Bayesian Detection Research Articles

Bayesian detection for distributed targets in compound Gaussian sea clutter with lognormal texture

This article investigates the Bayesian detection problem for the distributed targets in the compound Gaussian (CG) sea clutter. The CG sea clutter is formulated as a product of lognormal texture and speckle component with an inverse Wishart distribution covariance matrix (CM). A generalized likelihood ratio test (GLRT) based Bayesian detector, which can operate without training data, is proposed by integrating the speckle CM and estimating the texture using the maximum a posteriori (MAP) criterion. Additionally, three other Bayesian detectors are designed for distributed targets by exploiting the two-step GLRT, the complex-valued Rao, and Wald tests. We first derive the test statistics assuming known texture and speckle CM. Then, by incorporating the MAP-estimated texture components and speckle CM into the test statistics, we present three Bayesian detectors for distributed targets. Finally, simulation experiments validate the detection performance of the proposed Bayesian detectors using both simulated and real sea clutter data.

Bayesian detection with feedback for cooperative spectrum sensing in cognitive UAV networks

AbstractUnmanned aerial vehicles (UAVs) are becoming a popular research topic in applications that do not require human intervention. A variety of applications and devices coexist in the environment where UAVs operate, resulting in a serious spectrum shortage. Therefore, cognitive radio (CR) is a promising solution for opportunistic access to underutilized spectrum bands by the primary user (PU) through cooperative spectrum sensing (CSS) technique. However, the flexible location of UAVs makes CSS inefficient and even difficult to be implemented. In view of this, a cognitive UAV network model consisting of a pair of UAVs which follows a circular flight trajectory to participate in CSS is proposed in a spectrum sensing frame structure. According to the local energy detection, we further propose an optimization problem about the stopping time in a quickest detection paradigm and conduct out Bayesian detection method with feedback to minimize the sensing delay and the false alarm probability by optimizing the stopping time. Moreover, we theoretically derive the optimal threshold pair and prove the optimal stopping time by means of Markov process. At last, a series of numerical simulations are shown to corroborate the proposed Bayesian detection method with feedback, in terms of the false alarm probability, the sensing delay, and achievable throughput. In contrast to the classic Neyman‐Pearson and Bayesian detection methods, the advantage of Bayesian detection method with feedback sensing is presented.

Bayesian detection for distributed target with limited training data

The issue of subspace-based distributed target detection with limited training data is addressed in this study. We use the Bayesian method to tackle the issue by assuming that the covariance matrix follows an inverse Wishart distribution. According to the generalized likelihood ratio test, Rao test, and Wald test, three Bayesian detectors are designed. Real data and simulations both attest to the usefulness of the proposed detectors.

Signal Detection in MIMO Systems With Hardware Imperfections: Message Passing on Neural Networks

We investigate signal detection in multiple-input-multiple-output (MIMO) communication systems with hardware impairments, such as power amplifier nonlinearity and in-phase/quadrature imbalance. To deal with the complex combined effects of hardware imperfections, neural network (NN) techniques, in particular deep neural networks (DNNs), have been studied to directly compensate for the impact of hardware impairments. However, it is difficult to train a DNN with limited pilot signals, hindering its practical application. In this work, we investigate how to achieve efficient Bayesian signal detection in MIMO systems with hardware imperfections. Characterizing combined hardware imperfections often leads to complicated signal models, making Bayesian signal detection challenging. To address this issue, we first train an NN to ‘model’ the MIMO system with hardware imperfections and then perform Bayesian inference based on the trained NN. Modelling the MIMO system with NN enables the design of NN architectures based on the signal flow of the MIMO system, minimizing the number of NN layers and parameters, which is crucial to achieving efficient training with limited pilot signals. We then represent the trained NN with a factor graph, and design an efficient message passing based Bayesian signal detector, leveraging the unitary approximate message passing (UAMP) algorithm. The implementation of a turbo receiver with the proposed Bayesian detector is also investigated. Extensive simulation results demonstrate that the proposed technique delivers remarkably better performance than state-of-the-art methods.

Efficient Bayesian Detection of Faint Curved Edges in Noisy Images

Efficient Bayesian Detection of Faint Curved Edges in Noisy Images

Knowledge-Aided Bayesian Detection of Distributed Target for FDA-MIMO Radar in Gaussian Clutter

Knowledge-Aided Bayesian Detection of Distributed Target for FDA-MIMO Radar in Gaussian Clutter

Bayesian Detection of Bias in Peremptory Challenges Using Historical Strike Data

United States law bars using peremptory strikes during jury selection because of prospective juror race, ethnicity, sex, or membership in certain other cognizable classes. Here, we extend a Bayesian approach for detecting such illegal strike bias by showing how to incorporate historical data on an attorney’s use of peremptory strikes in past cases. In so doing, we use the power prior to adjust the weight of such historical information in the analysis. Using simulations, we show how the choice of the power prior’s discounting parameter influences bias detection (how likely the credible interval for the bias parameter excludes zero), depending on the degree of incompatibility between current and historical trial data. Finally, we extend this approach with a prototype software application that lawyers could use to detect strike bias in real time during jury-selection. We illustrate this application’s use with real historical strike data from a convenience sample of cases from one court.

