High-resolution remote sensing images(HRSIs)are now an essential data source for gathering surface information due to advancements in remote sensing data capture technologies.However,their significant scale changes an...High-resolution remote sensing images(HRSIs)are now an essential data source for gathering surface information due to advancements in remote sensing data capture technologies.However,their significant scale changes and wealth of spatial details pose challenges for semantic segmentation.While convolutional neural networks(CNNs)excel at capturing local features,they are limited in modeling long-range dependencies.Conversely,transformers utilize multihead self-attention to integrate global context effectively,but this approach often incurs a high computational cost.This paper proposes a global-local multiscale context network(GLMCNet)to extract both global and local multiscale contextual information from HRSIs.A detail-enhanced filtering module(DEFM)is proposed at the end of the encoder to refine the encoder outputs further,thereby enhancing the key details extracted by the encoder and effectively suppressing redundant information.In addition,a global-local multiscale transformer block(GLMTB)is proposed in the decoding stage to enable the modeling of rich multiscale global and local information.We also design a stair fusion mechanism to transmit deep semantic information from deep to shallow layers progressively.Finally,we propose the semantic awareness enhancement module(SAEM),which further enhances the representation of multiscale semantic features through spatial attention and covariance channel attention.Extensive ablation analyses and comparative experiments were conducted to evaluate the performance of the proposed method.Specifically,our method achieved a mean Intersection over Union(mIoU)of 86.89%on the ISPRS Potsdam dataset and 84.34%on the ISPRS Vaihingen dataset,outperforming existing models such as ABCNet and BANet.展开更多
Conductive hydrogel-based stretchable electronics have been extensively investigated,among which strain sensors are the most prominently studied.While the mechanical properties significantly affect the performance of ...Conductive hydrogel-based stretchable electronics have been extensively investigated,among which strain sensors are the most prominently studied.While the mechanical properties significantly affect the performance of these devices,the systematic correlation between specific mechanical parameters and sensing performance remains rarely explored.This work compares the influences of Young’s modulus and mechanical hysteresis on the sensing performance between highly entangled PAM-Li and double-network PAM-Li-Agar-3 strain sensors.Owing to the brittle agar network,which imparts a higher Young’s modulus and pronounced mechanical hysteresis to the double-network PAMLi-Agar-3 hydrogel,the corresponding sensor requires a greater driving force for deformation and yields signals with poor reproducibility.In comparison,the PAM-Li hydrogel,characterized by highly entangled polymer chains,exhibits a lower Young’s modulus and negligible mechanical hysteresis.Consequently,signals from the PAM-Li strain sensor demonstrate enhanced sensitivity and stability.Therefore,this work demonstrates that a low Young’s modulus and minimal mechanical hysteresis are critical factors for achieving superior sensing performance in strain sensors,as systematically validated through comparative analyses across diverse application scenarios.展开更多
Owing to their good biocompatibility,polysaccharide hydrogels have broad application prospects in the field of flexible strain sensors.However,there are still significant challenges in the preparation of polysaccharid...Owing to their good biocompatibility,polysaccharide hydrogels have broad application prospects in the field of flexible strain sensors.However,there are still significant challenges in the preparation of polysaccharide hydrogels with good mechanical properties.MCA-Li Cl hydrogels were prepared by introducing methacrylated hyaluronic acid(Me HA)into the polymer network in the presence of acrylic acid(AA),acryloyloxyethyltrimethyl ammonium chloride(CATAC),and metal ions.The polymer network not only has a chemically cross-linked network and a tough network structure,but also benefits from a variety of supramolecular interactions,such as hydrogen bonding and coordination covalent bonding,resulting in excellent mechanical properties,with an elongation at break of 1390%,a tensile strength of up to 1200 k Pa,a toughness of 9.4546 MJ/m^(3),and adhesive properties towards various substrates.At the same time,the hydrogel has a high conductivity(5.33 mS/cm)and high strain-sensing sensitivity(Gauge factor=2.55).The flexible strain sensor assembled from the prepared MCA-Li Cl hydrogel can be used to detect human movements,from micro-expressions(smiles,swallowing)to pulse signals and other physiological activities,as well as large-scale joint movements(wrists,elbows,knees,fingers,etc.),realizing the real-time monitoring of full-scale human movements.The prepared hydrogels have potential applications in wearable devices,electronic skin,and strain-sensor components.展开更多
Silicon-based microring resonator sensors are promising components for lab-on-chip sensing systems.However,developing a microring resonator sensor with both high sensitivity and wide detectable range has remained chal...Silicon-based microring resonator sensors are promising components for lab-on-chip sensing systems.However,developing a microring resonator sensor with both high sensitivity and wide detectable range has remained challenging.Here,we experimentally demonstrate a high-sensitivity and wide-range subwavelength grating microring resonator sensor by leveraging its dispersion properties.展开更多
A coordination polymer{[Cd(H_(2)dpa)(bpy)]·3H_(2)O}_(n)(Cd-CP)was designed and hydrothermal synthesized based on 4-(2,4-dicarboxyphenoxy)phthalic acid(H_(4)dpa),2,2'-bipyridine(bpy)and Cd(NO_(3))_(2)·4H_...A coordination polymer{[Cd(H_(2)dpa)(bpy)]·3H_(2)O}_(n)(Cd-CP)was designed and hydrothermal synthesized based on 4-(2,4-dicarboxyphenoxy)phthalic acid(H_(4)dpa),2,2'-bipyridine(bpy)and Cd(NO_(3))_(2)·4H_(2)O.The structure was characterized by single-crystal X-ray diffraction,powder X-ray diffraction,elemental analysis,and infrared spectroscopy.Cd-CP belongs to the monoclinic crystal system with the P2_1/c space group and performs in a 1D double-chain structure.The adjacent double chains further form a 3D supramolecular network structure through hydrogen bonding.Thermogravimetric analysis shows that Cd-CP has good thermal stability.Fluorescence analysis showed that Cd-CP had good choosing selectively and was sensitive to metal ions(Fe^(3+)and Zn^(2+)),2,4,6-trinitrophenylhydrazine(TRI),and pyrimethanil(Pth).Interestingly,when Cd-CP was used for fluorescence detection of metal ions,it was found to have a fluorescence quenching effect on Fe^(3+)but had an obvious enhancement effect on Zn^(2+).Therefore,we designed an“on-off-on”logic gate.In addition,the mechanism of fluorescence sensing has been deeply explored.CCDC:2258625.展开更多
To address the temperature cross-talk issue in detecting heavy metal ions in natural waters, a highly-integrated and fully fiber-optic metal ion sensing system capable of temperature-concentration decoupling measureme...To address the temperature cross-talk issue in detecting heavy metal ions in natural waters, a highly-integrated and fully fiber-optic metal ion sensing system capable of temperature-concentration decoupling measurement has been designed. This system integrates a fluidic detection structure assisted by side-polished fibers(SPFs) with a Sagnac interferometer.展开更多
