials. The problem addressed is the estimation of the positions and area distribution of each material. In the Bayesian framework, appropriate prior distributions are assigned to the unknown model parameters and a Markov chain Monte Carlo method is used to sample the resulting posterior distribution. The performance of the proposed algorithm is evaluated using synthetic MSL signals, for which single and multi-layered models are derived. To evaluate the expected estimation performance associated with MSL signal analysis, a Cramer-Rao lower bound associated with model considered is also derived, and compared with the experimental data. Both the theoretical lower bound and the experimental analysis will be of primary assistance in future instrument design.

Beschreibung: This paper is concerned with Gaussian approximations to the posterior probability density function (PDF) in the update step of Bayesian filtering with nonlinear measurements. In this setting, sigma-point approximations to the Kalman filter (KF) recursion are widely used due to their ease of implementation and relatively good performance. In the update step, these sigma-point KFs are equivalent to linearizing the nonlinear measurement function by statistical linear regression (SLR) with respect to the prior PDF. In this paper, we argue that the measurement function should be linearized using SLR with respect to the posterior rather than the prior to take into account the information provided by the measurement. The resulting filter is referred to as the posterior linearization filter (PLF). In practice, the exact PLF update is intractable but can be approximated by the iterated PLF (IPLF), which carries out iterated SLRs with respect to the best available approximation to the posterior. The IPLF can be seen as an approximate recursive Kullback-Leibler divergence minimization procedure. We demonstrate the high performance of the IPLF in relation to other Gaussian filters in two numerical examples.

Beschreibung: Optimal queueing control of multihop networks remains a challenging problem even in the simplest scenarios. In this paper, we consider a two-hop half-duplex relaying system with random channel connectivity. The relay is equipped with a finite buffer. We focus on stochastic link selection and transmission rate control to maximize the average system throughput subject to a half-duplex constraint. We formulate this stochastic optimization problem as an infinite horizon average cost Markov decision process (MDP), which is well known to be a difficult problem. By using sample-path analysis and exploiting the specific problem structure, we first obtain an equivalent Bellman equation with reduced state and action spaces. By using relative value iteration algorithm, we analyze the properties of the value function of the MDP. Then, we show that the optimal policy has a threshold-based structure by characterizing the supermodularity in the optimal control. Based on the threshold-based structure and Markov chain theory, we further simplify the original complex stochastic optimization problem to a static optimization problem over a small discrete feasible set and propose a low-complexity algorithm to solve the simplified static optimization problem by making use of its special structure. Furthermore, we obtain the closed-form optimal threshold for the symmetric case. The analytical results obtained in this paper also provide design insights for two-hop relaying systems with multiple relays equipped with finite relay buffers.

Beschreibung: This paper studies noise enhanced (NE) estimators, which are constructed from an original estimator by artificially adding noise to the observation and computing the expected estimator output. By this expectation operation, we take into account the neighbourhood of an observation and the resulting NE estimator often has a smaller Bayes risk than the original one. We derive some general properties of this estimator and also present a method to obtain a suitable approximation of the optimal NE estimator which can be computed numerically by solving a constrained optimization problem. Finally, we study two examples to show the Bayes risk improvement that we can obtain from the NE estimator and we compare it to the stochastic resonance estimator.

Beschreibung: Previous studies have confirmed the adverse impact of fading correlation on the mutual information (MI) of two-dimensional (2D) multiple-input multiple-output (MIMO) systems. More recently, the trend is to enhance the system performance by exploiting the channels degrees of freedom in the elevation, which necessitates the derivation and characterization of three-dimensional (3D) channels in the presence of spatial correlation. In this paper, an exact closed-form expression for the Spatial Correlation Function (SCF) is derived for 3D MIMO channels. The proposed method resorts to the spherical harmonic expansion (SHE) of plane waves and the trigonometric expansion of Legendre and associated Legendre polynomials. The resulting expression depends on the underlying arbitrary angular distributions and antenna patterns through the Fourier Series (FS) coefficients of power azimuth and elevation spectrums. The novelty of the proposed method lies in the SCF being valid for any 3D propagation environment. The developed SCF determines the covariance matrices at the transmitter and the receiver that form the Kronecker channel model. In order to quantify the effects of correlation on system performance, the information-theoretic deterministic equivalents of the MI for the Kronecker model are utilized in both mono-user and multi-user cases. Numerical results validate the proposed analytical expressions and elucidate the dependence of the system performance on azimuth and elevation angular spreads and antenna patterns. Some useful insights into the behavior of MI as a function of downtilt angles are provided. The derived model will help evaluate the performance of correlated 3D MIMO channels in the future.

Beschreibung: We study the problem of binary sequential hypothesis testing using multiple sensors with associated observation costs. An off-line randomized sensor selection strategy, in which a sensor is chosen at every time step with a given probability, is considered. The objective of this work is to find a sequential detection rule and a sensor selection probability vector such that the expected total observation cost is minimized subject to constraints on reliability and sensor usage. First, the sequential probability ratio test is shown to be the optimal sequential detection rule in this framework as well. Efficient algorithms for obtaining the optimal sensor selection probability vector are then derived. In particular, a special class of problems in which the algorithm has complexity that is linear in the number of sensors is identified. An upper bound for the average sensor usage to estimate the error incurred due to Wald’s approximations is also presented. This bound can be used to set a safety margin for guaranteed satisfaction of the constraints on the sensor usage.

Beschreibung: In this paper, we consider the problem of distributed inference in tree based networks. In the framework considered in this paper, distributed nodes make a 1-bit local decision regarding a phenomenon before sending it to the fusion center (FC) via intermediate nodes. We propose the use of coding theory based techniques to solve this distributed inference problem in such structures. Data is progressively compressed as it moves towards the FC. The FC makes the global inference after receiving data from intermediate nodes. Data fusion at nodes as well as at the FC is implemented via error correcting codes. In this context, we analyze the performance for a given code matrix and also design the optimal code matrices at every level of the tree. We address the problems of distributed classification and distributed estimation separately and develop schemes to perform these tasks in tree networks. The proposed schemes are of practical significance due to their simple structure. We study the asymptotic inference performance of our schemes for two different classes of tree networks: fixed height tree networks, and fixed degree tree networks. We derive the sufficient conditions under which the proposed schemes are asymptotically optimal.

