Shear Let Transform Residual Learning Approach for Single-Image Super-Resolution

Super-resolution techniques are employed to enhance image resolution by reconstructing high-resolution images from one or more low-resolution inputs.Super-resolution is of paramount importance in the context of remote sensing,satellite,aerial,security and surveillance imaging.Super-resolution remote sensing imagery is essential for surveillance and security purposes,enabling authorities to monitor remote or sensitive areas with greater clarity.This study introduces a single-image super-resolution approach for remote sensing images,utilizing deep shearlet residual learning in the shearlet transform domain,and incorporating the Enhanced Deep Super-Resolution network(EDSR).Unlike conventional approaches that estimate residuals between high and low-resolution images,the proposed approach calculates the shearlet coefficients for the desired high-resolution image using the provided low-resolution image instead of estimating a residual image between the high-and low-resolution image.The shearlet transform is chosen for its excellent sparse approximation capabilities.Initially,remote sensing images are transformed into the shearlet domain,which divides the input image into low and high frequencies.The shearlet coefficients are fed into the EDSR network.The high-resolution image is subsequently reconstructed using the inverse shearlet transform.The incorporation of the EDSR network enhances training stability,leading to improved generated images.The experimental results from the Deep Shearlet Residual Learning approach demonstrate its superior performance in remote sensing image recovery,effectively restoring both global topology and local edge detail information,thereby enhancing image quality.Compared to other networks,our proposed approach outperforms the state-of-the-art in terms of image quality,achieving an average peak signal-to-noise ratio of 35 and a structural similarity index measure of approximately 0.9.

AFBNet: A Lightweight Adaptive Feature Fusion Module for Super-Resolution Algorithms

At present,super-resolution algorithms are employed to tackle the challenge of low image resolution,but it is difficult to extract differentiated feature details based on various inputs,resulting in poor generalization ability.Given this situation,this study first analyzes the features of some feature extraction modules of the current super-resolution algorithm and then proposes an adaptive feature fusion block(AFB)for feature extraction.This module mainly comprises dynamic convolution,attention mechanism,and pixel-based gating mechanism.Combined with dynamic convolution with scale information,the network can extract more differentiated feature information.The introduction of a channel spatial attention mechanism combined with multi-feature fusion further enables the network to retain more important feature information.Dynamic convolution and pixel-based gating mechanisms enhance the module’s adaptability.Finally,a comparative experiment of a super-resolution algorithm based on the AFB module is designed to substantiate the efficiency of the AFB module.The results revealed that the network combined with the AFB module has stronger generalization ability and expression ability.

Efficient 2-D MUSIC algorithm for super-resolution moving target tracking based on an FMCW radar

Frequency modulated continuous wave(FMCW)radar is an advantageous sensor scheme for target estimation and environmental perception.However,existing algorithms based on discrete Fourier transform(DFT),multiple signal classification(MUSIC)and compressed sensing,etc.,cannot achieve both low complexity and high resolution simultaneously.This paper proposes an efficient 2-D MUSIC algorithm for super-resolution target estimation/tracking based on FMCW radar.Firstly,we enhance the efficiency of 2-D MUSIC azimuth-range spectrum estimation by incorporating 2-D DFT and multi-level resolution searching strategy.Secondly,we apply the gradient descent method to tightly integrate the spatial continuity of object motion into spectrum estimation when processing multi-epoch radar data,which improves the efficiency of continuous target tracking.These two approaches have improved the algorithm efficiency by nearly 2-4 orders of magnitude without losing accuracy and resolution.Simulation experiments are conducted to validate the effectiveness of the algorithm in both single-epoch estimation and multi-epoch tracking scenarios.

Pyramid Separable Channel Attention Network for Single Image Super-Resolution

Single Image Super-Resolution(SISR)technology aims to reconstruct a clear,high-resolution image with more information from an input low-resolution image that is blurry and contains less information.This technology has significant research value and is widely used in fields such as medical imaging,satellite image processing,and security surveillance.Despite significant progress in existing research,challenges remain in reconstructing clear and complex texture details,with issues such as edge blurring and artifacts still present.The visual perception effect still needs further enhancement.Therefore,this study proposes a Pyramid Separable Channel Attention Network(PSCAN)for the SISR task.Thismethod designs a convolutional backbone network composed of Pyramid Separable Channel Attention blocks to effectively extract and fuse multi-scale features.This expands the model’s receptive field,reduces resolution loss,and enhances the model’s ability to reconstruct texture details.Additionally,an innovative artifact loss function is designed to better distinguish between artifacts and real edge details,reducing artifacts in the reconstructed images.We conducted comprehensive ablation and comparative experiments on the Arabidopsis root image dataset and several public datasets.The experimental results show that the proposed PSCAN method achieves the best-known performance in both subjective visual effects and objective evaluation metrics,with improvements of 0.84 in Peak Signal-to-Noise Ratio(PSNR)and 0.017 in Structural Similarity Index(SSIM).This demonstrates that the method can effectively preserve high-frequency texture details,reduce artifacts,and have good generalization performance.