Detecting Episodic Evolution through Bayesian Inference of Molecular Clock Models.

Molecular evolutionary rate variation is a key aspect of the evolution of many organisms that can be modeled using molecular clock models. For example, fixed local clocks revealed the role of episodic evolution in the emergence of SARS-CoV-2 variants of concern. Like all statistical models, however, the reliability of such inferences is contingent on an assessment of statistical evidence. We present a novel Bayesian phylogenetic approach for detecting episodic evolution. It consists of computing Bayes factors, as the ratio of posterior and prior odds of evolutionary rate increases, effectively quantifying support for the effect size. We conducted an extensive simulation study to illustrate the power of this method and benchmarked it to formal model comparison of a range of molecular clock models using (log) marginal likelihood estimation, and to inference under a random local clock model. Quantifying support for the effect size has higher sensitivity than formal model testing and is straight-forward to compute, because it only needs samples from the posterior and prior distribution. However, formal model testing has the advantage of accommodating a wide range molecular clock models. We also assessed the ability of an automated approach, known as the random local clock, where branches under episodic evolution may be detected without their a priori definition. In an empirical analysis of a data set of SARS-CoV-2 genomes, we find "very strong" evidence for episodic evolution. Our results provide guidelines and practical methods for Bayesian detection of episodic evolution, as well as avenues for further research into this phenomenon.

An Automatic Digital Camouflage Pattern Generation Method based on Texture Structure

This article investigates the problem of scattered burst signal detection based on multiple sensors to obtain overall decisions. In the explosion detection system studied in the article, sensors independently transmit their decisions on measuring explosion information to the data fusion processing terminal, which provides overall decisions based on fusion rules. The researchers focus on the data fusion theory of the distributed parallel detection burst point data fusion system based on the Bayesian rule. This paper has obtained the data fusion rule and sensor decision criteria that make the overall system optimal, and proposed a nonlinear Gauss Seidel mathematical variable algorithm that optimizes the data fusion rule and multi-sensor decision criteria The data fusion problem when detecting burst point signals with two different and three identical types of sensors. The data fusion algorithm proposed in this article is validated and simulated through computer experiments on the detection of three types of sensors. The relevant experimental data show that the performance of a data fusion system based on Bayesian detection is significantly improved compared with the sensor acquisition of burst point information. In the experiment, the risk of Bayesian missing detection of burst point signal coefficient of the data fusion system using three sensors with the same performance is reduced by 32.7%.

Bayesian detection and tracking of odontocetes in 3-D from their echolocation clicks.

Localization and tracking of marine animals can reveal key insights into their behaviors underwater that would otherwise remain unexplored. A promising nonintrusive approach to obtaining location information of marine animals is to process their bioacoustic signals, which are passively recorded using multiple hydrophones. In this paper, a data processing chain that automatically detects and tracks multiple odontocetes (toothed whales) in three dimensions (3-D) from their echolocation clicks recorded with volumetric hydrophone arrays is proposed. First, the time-difference-of-arrival (TDOA) measurements are extracted with a generalized cross-correlation that whitens the received acoustic signals based on the instrument noise statistics. Subsequently, odontocetes are tracked in the TDOA domain using a graph-based multi-target tracking (MTT) method to reject false TDOA measurements and close gaps of missed detections. The resulting TDOA estimates are then used by another graph-based MTT stage that estimates odontocete tracks in 3-D. The tracking capability of the proposed data processing chain is demonstrated on real acoustic data provided by two volumetric hydrophone arrays that recorded echolocation clicks from Cuvier's beaked whales (Ziphius cavirostris). Simulation results show that the presented MTT method using 3-D can outperform an existing approach that relies on manual annotation.

Bayesian quickest detection‐based spectrum sensing for cognitive UAV networks

AbstractWith the gradual popularization of unmanned aerial vehicles (UAVs), spectrum resources are increasingly scarce. At this time, cognitive radio (CR) technology came into being, which can provide available spectrum resources for UAVs. However, different from the conventional CR networks, the UAV's location flexibility significantly reduces the spectrum sensing performance and increases the detection delay. Therefore, we propose a Bayesian quickest detection‐based spectrum sensing for cognitive UAV networks in this paper. To this aim, we establish a multislot spectrum sensing model in a cognitive UAV network to realize cooperative spectrum sensing (CSS) within the single UAV and avoid disadvantages of cooperation among multiple UAVs. On the basis of this, we make use of Bayesian quickest detection to implement multislot spectrum sensing and evaluate its false alarm probability and detection delay. Further, the tradeoff problem between the false alarm and the detection delay is developed and converted into an optimization stopping time problem. Subsequently, the stopping time problem is theoretically proved and solved. Finally, compared to Bayesian detection, numerical simulation results show that the superiority of Bayesian quickest detection with respect to the false alarm probability and the detection delay is evident, which proves the correctness and effectiveness of the proposed tradeoff problem.