Beschreibung: This paper studies the 2D localization problem of a sensor network given anchor node positions in a common global coordinate frame and relative position measurements in local coordinate frames between node pairs. It is assumed that the local coordinate frames of different sensors have different orientations and the orientation difference with respect to the global coordinate frame are not known. In terms of graph connectivity, a necessary and sufficient condition is obtained for self-localizability that leads to a fully distributed localization algorithm. Moreover, a distributed verification algorithm is developed to check the graph connectivity condition, which can terminate successfully when the sensor network is self-localizable. Finally, a fully distributed, linear, and iterative algorithm based on the complex-valued Laplacian associated with the sensor network is proposed, which converges globally and gives the correct localization result.

Beschreibung: In this paper, we propose a novel framework for decentralized, online learning by many learners. At each moment of time, an instance characterized by a certain context may arrive to each learner; based on the context, the learner can select one of its own actions (which gives a reward and provides information) or request assistance from another learner. In the latter case, the requester pays a cost and receives the reward but the provider learns the information. In our framework, learners are modeled as cooperative contextual bandits. Each learner seeks to maximize the expected reward from its arrivals, which involves trading off the reward received from its own actions, the information learned from its own actions, the reward received from the actions requested of others and the cost paid for these actions—taking into account what it has learned about the value of assistance from each other learner. We develop distributed online learning algorithms and provide analytic bounds to compare the efficiency of these with algorithms with the complete knowledge (oracle) benchmark (in which the expected reward of every action in every context is known by every learner). Our estimates show that regret—the loss incurred by the algorithm—is sublinear in time. Our theoretical framework can be used in many practical applications including Big Data mining, event detection in surveillance sensor networks and distributed online recommendation systems.

Beschreibung: A sensor network is considered where at each sensor a sequence of random variables is observed. At each time step, a processed version of the observations is transmitted from the sensors to a common node called the fusion center. At some unknown point in time the distribution of observations at an unknown subset of the sensor nodes changes. The objective is to detect the change in distribution as quickly as possible, subject to constraints on the false alarm rate, the cost of observations taken at each sensor, and the cost of communication between the sensors and the fusion center. Minimax formulations are proposed for the above problem and distributed algorithms are proposed in which on-off observation control and censoring is used at each sensor to meet the constraints on data. It is shown that the proposed algorithms are asymptotically optimal for the proposed formulations, as the false alarm rate goes to zero. The asymptotic optimality of the proposed algorithms implies that an arbitrary but fixed fraction of data can be skipped without any loss in asymptotic performance as compared to the scheme where all the observations are used for decision making. It is also shown, via numerical studies, that the proposed algorithms perform significantly better than those based on fractional sampling, in which the classical algorithms from the literature are used and the constraint on the cost of observations is met by skipping a fixed fraction of observations either deterministically or randomly, independent of the observation process.

Beschreibung: In this paper, we propose a new class of techniques to identify periodicities in data. We target the period estimation directly rather than inferring the period from the signal’s spectrum. By doing so, we obtain several advantages over the traditional spectrum estimation techniques such as DFT and MUSIC. Apart from estimating the unknown period of a signal, we search for finer periodic structure within the given signal. For instance, it might be possible that the given periodic signal was actually a sum of signals with much smaller periods. For example, adding signals with periods 3, 7, and 11 can give rise to a period 231 signal. We propose methods to identify these “hidden periods” 3, 7, and 11. We first propose a new family of square matrices called Nested Periodic Matrices (NPMs), having several useful properties in the context of periodicity. These include the DFT, Walsh–Hadamard, and Ramanujan periodicity transform matrices as examples. Based on these matrices, we develop high dimensional dictionary representations for periodic signals. Various optimization problems can be formulated to identify the periods of signals from such representations. We propose an approach based on finding the least $l_{2}$ norm solution to an under-determined linear system. Alternatively, the period identification problem can also be formulated as a sparse vector recovery problem and we show that by a slight modification to the usual $l_{1}$ norm minimization techniques, we can incorporate a number of new and computationally simple dictionaries.

Beschreibung: Cognitive radio (CR) technology is promising for next generation wireless networks. It allows unlicensed secondary users to use the licensed spectrum bands as long as they do not cause unacceptable interference to the primary users who own those bands. To efficiently allocate resources in CR networks, stable resource allocation based on graph theory is investigated, which takes all users' preferences into account. In this paper, we focus on improving robustness of the stable matching based resource allocation. A truncated scheme generating almost stable matchings is first investigated. Based on the properties of the truncated scheme, two types of edge-cutting algorithms, called direct edge-cutting (DEC) and Gale-Shapley based edge-cutting (GSEC), are developed to improve resource allocation robustness to the channel state information variation. To mitigate the problem that certain secondary users may not be able to find suitable resources after edge-cutting, multi-stage (MS) algorithms are then proposed. Numerical results show that the proposed algorithms are robust to the channel state information variation.

Beschreibung: This paper considers the waveform design problem for multiple-input multiple-output (MIMO) radars in order to improve the detection performance of the systems. We assume that target echoes are embedded in (signal-dependent) clutter as well as (colored) interference. Considering the optimal (Neyman-Pearson) detector, obtaining waveforms which maximize the detection probability for a fixed value of the probability of false alarm is intractable. Therefore, we employ relative entropy associated with the detection problem as the figure of merit for the waveform design. We devise an iterative method based on minorization-maximization (MM) technique to tackle the nonconvex design problem. This method also includes a novel trick for replacing a nonconvex constraint set (associated with an equivalent form of the design problem) with a convex one iteratively. The proposed method increases the design metric monotonically and is guaranteed to converge. We extend the devised method for using in design with peak-to-average power ratio (PAR) and similarity constraints. The method can be applied to both statistical and colocated MIMO radars. Several numerical examples are included to demonstrate the effectiveness of the proposed method.

