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.

Strong coupling and catenary field enhancement in the hybrid plasmonic metamaterial cavity and TMDC monolayers

Strong coupling between resonantly matched surface plasmons of metals and excitons of quantum emitters results in the formation of new plasmon-exciton hybridized energy states.In plasmon-exciton strong coupling,plasmonic nanocavities play a significant role due to their ability to confine light in an ultrasmall volume.Additionally,two-dimensional transition metal dichalcogenides(TMDCs) have a significant exciton binding energy and remain stable at ambient conditions,making them an excellent alternative for investigating light-matter interactions.As a result,strong plasmon-exciton coupling has been reported by introducing a single metallic cavity.However,single nanoparticles have lower spatial confinement of electromagnetic fields and limited tunability to match the excitonic resonance.Here,we introduce the concept of catenary-shaped optical fields induced by plasmonic metamaterial cavities to scale the strength of plasmon-exciton coupling.The demonstrated plasmon modes of metallic metamaterial cavities offer high confinement and tunability and can match with the excitons of TMDCs to exhibit a strong coupling regime by tuning either the size of the cavity gap or thickness.The calculated Rabi splitting of Au-MoSe_2 and Au-WSe_2 heterostructures strongly depends on the catenary-like field enhancement induced by the Au cavity,resulting in room-temperature Rabi splitting ranging between 77.86 and 320 me V.These plasmonic metamaterial cavities can pave the way for manipulating excitons in TMDCs and operating active nanophotonic devices at ambient temperature.

Is recovery enhancement after gastric cancer surgery really a safe approach for elderly patients?

BACKGROUND This study aimed to evaluate the safety of enhanced recovery after surgery(ERAS)in elderly patients with gastric cancer(GC).AIM To evaluate the safety of ERAS in elderly patients with GC.METHODS The PubMed,EMBASE,and Cochrane Library databases were used to search for eligible studies from inception to April 1,2023.The mean difference(MD),odds ratio(OR)and 95%confidence interval(95%CI)were pooled for analysis.The quality of the included studies was evaluated using the Newcastle-Ottawa Scale scores.We used Stata(V.16.0)software for data analysis.RESULTS This study consists of six studies involving 878 elderly patients.By analyzing the clinical outcomes,we found that the ERAS group had shorter postoperative hospital stays(MD=-0.51,I2=0.00%,95%CI=-0.72 to-0.30,P=0.00);earlier times to first flatus(defecation;MD=-0.30,I²=0.00%,95%CI=-0.55 to-0.06,P=0.02);less intestinal obstruction(OR=3.24,I2=0.00%,95%CI=1.07 to 9.78,P=0.04);less nausea and vomiting(OR=4.07,I2=0.00%,95%CI=1.29 to 12.84,P=0.02);and less gastric retention(OR=5.69,I2=2.46%,95%CI=2.00 to 16.20,P=0.00).Our results showed that the conventional group had a greater mortality rate than the ERAS group(OR=0.24,I2=0.00%,95%CI=0.07 to 0.84,P=0.03).However,there was no statistically significant difference in major complications between the ERAS group and the conventional group(OR=0.67,I2=0.00%,95%CI=0.38 to 1.18,P=0.16).CONCLUSION Compared to those with conventional recovery,elderly GC patients who received the ERAS protocol after surgery had a lower risk of mortality.

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.

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.

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.

Guided-YNet: Saliency Feature-Guided Interactive Feature Enhancement Lung Tumor Segmentation Network