Bayesian detection and tracking of odontocetes in 3D from their echolocation clicks

To study behaviors of marine mammals in a nonintrusive manner, their bio-acoustical signals can be recorded by volumetric hydrophone arrays that provide time difference of arrival (TDOA) measurements for localization and tracking. Multi-target tracking (MTT) in 3-D using TDOA measurements from multiple sensors, however, must cope with non-linear measurement models and high-dimensional states. False alarms, missed detections and unknown data associations impose further challenges, often requiring human operators to annotate the data manually. We propose a data processing chain that automatically detects and tracks odontocetes from their echolocation clicks. The echolocation clicks are detected with a generalized cross-correlation that whitens the instrument noise. Two stages of tracking are performed using a tracking framework based on factor graphs and the sum-product algorithm (SPA). The odontocetes are first tracked in the TDOA domain to remove false alarms and then in the 3-D domain, fusing the tracked TDOAs across all sensors. To efficiently handle the considered non-linear and high-dimensional MTT scenario, particle flow is embedded in the SPA. According to simulation results, the proposed tracking method outperforms the existing approach using manual data annotation. Tracking of Cuvier’s beaked whales (Ziphius cavirostris), whose echolocation clicks are recorded by two volumetric hydrophone arrays, is demonstrated.

Coherent Long-Time Integration and Bayesian Detection With Bernoulli Track-Before-Detect

We consider the problem of detecting small and manoeuvring objects with staring array radars. Coherent processing and long-time integration are key to addressing the undesirably low signal-to-noise/background conditions in this scenario and are complicated by the object manoeuvres. We propose a Bayesian solution that builds upon a Bernoulli state space model equipped with the likelihood of the radar data cubes through the radar ambiguity function. Likelihood evaluation in this model corresponds to coherent long-time integration. The proposed processing scheme consists of Bernoulli filtering within expectation maximisation iterations that aims at approximately finding complex reflection coefficients. We demonstrate the efficacy of our approach in a simulation example.

Bayesian characterization of circumbinary sub-stellar objects with LISA

ABSTRACT The Laser Interferometer Space Antenna (LISA) will detect and characterize ∼104 Galactic Binaries, consisting predominantly of two white dwarfs (WDs). An interesting prospect within this population is a third object – another WD star, a circumbinary exoplanet (CBP), or a brown dwarf (BD) – in orbit about the inner WD pair. We present the first fully Bayesian detection and posterior analysis of substellar objects with LISA, focusing on the characterization of CBPs. We used an optimistic astrophysically motivated catalogue of these CBP third-body sources, including their orbital eccentricity around the inner binary for the first time. We examined Bayesian evidence computations for detectability, as well as the effects on the posterior distributions for both the inner binary parameters and the third-body parameters. We find that the posterior behaviour bifurcates based on whether the third-body period is above or below half the observation time. Additionally, we find that undetectable third-body sources can bias the inner binary parameters whether or not the correct template is used. We used the information retrieved from the study of the CBP population to make an initial conservative prediction for the number of detectable BD systems in the original catalogue. We end with commentary on the predicted qualitative effects on LISA global fitting and Galactic Binary population analysis. The procedure used in this work is generic and can be directly applied to other astrophysical effects expected within the Galactic Binary population.

Bayesian Cloud Detection over Land for Climate Data Records

Cloud detection is a necessary step in the generation of land surface temperature (LST) climate data records (CDRs) and affects data quality and uncertainty. We present here a sensor-independent Bayesian cloud detection algorithm and show that it is suitable for use in the production of LST CDRs. We evaluate the performance of the cloud detection with reference to two manually masked datasets for the Advanced Along-Track Scanning Radiometer (AATSR) and find a 7.9% increase in the hit rate and 4.9% decrease in the false alarm rate when compared to the operational cloud mask. We then apply the algorithm to four instruments aboard polar-orbiting satellites, which together can produce a global, 25-year LST CDR: the second Along-Track Scanning Radiometer (ATSR-2), AATSR, the Moderate Resolution Spectroradiometer (MODIS Terra) and the Sea and Land Surface Temperature Radiometer (SLSTR-A). The Bayesian cloud detection hit rate is assessed with respect to in situ ceilometer measurements for periods of overlap between sensors. The consistency of the hit rate is assessed between sensors, with mean differences in the cloud hit rate of 4.5% for ATSR-2 vs. AATSR, 4.9% for AATSR vs. MODIS, and 2.5% for MODIS vs. SLSTR-A. This is important because consistent cloud detection performance is needed for the observational stability of a CDR. The application of a sensor-independent cloud detection scheme in the production of CDRs is thus shown to be a viable approach to achieving LST observational stability over time.