Beschreibung: We obtain the exact maximum Degrees of Freedom (DoF) region achieved by linear transceivers without symbol extensions of the 2 $,times,$ 2 $,times,$ 2 multiple-input multiple-output (MIMO) interference network, which is comprised of two sources, two relays and two destinations, each with arbitrary number of antennas. We prove that the maximum achievable DoF region for the networks under some antenna configurations coincide with the cut-set bound of the networks, while there is only one DoF gap from the bound for the networks under other configurations, which can not be bridged by linear transceivers. The basic idea of the proof is to construct a two-tier transceiver, where the first tier decomposes the general networks to several basic networks with special configurations, and the second tier achieves the maximal DoF tuples for these basic networks. A mechanism for constructing the second tier transceiver is proposed, which is referred to as channel scaling assisted interference elimination. Combined with interference avoidance at sources and interference cancelation at destinations depending on the antenna configurations, interference-free transmission can be ensured.

Beschreibung: This paper presents multi-frequency operation for increasing the number of resolvable sources in high-resolution direction-of-arrival (DOA) estimation using co-prime arrays. A single-frequency operation requires complicated and involved matrix completion to utilize the full extent of the degrees of freedom (DOFs) offered by the co-prime configuration. This processing complexity is attributed to the missing elements in the corresponding difference coarray. Alternate single-frequency schemes avoid such complexity by utilizing only the filled part of the coarray and, thus, cannot exploit all of the DOFs for DOA estimation. We utilize multiple frequencies to fill the missing coarray elements, thereby enabling the co-prime array to effectively utilize all of the offered DOFs. The sources are assumed to have a sufficient bandwidth to cover all the required operational frequencies. We consider both cases of sources with proportional and nonproportional power spectra at the employed frequencies. The former permits the use of multi-frequency measurements at the co-prime array to construct a virtual covariance matrix corresponding to a filled uniformly spaced coarray at a single frequency. This virtual covariance matrix can be employed for DOA estimation. The nonproportionality of the source spectra casts a more challenging situation, as it is not amenable to producing the same effect as that of an equivalent single-frequency filled coarray. Performance evaluation of the multi-frequency approach based on computer simulations is provided under both cases of proportional and nonproportional source spectra.

Beschreibung: Multicarrier waveforms bring several major advantages over single carrier waveforms in radar systems: frequency diversity, waveform diversity, short time on target and the possibility to optimize the transmitted waveforms, to mention a few. Interesting waveform designs utilizing diversity have been proposed in the literature already. In this paper, we develop a generalized model that can accommodate a wide variety of design options, both existing and novel ones, in an easy and intuitive way. The developed matrix equations for transmitter and receiver allow for implementing different waveforms simply by filling in the elements to corresponding matrices accordingly. Moreover, intuitive agile generation of waveforms in simulation environments and in practice is facilitated. Waveform optimization examples are provided using the derived model. A Mutual Information based criterion is employed to formulate the optimization problems which are solved analytically. Novel multicarrier spread spectrum waveforms are proposed and generated using the derived model. The radar performance of one of these waveforms is investigated through simulations. It is demonstrated that it can outperform well-known existing multicarrier waveforms. It is also shown that such waveform can lower the peak-to-average-power ratio due to the spreading operation, which is a benefit for the front end designs of the transmitter and receiver.

Beschreibung: In this paper, the secrecy performance of finite-sized cooperative cyclic prefixed single carrier systems with multiple eavesdroppers and unreliable wireless backhaul connections across multiple transmitters is investigated. For nonidentical frequency-selective fading channels between the relay and destination nodes, secrecy performance metrics including the secrecy outage probability, ergodic secrecy rate, and probability of nonzero achievable secrecy rate are derived. Furthermore, the existence of performance limits on the secrecy outage probability and probability of non-zero achievable secrecy rate are verified for various backhaul scenarios. These limits are found to be exclusively determined by the backhaul reliability. For imperfect backhaul connections, it is found that the diversity gain promised by cooperative cyclic prefixed single-carrier systems cannot be achieved in the conventional asymptotic high signal-to-noise ratio region. Link-level simulations are conducted to verify the derived impact of backhaul reliability on the secrecy performance.

Beschreibung: Recently, several high-resolution parameter estimation algorithms have been developed to exploit the structure of strictly second-order (SO) non-circular (NC) signals. They achieve a higher estimation accuracy and can resolve up to twice as many signal sources compared to the traditional methods for arbitrary signals. As a benchmark for these NC methods, we derive the closed-form deterministic $R$ -D NC Cramér-Rao bound (NC CRB) for the multi-dimensional parameter estimation of strictly non-circular (rectilinear) signal sources in this paper. Assuming a separable centro-symmetric $R$ -D array, we show that in some special cases, the deterministic $R$ -D NC CRB reduces to the existing deterministic $R$ -D CRB for arbitrary signals. This suggests that no gain from strictly non-circular sources (NC gain) can be achieved under the deterministic data assumption in these cases. For more general scenarios, finding an analytical expression of the NC gain for an arbitrary number of sources is very challenging. Thus, in this paper, we simplify the derived NC CRB and the existing CRB for the special case of two closely-spaced strictly non-circular sources captured by a uniform linear array (ULA). Subsequently, we use these simplified CRB expressions to analytically compute the maximum achievable asymptotic NC gain for the considered two source case. The resulting expression only depends on the various physical parameters and we find the conditions that provide the largest NC gain. Our analysis is supported by extensive simulation results.

