A tutorial review of both linear and quadratic representations is given. The discussed are the short-time Fourier transform wavelet transform. discussion concentrates on Wigner distribution, ambiguity function, smoothed versions various classes time-frequency representations. Examples application these to typical problems encountered in time-varying signal processing provided.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Situation-aware technologies enabled by multitarget tracking will lead to new services and applications in fields such as autonomous driving, indoor localization, robotic networks, crowd counting. In this tutorial paper, we advocate a recently proposed paradigm for scalable that is based on message passing or, more concretely, the loopy sum-product algorithm. This approach has advantages regarding estimation accuracy, computational complexity, implementation flexibility. Most importantly, it...

We consider the application of compressed sensing (CS) to estimation doubly selective channels within pulse-shaping multicarrier systems (which include OFDM as a special case). By exploiting sparsity in delay-Doppler domain, CS-based channel allows for an increase spectral efficiency through reduction number pilot symbols. For combating leakage effects that limit sparsity, we propose sparsity-enhancing basis expansion and method optimizing with or without prior statistical information about...

Distributed particle filter (DPF) algorithms are sequential state estimation that executed by a set of agents. Some or all the agents perform local filtering and interact with other to calculate global estimate. DPF attractive for large-scale, nonlinear, non-Gaussian distributed problems often occur in applications involving agent networks (ANs). In this article, we present survey, classification, comparison various approaches available date. Our emphasis is on decentralized ANs do not...

We propose a method for tracking an unknown number of targets based on measurements provided by multiple sensors. Our achieves low computational complexity and excellent scalability running belief propagation suitably devised factor graph. A redundant formulation data association uncertainty the use "augmented target states" including binary indicators make it possible to exploit statistical independencies drastic reduction complexity. An increase in targets, sensors, or leads additional...

Fusing probabilistic information is a fundamental task in signal and data processing with relevance to many fields of technology science. In this work, we investigate the fusion multiple probability density functions (pdfs) continuous random variable or vector. Although case variables problem pdf frequently arise multisensor processing, statistical inference, machine learning, universally accepted method for does not exist. The diversity approaches, perspectives, solutions related motivates...

We provide a frame-theoretic analysis of oversampled finite impulse response (FIR) and infinite uniform filter banks (FBs). Our is based on new relationship between the FBs polyphase matrices frame operator corresponding to an FB. For given FB, we present parameterization all synthesis providing perfect reconstruction. find necessary sufficient conditions for FB expansion. A procedure design paraunitary from nonparaunitary formulated. show that bounds can be obtained by eigen-analysis...

We consider the estimation of doubly selective wireless channels within pulse-shaping multicarrier systems (which include OFDM as a special case). A new channel technique using recent methodology compressed sensing (CS) is proposed. CS-based exploits channel's delay-Doppler sparsity to reduce number pilots and, hence, increase spectral efficiency. Simulation results demonstrate significant reduction relative least-squares estimation.

It is well known that suboptimal detection schemes for multiple-input multiple-output (MIMO) spatial multiplexing systems (equalization-based as nulling-and-cancelling schemes) are unable to exploit all of the available diversity, and thus, their performance inferior ML detection. Motivated by experimental evidence this primarily caused inability deal with "bad" (i.e., poorly conditioned) channel realizations, we study decision regions bad channels. Based on a simplified model channels, then...

We consider distributed state estimation in a wireless sensor network without fusion center. Each performs global task---based on the past and current measurements of all sensors---using only local processing communications with its neighbors. In this task, joint (all-sensors) likelihood function (JLF) plays central role as it epitomizes sensors. propose method for computing, at each sensor, an approximation JLF by means consensus algorithms. This "likelihood consensus" is applicable if...

We propose a Bayesian method for distributed sequential localization of mobile networks composed both cooperative agents and noncooperative objects. Our provides consistent combination self-localization (CS) tracking (DT). Multiple objects are localized tracked using measurements between agents. For operation low complexity, we combine particle-based belief propagation with consensus or gossip scheme. High accuracy is achieved through probabilistic information transfer the CS DT parts...