Phase singularities(PSs)in topological darkness-based sensors have received significant attention in optical sensing due to their rapid,ultra-sensitive,and label-free detection capabilities.Here,we present both experi...Phase singularities(PSs)in topological darkness-based sensors have received significant attention in optical sensing due to their rapid,ultra-sensitive,and label-free detection capabilities.Here,we present both experimental and theoretical investigations of an ultrasensitive and multiplexed phase-sensitive sensor utilizing dual topological PSs in the visible and near-infrared regions.This sensor uses a simple structure,which consists of an ultra-thin highly absorbing film deposited on a metal substrate.We demonstrate the achievement of dual-polarization darkness points for s-and p-polarizations at different incident angles.Furthermore,we theoretically explain the double topological PSs accompanied by a perfect±π-jump near a zero-reflection point,based on the temporal coupled-mode formalism.To validate its multifunctional capabilities,humidity sensing tests were carried out.The results demonstrate that the sensor has a detection limit reaching the level of 0.12‰.These findings go beyond the scope of conventional interference optical coatings and highlight the potential applications of this technology in gas sensing and biosensing domains.展开更多
While algorithms have been created for land usage in urban settings,there have been few investigations into the extraction of urban footprint(UF).To address this research gap,the study employs several widely used imag...While algorithms have been created for land usage in urban settings,there have been few investigations into the extraction of urban footprint(UF).To address this research gap,the study employs several widely used image classification method classified into three categories to evaluate their segmentation capabilities for extracting UF across eight cities.The results indicate that pixel-based methods only excel in clear urban environments,and their overall accuracy is not consistently high.RF and SVM perform well but lack stability in object-based UF extraction,influenced by feature selection and classifier performance.Deep learning enhances feature extraction but requires powerful computing and faces challenges with complex urban layouts.SAM excels in medium-sized urban areas but falters in intricate layouts.Integrating traditional and deep learning methods optimizes UF extraction,balancing accuracy and processing efficiency.Future research should focus on adapting algorithms for diverse urban landscapes to enhance UF extraction accuracy and applicability.展开更多
We explore the parity-time(PT)-symmetry breaking transition in a dimer circuit composed of two RLC resonators that are weakly coupled via an inductor.The energy behavior of this dimer circuit is reflected in the split...We explore the parity-time(PT)-symmetry breaking transition in a dimer circuit composed of two RLC resonators that are weakly coupled via an inductor.The energy behavior of this dimer circuit is reflected in the splitting or degeneracy of the systems eigenfrequencies as the gain–loss strength varies.Its dynamical properties can be described by a non-Hermitian Hamiltonian.The eigenfrequency spectrum of the system is divided by two critical points into three distinct regions:the symmetric region,the oscillatory growth region,and the fully exponential growth region.Building upon previous work on implementing the exceptional point(EP)in circuit systems,our study focuses on further exploring the variation patterns of circuit eigenfrequencies near the EP under weak coupling conditions.In addition,we construct a corresponding Dirac point(DP)circuit system for comparison.By leveraging the unique physical properties near both the EP and the DP,we further propose potential practical applications.Using perturbation theory and system simulations,we demonstrate that the square-root eigenfrequency splitting near the EP significantly enhances the sensitivity to small external perturbations,compared to the linear splitting behavior near the DP.This study presents promising prospects for next-generation sensing technologies.展开更多
Traditional resistive semiconductor gas sensors suffer from high operating temperatures and poor selectivity.Thus,to address these issues,a highly selective nitrogen dioxide(NO_(2))sensor based on lead sulfide(PbS)qua...Traditional resistive semiconductor gas sensors suffer from high operating temperatures and poor selectivity.Thus,to address these issues,a highly selective nitrogen dioxide(NO_(2))sensor based on lead sulfide(PbS)quantum dots(QDs)–lead molybdate(PbMoO_(4))–molybdenum disulfide(MoS_(2))ternary nanocomposites operating at room temperature was fabricated herein.The ternary nanocomposites were synthesized using an in situ method,yielding Pb S QDs with an average size of~10 nm and PbMoO_(4)nanoparticles in the 10-to 20-nm range,uniformly distributed on ultrathin MoS_(2)nanosheets with an average thickness of~7 nm.The optimized sensor demonstrated a significant improvement in response to 1 ppm NO_(2)at 25℃,achieving a response of 44.5%,which was approximately five times higher than that of the pure MoS_(2)-based sensor(8.5%).The sensor also achieved relatively short response/recovery times and full recovery properties.Notably,the optimal sensor displayed extraordinary selectivity toward NO_(2),showing negligible responses to different interfering gases.Density functional theory(DFT)calculations were conducted to elucidate the underlying sensing mechanism,which was attributed to the enhanced specific surface area,the receptor function of both PbS QDs and PbMoO_(4)nanoparticles,and the transducer function of MoS_(2) nanosheets.展开更多
Source identification and deformation analysis of disaster bodies are the main contents of high-steep slope risk assessment,the establishment of high-precision model and the quantification of the fine geometric featur...Source identification and deformation analysis of disaster bodies are the main contents of high-steep slope risk assessment,the establishment of high-precision model and the quantification of the fine geometric features of the slope are the prerequisites for the above work.In this study,based on the UAV remote sensing technology in acquiring refined model and quantitative parameters,a semi-automatic dangerous rock identification method based on multi-source data is proposed.In terms of the periodicity UAV-based deformation monitoring,the monitoring accuracy is defined according to the relative accuracy of multi-temporal point cloud.Taking a high-steep slope as research object,the UAV equipped with special sensors was used to obtain multi-source and multitemporal data,including high-precision DOM and multi-temporal 3D point clouds.The geometric features of the outcrop were extracted and superimposed with DOM images to carry out semi-automatic identification of dangerous rock mass,realizes the closed-loop of identification and accuracy verification;changing detection of multi-temporal 3D point clouds was conducted to capture deformation of slope with centimeter accuracy.The results show that the multi-source data-based semiautomatic dangerous rock identification method can complement each other to improve the efficiency and accuracy of identification,and the UAV-based multi-temporal monitoring can reveal the near real-time deformation state of slopes.展开更多