Multimodal lung tumor medical images can provide anatomical and functional information for the same lesion.Such as Positron Emission Computed Tomography(PET),Computed Tomography(CT),and PET-CT.How to utilize the lesion anatomical and functional information effectively and improve the network segmentation performance are key questions.To solve the problem,the Saliency Feature-Guided Interactive Feature Enhancement Lung Tumor Segmentation Network(Guide-YNet)is proposed in this paper.Firstly,a double-encoder single-decoder U-Net is used as the backbone in this model,a single-coder single-decoder U-Net is used to generate the saliency guided feature using PET image and transmit it into the skip connection of the backbone,and the high sensitivity of PET images to tumors is used to guide the network to accurately locate lesions.Secondly,a Cross Scale Feature Enhancement Module(CSFEM)is designed to extract multi-scale fusion features after downsampling.Thirdly,a Cross-Layer Interactive Feature Enhancement Module(CIFEM)is designed in the encoder to enhance the spatial position information and semantic information.Finally,a Cross-Dimension Cross-Layer Feature Enhancement Module(CCFEM)is proposed in the decoder,which effectively extractsmultimodal image features through global attention and multi-dimension local attention.The proposed method is verified on the lung multimodal medical image datasets,and the results showthat theMean Intersection overUnion(MIoU),Accuracy(Acc),Dice Similarity Coefficient(Dice),Volumetric overlap error(Voe),Relative volume difference(Rvd)of the proposed method on lung lesion segmentation are 87.27%,93.08%,97.77%,95.92%,89.28%,and 88.68%,respectively.It is of great significance for computer-aided diagnosis.

Synergistic enhancement of cathode/anode interfaces with high water-retentive organohydrogel enabling highly stable zinc ion batteries

Current aqueous battery electrolytes,including conve ntional hydrogel electrolytes,exhibit unsatisfactory water retention capabilities.The sustained water loss will lead to subsequent polarization and increased internal resistance,ultimately resulting in battery failure.Herein,a double network(DN) orga no hydrogel electrolyte based on dimethyl sulfoxide(DMSO)/H_(2)O binary solvent was proposed.Through directionally reconstructing hydrogen bonds and reducing active H_(2)O molecules,the water retention ability and cathode/anode interfaces were synergistic enhanced.As a result,the synthesized DN organohydrogel demonstrates exceptional water retention capabilities,retaining approximately 75% of its original weight even after the exposure to air for 20 days.The Zn MnO_(2) battery delivers an outstanding specific capacity of275 mA h g^(-1) at 1 C,impressive rate performance with 85 mA h g^(-1) at 30 C,and excellent cyclic stability(95% retention after 6000 cycles at 5 C).Zn‖Zn symmetric battery can cycle more than 5000 h at 1 mA cm^(-2) and 1 mA h cm^(-2) without short circuiting.This study will encourage the further development of functional organohydrogel electrolytes for advanced energy storage devices.

A Novel Multi-Stream Fusion Network for Underwater Image Enhancement

Due to the selective absorption of light and the existence of a large number of floating media in sea water, underwater images often suffer from color casts and detail blurs. It is therefore necessary to perform color correction and detail restoration. However,the existing enhancement algorithms cannot achieve the desired results. In order to solve the above problems, this paper proposes a multi-stream feature fusion network. First, an underwater image is preprocessed to obtain potential information from the illumination stream, color stream and structure stream by histogram equalization with contrast limitation, gamma correction and white balance, respectively. Next, these three streams and the original raw stream are sent to the residual blocks to extract the features. The features will be subsequently fused. It can enhance feature representation in underwater images. In the meantime, a composite loss function including three terms is used to ensure the quality of the enhanced image from the three aspects of color balance, structure preservation and image smoothness. Therefore, the enhanced image is more in line with human visual perception.Finally, the effectiveness of the proposed method is verified by comparison experiments with many stateof-the-art underwater image enhancement algorithms. Experimental results show that the proposed method provides superior results over them in terms of MSE,PSNR, SSIM, UIQM and UCIQE, and the enhanced images are more similar to their ground truth images.

