In this paper, a sequence-to-sequence deep learning architecture based on the bidirectional gated recurrent unit (Bi-GRU) for type recognition and time location of combined power quality disturbance is proposed. Especially, proposed methodology can determine each element in input sequence, which different from existing model employing encoder–decoder network. First, sequence normalized batched. Second, features are extracted by constructing Bi-GRU neural network, where multiple layers...

For inverse synthetic aperture radar imagery, the inherent sparsity of scatterers in range-Doppler domain has been exploited to achieve a high-resolution range profile or Doppler spectrum. Prior applying sparse recovery technique, preprocessing procedures are performed for minimization translational-motion-induced effects. Due imperfection coarse motion compensation, autofocus technique is further required eliminate residual phase errors. This paper considers error correction problem context...

This paper presents a novel inverse synthetic aperture radar (ISAR) imaging method by exploiting the inherent continuity of scatterers on target scene to obtain enhanced images within Bayesian framework. A simplified system is utilized transmitting sparse probing frequency signal, where ISAR problem can be converted deal with underdetermined linear scattering. Following compressive sensing (BCS) theory, hierarchical prior employed model in range-Doppler plane. In contrast independent each...

Direction of arrival (DOA) estimation methods based on joint sparsity are attractive due to their superiority high resolution with a limited number snapshots. However, the common assumption that signals from different directions share spectral band is inappropriate when they occupy bands. To flexibly deal this situation, novel wideband DOA algorithm proposed simultaneously infer occupation and estimate high-resolution DOAs by leveraging in angular domain. The exploited exerting Dirichlet...

The exploitation of sparsity has significantly advanced the field radar imaging over last few decades, leading to substantial improvements in resolution and quality processed images. More recent developments compressed sensing (CS) suggest that statistical can lead further performance benefits by imposing as a prior on considered signal. In this article, comprehensive survey is made progress based techniques for various imagery applications.

This letter considers the multiplicative perturbation problem in compressive sensing, which has become an increasingly important issue on obtaining robust performance for practical applications. The is formulated a probabilistic model and auto-calibration sparse Bayesian learning algorithm proposed. In this algorithm, signal are iteratively estimated to achieve sparsity by leveraging variational expectation maximization technique. Results from numerical experiments have demonstrated that...

To encourage the continuity of target scene, a novel sparse representation (SR)-based inverse synthetic aperture radar (ISAR) imaging algorithm is proposed by leveraging Markov random fields (MRF). The ISAR problem reformulated in Bayesian framework where correlated priors are used for hidden variables to enforce scene. further nonzero or zero scatterers cluster spatial consistent manner, MRF as prior support surmount difficulty calculating posterior due imposed and MRF, variational Bayes...

Abstract Many animals exploit polarized light in order to calibrate their magnetic compasses for navigation. For example, some birds are equipped with biological and celestial enabling them migrate between the Western Eastern Hemispheres. The Vikings' ability derive true direction from is also widely accepted. However, amazing navigational capabilities still not completely clear. Inspired by birds' ancient skills. Here we present a combined real-time position method based on use of...

We consider the problem of recovering block sparse signals with unknown partition and propose a better alternative to extended Bayesian learning (EBSBL). The underlying relationship between proposed method EBSBL pattern-coupled (PC-SBL) is explicitly revealed. adopts cluster-structured prior for coefficients, which encourages dependencies among neighboring coefficients by properly manipulating hyperparameters neighborhood. Due entanglement hyperparameters, joint sparsity assumption made...

Human body posture recognition has attracted considerable attention in recent years wireless area networks (WBAN). In order to precisely recognize human posture, many algorithms have been proposed. However, the rate is relatively low. this paper, we apply back propagation (BP) neural network as a classifier recognizing where signals are collected from VG350 acceleration sensor and signal collection system based on WBAN designed. vector magnitude (SVM) tri-axial data used describe postures....

Traditional range-instantaneous Doppler (RID) methods for maneuvering target imaging suffer from the problems of low resolution and poor noise suppression. We propose a new super-resolution inverse synthetic aperture radar (ISAR) method based on deep-learning-assisted time–frequency analysis (TFA). Our deep neural network resembles basic structure U-net with two additional convolutional-upsampling layers <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML"...

This paper considers the problem of estimating multiple frequency hopping signals with unknown pattern. By segmenting received into overlapped measurements and leveraging property that content at each time instant is intrinsically parsimonious, a sparsity-inspired high-resolution time-frequency representation (TFR) developed to achieve robust estimation. Inspired by sparse Bayesian learning algorithm, formulated hierarchically induce sparsity. In addition sparsity, pattern exploited via...

An optically tunable and rewritable liquid crystal (LC) diffraction grating cell has been revealed that consists of an active passive alignment layer. The profile is created by confining the LC director distribution in alternate planar twisted domains means photoalignment LCs. proposed for diffractive nondiffractive states with a small response time depends on exposure energy parameters. In addition, can be erased rewritten different diffracting characteristics. These elements could find...