EDU-GAN:Edge Enhancement Generative Adversarial Networks with Dual-Domain Discriminators for Inscription Images Denoising

Recovering high-quality inscription images from unknown and complex inscription noisy images is a challenging research issue.Different fromnatural images,character images pay more attention to stroke information.However,existingmodelsmainly consider pixel-level informationwhile ignoring structural information of the character,such as its edge and glyph,resulting in reconstructed images with mottled local structure and character damage.To solve these problems,we propose a novel generative adversarial network(GAN)framework based on an edge-guided generator and a discriminator constructed by a dual-domain U-Net framework,i.e.,EDU-GAN.Unlike existing frameworks,the generator introduces the edge extractionmodule,guiding it into the denoising process through the attention mechanism,which maintains the edge detail of the restored inscription image.Moreover,a dual-domain U-Net-based discriminator is proposed to learn the global and local discrepancy between the denoised and the label images in both image and morphological domains,which is helpful to blind denoising tasks.The proposed dual-domain discriminator and generator for adversarial training can reduce local artifacts and keep the denoised character structure intact.Due to the lack of a real-inscription image,we built the real-inscription dataset to provide an effective benchmark for studying inscription image denoising.The experimental results show the superiority of our method both in the synthetic and real-inscription datasets.

Bacterial Cellulose/Zwitterionic Dual-network Porous Gel Polymer Electrolytes with High Ionic Conductivity

Bacterial cellulose(BC)was innovatively combined with zwitterionic copolymer acrylamide and sulfobetaine methacrylic acid ester[P(AM-co-SBMA)]to build a dual-network porous structure gel polymer electrolytes(GPEs)with high ionic conductivity.The dual network structure BC/P(AM-co-SBMA)gels were formed by a simple one-step polymerization method.The results show that ionic conductivity of BC/P(AM-co-SBMA)GPEs at the room temperature are 3.2×10^(-2) S/cm@1 M H_(2)SO_(4),4.5×10^(-2) S/cm@4 M KOH,and 3.6×10^(-2) S/cm@1 M NaCl,respectively.Using active carbon(AC)as the electrodes,BC/P(AM-co-SBMA)GPEs as both separator and electrolyte matrix,and 4 M KOH as the electrolyte,a symmetric solid supercapacitors(SSC)(AC-GPE-KOH)was assembled and testified.The specific capacitance of AC electrode is 173 F/g and remains 95.0%of the initial value after 5000 cycles and 86.2%after 10,000 cycles.

Learning Dual-Domain Calibration and Distance-Driven Correlation Filter:A Probabilistic Perspective for UAV Tracking

Unmanned Aerial Vehicle(UAV)tracking has been possible because of the growth of intelligent information technology in smart cities,making it simple to gather data at any time by dynamically monitoring events,people,the environment,and other aspects in the city.The traditional filter creates a model to address the boundary effect and time filter degradation issues in UAV tracking operations.But these methods ignore the loss of data integrity terms since they are overly dependent on numerous explicit previous regularization terms.In light of the aforementioned issues,this work suggests a dual-domain Jensen-Shannon divergence correlation filter(DJSCF)model address the probability-based distance measuring issue in the event of filter degradation.The two-domain weighting matrix and JS divergence constraint are combined to lessen the impact of sample imbalance and distortion.Two new tracking models that are based on the perspectives of the actual probability filter distribution and observation probability filter distribution are proposed to translate the statistical distance in the online tracking model into response fitting.The model is roughly transformed into a linear equality constraint issue in the iterative solution,which is then solved by the alternate direction multiplier method(ADMM).The usefulness and superiority of the suggested strategy have been shown by a vast number of experimental findings.