PSMFNet:Lightweight Partial Separation and Multiscale Fusion Network for Image Super-Resolution

The employment of deep convolutional neural networks has recently contributed to significant progress in single image super-resolution(SISR)research.However,the high computational demands of most SR techniques hinder their applicability to edge devices,despite their satisfactory reconstruction performance.These methods commonly use standard convolutions,which increase the convolutional operation cost of the model.In this paper,a lightweight Partial Separation and Multiscale Fusion Network(PSMFNet)is proposed to alleviate this problem.Specifically,this paper introduces partial convolution(PConv),which reduces the redundant convolution operations throughout the model by separating some of the features of an image while retaining features useful for image reconstruction.Additionally,it is worth noting that the existing methods have not fully utilized the rich feature information,leading to information loss,which reduces the ability to learn feature representations.Inspired by self-attention,this paper develops a multiscale feature fusion block(MFFB),which can better utilize the non-local features of an image.MFFB can learn long-range dependencies from the spatial dimension and extract features from the channel dimension,thereby obtaining more comprehensive and rich feature information.As the role of the MFFB is to capture rich global features,this paper further introduces an efficient inverted residual block(EIRB)to supplement the local feature extraction ability of PSMFNet.A comprehensive analysis of the experimental results shows that PSMFNet maintains a better performance with fewer parameters than the state-of-the-art models.

Engineering of geometrical configurations in dual-atom catalysts for electrocatalytic applications

Geometrical configurations play a crucial role in dual-atom catalysts(DACs)for electrocatalytic applications.Significant progress has been made to design DACs electrocatalysts with various geometri-cal configurations,but in-depth understanding the relationship between geometrical configurations and metal-metal interaction mechanisms for designing targeted DACs is still required.In this review,the recent progress in engineering of geometrical configurations of DACs is systematically summarized.Based on the polarity of geometrical configuration,DACs can be classified into two different types that are homonuclear and heteronuclear DACs.Furthermore,with regard to the geometrical configurations of the active sites,homonuclear DACs are identified into adjacent and bridged configurations,and heteronuclear DACs can be classified into adjacent,bridged,and separated configurations.Subsequently,metal-metal interactions in DACs with different geometrical configurations are introduced.Additionally,the applications of DACs in different electrocatalytic reactions are discussed,including the oxygen reduction reaction(ORR),oxygen evolution reaction(OER),hydrogen evolution reaction(HER),and other catalysis.Finally,the future challenges and perspectives for advancements in DACs are high-lighted.This review aims to provide inspiration for the design of highly effcient DACs towards energy relatedapplications.

Multi-prior physics-enhanced neural network enables pixel super-resolution and twin-imagefree phase retrieval from single-shot hologram

Digital in-line holographic microscopy(DIHM)is a widely used interference technique for real-time reconstruction of living cells’morphological information with large space-bandwidth product and compact setup.However,the need for a larger pixel size of detector to improve imaging photosensitivity,field-of-view,and signal-to-noise ratio often leads to the loss of sub-pixel information and limited pixel resolution.Additionally,the twin-image appearing in the reconstruction severely degrades the quality of the reconstructed image.The deep learning(DL)approach has emerged as a powerful tool for phase retrieval in DIHM,effectively addressing these challenges.However,most DL-based strategies are datadriven or end-to-end net approaches,suffering from excessive data dependency and limited generalization ability.Herein,a novel multi-prior physics-enhanced neural network with pixel super-resolution(MPPN-PSR)for phase retrieval of DIHM is proposed.It encapsulates the physical model prior,sparsity prior and deep image prior in an untrained deep neural network.The effectiveness and feasibility of MPPN-PSR are demonstrated by comparing it with other traditional and learning-based phase retrieval methods.With the capabilities of pixel super-resolution,twin-image elimination and high-throughput jointly from a single-shot intensity measurement,the proposed DIHM approach is expected to be widely adopted in biomedical workflow and industrial measurement.