The service life of refractory brick in the slag tapping hole of gasifiers is a significant concern for long-term and stable operation.This study examined the damage mechanism of high chromia refractory of four commer...The service life of refractory brick in the slag tapping hole of gasifiers is a significant concern for long-term and stable operation.This study examined the damage mechanism of high chromia refractory of four commercial coal-water slurry gasifiers with their corresponding gasification coal samples and the corroded refractory bricks in the slag tapping hole of the gasifier.The slag characteristic,including crystallization and viscosity-temperature of four gasification coal samples were analyzed.The results revealed that the low viscosity slag could lead to more severe damage to refractory bricks.Given the risk of slag crystallization,it is recommended to establish a safe slag tapping temperature range should be set as tICT(initial crystallization temperature)−t_(2.5) when tICT is higher than t_(25).Upon examining interior morphology of these corroded refractory bricks,some cracks were observed within them.The chemical composition of molten slag was analyzed using SEM-EDS.However,XRD results found no spinel containing zirconium in these cracks.This suggests that the emergence of these cracks are mainly attributed to the molten slag penetration and the subsequent reaction with the refractory material.The difference in thermal expansion between the newly formed substances and refractory material is critical in forming these cracks.Furthermore,SEM-EDS analysis was also conducted on the slag-aggregate and the slag-matrix interface.The results reveal that the reduction in Cr_(2)O_(3) content is the earliest characteristic of damage in high chromia refractories.A proposed damage mechanism of refractory brick suggests that the matrix and aggregate of high chromia refractory are initially compromised because of the reduced Cr_(2)O_(3) content.Subsequently,the molten slag penetrates the interior of the refractory brick,forming new substances,leading to damage caused by the difference in thermal expansion between the new substances and the refractory brick.Understanding and preventing the reduction of Cr_(2)O_(3) content is vital to prolonging the service life of refractory brick in the slag tapping hole of the gasifier based on this damage mechanism.展开更多
High-entropy materials(HEMs)have attracted considerable research attention in battery applications due to exceptional properties such as remarkable structural stability,enhanced ionic conductivity,superior mechanical ...High-entropy materials(HEMs)have attracted considerable research attention in battery applications due to exceptional properties such as remarkable structural stability,enhanced ionic conductivity,superior mechanical strength,and outstanding catalytic activity.These distinctive characteristics render HEMs highly suitable for various battery components,such as electrodes,electrolytes,and catalysts.This review systematically examines recent advances in the application of HEMs for energy storage,beginning with fundamental concepts,historical development,and key definitions.Three principal categories of HEMs,namely high-entropy alloys,high-entropy oxides,and highentropy MXenes,are analyzed with a focus on electrochemical performance metrics such as specific capacity,energy density,cycling stability,and rate capability.The underlying mechanisms by which these materials enhance battery performance are elucidated in the discussion.Furthermore,the pivotal role of machine learning in accelerating the discovery and optimization of novel high-entropy battery materials is highlighted.The review concludes by outlining future research directions and potential breakthroughs in HEM-based battery technologies.展开更多
Platinum group metals have high melting points,strong corrosion resistance,stable chemical properties,and low oxygen permeability in high-temperature oxygen-containing environments.As thermal protective coating materi...Platinum group metals have high melting points,strong corrosion resistance,stable chemical properties,and low oxygen permeability in high-temperature oxygen-containing environments.As thermal protective coating materials,they have gained essential applications in the aerospace field and have excellent prospects for application in frontier military fields,such as protecting hot-end components of hypersonic aircraft.This research reviewed the latest research progress of platinum group metal coatings with hightemperature oxidation resistance,including coating preparation techniques,oxidation failure,and alloying modification.The leading preparation techniques of current platinum group metal coatings were discussed,as well as the advantages and disadvantages of various existing preparation techniques.Besides,the intrinsic properties,failure forms,and failure mechanisms of coatings of single platinum group metal in high-temperature oxygen-containing environments were analyzed.On this basis,the necessity,main methods,and main achievements of alloying modification of platinum group metals were summarized.Finally,the future development of platinum group coatings with high-temperature oxidation resistance was discussed and prospected.展开更多
Motor imbalance is a critical failure mode in rotating machinery,potentially causing severe equipment damage if undetected.Traditional vibration-based diagnostic methods rely on direct sensor contact,leading to instal...Motor imbalance is a critical failure mode in rotating machinery,potentially causing severe equipment damage if undetected.Traditional vibration-based diagnostic methods rely on direct sensor contact,leading to installation challenges and measurement artifacts that can compromise accuracy.This study presents a novel radar-based framework for non-contact motor imbalance detection using 24 GHz continuous-wave radar.A dataset of 1802 experimental trials was sourced,covering four imbalance levels(0,10,20,30 g)across varying motor speeds(500–1500 rpm)and load torques(0–3 Nm).Dual-channel in-phase and quadrature radar signals were captured at 10,000 samples per second for 30-s intervals,preserving both amplitude and phase information for analysis.A multi-domain feature extraction methodology captured imbalance signatures in time,frequency,and complex signal domains.From 65 initial features,statistical analysis using Kruskal–Wallis tests identified significant descriptors,and recursive feature elimination with Random Forest reduced the feature set to 20 dimensions,achieving 69%dimensionality reduction without loss of performance.Six machine learning algorithms,Random Forest,Extra Trees Classifier,Extreme Gradient Boosting,Categorical Boosting,Support Vector Machine with radial basis function kernel,and k-Nearest Neighbors were evaluated with grid-search hyperparameter optimization and five-fold cross-validation.The Extra Trees Classifier achieved the best performance with 98.52%test accuracy,98%cross-validation accuracy,and minimal variance,maintaining per-class precision and recall above 97%.Its superior performance is attributed to its randomized split selection and full bootstrapping strategy,which reduce variance and overfitting while effectively capturing the nonlinear feature interactions and non-normal distributions present in the dataset.The model’s average inference time of 70 ms enables near real-time deployment.Comparative analysis demonstrates that the radar-based framework matches or exceeds traditional contact-based methods while eliminating their inherent limitations,providing a robust,scalable,and noninvasive solution for industrial motor condition monitoring,particularly in hazardous or space-constrained environments.展开更多