A Dual Domain Robust Reversible Watermarking Algorithm for Frame Grouping Videos Using Scene Smoothness

The proposed robust reversible watermarking algorithm addresses the compatibility challenges between robustness and reversibility in existing video watermarking techniques by leveraging scene smoothness for frame grouping videos.Grounded in the H.264 video coding standard,the algorithm first employs traditional robust watermark stitching technology to embed watermark information in the low-frequency coefficient domain of the U channel.Subsequently,it utilizes histogram migration techniques in the high-frequency coefficient domain of the U channel to embed auxiliary information,enabling successful watermark extraction and lossless recovery of the original video content.Experimental results demonstrate the algorithm’s strong imperceptibility,with each embedded frame in the experimental videos achieving a mean peak signal-to-noise ratio of 49.3830 dB and a mean structural similarity of 0.9996.Compared with the three comparison algorithms,the performance of the two experimental indexes is improved by 7.59%and 0.4%on average.At the same time,the proposed algorithm has strong robustness to both offline and online attacks:In the face of offline attacks,the average normalized correlation coefficient between the extracted watermark and the original watermark is 0.9989,and the average bit error rate is 0.0089.In the face of online attacks,the normalized correlation coefficient between the extracted watermark and the original watermark is 0.8840,and the mean bit error rate is 0.2269.Compared with the three comparison algorithms,the performance of the two experimental indexes is improved by 1.27%and 18.16%on average,highlighting the algorithm’s robustness.Furthermore,the algorithm exhibits low computational complexity,with the mean encoding and the mean decoding time differentials during experimental video processing being 3.934 and 2.273 s,respectively,underscoring its practical utility.

Adaptive Video Dual Domain Watermarking Scheme Based on PHT Moment and Optimized Spread Transform Dither Modulation

To address the challenges of video copyright protection and ensure the perfect recovery of original video,we propose a dual-domain watermarking scheme for digital video,inspired by Robust Reversible Watermarking(RRW)technology used in digital images.Our approach introduces a parameter optimization strategy that incre-mentally adjusts scheme parameters through attack simulation fitting,allowing for adaptive tuning of experimental parameters.In this scheme,the low-frequency Polar Harmonic Transform(PHT)moment is utilized as the embedding domain for robust watermarking,enhancing stability against simulation attacks while implementing the parameter optimization strategy.Through extensive attack simulations across various digital videos,we identify the optimal low-frequency PHT moment using adaptive normalization.Subsequently,the embedding parameters for robust watermarking are adaptively adjusted to maximize robustness.To address computational efficiency and practical requirements,the unnormalized high-frequency PHT moment is selected as the embedding domain for reversible watermarking.We optimize the traditional single-stage extended transform dithering modulation(STDM)to facilitate multi-stage embedding in the dual-domain watermarking process.In practice,the video embedded with a robust watermark serves as the candidate video.This candidate video undergoes simulation according to the parameter optimization strategy to balance robustness and embedding capacity,with adaptive determination of embedding strength.The reversible watermarking is formed by combining errors and other information,utilizing recursive coding technology to ensure reversibility without attacks.Comprehensive analyses of multiple performance indicators demonstrate that our scheme exhibits strong robustness against Common Signal Processing(CSP)and Geometric Deformation(GD)attacks,outperforming other advanced video watermarking algorithms under similar conditions of invisibility,reversibility,and embedding capacity.This underscores the effectiveness and feasibility of our attack simulation fitting strategy.

Robust,self-adhesive,and low-contact impedance polyvinyl alcohol/polyacrylamide dual-network hydrogel semidry electrode for biopotential signal acquisition