Modeling Geometrically Nonlinear FG Plates: A Fast and Accurate Alternative to IGA Method Based on Deep Learning

Isogeometric analysis (IGA) is known to showadvanced features compared to traditional finite element approaches.Using IGA one may accurately obtain the geometrically nonlinear bending behavior of plates with functionalgrading (FG). However, the procedure is usually complex and often is time-consuming. We thus put forward adeep learning method to model the geometrically nonlinear bending behavior of FG plates, bypassing the complexIGA simulation process. A long bidirectional short-term memory (BLSTM) recurrent neural network is trainedusing the load and gradient index as inputs and the displacement responses as outputs. The nonlinear relationshipbetween the outputs and the inputs is constructed usingmachine learning so that the displacements can be directlyestimated by the deep learning network. To provide enough training data, we use S-FSDT Von-Karman IGA andobtain the displacement responses for different loads and gradient indexes. Results show that the recognition erroris low, and demonstrate the feasibility of deep learning technique as a fast and accurate alternative to IGA formodeling the geometrically nonlinear bending behavior of FG plates.

Iterative Subregion Correction Preconditioners with Adaptive Tolerance for Problems with Geometrically Localized Stiffness

We present a class of preconditioners for the linear systems resulting from a finite element or discontinuous Galerkin discretizations of advection-dominated problems.These preconditioners are designed to treat the case of geometrically localized stiffness,where the convergence rates of iterative methods are degraded in a localized subregion of the mesh.Slower convergence may be caused by a number of factors,including the mesh size,anisotropy,highly variable coefficients,and more challenging physics.The approach taken in this work is to correct well-known preconditioners such as the block Jacobi and the block incomplete LU(ILU)with an adaptive inner subregion iteration.The goal of these preconditioners is to reduce the number of costly global iterations by accelerating the convergence in the stiff region by iterating on the less expensive reduced problem.The tolerance for the inner iteration is adaptively chosen to minimize subregion-local work while guaranteeing global convergence rates.We present analysis showing that the convergence of these preconditioners,even when combined with an adaptively selected tolerance,is independent of discretization parameters(e.g.,the mesh size and diffusion coefficient)in the subregion.We demonstrate significant performance improvements over black-box preconditioners when applied to several model convection-diffusion problems.Finally,we present performance results of several variations of iterative subregion correction preconditioners applied to the Reynolds number 2.25×10^(6)fluid flow over the NACA 0012 airfoil,as well as massively separated flow at 30°angle of attack.

Faster split-based feedback network for image super-resolution

Although most of the existing image super-resolution(SR)methods have achieved superior performance,contrastive learning for high-level tasks has not been fully utilized in the existing image SR methods based on deep learning.This work focuses on two well-known strategies developed for lightweight and robust SR,i.e.,contrastive learning and feedback mechanism,and proposes an integrated solution called a split-based feedback network(SPFBN).The proposed SPFBN is based on a feedback mechanism to learn abstract representations and uses contrastive learning to explore high information in the representation space.Specifically,this work first uses hidden states and constraints in recurrent neural network(RNN)to implement a feedback mechanism.Then,use contrastive learning to perform representation learning to obtain high-level information by pushing the final image to the intermediate images and pulling the final SR image to the high-resolution image.Besides,a split-based feedback block(SPFB)is proposed to reduce model redundancy,which tolerates features with similar patterns but requires fewer parameters.Extensive experimental results demonstrate the superiority of the proposed method in comparison with the state-of-the-art methods.Moreover,this work extends the experiment to prove the effectiveness of this method and shows better overall reconstruction quality.

Quantification of grain boundary effects on the geometrically necessary dislocation density evolution and strain hardening of polycrystalline Mg-4Al using in situ tensile testing in scanning electron microscope and HR-EBSD

In situ tensile testing in a scanning electron microscope(SEM)in conjunction with high-resolution electron backscatter diffraction(HR-EBSD)under load was used to characterize the evolution of geometrically necessary dislocation(GND)densities at individual grain boundaries as a function of applied strain in a polycrystalline Mg-4Al alloy.The increase in GND density was investigated at plastic strains of 0%,0.6%,2.2%,3.3% from the area including 76 grains and correlated with(i)geometric compatibility between slip systems across grain boundaries,and(ii)plastic incompatibility.We develop expressions for the grain boundary GND density evolution as a function of plastic strain and plastic incompatibility,from which uniaxial tensile stress-strain response of polycrystalline Mg-4Al are computed and compared with experimental measurement.The findings in this study contribute to understanding the mechanisms governing the strain hardening response of single-phase polycrystalline alloys and more reliable prediction of mechanical behaviors in diverse microstructures.