In this study,using 3,5‑di(3′,5′‑dicarboxylphenyl)‑1H‑1,2,4‑triazole(H4L)as ligands,a gadolinia‑based organic framework complex{[GdNa(L)(H_(2)O)3]·2H_(2)O}_(n)(Gd‑Na‑MOF)was successfully designed and synthesize...In this study,using 3,5‑di(3′,5′‑dicarboxylphenyl)‑1H‑1,2,4‑triazole(H4L)as ligands,a gadolinia‑based organic framework complex{[GdNa(L)(H_(2)O)3]·2H_(2)O}_(n)(Gd‑Na‑MOF)was successfully designed and synthesized by hydrothermal method.The structure and properties were systematically characterized and tested by techniques such as single‑crystal X‑ray diffraction,powder X‑ray diffraction,thermogravimetric analysis,infrared spectroscopy,and fluorescence spectroscopy.The results indicate that this complex has a unique 3D structure,excellent thermal stability,and outstanding luminescent performance.Based on its luminescent properties,a polymer‑embedding method was employed to fabricate the Gd‑Na‑MOF into a flexible,washable composite fluorescent film,Gd‑Na‑MOF@PMMA/BMA(PMMA=polymethyl methacrylate,BMA=butyl methacrylate).This fluorescent film exhibited highly sensitive recognition capability for tyramine,with a low detection limit of 1.66μmol·L^(-1).It was used for the detection of tyramine in bananas,with a recovery rate of 96.92%‑100.26%.CCDC:2466949.展开更多
In this study,we investigated the effect of high-solubility wheat gluten proteins(hs-WGP) prepared by pH-cycle treatment on soybean isolate-based extrudates.The results showed that the addition of hs-WGP can improve t...In this study,we investigated the effect of high-solubility wheat gluten proteins(hs-WGP) prepared by pH-cycle treatment on soybean isolate-based extrudates.The results showed that the addition of hs-WGP can improve textural properties of soybean isolate-based extrudate via regulating the hardness to appropriate range.At molecular level,it was further found that the hs-WGP was cross-linked with soy protein isolate mainly through hydrogen bonding and disulfide bonding,and the spherical protein of soy protein isolate was wrapped by the hs-WGP,which weakened the thermal unfolding of globular proteins during heating process,reduced the degree of heat-curing gel,resulted in a reduction in hardness.In addition,hs-WGP/soybean protein composite extrudates possessed a more balanced amino acid composition,which have a positive impact on meat analogues at the nutritional level.展开更多
Azobenzene-winged phenanthrolines(L1 and L2)were designed,synthesized,and fully characterized.Ligand L1 forms an in-situ cobalt complex,which has been effectively employed as a circular dichroism(CD)-active chiral sen...Azobenzene-winged phenanthrolines(L1 and L2)were designed,synthesized,and fully characterized.Ligand L1 forms an in-situ cobalt complex,which has been effectively employed as a circular dichroism(CD)-active chiral sensor.The resulting ternary complex(L1-Co^(2+)-amino alcohol)exhibits pronounced exciton-coupled circular dichroism(ECCD)signals at the characteristic azobenzene absorption bands.These signals arise from efficient chirality transfer from the chiral amino alcohol to the azobenzene chromophores,enabling the determination of the absolute configuration of chiral amino alcohols.Accordingly,the L1-Co^(2+)coordination system demonstrates considerably potential in chirality sensing applications.Remarkably,the induced ECCD signals are highly responsive to multiple external stimuli,including photoirradiation,solvent polarity,temperature,and redox conditions.In particular,temperature and redox changes can induce a reversible inversion of the ECCD signal,thereby establishing this system as a multifunctional,stimuli-responsive chiroptical molecular switch.展开更多
Vibrio harveyi,a Gram-negative bacterium ubiquitous in marine environments,is recognized as an opportunistic pathogen affecting various aquatic organisms such as fish,shrimp,and shellfish.To enhance its environmental ...Vibrio harveyi,a Gram-negative bacterium ubiquitous in marine environments,is recognized as an opportunistic pathogen affecting various aquatic organisms such as fish,shrimp,and shellfish.To enhance its environmental resilience and adaptive capacity,V.harveyi employs a complex quorum sensing mechanism to modulate its virulence factors,such as bioluminescence,biofilm formation,and motility.Therefore,targeting the quorum sensing of V.harveyi could be a promising strategy to develop novel approaches to ensure the microbial safety of seafood products.This study aims to evaluate the impact of curcumin-mediated photo/sonodynamic treatment on quorum sensing in V.harveyi and its regulated functions.The results indicate a significant decrease of luminescence in V.harveyi following curcumin-mediated photo/sonodynamic treatment.Correspondingly,the biofilm formation ability and bacterial motility of V.harveyi were also greatly impaired by the treatment.Notably,the production of reactive oxygen species in bacteria induced by the photo/sonodynamic treatment could be the underlying mechanism involved in the observed disruption of quorum sensing.These findings underscore the great potential of photo/sonodynamic treatment as a promising strategy to disrupt quorum sensing and mitigate the virulence of V.harveyi,thereby contributing to the development of effective control strategies against this pervasive pathogen.展开更多
Accurate and efficient detection of building changes in remote sensing imagery is crucial for urban planning,disaster emergency response,and resource management.However,existing methods face challenges such as spectra...Accurate and efficient detection of building changes in remote sensing imagery is crucial for urban planning,disaster emergency response,and resource management.However,existing methods face challenges such as spectral similarity between buildings and backgrounds,sensor variations,and insufficient computational efficiency.To address these challenges,this paper proposes a novel Multi-scale Efficient Wavelet-based Change Detection Network(MewCDNet),which integrates the advantages of Convolutional Neural Networks and Transformers,balances computational costs,and achieves high-performance building change detection.The network employs EfficientNet-B4 as the backbone for hierarchical feature extraction,integrates multi-level feature maps through a multi-scale fusion strategy,and incorporates two key modules:Cross-temporal Difference Detection(CTDD)and Cross-scale Wavelet Refinement(CSWR).CTDD adopts a dual-branch architecture that combines pixel-wise differencing with semanticaware Euclidean distance weighting to enhance the distinction between true changes and background noise.CSWR integrates Haar-based Discrete Wavelet Transform with multi-head cross-attention mechanisms,enabling cross-scale feature fusion while significantly improving edge localization and suppressing spurious changes.Extensive experiments on four benchmark datasets demonstrate MewCDNet’s superiority over comparison methods:achieving F1 scores of 91.54%on LEVIR,93.70%on WHUCD,and 64.96%on S2Looking for building change detection.Furthermore,MewCDNet exhibits optimal performance on the multi-class⋅SYSU dataset(F1:82.71%),highlighting its exceptional generalization capability.展开更多
基金provided by the Science Research Project of Hebei Education Department under grant No.BJK2024115.