Beschreibung: As communication systems scale up in bandwidth, the limited resolution in high-speed analog-to-digital converters (ADCs) is a key challenge in realizing low-cost “mostly digital” transceiver architectures. This motivates a systematic effort to understand the limits of such architectures under the severe quantization constraints imposed by the use of low-precision ADCs. In particular, we investigate a canonical problem of blind carrier phase and frequency synchronization with coarse phase quantization in this paper. We develop a Bayesian approach to blind phase estimation, jointly modeling the unknown data, unknown phase and the quantization nonlinearity. We highlight the crucial role of dither, implemented via a mixed signal architecture with a digitally controlled phase shift prior to the ADC. We show the efficacy of random dither, and then improve upon its performance with a simple feedback control policy that is close to optimal in terms of rapidly reducing the mean squared error of phase estimation. This initial blind phase acquisition stage is followed by feedback-based phase/frequency tracking using an Extended Kalman Filter. Performance evaluations for a QPSK system show that excellent bit error rate (BER) performance, close to that of an unquantized system, is achieved by the use of 8 phase bins (implementable using 4 one-bit ADCs operating on linear combinations of in-phase and quadrature components).

Beschreibung: State estimation is studied for a special class of flag Hidden Markov Models (HMMs), which comprise 1) an arbitrary finite-state underlying Markov chain and 2) a structured observation process wherein a subset of states emit distinct flags with some probability while other states are unmeasured. For flag HMMs, an explicit computation of the probability of error for the maximum-likelihood filter and smoother is developed. Also, the form of the optimal filter is further characterized in terms of the time since the last flag, and this result is used to further simplify the error-probability computation. Some preliminary graph-theoretic insights into the error probability and its computation are discussed. Finally, these algebraic and structural results are leveraged to address sensor placement in two examples, including one on activity-monitoring in a home environment that is drawn from field data. These examples indicate that low error-probability filtering and smoothing can be achieved with relatively few sensors.

Beschreibung: In this paper, we consider the problem of multi-parameter estimation in the presence of compound Gaussian clutter for cognitive radar by the variational Bayesian method. The advantage of variational Bayesian is that the estimation of multi-variate parameters is decomposed to problems of estimation of univariate parameters by variational approximation, thus enabling analytically tractable approximate posterior densities in complex statistical models consisting of observed data, unknown parameters, and hidden variables. We derive the asymptotic Bayesian Cramer–Rao bounds and demonstrate by numerical simulations that the proposed approach leads to improved estimation accuracy than the expectation maximization method and the exact Bayesian method in the case of non-Gaussian nonlinear signal models and small data sample size.

Beschreibung: Spatiotemporal signal reconstruction from samples randomly gathered in a multidimensional space with uncertainty is a crucial problem for a variety of applications. Such a problem generalizes the reconstruction of a deterministic signal and that of a stationary random process in one dimension, which was first addressed by Whittaker, Kotelnikov, and Shannon. In this work we analyze multidimensional random sampling with uncertainties jointly accounting for signal properties (signal spectrum and spatial correlation) and for sampling properties (inhomogeneous sample spatial distribution, sample availability, and non-ideal knowledge of sample positions). The reconstructed signal spectrum and the signal reconstruction accuracy are derived as a function of signal and sampling properties. It is shown that some of these properties expand the signal spectrum while others modify the spectrum without expansion. The signal reconstruction accuracy is first determined in a general case and then specialized for cases of practical interests. The optimal interpolator function is derived and asymptotic results are obtained to show the impact of sampling non-idealities. The analysis is corroborated by verifying that previously known results can be obtained as special cases of the general one and by means of a case study accounting for various settings of signal and sample properties.

Beschreibung: We study strategies for enhanced secrecy using cooperative jamming in secure communication systems with limited rate feedback. A Gaussian multiple-input multiple-output (MIMO) wiretap channel with a jamming helper is considered. The transmitter and helper both require channel state information (CSI), which is quantized at the receiver and fed back through two sum-rate-limited feedback channels. The quantization errors result in reduced beamforming gain from the transmitter, as well as interference leakage from the helper. First, under the assumption that the eavesdropper's CSI is completely unknown, we derive a lower bound on the average main channel rate and find the feedback bit allocation that maximizes the jamming power under a constraint on the bound. For the case where statistical CSI for the eavesdropper's channel is available, we derive a lower bound on the average secrecy rate, and we optimize the bound to find a suitable bit allocation and the transmit powers allocated to the transmitter and helper. For the case where the transmitter and helper have the same number of antennas, we obtain a closed-form solution for the optimal bit allocation. Simulations verify the theoretical analysis and demonstrate the significant performance gain that results with intelligent feedback bit allocation and power control.

Beschreibung: As a good way to represent target backscatter measured by high-frequency synthetic aperture radar (SAR) systems, the attributed scattering center (ASC) model is able to provide concise and physically relevant features of a complex target and has played an important role in model-based automatic target recognition (ATR). However, most existing ASC feature extraction methods suffer from imprecise image segmentation or high computational cost, which greatly encumber their practical applications. To tackle this problem, we present a novel ASC feature extraction algorithm for SAR targets based on Lévy random fields in a nonparametric Bayesian framework. Specifically, Lévy random fields, yielding a natural sparse representation of the unknown ASC model, are introduced to construct prior distributions, which lead to the specification of a joint prior distribution for the number of ASCs and the ASC associated parameters. Meanwhile, the problem may be formulated as a sparse representation problem, with regularization induced through the Lévy random field prior. We also develop a reversible jump Markov chain Monte Carlo (RJ-MCMC) method to enable relatively fast posterior inference. Experimental results confirm the effectiveness and efficiency of the proposed algorithm.