Influence of manufacturing process-induced geometrical defects on the energy absorption capacity of polymer lattice structures

Modern additive manufacturing processes enable fabricating architected cellular materials of complex shape,which can be used for different purposes.Among them,lattice structures are increasingly used in applications requiring a compromise among lightness and suited mechanical properties,like improved energy absorption capacity and specific stiffness-to-weight and strength-to-weight ratios.A dedicated modeling strategy to assess the energy absorption capacity of lattice structures under uni-axial compression loading is presented in this work.The numerical model is developed in a non-linear framework accounting for the strain rate effect on the mechanical responses of the lattice structure.Four geometries,i.e.,cubic body centered cell,octet cell,rhombic-dodecahedron and truncated cuboctahedron 2+,are investigated.Specifically,the influence of the relative density of the representative volume element of each geometry,the strain-rate dependency of the bulk material and of the presence of the manufacturing process-induced geometrical imperfections on the energy absorption capacity of the lattice structure is investigated.The main outcome of this study points out the importance of correctly integrating geometrical imperfections into the modeling strategy when shock absorption applications are aimed for.

Nonlinear dynamics of a circular curved cantilevered pipe conveying pulsating fluid based on the geometrically exact model

Due to the novel applications of flexible pipes conveying fluid in the field of soft robotics and biomedicine,the investigations on the mechanical responses of the pipes have attracted considerable attention.The fluid-structure interaction(FSI)between the pipe with a curved shape and the time-varying internal fluid flow brings a great challenge to the revelation of the dynamical behaviors of flexible pipes,especially when the pipe is highly flexible and usually undergoes large deformations.In this work,the geometrically exact model(GEM)for a curved cantilevered pipe conveying pulsating fluid is developed based on the extended Hamilton's principle.The stability of the curved pipe with three different subtended angles is examined with the consideration of steady fluid flow.Specific attention is concentrated on the large-deformation resonance of circular pipes conveying pulsating fluid,which is often encountered in practical engineering.By constructing bifurcation diagrams,oscillating shapes,phase portraits,time traces,and Poincarémaps,the dynamic responses of the curved pipe under various system parameters are revealed.The mean flow velocity of the pulsating fluid is chosen to be either subcritical or supercritical.The numerical results show that the curved pipe conveying pulsating fluid can exhibit rich dynamical behaviors,including periodic and quasi-periodic motions.It is also found that the preferred instability type of a cantilevered curved pipe conveying steady fluid is mainly in the flutter of the second mode.For a moderate value of the mass ratio,however,a third-mode flutter may occur,which is quite different from that of a straight pipe system.

Effect of the Geometrical Parameter of OpenMicrochannel on Pool Boiling Enhancement

High heat dissipation is required for miniaturization and increasing the power of electronic systems.Pool boiling is a promising option for achieving efficient heat dissipation at low wall superheat without the need for moving parts.Many studies have focused on improving heat transfer efficiency during boiling by modifying the surface of the heating element.This paper presents an experimental investigation on improving pool boiling heat transfer using an open microchannel.The primary goal of this work is to investigate the impact of the channel geometry characteristics on boiling heat transfer.Initially,rectangular microchannels were prepared on a circular copper test piece with a diameter of 20 mm.Then,the boiling characteristics of these microchannels were compared with those of a smooth surface under saturated conditions using deionized water.In this investigation,a wire-cutting electrical discharge machine(EDM)machine was used to produce parallel microchannels with channel widths of 0.2,0.4,and 0.8 mm.The fin thicknesses were 0.2,0.4,and 0.6 mm,while the channel depth remained constant at 0.4 mm.The results manifested that the surface featuring narrower fins and broader channels achieved superior performance.The heat transfer coefficient(HTC)was enhanced by a maximum of 248%,and the critical heat flux(CHF)was enhanced by a maximum of 101%compared to a plain surface.Eventually,the obtained results were compared with previous research and elucidated a good agreement.

An Efficient Algorithm for Calculating Aircraft RCS Based on the Geometrical Characteristics

Taking into account the influences of scatterer geometrical shapes on induced currents, an algorithm, termed the sparse-matrix method （SMM）, is proposed to calculate radar cross section （RCS） of aircraft configuration. Based on the geometrical characteristics and the method of moment （MOM）, the SMM points out that the strong current coupling zone could be predefined according to the shape of scatterers. Two geometrical parameters, the surface curvature and the electrical space between the field position and source position, are deducted to distinguish the dominant current coupling. Then the strong current coupling is computed to construct an impedance matrix having sparse nature, which is solved to compute RCS. The efficiency and feasibility of the SMM are demonstrated by computing electromagnetic scattering of some kinds of shapes such as a cone-sphere with a gap, a bi-arc column and a stealth aircraft configuration. The numerical results show that： （1） the accuracy of SMM is satisfied, as compared with MOM, and the computational time it spends is only about 8% of the MOM; （2） with the electrical space considered, making another allowance for the surface curvature can reduce the computation time by 9.5%.