文摘High-resolution remote sensing images(HRSIs)are now an essential data source for gathering surface information due to advancements in remote sensing data capture technologies.However,their significant scale changes and wealth of spatial details pose challenges for semantic segmentation.While convolutional neural networks(CNNs)excel at capturing local features,they are limited in modeling long-range dependencies.Conversely,transformers utilize multihead self-attention to integrate global context effectively,but this approach often incurs a high computational cost.This paper proposes a global-local multiscale context network(GLMCNet)to extract both global and local multiscale contextual information from HRSIs.A detail-enhanced filtering module(DEFM)is proposed at the end of the encoder to refine the encoder outputs further,thereby enhancing the key details extracted by the encoder and effectively suppressing redundant information.In addition,a global-local multiscale transformer block(GLMTB)is proposed in the decoding stage to enable the modeling of rich multiscale global and local information.We also design a stair fusion mechanism to transmit deep semantic information from deep to shallow layers progressively.Finally,we propose the semantic awareness enhancement module(SAEM),which further enhances the representation of multiscale semantic features through spatial attention and covariance channel attention.Extensive ablation analyses and comparative experiments were conducted to evaluate the performance of the proposed method.Specifically,our method achieved a mean Intersection over Union(mIoU)of 86.89%on the ISPRS Potsdam dataset and 84.34%on the ISPRS Vaihingen dataset,outperforming existing models such as ABCNet and BANet.
基金supported by the National Natural Science Foundation of China(52303145,52403083)the Natural Science Foundation of Sichuan Province(2025ZNSFSC1400)supported by the start-up funding at Chengdu University(T202207)。
文摘Conductive hydrogel-based stretchable electronics have been extensively investigated,among which strain sensors are the most prominently studied.While the mechanical properties significantly affect the performance of these devices,the systematic correlation between specific mechanical parameters and sensing performance remains rarely explored.This work compares the influences of Young’s modulus and mechanical hysteresis on the sensing performance between highly entangled PAM-Li and double-network PAM-Li-Agar-3 strain sensors.Owing to the brittle agar network,which imparts a higher Young’s modulus and pronounced mechanical hysteresis to the double-network PAMLi-Agar-3 hydrogel,the corresponding sensor requires a greater driving force for deformation and yields signals with poor reproducibility.In comparison,the PAM-Li hydrogel,characterized by highly entangled polymer chains,exhibits a lower Young’s modulus and negligible mechanical hysteresis.Consequently,signals from the PAM-Li strain sensor demonstrate enhanced sensitivity and stability.Therefore,this work demonstrates that a low Young’s modulus and minimal mechanical hysteresis are critical factors for achieving superior sensing performance in strain sensors,as systematically validated through comparative analyses across diverse application scenarios.
基金financially supported by the National Natural Science Foundation of China(No.22271074)Natural Science Foundation of Hebei Province(Nos.B2023208042,B2022208032,B2021208066,E2024208084,and E2024208088)+2 种基金Science Research Project of Hebei Education Department(No.JZX2024013)Special Fund for Local Scientific and Technological Development under the Guidance of the Central Government(No.236Z3704G)Hebei Province High Level Talent Funding(No.A202001010)。
文摘Owing to their good biocompatibility,polysaccharide hydrogels have broad application prospects in the field of flexible strain sensors.However,there are still significant challenges in the preparation of polysaccharide hydrogels with good mechanical properties.MCA-Li Cl hydrogels were prepared by introducing methacrylated hyaluronic acid(Me HA)into the polymer network in the presence of acrylic acid(AA),acryloyloxyethyltrimethyl ammonium chloride(CATAC),and metal ions.The polymer network not only has a chemically cross-linked network and a tough network structure,but also benefits from a variety of supramolecular interactions,such as hydrogen bonding and coordination covalent bonding,resulting in excellent mechanical properties,with an elongation at break of 1390%,a tensile strength of up to 1200 k Pa,a toughness of 9.4546 MJ/m^(3),and adhesive properties towards various substrates.At the same time,the hydrogel has a high conductivity(5.33 mS/cm)and high strain-sensing sensitivity(Gauge factor=2.55).The flexible strain sensor assembled from the prepared MCA-Li Cl hydrogel can be used to detect human movements,from micro-expressions(smiles,swallowing)to pulse signals and other physiological activities,as well as large-scale joint movements(wrists,elbows,knees,fingers,etc.),realizing the real-time monitoring of full-scale human movements.The prepared hydrogels have potential applications in wearable devices,electronic skin,and strain-sensor components.
基金National Key Research and Development Program of China(2022YFB2803600)National Natural Science Foundation of China(61905022,62175080)+3 种基金Department of Science and Technology of Jilin Province(20240101338JC)Songshan Lake Materials Laboratory(2023SLABFK11)Science and Technology Planning Project of Shenzhen Municipality(CJGJZD20220517141202005)Hubei Provincial Program for Outstanding Young Talents。
文摘Silicon-based microring resonator sensors are promising components for lab-on-chip sensing systems.However,developing a microring resonator sensor with both high sensitivity and wide detectable range has remained challenging.Here,we experimentally demonstrate a high-sensitivity and wide-range subwavelength grating microring resonator sensor by leveraging its dispersion properties.
文摘A coordination polymer{[Cd(H_(2)dpa)(bpy)]·3H_(2)O}_(n)(Cd-CP)was designed and hydrothermal synthesized based on 4-(2,4-dicarboxyphenoxy)phthalic acid(H_(4)dpa),2,2'-bipyridine(bpy)and Cd(NO_(3))_(2)·4H_(2)O.The structure was characterized by single-crystal X-ray diffraction,powder X-ray diffraction,elemental analysis,and infrared spectroscopy.Cd-CP belongs to the monoclinic crystal system with the P2_1/c space group and performs in a 1D double-chain structure.The adjacent double chains further form a 3D supramolecular network structure through hydrogen bonding.Thermogravimetric analysis shows that Cd-CP has good thermal stability.Fluorescence analysis showed that Cd-CP had good choosing selectively and was sensitive to metal ions(Fe^(3+)and Zn^(2+)),2,4,6-trinitrophenylhydrazine(TRI),and pyrimethanil(Pth).Interestingly,when Cd-CP was used for fluorescence detection of metal ions,it was found to have a fluorescence quenching effect on Fe^(3+)but had an obvious enhancement effect on Zn^(2+).Therefore,we designed an“on-off-on”logic gate.In addition,the mechanism of fluorescence sensing has been deeply explored.CCDC:2258625.
基金supported by the National Natural Science Foundation of China(Nos.61705027,62375031 and 52075131)the Chongqing Science and Technology Commission Basic Research Project(No.CSTC-2020jcyj-msxm0603)the Chongqing Municipal Education Commission Science and Technology Research Program(No.KJQN202000609)。
文摘To address the temperature cross-talk issue in detecting heavy metal ions in natural waters, a highly-integrated and fully fiber-optic metal ion sensing system capable of temperature-concentration decoupling measurement has been designed. This system integrates a fluidic detection structure assisted by side-polished fibers(SPFs) with a Sagnac interferometer.