Beschreibung: A Bayesian framework is proposed to define flexible coupling models for joint tensor decompositions of multiple datasets. Under this framework, a natural formulation of the data fusion problem is to cast it in terms of a joint maximum a posteriori (MAP) estimator. Data-driven scenarios of joint posterior distributions are provided, including general Gaussian priors and non Gaussian coupling priors. We present and discuss implementation issues of algorithms used to obtain the joint MAP estimator. We also show how this framework can be adapted to tackle the problem of joint decompositions of large datasets. In the case of a conditional Gaussian coupling with a linear transformation, we give theoretical bounds on the data fusion performance using the Bayesian Cramér–Rao bound. Simulations are reported for hybrid coupling models ranging from simple additive Gaussian models to Gamma-type models with positive variables and to the coupling of data sets which are inherently of different size due to different resolution of the measurement devices.

Beschreibung: The objective of generalized sampling expansion (GSE) is the reconstruction of an unknown, continuously defined function $fleft(tright)$ from samples of the responses from $M$ linear time-invariant (LTI) systems that are each sampled using the $1/M$ th Nyquist rate. In this paper, we investigate the GSE for lowpass and bandpass signals with multiple sampling rates in the fractional Fourier transform (FRFT) domain. First, we propose an improvement of Papoulis’ GSE, which has multiple sampling rates in the FRFT domain. Based on the proposed GSE, we derive the periodic nonuniform sampling scheme and the derivative interpolation method by designing different fractional filters and selecting specific sampling rates. In addition, the Papoulis GSE and the previous GSE associated with FRFT are shown to be special instances of our results. Second, we address the problem of the GSE of fractional bandpass signals. A new GSE for fractional bandpass signals with equal sampling rates is derived. We show that the restriction of an even number of channels in the GSE for fractional bandpass signals is unnecessary, and perfect signal reconstruction is possible for any arbitrary number of channels. Further, we develop the GSE for a fractional bandpass signal with multiple sampling rates. Lastly, we discuss the application of the proposed method in the context of single-image super-resolution reconstruction based on GSE. Illustrations and simulations are presented to verify the validity and effectiveness of the proposed results.

Beschreibung: We consider a sensor scheduling problem where the sensors have multiple choices of communication channel to send their local measurements to a remote state estimator for state estimation. Specifically, the sensors can transmit high-precision data packets over an expensive channel or low-precision data packets, which are quantized in several bits, over some cheap channels. The expensive channel, though being able to deliver more accurate data which leads to good estimation quality at the remote estimator, can only be used scarcely due to its high cost (e.g., high energy consumption). On the other hand, the cheap channel, though having a small cost, delivers less accurate data which inevitably deteriorates the remote estimation quality. In this work we propose a new framework in which the sensors switch between the two channels to achieve a better tradeoff among the communication cost, the estimation performance and the computational complexity, where the two-channel case can be easily extended to a multiple-channel case. We propose an opportunistic sensor schedule which reduces the communication cost by randomly switching among the expensive and cheap channels, and in the meantime maintains low computational complexity while introducing data quantization into the estimation problem. We present a minimum mean square error (MMSE) estimator in a closed-form under the proposed opportunistic sensor schedule. We also formulate an optimization problem to search the best opportunistic schedule with a linear quantizer. Furthermore, we show that the MMSE estimator in the limiting case becomes the standard Kalman filter.

Beschreibung: The stability problems of the least mean fourth (LMF) algorithm put a limitation on its tracking capability. The paper investigates the possibility of solving this problem via stabilization of the algorithm. The analysis is done for a Markov plant. It is found that the available stable normalized LMF (NLMF) algorithm has a tracking limitation for high signal-to-noise ratio. The paper presents a new stable NLMF algorithm that is free of this limitation. Mean-square stability of the algorithm is proved. Expressions are derived for the minimum steady-state mean square deviation (MSD) and the corresponding convergence time. The new algorithm outperforms the available stable NLMF algorithm in both the transient and steady states. The new algorithm is also compared with the NLMS algorithm when the adaptation parameter of each algorithm is set to the value that minimizes its steady-state MSD. For large initial MSD, the algorithm outperforms the NLMS algorithm, even for Gaussian noise. For small initial MSD, the algorithm outperforms the NLMS algorithm for sub-Gaussian noise, while the situation is opposite for Gaussian noise. Analytical results are supported by simulations.

Beschreibung: Twisted particle filters are a class of sequential Monte Carlo methods recently introduced by Whiteley and Lee to improve the efficiency of marginal likelihood estimation in state-space models. The purpose of this article is to extend the twisted particle filtering methodology, establish accessible theoretical results which convey its rationale, and provide a demonstration of its practical performance within particle Markov chain Monte Carlo for estimating static model parameters. We derive twisted particle filters that incorporate systematic or multinomial resampling and information from historical particle states, and a transparent proof which identifies the optimal algorithm for marginal likelihood estimation. We demonstrate how to approximate the optimal algorithm for nonlinear state-space models with Gaussian noise and we apply such approximations to two examples: a range and bearing tracking problem and an indoor positioning problem with Bluetooth signal strength measurements. We demonstrate improvements over standard algorithms in terms of variance of marginal likelihood estimates and Markov chain autocorrelation for given CPU time, and improved tracking performance using estimated parameters.

Beschreibung: This paper deals with a novel generalization of classical blind source separation (BSS) in two directions. First, relaxing the constraint that the latent sources must be statistically independent. This generalization is well-known and sometimes termed independent subspace analysis (ISA). Second, jointly analyzing several ISA problems, where the link is due to statistical dependence among corresponding sources in different mixtures. When the data are one-dimensional, i.e., multiple classical BSS problems, this model, known as independent vector analysis (IVA), has already been studied. In this paper, we combine IVA with ISA and term this new model joint independent subspace analysis (JISA). We provide full performance analysis of JISA, including closed-form expressions for minimal mean square error (MSE), Fisher information and Cramér–Rao lower bound, in the separation of Gaussian data. The derived MSE applies also for non-Gaussian data, when only second-order statistics are used. We generalize previously known results on IVA, including its ability to uniquely resolve instantaneous mixtures of real Gaussian stationary data, and having the same arbitrary permutation at all mixtures. Numerical experiments validate our theoretical results and show the gain with respect to two competing approaches that either use a finer block partition or a different norm.