We present a simultaneous localization and mapping (SLAM) algorithm that is based on radio signals the association of specular multipath components (MPCs) with geometric features. Especially in indoor scenarios, robust from challenging due to diffuse propagation, unknown MPC-feature association, limited visibility In our approach, reflections at flat surfaces are described terms virtual anchors (VAs) mirror images physical (PAs). The positions these VAs possibly also PAs unknown. develop...

Situation-aware technologies enabled by multitarget tracking algorithms will create new services and applications in emerging fields such as autonomous navigation maritime surveillance. The system models underlying often involve unknown parameters that are potentially time-varying. A manual tuning of model the user is prone to errors can, thus, dramatically reduce target detection performance. We address this challenge proposing a framework "self-tuning" multisensor-multitarget algorithms....

The time-frequency (TF) version of the wavelet transform and "affine" quadratic/bilinear TF representations can be used for a analysis with constant-Q characteristic. paper considers new approach to analysis. A specific warping is applied Cohen's class quadratic representations, which results in related "hyperbolic geometry" thus called hyperbolic (HC). Two prominent previously considered literature, Bertrand P/sub 0/ distribution Altes-Marinovic Q-distribution, are members HC. authors show...

Hitherto communication theory was based on two alternative methods of signal analysis. One is the description as a function time; other Fourier Both are idealizations, first method operates with sharply defined instants time, second infinite wave-trains rigorously frequencies. But our everyday experiences?especially auditory sensations?insist in terms both time and frequency.?

The sigma point (SP) filter, also known as unscented Kalman is an attractive alternative to the extended filter and particle filter. Here, we extend SP nonsequential Bayesian inference corresponding loopy factor graphs. We propose belief propagation (SPBP) a low-complexity approximation of (BP) message passing scheme. SPBP achieves approximate marginalizations posterior distributions (generally) It well suited for decentralized because its low communication requirements. For decentralized,...

Cooperative localization in agent networks based on interagent time-of-flight measurements is closely related to synchronization. To leverage this relation, we propose a Bayesian factor graph framework for cooperative simultaneous and synchronization (CoSLAS). This suited mobile agents time-varying local clock parameters. Building the CoSLAS graph, develop distributed (decentralized) belief propagation algorithm practically important case of an affine model asymmetric time stamping. Our...

We introduce a distributed cooperative framework and method for Bayesian estimation control in decentralized agent networks. Our combines joint of time-varying global local states with information-seeking optimizing the behavior agents. It is suited to nonlinear non-Gaussian problems and, particular, location-aware For estimation, combination belief propagation message passing consensus used. control, negative posterior entropy all maximized via gradient ascent. The layer provides...

Oversampled filter banks (FBs) offer more design freedom and better noise immunity than critically sampled FBs. Due to the increased computational complexity caused by oversampling, oversampled FBs allowing an efficient implementation, such as cosine modulated (CMFBs), are of particular interest. So far, only CMFBs have been considered. In this paper, we introduce with perfect reconstruction (PR). Extending a classification recently proposed Gopinath, consider two types PR. One these allows...

This paper considers pulse-shaping multicarrier (MC) systems that transmit over doubly dispersive fading channels. We provide exact and approximate expressions for the intersymbol intercarrier interference occurring, in such systems. analysis reveals time frequency concentration of receive pulses is paramount importance low interference. prove (nonobvious) existence jointly concentrated pulse pairs by adapting recent mathematical results on Weyl-Heisenberg frames to MC context. Furthermore,...

In bit-interleaved coded modulation (BICM) systems employing maximum-likelihood decoding, a demodulator (demapper) calculates log-likelihood ratio (LLR) for each bit, which is then used as bit metric Viterbi decoding. the MIMO case, computational complexity of LLR calculation tends to be excessively high, even if log-sum approximation used. Thus, there strong demand efficient suboptimum MIMO-BICM demodulation algorithms with near-optimum performance. We propose an that derived by means...