基金supported by the National Key R&D Program of China(2022YFA1404701)Program of Shanghai Academic Research Leader under Grant(22XD1422100)+4 种基金National Natural Science Foundation of China(62075231,12141303,12073018)Shanghai Science and Technology Committee(20JC1414603,23dz2260100)Shanghai Pujiang Program(21PJ1411400)China Postdoctoral Science Foundation(2021M703335)Young Elite Scientists Sponsorship Program by CAST(YESS20220355).
文摘Phase singularities(PSs)in topological darkness-based sensors have received significant attention in optical sensing due to their rapid,ultra-sensitive,and label-free detection capabilities.Here,we present both experimental and theoretical investigations of an ultrasensitive and multiplexed phase-sensitive sensor utilizing dual topological PSs in the visible and near-infrared regions.This sensor uses a simple structure,which consists of an ultra-thin highly absorbing film deposited on a metal substrate.We demonstrate the achievement of dual-polarization darkness points for s-and p-polarizations at different incident angles.Furthermore,we theoretically explain the double topological PSs accompanied by a perfect±π-jump near a zero-reflection point,based on the temporal coupled-mode formalism.To validate its multifunctional capabilities,humidity sensing tests were carried out.The results demonstrate that the sensor has a detection limit reaching the level of 0.12‰.These findings go beyond the scope of conventional interference optical coatings and highlight the potential applications of this technology in gas sensing and biosensing domains.
文摘While algorithms have been created for land usage in urban settings,there have been few investigations into the extraction of urban footprint(UF).To address this research gap,the study employs several widely used image classification method classified into three categories to evaluate their segmentation capabilities for extracting UF across eight cities.The results indicate that pixel-based methods only excel in clear urban environments,and their overall accuracy is not consistently high.RF and SVM perform well but lack stability in object-based UF extraction,influenced by feature selection and classifier performance.Deep learning enhances feature extraction but requires powerful computing and faces challenges with complex urban layouts.SAM excels in medium-sized urban areas but falters in intricate layouts.Integrating traditional and deep learning methods optimizes UF extraction,balancing accuracy and processing efficiency.Future research should focus on adapting algorithms for diverse urban landscapes to enhance UF extraction accuracy and applicability.
基金the financial support of the Natural Science Foundation of Jiangsu Province(Grant No.BK20231320)。
文摘We explore the parity-time(PT)-symmetry breaking transition in a dimer circuit composed of two RLC resonators that are weakly coupled via an inductor.The energy behavior of this dimer circuit is reflected in the splitting or degeneracy of the systems eigenfrequencies as the gain–loss strength varies.Its dynamical properties can be described by a non-Hermitian Hamiltonian.The eigenfrequency spectrum of the system is divided by two critical points into three distinct regions:the symmetric region,the oscillatory growth region,and the fully exponential growth region.Building upon previous work on implementing the exceptional point(EP)in circuit systems,our study focuses on further exploring the variation patterns of circuit eigenfrequencies near the EP under weak coupling conditions.In addition,we construct a corresponding Dirac point(DP)circuit system for comparison.By leveraging the unique physical properties near both the EP and the DP,we further propose potential practical applications.Using perturbation theory and system simulations,we demonstrate that the square-root eigenfrequency splitting near the EP significantly enhances the sensitivity to small external perturbations,compared to the linear splitting behavior near the DP.This study presents promising prospects for next-generation sensing technologies.
基金supported by the National Natural Science Foundation of China(No.52274255)Fundamental Research Funds for the Central Universities,China(Nos.N2401003,N2301003,N2201008,N2201004,and N2301025)+3 种基金Liaoning Revitalization Talents Program,China(No.XLYC2202028)Postdoctoral Foundation of Northeastern University,ChinaYoung Elite Scientists Sponsorship Program by CAST(No.2022QNRC001)China Postdoctoral Science Foundation(No.2022M720025)。
文摘Traditional resistive semiconductor gas sensors suffer from high operating temperatures and poor selectivity.Thus,to address these issues,a highly selective nitrogen dioxide(NO_(2))sensor based on lead sulfide(PbS)quantum dots(QDs)–lead molybdate(PbMoO_(4))–molybdenum disulfide(MoS_(2))ternary nanocomposites operating at room temperature was fabricated herein.The ternary nanocomposites were synthesized using an in situ method,yielding Pb S QDs with an average size of~10 nm and PbMoO_(4)nanoparticles in the 10-to 20-nm range,uniformly distributed on ultrathin MoS_(2)nanosheets with an average thickness of~7 nm.The optimized sensor demonstrated a significant improvement in response to 1 ppm NO_(2)at 25℃,achieving a response of 44.5%,which was approximately five times higher than that of the pure MoS_(2)-based sensor(8.5%).The sensor also achieved relatively short response/recovery times and full recovery properties.Notably,the optimal sensor displayed extraordinary selectivity toward NO_(2),showing negligible responses to different interfering gases.Density functional theory(DFT)calculations were conducted to elucidate the underlying sensing mechanism,which was attributed to the enhanced specific surface area,the receptor function of both PbS QDs and PbMoO_(4)nanoparticles,and the transducer function of MoS_(2) nanosheets.
基金financially supported by the Youth Innovation Promotion Association CAS(No.2021325)the National Natural Science Foundation of China(Nos.52179117,U21A20159)the Research project of Panzhihua Iron and Steel Group Mining Co.,Ltd.(No.2021-P6-D2-05)。
文摘Source identification and deformation analysis of disaster bodies are the main contents of high-steep slope risk assessment,the establishment of high-precision model and the quantification of the fine geometric features of the slope are the prerequisites for the above work.In this study,based on the UAV remote sensing technology in acquiring refined model and quantitative parameters,a semi-automatic dangerous rock identification method based on multi-source data is proposed.In terms of the periodicity UAV-based deformation monitoring,the monitoring accuracy is defined according to the relative accuracy of multi-temporal point cloud.Taking a high-steep slope as research object,the UAV equipped with special sensors was used to obtain multi-source and multitemporal data,including high-precision DOM and multi-temporal 3D point clouds.The geometric features of the outcrop were extracted and superimposed with DOM images to carry out semi-automatic identification of dangerous rock mass,realizes the closed-loop of identification and accuracy verification;changing detection of multi-temporal 3D point clouds was conducted to capture deformation of slope with centimeter accuracy.The results show that the multi-source data-based semiautomatic dangerous rock identification method can complement each other to improve the efficiency and accuracy of identification,and the UAV-based multi-temporal monitoring can reveal the near real-time deformation state of slopes.
