Sparse Bayesian consensus-based distributed field estimation

In this article we study the sparse signal recovery problem in a Bayesian framework using a novel Bootstrapped Sparse Bayesian Learning method. Sparse Bayesian Learning (SBL) framework is an effective tool for pruning out the irrelevant features and ending up with a sparse representation. In SBL the choice of prior over the variances of the Gaussian Scale mixture has been an interesting area of research for some time now. This motivates us to use a more generalized maximum entropy density as the prior which results in a new variant of SBL. It has been shown to perform better than traditional SBL empirically and it also accelerates the pruning procedure. Because of this advantage, this variant of SBL can be claimed as more robust choice as it is less sensitive to the threshold for pruning. Theoretical justifications have also been provided to show that the proposed model actually promotes sparse point estimates.

Hyperspectral unmixing is a technique that can be used to find the materials and their corresponding proportions present in observed mixed pixels. It has been widely used for hyperspectral data exploitation. Traditionally, this problem is solved using the constrained least squares optimization, which would lead to a dense solution. In recent years, researchers have observed that the number of materials in a mixed pixel is generally much smaller than the whole number of materials present in a given scene. They proposed to solve the problem through sparse unmixing approaches, which generally lead to constrained optimization. These sparse unmixing approaches have received considerable attention over the past few years. From the perspective of Bayesian inference, these methods assume fixed priors. In this article, we propose to solve the spectral unmixing problem by using sparse Bayesian learning (SBL) framework. In contrast to the approaches that use fixed priors, SBL incorporates a hierarchical parameterized prior that encourages sparsity in representation in its Bayesian inference to obtain a sparse solution. Experimental results on simulated data sets and a real hyperspectral scene demonstrate that the proposed method can achieve good performance compared with some state-of-the-art sparse unmixing algorithms. Our results also show that the proposed method can achieve good performance with a set of default parameter settings.

The compressive sensing(CS) and sparse representation(SR) technique provide new way to improve the ISAR image resolution. At present, in most traditional CS and SR based ISAR imaging methods, the target is regarded as a set of isolated scattering centers. As a matter of fact, adjacent scattering centers compose a lot of small sets which can reflect the structure of the target. It is no doubt that these small sets can be exploited to improve the ISAR image quality, but the traditional CS and SR ISAR imaging methods ignore this. So in this paper, a block sparse signal recovery algorithm-Block Sparse Bayesian Learning(BSBL) method is introduced to modify the traditional method, and the simulate experiment show that this method can get better ISAR image than the other methods.

Wireless sensor networks area collection of a large number of unattended sensor nodes. The sensor nodes are dynamically deployed in the region. In wireless sensor networks, the unlicensed sensor nodes use their temporarily available vacant licensed channels or spectrum band in a telecommunication network. The many open challenges with issues such as adaptive in self-organisation, fault-tolerance and network scalability with cooperative spectrum sensing and sharing are identifying new challenges in wireless sensor networks. In this paper, we proposed the bio-inspired adaptive routing algorithm for cognitive radio wireless sensor networks. The utilisation of the foraging approach of ANTs and BEEs for making the decision of using the available spectrum sensing and sharing of channels over multi-hops communication, provides the method to utilise idle channel and decrease the delay for communication in wireless sensor network. In this paper, we design the algorithm to solve the issue of wireless sensor network and performance of classical routing protocol LEACH and cognitive radio sensor networks (CRSN) evaluates the parameters which proof the self-organisation routing algorithm.