Herein,we fabricated a flexible semidry electrode with excellent mechanical performance,satisfactory self-adhesiveness,and low-contact impedance using physical/chemical crosslinked polyvinyl alcohol/polyacrylamide dual-network hydrogels(PVA/PAM DNHs)as an efficient saline reservoir.The resultant PVA/PAM DNHs showed admirable adhesive and compliance to the hairy scalp,facilitating the establishment of a robust electrode/skin interface for biopotential signal transmission.Moreover,the PVA/PAM DNHs steadily released trace saline onto the scalp to achieve the minimized potential drift(1.47±0.39 mV/min)and low electrode–scalp impedance(18.2±8.9 kΩ@10 Hz).More importantly,the application feasibility of real-world brain−computer interfaces(BCIs)was preliminarily validated by 10 participants using two classic BCI paradigms.The mean temporal cross-correlation coefficients between the semidry and wet electrodes in the eyes open/closed and the N200 speller paradigms are 0.919±0.054 and 0.912±0.050,respectively.Both electrodes demonstrate anticipated neuroelectrophysiological responses with similar patterns.This semidry electrode could also effectively capture robust P-QRS-T peaks during electrocardiogram recording.Considering their outstanding advantages of fast setup,user-friendliness,and robust signals,the proposed PVA/PAM DNH-based electrode is a promising alternative to wet electrodes in biopotential signal acquisition.

A lightweight and high compressive resistance thermal insulation material with dual-network structure

Ceramic fibrous aerogels are highly desirable for thermal management materials due to their high porosity,excellent elasticity,thermal conductivity,and good thermal resistance.However,the fabrication of nanofibrous aerogel with super-elasticity and good shape retention at the same time has remained challenging.To meet the requirements,a novel anisotropy nanofibrous-granular aerogel with a quasi-layered multi-arch-like and hierarchical-cellular structure is designed and prepared by vacuum-filtration-assisted freeze-drying and sintering.The quasi-layered multi-arch and flexible nanofibers endowed the aerogels with excellent mechanical robustness(ultimate stress up to 60 kPa with strain 60%)and super-elasticity with recoverable compression strain up to 60%.The introduced SiO_(2) aerogel nanoparticles and nanofibers are assembled into an arch-like structure and become the connection point of adjacent nanofibers,which endows low thermal conductivity(0.024 mW/(m·K))of composite aerogel.This novel strategy provides a fresh perspective for the preparation of nanofibrous aerogel with robust mechanical in thermal insulation and other fields.

Dual-domain and Multiscale Fusion Deep Neural Network for PPG Biometric Recognition

Photoplethysmography(PPG)biometrics have received considerable attention.Although deep learning has achieved good performance for PPG biometrics,several challenges remain open:1)How to effectively extract the feature fusion representation from time and frequency PPG signals.2)How to effectively capture a series of PPG signal transition information.3)How to extract timevarying information from one-dimensional time-frequency sequential data.To address these challenges,we propose a dual-domain and multiscale fusion deep neural network(DMFDNN)for PPG biometric recognition.The DMFDNN is mainly composed of a two-branch deep learning framework for PPG biometrics,which can learn the time-varying and multiscale discriminative features from the time and frequency domains.Meanwhile,we design a multiscale extraction module to capture transition information,which consists of multiple convolution layers with different receptive fields for capturing multiscale transition information.In addition,the dual-domain attention module is proposed to strengthen the domain of greater contributions from time-domain and frequency-domain data for PPG biometrics.Experiments on the four datasets demonstrate that DMFDNN outperforms the state-of-the-art methods for PPG biometrics.

Self-healing Behavior of Ethylene Propylene Diene Rubbers Based on Ionic Association

To meet the increasing demand for safe, environmentally friendly and high-performance smart materials, self-healing rubbers are highly desired. Here, the self-healing performance of ethylene propylene diene monomer rubber (EPDM) is reported, which was designed by graft-polymerization of zinc dimethacrylate (ZDMA) onto rubber chains to form a reversible ionic cross-linked network. Single ionic cross-linked network and dual network, combining covalent and ionic cross-links, could be tuned by controlling vulcanization process to achieve tailorable mechanical and self-healing properties. It was found that ionic cross-linked EPDM showed a recovery of more than 95% of the original mechanical strength through a healing process of 1 h at 100 °C. The covalent cross-links could improve mechanical properties but block self-healing. Adding 50 wt% liquid rubber to “dry” EPDM could effectively enhance self-healing capability of the dual cross-linked network and the healed tensile strength could reach 0.9 MPa. A compromise between mechanical performance and healing capability could be potentially tailored by controlling vulcanization process and liquid rubber content.