基金Supported by Carbon Neutrality and Energy System Transformation (CNEST) ProgramScience and Technology Innovation Project of CHN Energy (GJNY-24-26)。
文摘The service life of refractory brick in the slag tapping hole of gasifiers is a significant concern for long-term and stable operation.This study examined the damage mechanism of high chromia refractory of four commercial coal-water slurry gasifiers with their corresponding gasification coal samples and the corroded refractory bricks in the slag tapping hole of the gasifier.The slag characteristic,including crystallization and viscosity-temperature of four gasification coal samples were analyzed.The results revealed that the low viscosity slag could lead to more severe damage to refractory bricks.Given the risk of slag crystallization,it is recommended to establish a safe slag tapping temperature range should be set as tICT(initial crystallization temperature)−t_(2.5) when tICT is higher than t_(25).Upon examining interior morphology of these corroded refractory bricks,some cracks were observed within them.The chemical composition of molten slag was analyzed using SEM-EDS.However,XRD results found no spinel containing zirconium in these cracks.This suggests that the emergence of these cracks are mainly attributed to the molten slag penetration and the subsequent reaction with the refractory material.The difference in thermal expansion between the newly formed substances and refractory material is critical in forming these cracks.Furthermore,SEM-EDS analysis was also conducted on the slag-aggregate and the slag-matrix interface.The results reveal that the reduction in Cr_(2)O_(3) content is the earliest characteristic of damage in high chromia refractories.A proposed damage mechanism of refractory brick suggests that the matrix and aggregate of high chromia refractory are initially compromised because of the reduced Cr_(2)O_(3) content.Subsequently,the molten slag penetrates the interior of the refractory brick,forming new substances,leading to damage caused by the difference in thermal expansion between the new substances and the refractory brick.Understanding and preventing the reduction of Cr_(2)O_(3) content is vital to prolonging the service life of refractory brick in the slag tapping hole of the gasifier based on this damage mechanism.
基金supported by the Fujian Provincial Science and Technology Planning Project(No.2022HZ027006,No.2024HZ021023)National Natural Science Foundation of China(No.U22A20118).
文摘High-entropy materials(HEMs)have attracted considerable research attention in battery applications due to exceptional properties such as remarkable structural stability,enhanced ionic conductivity,superior mechanical strength,and outstanding catalytic activity.These distinctive characteristics render HEMs highly suitable for various battery components,such as electrodes,electrolytes,and catalysts.This review systematically examines recent advances in the application of HEMs for energy storage,beginning with fundamental concepts,historical development,and key definitions.Three principal categories of HEMs,namely high-entropy alloys,high-entropy oxides,and highentropy MXenes,are analyzed with a focus on electrochemical performance metrics such as specific capacity,energy density,cycling stability,and rate capability.The underlying mechanisms by which these materials enhance battery performance are elucidated in the discussion.Furthermore,the pivotal role of machine learning in accelerating the discovery and optimization of novel high-entropy battery materials is highlighted.The review concludes by outlining future research directions and potential breakthroughs in HEM-based battery technologies.
文摘Platinum group metals have high melting points,strong corrosion resistance,stable chemical properties,and low oxygen permeability in high-temperature oxygen-containing environments.As thermal protective coating materials,they have gained essential applications in the aerospace field and have excellent prospects for application in frontier military fields,such as protecting hot-end components of hypersonic aircraft.This research reviewed the latest research progress of platinum group metal coatings with hightemperature oxidation resistance,including coating preparation techniques,oxidation failure,and alloying modification.The leading preparation techniques of current platinum group metal coatings were discussed,as well as the advantages and disadvantages of various existing preparation techniques.Besides,the intrinsic properties,failure forms,and failure mechanisms of coatings of single platinum group metal in high-temperature oxygen-containing environments were analyzed.On this basis,the necessity,main methods,and main achievements of alloying modification of platinum group metals were summarized.Finally,the future development of platinum group coatings with high-temperature oxidation resistance was discussed and prospected.
基金funded by Princess Nourah bint Abdulrahman University Researchers Support-ing Project number(PNURSP2026R346)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Motor imbalance is a critical failure mode in rotating machinery,potentially causing severe equipment damage if undetected.Traditional vibration-based diagnostic methods rely on direct sensor contact,leading to installation challenges and measurement artifacts that can compromise accuracy.This study presents a novel radar-based framework for non-contact motor imbalance detection using 24 GHz continuous-wave radar.A dataset of 1802 experimental trials was sourced,covering four imbalance levels(0,10,20,30 g)across varying motor speeds(500–1500 rpm)and load torques(0–3 Nm).Dual-channel in-phase and quadrature radar signals were captured at 10,000 samples per second for 30-s intervals,preserving both amplitude and phase information for analysis.A multi-domain feature extraction methodology captured imbalance signatures in time,frequency,and complex signal domains.From 65 initial features,statistical analysis using Kruskal–Wallis tests identified significant descriptors,and recursive feature elimination with Random Forest reduced the feature set to 20 dimensions,achieving 69%dimensionality reduction without loss of performance.Six machine learning algorithms,Random Forest,Extra Trees Classifier,Extreme Gradient Boosting,Categorical Boosting,Support Vector Machine with radial basis function kernel,and k-Nearest Neighbors were evaluated with grid-search hyperparameter optimization and five-fold cross-validation.The Extra Trees Classifier achieved the best performance with 98.52%test accuracy,98%cross-validation accuracy,and minimal variance,maintaining per-class precision and recall above 97%.Its superior performance is attributed to its randomized split selection and full bootstrapping strategy,which reduce variance and overfitting while effectively capturing the nonlinear feature interactions and non-normal distributions present in the dataset.The model’s average inference time of 70 ms enables near real-time deployment.Comparative analysis demonstrates that the radar-based framework matches or exceeds traditional contact-based methods while eliminating their inherent limitations,providing a robust,scalable,and noninvasive solution for industrial motor condition monitoring,particularly in hazardous or space-constrained environments.