Vein visualization enhancement by dual-wavelength phase-locked denoising technology

Visual near-infrared imaging equipment has broad applications in various fields such as venipuncture,facial injections,and safety verification due to its noncontact,compact,and portable design.Currently,most studies utilize near-infrared single-wavelength for image acquisition of veins.However,many substances in the skin,including water,protein,and melanin can create significant background noise,which hinders accurate detection.In this paper,we developed a dual-wavelength imaging system with phase-locked denoising technology to acquire vein image.The signals in the effective region are compared by using the absorption valley and peak of hemoglobin at 700nm and 940nm,respectively.The phase-locked denoising algorithm is applied to decrease the noise and interference of complex surroundings from the images.The imaging results of the vein are successfully extracted in complex noise environment.It is demonstrated that the denoising effect on hand veins imaging can be improved with 57.3%by using our dual-wavelength phase-locked denoising technology.Consequently,this work proposes a novel approach for venous imaging with dual-wavelengths and phase-locked denoising algorithm to extract venous imaging results in complex noisy environment better.

Unsupervised Multi-Expert Learning Model for Underwater Image Enhancement

Underwater image enhancement aims to restore a clean appearance and thus improves the quality of underwater degraded images.Current methods feed the whole image directly into the model for enhancement.However,they ignored that the R,G and B channels of underwater degraded images present varied degrees of degradation,due to the selective absorption for the light.To address this issue,we propose an unsupervised multi-expert learning model by considering the enhancement of each color channel.Specifically,an unsupervised architecture based on generative adversarial network is employed to alleviate the need for paired underwater images.Based on this,we design a generator,including a multi-expert encoder,a feature fusion module and a feature fusion-guided decoder,to generate the clear underwater image.Accordingly,a multi-expert discriminator is proposed to verify the authenticity of the R,G and B channels,respectively.In addition,content perceptual loss and edge loss are introduced into the loss function to further improve the content and details of the enhanced images.Extensive experiments on public datasets demonstrate that our method achieves more pleasing results in vision quality.Various metrics(PSNR,SSIM,UIQM and UCIQE) evaluated on our enhanced images have been improved obviously.

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.

Physics-Constrained Robustness Enhancement for Tree Ensembles Applied in Smart Grid

With the widespread use of machine learning(ML)technology,the operational efficiency and responsiveness of power grids have been significantly enhanced,allowing smart grids to achieve high levels of automation and intelligence.However,tree ensemble models commonly used in smart grids are vulnerable to adversarial attacks,making it urgent to enhance their robustness.To address this,we propose a robustness enhancement method that incorporates physical constraints into the node-splitting decisions of tree ensembles.Our algorithm improves robustness by developing a dataset of adversarial examples that comply with physical laws,ensuring training data accurately reflects possible attack scenarios while adhering to physical rules.In our experiments,the proposed method increased robustness against adversarial attacks by 100%when applied to real grid data under physical constraints.These results highlight the advantages of our method in maintaining efficient and secure operation of smart grids under adversarial conditions.

Finesse measurement for high-power optical enhancement cavity

Finesse is a critical parameter for describing the characteristics of an optical enhancement cavity(OEC). This paper first presents a review of finesse measurement techniques, including a comparative analysis of the advantages, disadvantages, and potential limitations of several main methods from both theoretical and practical perspectives. A variant of the existing method called the free spectral range(FSR) modulation method is proposed and compared with three other finesse measurement methods, i.e., the fast-switching cavity ring-down(CRD) method, the rapidly swept-frequency(SF) CRD method, and the ringing effect method. A high-power OEC platform with a high finesse of approximately 16000 is built and measured with the four methods. The performance of these methods is compared, and the results show that the FSR modulation method and the fast-switching CRD method are more suitable and accurate than the other two methods for high-finesse OEC measurements. The CRD method and the ringing effect method can be implemented in open loop using simple equipment and are easy to perform. Additionally, recommendations for selecting finesse measurement methods under different conditions are proposed, which benefit the development of OEC and its applications.