Rhodamine Mechanophore Functionalized Mechanochromic Double Network Hydrogels with High Sensitivity to Stress

Mechanochromic hydrogels, a new class of stimuli-responsive soft materials, have potential applications in a number of fields such as damage reporting and stress/strain sensing. We prepared a novel mechanochromic hydrogel using a strategy that has been developed to prepare dual-network(DN) hydrogels. A hydrophobic rhodamine derivative(Rh mechanophore) was covalently incorporated into a first network as a cross-linker. This first network embedded with Rh mechanophore within the DN hydrogel was pre-stretched. This guaranteed that the stress could be transferred extensively to the Rh-crosslinked first network once the hydrogel was under an applied force. Interestingly, we found that the threshold stress required to activate the mechanochromism of the hydrogel was less than 200 kPa, and much less than those in previous reports. Moreover, because of the excellent sensitivity of the hydrogel to stress, the DN hydrogel exhibited reversible freezing-induced mechanochromism. Benefiting from the sensitivity of Rh mechanophore to both p H and force, the DN hydrogel showed p H-regulated mechanochromic behavior. Our experimental results indicate that the preparation strategy we used introduces sensitive mechanochromism into the hydrogel and preserves the advantageous mechanical properties of the DN hydrogel. These results will be beneficial to the design and preparation of mechanochromic hydrogels with high stress sensitivity, and foster their practical applications in a number of fields such as damage reporting and stress/strain sensing.

Topological network design toward high-performance vegetable oil-based elastomers

As a kind of bio-derived feedstock,vegetable oil(VO)shows great potential to replace petroleum-based monomers to develop sustainable polymer materials because of its easy availability,low cost,bio-renewable,and environmentally friendly nature.However,due to the high cross-linking density and amorphous nature,directly cured VOs generally tend to be brittle and weak.To date,it is still difficult to adopt VOs and their derivatives as structural materials to prepare high-performance elastomers.To address this important issue,amulti-scale topology design strategy was proposed in this work.First,topology regulation and functionalization of VO-based networks were realized by managing functional groups proportion during the bulk polymerization of epoxidized soybean oil with dimer fatty acids.Furthermore,a second polymer(SN)network was introduced into the VO-based network as a protective layer via interfacial cross-links.The generated VO-based elastomers(VOEs)exhibit unprecedented comprehensive properties(VO content≥70 wt.%,T_(g)as low as−24.4℃,toughness up to 6.8 MJ/m^(3)).Besides,the VOEs also exhibit excellent reprocessability and self-healing capability.Overall,this work developed a novel kind of VOEs with significant comprehensive advantages and provided important inspiration for the preparation of high-performance elastomers throughmulti-scale topology regulation.

Nanonet-/fiber-structured flexible ceramic membrane enabling dielectric energy storage

Ceramics are considered intrinsically brittle at macro scale due to the lack of slip mechanism and pre-existing defects,which greatly limits their potential applications in emerging fields including wearable electronic devices and flexible display.In this contribution,we developed BiFeO_(3)/SiO_(2) dual-networks with exceptional flexibility through a coupled electronetting/electrospun method.The hybrid nanostructured networks endow the material with high tensile strength(2.7 MPa),excellent flexibility(80%recoverable deformation),and robust fatigue resistance performance(maintain flexibility after a 1000-cyclic compress test).After in-situ compounded with dielectric polymer via a layer-by-layer solution casting method,the resultant three-dimensional(3D)composite film exhibits a twice higher dielectric constant(εr)than polyether imide(PEI)film.More importantly,the breakdown strength of the 3D composite film is almost the same as that of the PEI film,resulting in an enhanced energy density of~6.0 J/cm^(3) and a high efficiency of 80%at 4.58 MV/cm.The unique structure,combined with the excellent balance between mechanical and dielectric properties in flexible structures,is of critical significance to the design of flexible functional ceramics and broadening their applications in wearable electric devices.