In this paper, we propose a detailed energy survey of the physical, data link, and network layer by analytical techniques. We also show the impact of regular sleep periods on node energy consumption and present a comparison analysis of single-hop vs. multi-hop communications in the energy realm. A detailed energy expenditure analysis of not only the physical layer but also the link and network layer provides a basis for developing new energy efficient wireless sensor networks. Regular, coordinated sleeping extends the lifetime of sensor nodes, but systems can only benefit from sleeping in terms of transmitted packets if the data arrival rate to the system is low. Energy efficiency is the driving motivation for it can be considered the most important factor for wireless sensor networks because of the power constraints set by battery operation. Radio solutions in the lower ISM bands are attractive because of their relatively easy implementation and low power consumption. However, the data rates of these commercial radios are also relatively low, limiting transmittable frame sizes to a few tens of octets along with strict duty cycle requirements. From the analysis we extract key parameters of selected MAC protocols and show that some traditional mechanisms, such as binary exponential backoff, have some inherent problems. We also argue that single-hop communications has up todo% lower energy consumption than multi-hop forwarding within the feasible transmission distances of an ISM radio. Index Terms-Energy efficiency, Wireless sensor net- works, Medium access control (MAC) protocols, multi-hop communications a duty cycIe (Z), (3), which is normally 10% for the 434MHz band and 1% for the 868MHz band. The duty cycle is defined as the ratio, expressed as a percentage, of the maximum transmitter on-time, relative to a one hour period. When a sensor network is expected to work continuously, this duty cycle has to be taken into account and it can affect the energy efficiency of a network. In this paper we perform cross-layer analysis by pre- senting topology, medium access control (MAC) and ra- dio transceiver energy consumption models that work in unison. The hear topology model represents a common network after network layer route discovery has been accomplished. We use an energy consumption model for the transmission and reception of MAC frames originally presented in (4), develop a coordinated sleep group energy consumption model, and analytically investigate the effect of sleep on sensor networks using three MAC protocols. From the analysis we show that although in an ideal scenario multi-hop communications perform better than single-hop communications, realistic energy models and especially the MAC protocol design have a significant impact. We propose a multi-group sleep model for our nanoMAC protocol, and show that reg- ular sleep periods have a significant, energy reducing impact on node energy consumption with low traf!fic rates. The radio transceiver energy model takes into account several important radio parameters and we use the RFM TRlOOO and RFM radio designers guide (5) for realistic transceiver parameters. The main metric used is absolute energy, consumption per useful transmitted bit. This means only the MAC or thc network protocol data unit (PDU) will be considered and all the other communicated bits, headers, control frames, preambles, etc. are considered as overhead. The rest of the paper is organized as follows. Some related work is discussed in Section IT and in Section 111 we look at the radio propagation energy model. Section TV presents the network topology and energy

The paper proposes a new variational Bayesian algorithm for l 1 -penalized multivariate regression with attribute-distributed data. The algorithm is based on the variational Bayesian version of the SAGE algorithm that realizes a training of individual agents in a distributed fashion and sparse Bayesian learning (SBL) with hierarchical sparsity prior modeling of the agent weights. The SBL introduces constraints on the weights of individual agents, thus reducing the effects of overfitting and removing/suppressing poorly performing agents in the ensemble estimator. The l 1 constraint is introduced using a product of a Gaussian and an exponential probability density function with the resulting marginalized prior being a Laplace pdf. Such a hierarchical formulation of the prior allows for a computation of the stationary points of the variational update expressions for prior parameters, as well as deriving conditions that ensure convergence to these stationary points. Using synthetic data it is demonstrated that the proposed algorithm performs very well in terms of the achieved MSE, and outperforms other algorithms in the ability to sparsify non-informative agents, while at the same time allowing distributed implementation and flexible agent update protocols.

Event-triggered distributed state estimation over wireless sensor networks

Gearbox oil temperature anomaly detection for wind turbine based on sparse Bayesian probability estimation

This work proposes a new turbulence-transition model able of providing closure for the Reynolds stress tensor in Reynolds-Averaged Navier-Stokes (RANS) simulations. The model has been trained by Sparse Bayesian Learning from a large experimental database of separated flows acquired in a flat plate test section by means of Time-Resolved Particle Image Velocimetry. The data provide the mean flow and Reynolds stress components for many cases of separation-induced transitional flows evolving on the flat plate under different Reynolds numbers, adverse pressure gradients, and turbulence intensity levels. A total amount of about 90 flow conditions have been tested reproducing turbine-like operating conditions generating bubbles of both short and the long types. Two different sub-models have been trained, one for short and another for long bubbles, independently. To address the limitations of the Boussinesq’s hypothesis, they have been formulated adopting an Explicit Algebraic Reynolds Stress (EARSM) closure based on the Pope's tensorial expansion. This approach introduces two additional turbulent viscosities, allowing for a misalignment between the stress and strain tensors. Tuning the two sub-models by Sparse Bayesian Learning allows defining sparse representation of the turbulent viscosities depending solely on combinations of the strain rate and rotation tensors invariants. Once identified the two sub-models, an additional aggregated model able of modelling bubbles with intermediate behaviour between the two configurations has been defined. Model aggregation has been achieved by weighing the two sub-models with coefficients defined from a large predictor library of physical-based flow features. Sparse Bayesian Learning has been exploited again for the identification of the leading predictors defining the weighting coefficients. A final validation set of short, long and intermediate-length bubbles has been adopted for validating the final model, to be as generalizable as possible. The proposed model may be used into RANS solvers as a data-driven specialized model for separated flow cases, with the aim of improving the RANS prediction of transitional flows characterized by separation-induced transition. The approach here used can also be extended to other flow cases where high-quality data are available, to generally enhance RANS simulations via machine-learning tools.