Beschreibung: This paper addresses the design of adaptive subspace matched filter (ASMF) detectors in the presence of a mismatch in the steering vector. These detectors are coined as adaptive in reference to the step of utilizing an estimate of the clutter covariance matrix using training data of signal-free observations. To estimate the clutter covariance matrix, we employ regularized covariance estimators that, by construction, force the eigenvalues of the covariance estimates to be greater than a positive scalar $rho $ . While this feature is likely to increase the bias of the covariance estimate, it presents the advantage of improving its conditioning, thus making the regularization suitable for handling high-dimensional regimes. In this paper, we consider the setting of the regularization parameter and the threshold for ASMF detectors in both Gaussian and compound Gaussian clutters. In order to allow for a proper selection of these parameters, it is essential to analyze the false alarm and detection probabilities. For tractability, such a task is carried out under the asymptotic regime in which the number of observations and their dimensions grow simultaneously large, thereby allowing us to leverage existing results from random matrix theory. Simulation results are provided in order to illustrate the relevance of the proposed design strategy and to compare the performances of the proposed ASMF detectors versus adaptive normalized matched filter (ANMF) detectors under mismatch scenarios.

Beschreibung: A robust minimax test for two composite hypotheses, which are determined by the neighborhoods of two nominal distributions with respect to a set of distances—called $alpha $ —divergence distances, is proposed. Sion's minimax theorem is adopted to characterize the saddle value condition. Least favorable distributions, the robust decision rule and the robust likelihood ratio test are derived. If the nominal probability distributions satisfy a symmetry condition, the design procedure is shown to be simplified considerably. The parameters controlling the degree of robustness are bounded from above and the bounds are shown to be resulting from a solution of a set of equations. The simulations performed evaluate and exemplify the theoretical derivations.

Beschreibung: This paper considers robust low-rank matrix completion in the presence of outliers. The objective is to recover a low-rank data matrix from a small number of noisy observations. We exploit the bilinear factorization formulation and develop a novel algorithm fully utilizing parallel computing resources. Our main contributions are i) providing two smooth loss functions that promote robustness against two types of outliers, namely, dense outliers drawn from some elliptical distribution and sparse spike-like outliers with small additive Gaussian noise; and ii) an efficient algorithm with provable convergence to a stationary solution based on a parallel update scheme. Numerical results show that the proposed algorithm obtains a better solution with faster convergence speed than the benchmark algorithms in both synthetic and real data scenarios.

Beschreibung: Subspace tracking using low-complexity methods is a common research area in signal processing. While numerical properties of available methods are extensively addressed in literature, there is a paucity of statistical results on limiting behavior of subspace tracking methods. In this contribution, we will study steady-state error of DPM, MALASE, Champagne's PA, Karasalo, and PAST methods. We show that DPM, MALASE, and PAST are approximations of the PA method, while Karasalo's method is equivalent to the PA method in convergence region. A tradeoff between steady-state error of methods and their local convergence rate is demonstrated. A nonstationary signal model is assumed, in which true subspace is slowly and randomly varying. Simulation results show PA and PAST are asymptotically close to the optimum sample covariance matrix (SCM), while this is not true for DPM and MALASE in stationary signal case. In the steady state, these methods can be expressed with a unified approach using stochastic first-order difference equations, whose fixed points are calculated. The results can be used to determine optimal step-size in terms of tolerable total signal subspace projection error. Simulation results confirm the validity of theoretical error calculations.

Beschreibung: In this paper, we propose a strategy that is based on expectation maximization for tracking multiple point targets. The algorithm is similar to probabilistic multi-hypothesis tracking (PMHT) but does not relax the point target model assumptions. According to the point target models, a target can generate at most one measurement, and a measurement is generated by at most one target. With this model assumption, we show that the proposed algorithm can be implemented as iterations of Rauch-Tung-Striebel (RTS) smoothing for state estimation, and the loopy belief propagation method for marginal data association probabilities calculation. Using example illustrations with tracks, we compare the proposed algorithm with PMHT and joint probabilistic data association (JPDA) and show that PMHT and JPDA exhibit coalescence when there are closely moving targets whereas the proposed algorithm does not. Furthermore, extensive simulations c comparing the mean optimal subpattern assignment (MOSPA) performance of the algorithm for different scenarios averaged over several Monte Carlo iterations show that the proposed algorithm performs better than JPDA and PMHT. We also compare it to benchmarking algorithm: $N$ -scan pruning based track-oriented multiple hypothesis tracking (TOMHT). The proposed algorithm shows a good tradeoff between computational complexity and the MOSPA performance.

Beschreibung: We consider the problem of low-rank decomposition of incomplete tensors. Since many real-world data lie on an intrinsically low-dimensional subspace, tensor low-rank decomposition with missing entries has applications in many data analysis problems such as recommender systems and image inpainting. In this paper, we focus on Tucker decomposition which represents an $N$ th-order tensor in terms of $N$ factor matrices and a core tensor via multilinear operations. To exploit the underlying multilinear low-rank structure in high-dimensional datasets, we propose a group-based log-sum penalty functional to place structural sparsity over the core tensor, which leads to a compact representation with smallest core tensor. The proposed method is developed by iteratively minimizing a surrogate function that majorizes the original objective function. This iterative optimization leads to an iteratively reweighted least squares algorithm. In addition, to reduce the computational complexity, an over-relaxed monotone fast iterative shrinkage-thresholding technique is adapted and embedded in the iterative reweighted process. The proposed method is able to determine the model complexity (i.e., multilinear rank) in an automatic way. Simulation results show that the proposed algorithm offers competitive performance compared with other existing algorithms.