Residual elastic stress strain field and geometrically necessary dislocation density distribution around nano-indentation in TA15 titanium alloy

Nanoindentation and high resolution electron backscatter diffraction（EBSD） were combined to examine the elastic modulus and hardness of α and β phases,anisotropy in residual elastic stress strain fields and distributions of geometrically necessary dislocation（GND） density around the indentations within TA15 titanium alloy.The nano-indention tests were conducted on α and β phases,respectively.The residual stress strain fields surrounding the indentation were calculated through crosscorrelation method from recorded patterns.The GND density distribution around the indentation was calculated based on the strain gradient theories to reveal the micro-mechanism of plastic deformation.The results indicate that the elastic modulus and hardness for α p hase are 129.05 GPas and 6.44 GPa,while for β phase,their values are 109.80 GPa and 4.29 GPa,respectively.The residual Mises stress distribution around the indentation is relatively heterogeneous and significantly influenced by neighboring soft β phase.The region with low residual stress around the indentation is accompanied with markedly high a type and prismatic-GND density.

Effect of geometrical parameters on forming quality of high-strength TA18 titanium alloy tube in numerical control bending

The forming quality of high-strength TA18 titanium alloy tube during numerical control bending in changing bending angle β, relative bending radius R/D and tube sizes such as diameter D and wall thickness t was clarified by finite element simulation. The results show that the distribution of wall thickness change ratio Δt and cross section deformation ratio ΔD are very similar under different β; the Δt and ΔD decrease with the increase of R/D, and to obtain the qualified bent tube, the R/D must be greater than 2.0; the wall thinning ratio Δto slightly increases with larger D and t, while the wall thickening ratio Δti and ΔD increase with the larger D and smaller t; the Δto and ΔD firstly decrease and then increase, while the Δti increases, for the same D/t with the increase of D and t.

New tangent stiffness matrix for geometrically nonlinear analysis of space frames

A three-dimensional beam element is derived based on the principle of stationary total potential energy for geometrically nonlinear analysis of space frames. A new tangent stiffness matrix, which allows for high order effects of element deformations, replaces the conventional incremental secant stiffness matrix. Two deformation stiffness matrices due to the variation of axial force and bending moments are included in the tangent stiffness. They are functions of element deformations and incorporate the coupling among axial, lateral and torsional deformations. A correction matrix is added to the tangent stiffness matrix to make displacement derivatives equivalent to the commutative rotational degrees of freedom. Numerical examples show that the proposed dement is accurate and efficient in predicting the nonlinear behavior, such as axial-torsional and flexural-torsional buckling, of space frames even when fewer elements are used to model a member.

Super-resolution reconstruction for license plate images of moving vehicles

A novel reconstruction method to improve the recognition of license plate texts of moving vehicles in real traffic videos is proposed, which fuses complimentary information among low resolution （LR） images to yield a high resolution （HR） image. Based on the regularization super-resolution （SR） reconstruction schemes, this paper first introduces a residual gradient （RG） term as a new regularization term to improve the quality of the reconstructed image. Moreover, L1 norm is used to measure the residual data （RD） term and the RG term in order to improve the robustness of the proposed method. Finally, the steepest descent method is exploited to solve the energy functional. Simulated and real acquired video sequence experiments show the effectiveness and practicability of the proposed method and demonstrate its superiority over the bi-cubic interpolation and discontinuity adaptive Markov random field （DAMRF） SR method in both signal to noise ratios （SNR） and visual effects.

REFINED HYBRID MINDLIN PLATE ELEMENT FOR GEOMETRICALLY NON LINEAR ANALYSIS

Based upon a generalized variational principle, which relaxed the inter element continuity requirements, a novel refined hybrid Mindlin plate element is developed, its non linear element stiffness matrices are decomposed into a series of matrices with respect to the assumed strain modes. The formulation presented in this paper is different from any other non linear mixed/hybrid element formulation all successful experience of linear hybrid formulation is absorbed into the formulation(adding non conforming modes and realizing orthogonalization) Numerical results show that the present approach is more effective than any other non linear hybrid element formulation over the accuracy and computational efficiency. In addition, non conforming modes can also overcome the shear locking effect.