文摘In this study,using 3,5‑di(3′,5′‑dicarboxylphenyl)‑1H‑1,2,4‑triazole(H4L)as ligands,a gadolinia‑based organic framework complex{[GdNa(L)(H_(2)O)3]·2H_(2)O}_(n)(Gd‑Na‑MOF)was successfully designed and synthesized by hydrothermal method.The structure and properties were systematically characterized and tested by techniques such as single‑crystal X‑ray diffraction,powder X‑ray diffraction,thermogravimetric analysis,infrared spectroscopy,and fluorescence spectroscopy.The results indicate that this complex has a unique 3D structure,excellent thermal stability,and outstanding luminescent performance.Based on its luminescent properties,a polymer‑embedding method was employed to fabricate the Gd‑Na‑MOF into a flexible,washable composite fluorescent film,Gd‑Na‑MOF@PMMA/BMA(PMMA=polymethyl methacrylate,BMA=butyl methacrylate).This fluorescent film exhibited highly sensitive recognition capability for tyramine,with a low detection limit of 1.66μmol·L^(-1).It was used for the detection of tyramine in bananas,with a recovery rate of 96.92%‑100.26%.CCDC:2466949.
基金supported by the National Key Research and Development Program of China (2023YFF1103404)the Key Research & Development Program of Shaanxi Province (2022NY-010)。
文摘In this study,we investigated the effect of high-solubility wheat gluten proteins(hs-WGP) prepared by pH-cycle treatment on soybean isolate-based extrudates.The results showed that the addition of hs-WGP can improve textural properties of soybean isolate-based extrudate via regulating the hardness to appropriate range.At molecular level,it was further found that the hs-WGP was cross-linked with soy protein isolate mainly through hydrogen bonding and disulfide bonding,and the spherical protein of soy protein isolate was wrapped by the hs-WGP,which weakened the thermal unfolding of globular proteins during heating process,reduced the degree of heat-curing gel,resulted in a reduction in hardness.In addition,hs-WGP/soybean protein composite extrudates possessed a more balanced amino acid composition,which have a positive impact on meat analogues at the nutritional level.
基金the support of this work by the National Natural Science Foundation of China(Nos.22471182,22271201,22422108,22171194)the Science&Technology Department of Sichuan Province(No.2025zNSFSC0125)+1 种基金the Fundamental Research Funds for the Central Universities(No.20826041D4117)the Comprehensive Training Platform of Specialized Laboratory,College of Chemistry,Prof.Peng Wu of the Analytical&Testing Center,Sichuan University.
文摘Azobenzene-winged phenanthrolines(L1 and L2)were designed,synthesized,and fully characterized.Ligand L1 forms an in-situ cobalt complex,which has been effectively employed as a circular dichroism(CD)-active chiral sensor.The resulting ternary complex(L1-Co^(2+)-amino alcohol)exhibits pronounced exciton-coupled circular dichroism(ECCD)signals at the characteristic azobenzene absorption bands.These signals arise from efficient chirality transfer from the chiral amino alcohol to the azobenzene chromophores,enabling the determination of the absolute configuration of chiral amino alcohols.Accordingly,the L1-Co^(2+)coordination system demonstrates considerably potential in chirality sensing applications.Remarkably,the induced ECCD signals are highly responsive to multiple external stimuli,including photoirradiation,solvent polarity,temperature,and redox conditions.In particular,temperature and redox changes can induce a reversible inversion of the ECCD signal,thereby establishing this system as a multifunctional,stimuli-responsive chiroptical molecular switch.
基金financially supported by National Natural Science Foundation of China(32272450)Science Fund for Distinguished Young Scholars of Fujian Province(2023J06020)Special Funds for Science and Technology Innovation of Fujian Agriculture and Forestry University(KFB23132A)。
文摘Vibrio harveyi,a Gram-negative bacterium ubiquitous in marine environments,is recognized as an opportunistic pathogen affecting various aquatic organisms such as fish,shrimp,and shellfish.To enhance its environmental resilience and adaptive capacity,V.harveyi employs a complex quorum sensing mechanism to modulate its virulence factors,such as bioluminescence,biofilm formation,and motility.Therefore,targeting the quorum sensing of V.harveyi could be a promising strategy to develop novel approaches to ensure the microbial safety of seafood products.This study aims to evaluate the impact of curcumin-mediated photo/sonodynamic treatment on quorum sensing in V.harveyi and its regulated functions.The results indicate a significant decrease of luminescence in V.harveyi following curcumin-mediated photo/sonodynamic treatment.Correspondingly,the biofilm formation ability and bacterial motility of V.harveyi were also greatly impaired by the treatment.Notably,the production of reactive oxygen species in bacteria induced by the photo/sonodynamic treatment could be the underlying mechanism involved in the observed disruption of quorum sensing.These findings underscore the great potential of photo/sonodynamic treatment as a promising strategy to disrupt quorum sensing and mitigate the virulence of V.harveyi,thereby contributing to the development of effective control strategies against this pervasive pathogen.
基金supported by the Henan Province Key R&D Project under Grant 241111210400the Henan Provincial Science and Technology Research Project under Grants 252102211047,252102211062,252102211055 and 232102210069+2 种基金the Jiangsu Provincial Scheme Double Initiative Plan JSS-CBS20230474,the XJTLU RDF-21-02-008the Science and Technology Innovation Project of Zhengzhou University of Light Industry under Grant 23XNKJTD0205the Higher Education Teaching Reform Research and Practice Project of Henan Province under Grant 2024SJGLX0126。
文摘Accurate and efficient detection of building changes in remote sensing imagery is crucial for urban planning,disaster emergency response,and resource management.However,existing methods face challenges such as spectral similarity between buildings and backgrounds,sensor variations,and insufficient computational efficiency.To address these challenges,this paper proposes a novel Multi-scale Efficient Wavelet-based Change Detection Network(MewCDNet),which integrates the advantages of Convolutional Neural Networks and Transformers,balances computational costs,and achieves high-performance building change detection.The network employs EfficientNet-B4 as the backbone for hierarchical feature extraction,integrates multi-level feature maps through a multi-scale fusion strategy,and incorporates two key modules:Cross-temporal Difference Detection(CTDD)and Cross-scale Wavelet Refinement(CSWR).CTDD adopts a dual-branch architecture that combines pixel-wise differencing with semanticaware Euclidean distance weighting to enhance the distinction between true changes and background noise.CSWR integrates Haar-based Discrete Wavelet Transform with multi-head cross-attention mechanisms,enabling cross-scale feature fusion while significantly improving edge localization and suppressing spurious changes.Extensive experiments on four benchmark datasets demonstrate MewCDNet’s superiority over comparison methods:achieving F1 scores of 91.54%on LEVIR,93.70%on WHUCD,and 64.96%on S2Looking for building change detection.Furthermore,MewCDNet exhibits optimal performance on the multi-class⋅SYSU dataset(F1:82.71%),highlighting its exceptional generalization capability.