Beschreibung: The usual known methods for generating signals with given marginal probability and spectral properties cannot be applied to binary signals widely used in theoretical problems and communications systems. To overcome this difficulty, we first present some structural properties of power spectral densities, enabling the precise definition of the concept of spectral properties. This allows us to introduce a new method valid for symmetric binary random signals. This method uses some specific properties of filters with random impulse responses. Results of computer simulations show clearly the good performance of this method. Some extensions by using random thinning can further improve its performance.

Beschreibung: In this paper, we propose novel fractionally-spaced frequency-domain equalizers for the amplify-and-forward cooperative systems. In the proposed equalization schemes, the sampling rate of the received signal remains at least as high as the Nyquist rate within the digital processing chain of the relay node(s), upon which a true fractionally-spaced equalization becomes feasible at the destination. Based on minimum-mean-square-error (MMSE) criterion, different equalization structures (linear and non-linear) are designed, and approximations for their bit error rate (BER) performance are presented. The BER performance of the proposed schemes are further lower bounded through a matched-filter bound (MFB) analysis which provides insight into system design such as optimum power allocation and relay selection strategy. Our results show that, under certain channel realizations and sampling phase errors (that may occur in the relay and destination terminals), the performance of the conventional symbol-spaced cooperative systems reduces to that of no relay scenario. However, the performance of cooperative systems with the proposed fractionally-spaced equalizers is independent of the samplers' phases, and as a result, full benefit of cooperation is retained.

Beschreibung: This paper computes the distortion power at the receiver side of an FBMC/OQAM-based OFDMA uplink channel under strong frequency selectivity and/or user timing errors. More precisely, it provides a distortion expression that is valid for a wide class of prototype pulses (not necessarily perfect-reconstruction ones) when the number of subcarriers is sufficiently large. This result is a valuable instrument for analyzing how users interfere to one another and to justify, formally, the common choice of placing an empty guard band between adjacent users. Interestingly, the number of out-band subcarriers contaminated by each user only depends on the prototype pulses and not on the channel nor on the equalizer. To conclude, the distortion analysis presented in this paper, together with some simulation results for a realistic scenario, also provide convincing evidence that FBMC/OQAM-based OFDMA is superior to classic circular-prefix OFDMA in the case of asynchronous users.

Beschreibung: The goal of an infection source node (e.g., a rumor or computer virus source) in a network is to spread its infection to as many nodes as possible, while remaining hidden from the network administrator. On the other hand, the network administrator aims to identify the source node based on knowledge of which nodes have been infected. We model the infection spreading and source identification problem as a strategic game, where the infection source and the network administrator are the two players. As the Jordan center estimator is a minimax source estimator that has been shown to be robust in recent works, we assume that the network administrator utilizes a source estimation strategy that can probe any nodes within a given radius of the Jordan center. Given any estimation strategy, we design a best-response infection strategy for the source. Given any infection strategy, we design a best-response estimation strategy for the network administrator. We derive conditions under which a Nash equilibrium of the strategic game exists. Simulations in both synthetic and real-world networks demonstrate that our proposed infection strategy infects more nodes while maintaining the same safety margin between the true source node and the Jordan center source estimator.

Beschreibung: Resampling is a standard step in particle filters and more generally sequential Monte Carlo methods. We present an algorithm, called chopthin, for resampling weighted particles. In contrast to standard resampling methods the algorithm does not produce a set of equally weighted particles; instead it merely enforces an upper bound on the ratio between the weights. Simulation studies show that the chopthin algorithm consistently outperforms standard resampling methods. The algorithms chops up particles with large weight and thins out particles with low weight, hence its name. It implicitly guarantees a lower bound on the effective sample size. The algorithm can be implemented efficiently, making it practically useful. We show that the expected computational effort is linear in the number of particles. Implementations for C++, R (on CRAN), Python and Matlab are available.

Beschreibung: In many application scenarios, the signals impinging on the array of sensors comprise the noncoherent (uncorrelated and/or partially correlated) signals and the coherent signals with several groups due to multipath propagation. In this paper, we consider the problem of estimating the number of noncoherent narrowband signals and that of coherent narrowband signals with multiple groups impinging on a planar sensor array composed of two parallel uniform linear arrays (ULAs), and an oblique projection based enumerator for the mixed signals (OPEMS) is proposed by utilizing the QR decomposition based ratio criterion (QRRC) for rank determination of a matrix. In the OPEMS, the number of noncoherent signals and that of coherent signals in each group are estimated separately, where only the elevation angles of noncoherent signals are estimated to isolate the coherent signals from the noncoherent ones, and the computationally intensive and time-consuming eigendecomposition procedure is avoided. The consistency of the proposed OPEMS is analyzed, and its effectiveness is verified through numerical examples.

Beschreibung: This paper considers the discrete sum rate maximization (DSRM) problem for beamformer optimization in multi-input single-output interference broadcast channels. In this problem, the achievable rates of the receivers are restricted to be taken from a set of finite discrete rate values, and such constraints arise from practical limitations with the modulation and coding schemes. Many existing studies consider sum rate maximization without the discrete rate constraints, and that may result in performance loss. In this paper, the DSRM problem is tackled via a convex approximation approach. Due to the discrete rate constraints, DSRM is a mixed-integer program. The idea of the proposed approach is to reformulate DSRM as a continuous, but still nonconvex, optimization problem. Then, appropriate convex approximations are applied. The advantage of the proposed approach is that the resulting approximate problems can be easily decomposed from a first-order optimization viewpoint. Utilizing this special feature, low-complexity and decentralized algorithms based on projected gradient are derived. Numerical results are used to show the efficiencies of the proposed algorithms in a multicell coordinated beamforming scenario. Also, this paper provides a proof for the convergence guarantee of one decentralized optimization strategy, namely, inexact maximum block improvement.