Image enhancement with intensity transformation on embedding space

In recent times,an image enhancement approach,which learns the global transformation function using deep neural networks,has gained attention.However,many existing methods based on this approach have a limitation:their transformation functions are too simple to imitate complex colour transformations between low-quality images and manually retouched high-quality images.In order to address this limitation,a simple yet effective approach for image enhancement is proposed.The proposed algorithm based on the channel-wise intensity transformation is designed.However,this transformation is applied to the learnt embedding space instead of specific colour spaces and then return enhanced features to colours.To this end,the authors define the continuous intensity transformation(CIT)to describe the mapping between input and output intensities on the embedding space.Then,the enhancement network is developed,which produces multi-scale feature maps from input images,derives the set of transformation functions,and performs the CIT to obtain enhanced images.Extensive experiments on the MIT-Adobe 5K dataset demonstrate that the authors’approach improves the performance of conventional intensity transforms on colour space metrics.Specifically,the authors achieved a 3.8%improvement in peak signal-to-noise ratio,a 1.8%improvement in structual similarity index measure,and a 27.5%improvement in learned perceptual image patch similarity.Also,the authors’algorithm outperforms state-of-the-art alternatives on three image enhancement datasets:MIT-Adobe 5K,Low-Light,and Google HDRþ.

More Than Lightening:A Self-Supervised Low-Light Image Enhancement Method Capable for Multiple Degradations

Low-light images suffer from low quality due to poor lighting conditions,noise pollution,and improper settings of cameras.To enhance low-light images,most existing methods rely on normal-light images for guidance but the collection of suitable normal-light images is difficult.In contrast,a self-supervised method breaks free from the reliance on normal-light data,resulting in more convenience and better generalization.Existing self-supervised methods primarily focus on illumination adjustment and design pixel-based adjustment methods,resulting in remnants of other degradations,uneven brightness and artifacts.In response,this paper proposes a self-supervised enhancement method,termed as SLIE.It can handle multiple degradations including illumination attenuation,noise pollution,and color shift,all in a self-supervised manner.Illumination attenuation is estimated based on physical principles and local neighborhood information.The removal and correction of noise and color shift removal are solely realized with noisy images and images with color shifts.Finally,the comprehensive and fully self-supervised approach can achieve better adaptability and generalization.It is applicable to various low light conditions,and can reproduce the original color of scenes in natural light.Extensive experiments conducted on four public datasets demonstrate the superiority of SLIE to thirteen state-of-the-art methods.Our code is available at https://github.com/hanna-xu/SLIE.

Non-dimensional analysis on blast wave propagation in foam concrete:Minimum thickness to avoid stress enhancement

Foam concrete is a prospective material in defense engineering to protect structures due to its high energy absorption capability resulted from the long plateau stage.However,stress enhancement rather than stress mitigation may happen when foam concrete is used as sacrificial claddings placed in the path of an incoming blast load.To investigate this interesting phenomenon,a one-dimensional difference model for blast wave propagation in foam concrete is firstly proposed and numerically solved by improving the second-order Godunov method.The difference model and numerical algorithm are validated against experimental results including both the stress mitigation and the stress enhancement.The difference model is then used to numerically analyze the blast wave propagation and deformation of material in which the effects of blast loads,stress-strain relation and length of foam concrete are considered.In particular,the concept of minimum thickness of foam concrete to avoid stress enhancement is proposed.Finally,non-dimensional analysis on the minimum thickness is conducted and an empirical formula is proposed by curve-fitting the numerical data,which can provide a reference for the application of foam concrete in defense engineering.

Hybrid Optimization Algorithm for Handwritten Document Enhancement

The Gannet Optimization Algorithm (GOA) and the Whale Optimization Algorithm (WOA) demonstrate strong performance;however, there remains room for improvement in convergence and practical applications. This study introduces a hybrid optimization algorithm, named the adaptive inertia weight whale optimization algorithm and gannet optimization algorithm (AIWGOA), which addresses challenges in enhancing handwritten documents. The hybrid strategy integrates the strengths of both algorithms, significantly enhancing their capabilities, whereas the adaptive parameter strategy mitigates the need for manual parameter setting. By amalgamating the hybrid strategy and parameter-adaptive approach, the Gannet Optimization Algorithm was refined to yield the AIWGOA. Through a performance analysis of the CEC2013 benchmark, the AIWGOA demonstrates notable advantages across various metrics. Subsequently, an evaluation index was employed to assess the enhanced handwritten documents and images, affirming the superior practical application of the AIWGOA compared with other algorithms.