A Bayesian detection of structural changes in autoregressive time series models

A Bayesian detection of structural changes in autoregressive time series models

Comparing the frequentist and Bayesian periodic signal detection: rates of statistical mistakes and sensitivity to priors

ABSTRACT We perform extensive Monte Carlo simulations to systematically compare the frequentist and Bayesian treatments of the Lomb–Scargle periodogram. The goal is to investigate whether the Bayesian period search is advantageous over the frequentist one in terms of the detection efficiency, how much if yes, and how sensitive it is regarding the choice of the priors, in particular in case of a misspecified prior (whenever the adopted prior does not match the actual distribution of physical objects). We find that the Bayesian and frequentist analyses always offer nearly identical detection efficiency in terms of their trade-off between type-I and type-II mistakes. Bayesian detection may reveal a formal advantage if the frequency prior is non-uniform, but this results in only ∼1 per cent extra detected signals. In case if the prior was misspecified (adopting non-uniform one over the actual uniform) this may turn into an opposite advantage of the frequentist analysis. Finally, we revealed that Bayes factor of this task appears rather overconservative if used without a calibration against type-I mistakes (false positives), thereby necessitating such a calibration in practice.

Point Event Cluster Detection via the Bayesian Generalized Fused Lasso

Spatial cluster detection is one of the focus areas of spatial analysis, whose objective is the identification of clusters from spatial distributions of point events aggregated in districts with small areas. Choi et al. (2018) formulated cluster detection as a parameter estimation problem to leverage the parameter selection capability of the sparse modeling method called the generalized fused lasso. Although this work is superior to conventional methods for detecting multiple clusters, its estimation results are limited to point estimates. This study therefore extended the above work as a Bayesian cluster detection method to describe the probabilistic variations of clustering results. The proposed method combines multiple sparsity-inducing priors and encourages sparse solutions induced by the generalized fused lasso. Evaluations were performed with simulated and real-world distributions of point events to demonstrate that the proposed method provides new information on the quantified reliabilities of clustering results at the district level while achieving comparable detection performances to that of the previous work.

Bayesian Detection in Gaussian Clutter for FDA-MIMO Radar

This paper investigates the Bayesian detection problem for a moving target that is embedded in a homogeneous Gaussian clutter with an unknown but stochastic covariance matrix for frequency diverse array multiple-input multiple-output (FDA-MIMO) radar. First, we propose a Bayesian detector based on structured generalized likelihood ratio test (SGLRT), namely BSGLRT, criteria that requires no training data. Then, we present a detector based on the Bayesian unstructured generalized likelihood ratio test (BUGLRT) to reduce the three dimensions (range-angle-Doppler) search into one-dimension Doppler searches for low-complexity implementation in practical applications. Moreover, the robustness of the BSGLRT and BUGLRT detectors is also analyzed. Numerical results reveal that the proposed Bayesian detectors and estimators, i.e. BSGLRT and BUGLRT, outperform their non-Bayesian counterparts in Gaussian clutter with a small number of snapshots and/or low signal-to-clutter rate (SCR) for FDA-MIMO radar.

Joint detection threshold adjustment and power allocation strategy for cognitive MIMO radar target tracking

Co-located multiple-input multiple-output (MIMO) radar can track multiple targets in the simultaneous multi-beam mode, where the defocused beams are transmitted to illuminate the whole surveillance space, while focused beams are received to attain a high Doppler resolution. A joint detection threshold adjustment and power allocation (JTAPA) strategy for this mode is proposed. The mechanism of our strategy is to improve the tracking accuracy in the clutter zone by exploiting prior target information, feedback from the filter, to facilitate transmitter and detector operation. The predicted conditional-Cramér-Rao lower bound (PC-CRLB), which provides a much tighter bound for the estimation error than the standard Bayesian CRLB (BCRLB), is derived, normalized and used as the optimization criterion. The Bayesian detection framework is embedded in the derivation to connect the detector with the filter. The optimization model is then established with bounding the transmit power and predetection threshold within intervals. It is shown that the objective function is nonlinear and nonconvex, and a flexible proximal alternating direction method of multipliers (ADMM)-based solver is proposed for solving the optimization model. Simulation results show the effectiveness of the JTAPA strategy, compared with the strategies adopting the tunable detection threshold and/or optimal power allocation (PA). In addition, the results imply that the target distance and the target radar cross section are two main factors that influence the JTAPA results.