Energy efficient head node selection is the major issue in wireless sensor networks. Due to irregular node distribution energy consumption is not a balanced one in cluster-based wireless sensor networks. The proposed system provides techniques to rectify this problem through: (i) Forming Maximal Independent Set (MIS) (ii) Effective Set Head selection (iii) Multi-hop communication. Non adjacency of nodes has been leveraged for creating MIS. Intra-set energy consumption has been reduced by selecting a node as Set Head (SH), which is geographically nearer to all other nodes. Inter Set efficient energy consumption is achieved by using multi-hop communication between SH to BS. The proposed system EECDC forms more efficient and stable sets, which increases the lifetime of sensor networks i.e., Number of data collection rounds.

In this paper, we examine some of the challenges concerning error correction and multi-hop communication in wireless sensor networks (WSNs). We consider Bose, Chaudhuri and Hoquenghem (BCH) codes with different codeword lengths and error correction capabilities. In contrast with previous works, that implement coding algorithm in hardware and consequently used hardware energy profiling, in this work we consider a more realistic assumption that the node's /spl mu/-processor performs coding and energy consumption of decoding is measured using JouleTrack. Energy efficiency is used as the performance metric for communication and the interaction of multi-hop communication and coding is investigated. Simulation results show that communicating long packets is more energy efficient. If communication is multi-hop with sufficient number of hops, then, the uncoded system is beneficial. However, coding is inevitable in the case where intermediate nodes, when needed, are not available.

Collaborative Direction of Arrival estimation by using Alternating Direction Method of Multipliers in distributed sensor array networks employing Sparse Bayesian Learning framework

This paper investigates the use of cooperative multiple-input-multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) technique to limit energy consumption used to set up communications among distant hubs in a remote wireless sensor network (WSN). As energy exhaustion is a pertinent issue in WSN field, various methods aim to safeguard such asset, particularly by means for harvesting energy amidst communication among sensor hubs. One such widely utilized strategy is multi-hop communication to reduce the energy required by a single hub to transmit a given message, giving a homogeneous utilization of the energy assets among the hubs in the system. The case of multi-hop communication is not continuously more effective than single-hop. In multi-hop communication, energy efficiency will depend upon the distance between transmit and receive clusters. If the distance is large, then the energy expended will be less than single-hop communication. In this paper, an agreeable MIMO-OFDM transmission strategy for WSN is exhibited, which is contrasted with single-hop. The cooperation among adjacent nodes is analyzed, highlighting its points of interest in connection with both. The inference drawn from performance improvement manifests itself in the utility of applying the proposed strategy for energy-sparing purposes.

In this paper, we focus on a multi-task sparse Bayesian learning (SBL) theory that simultaneously utilizes multiple measurement vectors that are marked by a similar sparseness profile. Joint learning for sparse representations of multiple tasks has been mostly overlooked, although it is a useful tool for exploiting data redundancy by modeling the statistical relationships within groups of measurements. We first present a hierarchical Bayesian model and Bayesian inference framework for the multi-task SBL algorithm. Then we investigate the application of the multi-task SBL for model updating in structural health monitoring. The results verify that exploiting common information among multiple related tasks leads to better performance of the Bayesian inversion

It is critical to deploy wireless data transmission technologies remotely, in real-time, to monitor the health state of diesel engines dynamically. The usual approach to data compression is to collect data first, then compress it; however, we cannot ensure the correctness and efficiency of the data. Based on sparse Bayesian optimization block learning, this research provides a method for compression reconstruction and fault diagnostics of diesel engine vibration data. This method’s essential contribution is combining compressive sensing technology with fault diagnosis. To achieve a better diagnosis effect, we can effectively improve the wireless transmission efficiency of the vibration signal. First, the dictionary is dynamically updated by learning the dictionary using singular value decomposition to produce the ideal sparse form. Second, a block sparse Bayesian learning boundary optimization approach is utilized to recover structured non-sparse signals rapidly. A detailed assessment index of the data compression effect is created. Finally, the experimental findings reveal that the approach provided in this study outperforms standard compression methods in terms of compression efficiency and accuracy and its ability to produce the desired fault diagnostic effect, proving the usefulness of the proposed method.