Beschreibung: This paper revisits grid based recursive approximate filtering of general Markov processes in discrete time, partially observed in conditionally Gaussian noise. The grid based filters considered rely on two types of state quantization, namely, the Markovian type and the marginal type. A set of novel, relaxed sufficient conditions is proposed, ensuring strong and fully characterized pathwise convergence of these filters to the respective MMSE state estimator. In particular, for marginal state quantizations, the notion of conditional regularity of stochastic kernels is introduced which, to the best of the authors' knowledge, constitutes the most relaxed condition under which asymptotic optimality of the respective grid based filters is guaranteed. Further, the convergence results are extended to include filtering of bounded and continuous functionals of the state, as well as recursive approximate state prediction. For both Markovian and marginal quantizations, the whole development of the respective grid-based filters relies more on linear-algebraic techniques and less on measure theoretic arguments, making the presentation considerably shorter and technically simpler.

Beschreibung: This paper addresses the issue of detecting change-points in time series. The proposed model, called the Bernoulli Detector, is presented first in a univariate context. This approach differs from existing counterparts by making only assumptions on the nature of the change-points, and does not depend on hypothesis on the distribution of the data, contrary to the parametric methods. It relies on the combination of a local robust statistical test, based on the computation of ranks and acting on individual time segments, with a global Bayesian framework able to optimize the change-points configurations from multiple local statistics, provided as $p$ -values. The control of the detection of a single change-point is proved even for small samples. The interest of such a generalizable nonparametric approach is shown on simulated data by the good performances attained for Gaussian noise as well as in presence of outliers, without adapting the model. The model is extended to the multivariate case by introducing the probabilities that the change-points affect simultaneously several time series. The method presents then the advantage to detect both unique and shared change-points for each signal. We finally illustrate our algorithm with real datasets from energy monitoring and genomic. Segmentations are compared to state-of-the-art approaches like the group lasso and the BARD algorithm.

Beschreibung: New schemes to recover signals defined in the nodes of a graph are proposed. Our focus is on reconstructing bandlimited graph signals, which are signals that admit a sparse representation in a frequency domain related to the structure of the graph. Most existing formulations focus on estimating an unknown graph signal by observing its value on a subset of nodes. By contrast, in this paper, we study the problem of inducing a known graph signal using as input a graph signal that is nonzero only for a small subset of nodes. The sparse signal is then percolated (interpolated) across the graph using a graph filter. Alternatively, one can interpret graph signals as network states and study graph-signal reconstruction as a network-control problem where the target class of states is represented by bandlimited signals. Three setups are investigated. In the first one, a single simultaneous injection takes place on several nodes in the graph. In the second one, successive value injections take place on a single node. The third one is a generalization where multiple nodes inject multiple signal values. For noiseless settings, conditions under which perfect reconstruction is feasible are given, and the corresponding schemes to recover the desired signal are specified. Scenarios leading to imperfect reconstruction, either due to insufficient or noisy signal value injections, are also analyzed. Moreover, connections with classical interpolation in the time domain are discussed. Specifically, for time-varying signals, where the ideal interpolator after uniform sampling is a (low-pass) filter, our proposed approach and the reconstruction of a sampled signal coincide. Nevertheless, for general graph signals, we show that these two approaches differ. The last part of the paper presents numerical experiments that illustrate the results developed through synthetic and real-world signal reconstruction problems.

Beschreibung: High SNR consistency of model order selection criteria in linear regression models has attracted a lot of attention in the signal processing community recently. It is now known that Exponentially Embedded Family, versions of Minimum Description Length etc. are high SNR consistent. However, a general framework for high SNR consistency in linear regression is still missing. This paper fills this gap by deriving necessary and sufficient conditions (NSCs) for model order selection criteria in both known and unknown noise variance situations to be high SNR consistent. Many popular model order selection criteria are proved to be high SNR consistent using these NSCs. We also provide a convergence rate analysis to discriminate between various high SNR consistent model order selection criteria. A direct application of model order selection techniques to the very important subset selection problem is computationally infeasible. This paper establish the high SNR consistency of an existing t-statistics based index ordering scheme that allows the conversion of a subset selection problem into a model order selection problem. Combining this index ordering with high SNR consistent model order selection criteria leads to a novel subset selection procedure (SSP) that is numerically shown to outperform existing high SNR consistent SSPs.

Beschreibung: In this paper, we study an optimal transmit strategy for multiple-input single-output (MISO) Gaussian channels with joint sum and per-antenna power constraints. We study in detail the interesting case where the sum of the per-antenna power constraints is larger than sum power constraint. A closed-form characterization of an optimal beamforming strategy is derived. It is shown that we can always find an optimal beamforming transmit strategy that allocates the maximal sum power with phases matched to the complex channel coefficients. The main result is a simple recursive algorithm to compute the optimal power allocation. Whenever the optimal power allocation of the corresponding problem with sum power constraint only exceeds per-antenna power constraints, it is optimal to allocate maximal per-antenna power to those antennas to satisfy the per-antenna power constraints. The remaining power is divided amongst the other antennas whose optimal allocation follows from a reduced joint sum and per-antenna power constraints problem of smaller channel coefficient dimension and reduced sum power constraint. Finally, the theoretical results are illustrated by numerical examples.

Beschreibung: First, we study a basic kernel adaptive filtering algorithm based on stochastic restricted-gradient , which is a natural extension of the naive online regularized risk minimization algorithm (NORMA). Our error surface analysis shows that the algorithm has a decorrelation property due to its explicit use of kernel matrix. It turns out that its normalized version projects the current coefficient vector onto the same hyperplane, but with a different metric, as the kernel normalized least mean square (KNLMS) algorithm. This gives us a fundamental insight bridging two classes of kernel adaptive filtering algorithms. Second, we use this insight to derive an efficient forward-backward splitting algorithm. The same metric as used for the normalized algorithm is employed in the forward step, whereas the ordinary Euclidean metric is employed in the backward step, leading to efficient adaptive refinements of the filter dictionary. We show a monotone approximation property of the proposed algorithm with respect to some modified cost function under certain conditions. Numerical examples show the efficacy of the proposed algorithm.