Most ground faults in distribution network are caused by insulation deterioration of power equipment.It is difficult to find the insulation deterioration of the distribution network in time,and the development trend o...Most ground faults in distribution network are caused by insulation deterioration of power equipment.It is difficult to find the insulation deterioration of the distribution network in time,and the development trend of the initial insulation fault is unknown,which brings difficulties to the distribution inspection.In order to solve the above problems,a situational awareness method of the initial insulation fault of the distribution network based on a multi-feature index comprehensive evaluation is proposed.Firstly,the insulation situation evaluation index is selected by analyzing the insulation fault mechanism of the distribution network,and the relational database of the distribution network is designed based on the data and numerical characteristics of the existing distribution management system.Secondly,considering all kinds of fault factors of the distribution network and the influence of the power supply region,the evaluation method of the initial insulation fault situation of the distribution network is proposed,and the development situation of the distribution network insulation fault is classified according to the evaluation method.Then,principal component analysis was used to reduce the dimension of the training samples and test samples of the distribution network data,and the support vector machine(SVM)was trained.The optimal parameter combination of the SVM model was found by the grid search method,and a multi-class SVM model based on 1-v-1 method was constructed.Finally,the trained multi-class SVM was used to predict 6 kinds of situation level prediction samples.The results of simulation examples show that the average prediction accuracy of 6 situation levels is above 95%,and the perception accuracy of 4 situation levels is above 96%.In addition,the insulation maintenance decision scheme under different situation levels is able to be given when no fault occurs or the insulation fault is in the early stage,which can meet the needs of power distribution and inspection for accurately sensing the insulation fault situation.The correctness and effectiveness of this method are verified.展开更多
Digital watermarking technology plays an important role in detecting malicious tampering and protecting image copyright.However,in practical applications,this technology faces various problems such as severe image dis...Digital watermarking technology plays an important role in detecting malicious tampering and protecting image copyright.However,in practical applications,this technology faces various problems such as severe image distortion,inaccurate localization of the tampered regions,and difficulty in recovering content.Given these shortcomings,a fragile image watermarking algorithm for tampering blind-detection and content self-recovery is proposed.The multi-feature watermarking authentication code(AC)is constructed using texture feature of local binary patterns(LBP),direct coefficient of discrete cosine transform(DCT)and contrast feature of gray level co-occurrence matrix(GLCM)for detecting the tampered region,and the recovery code(RC)is designed according to the average grayscale value of pixels in image blocks for recovering the tampered content.Optimal pixel adjustment process(OPAP)and least significant bit(LSB)algorithms are used to embed the recovery code and authentication code into the image in a staggered manner.When detecting the integrity of the image,the authentication code comparison method and threshold judgment method are used to perform two rounds of tampering detection on the image and blindly recover the tampered content.Experimental results show that this algorithm has good transparency,strong and blind detection,and self-recovery performance against four types of malicious attacks and some conventional signal processing operations.When resisting copy-paste,text addition,cropping and vector quantization under the tampering rate(TR)10%,the average tampering detection rate is up to 94.09%,and the peak signal-to-noise ratio(PSNR)of the watermarked image and the recovered image are both greater than 41.47 and 40.31 dB,which demonstrates its excellent advantages compared with other related algorithms in recent years.展开更多
In global navigation satellite system denial environment,cross-view geo-localization based on image retrieval presents an exceedingly critical visual localization solution for Unmanned Aerial Vehicle(UAV)systems.The e...In global navigation satellite system denial environment,cross-view geo-localization based on image retrieval presents an exceedingly critical visual localization solution for Unmanned Aerial Vehicle(UAV)systems.The essence of cross-view geo-localization resides in matching images containing the same geographical targets from disparate platforms,such as UAV-view and satellite-view images.However,images of the same geographical targets may suffer from occlusions and geometric distortions due to variations in the capturing platform,view,and timing.The existing methods predominantly extract features by segmenting feature maps,which overlook the holistic semantic distribution and structural information of objects,resulting in loss of image information.To address these challenges,dilated neighborhood attention Transformer is employed as the feature extraction backbone,and Multi-feature representations based on Multi-scale Hierarchical Contextual Aggregation(MMHCA)is proposed.In the proposed MMHCA method,the multiscale hierarchical contextual aggregation method is utilized to extract contextual information from local to global across various granularity levels,establishing feature associations of contextual information with global and local information in the image.Subsequently,the multi-feature representations method is utilized to obtain rich discriminative feature information,bolstering the robustness of model in scenarios characterized by positional shifts,varying distances,and scale ambiguities.Comprehensive experiments conducted on the extensively utilized University-1652 and SUES-200 benchmarks indicate that the MMHCA method surpasses the existing techniques.showing outstanding results in UAV localization and navigation.展开更多
This study proposes a learner profile framework based on multi-feature fusion,aiming to enhance the precision of personalized learning recommendations by integrating learners’static attributes(e.g.,demographic data a...This study proposes a learner profile framework based on multi-feature fusion,aiming to enhance the precision of personalized learning recommendations by integrating learners’static attributes(e.g.,demographic data and historical academic performance)with dynamic behavioral patterns(e.g.,real-time interactions and evolving interests over time).The research employs Term Frequency-Inverse Document Frequency(TF-IDF)for semantic feature extraction,integrates the Analytic Hierarchy Process(AHP)for feature weighting,and introduces a time decay function inspired by Newton’s law of cooling to dynamically model changes in learners’interests.Empirical results demonstrate that this framework effectively captures the dynamic evolution of learners’behaviors and provides context-aware learning resource recommendations.The study introduces a novel paradigm for learner modeling in educational technology,combining methodological innovation with a scalable technical architecture,thereby laying a foundation for the development of adaptive learning systems.展开更多
The traditional EnFCM(Enhanced fuzzy C-means)algorithm only considers the grey-scale features in image segmentation,resulting in less than satisfactory results when the algorithm is used for remote sensing woodland im...The traditional EnFCM(Enhanced fuzzy C-means)algorithm only considers the grey-scale features in image segmentation,resulting in less than satisfactory results when the algorithm is used for remote sensing woodland image segmentation and extraction.An EnFCM remote sensing forest land extraction method based on PCA multi-feature fusion was proposed.Firstly,histogram equalization was applied to improve the image contrast.Secondly,the texture and edge features of the image were extracted,and a multi-feature fused pixel image was generated using the PCA technique.Moreover,the fused feature was used as a feature constraint to measure the difference of pixels instead of a single grey-scale feature.Finally,an improved feature distance metric calculated the similarity between the pixel points and the cluster center to complete the cluster segmentation.The experimental results showed that the error was between 1.5%and 4.0%compared with the forested area counted by experts’hand-drawing,which could obtain a high accuracy segmentation and extraction result.展开更多
The atom-bond sum-connectivity(ABS)index,put forward by[J.Math.Chem.,2022,60(10):20812093],exhibits a strong link with the acentric factor of octane isomers.The experimental physico-chemical properties of octane isome...The atom-bond sum-connectivity(ABS)index,put forward by[J.Math.Chem.,2022,60(10):20812093],exhibits a strong link with the acentric factor of octane isomers.The experimental physico-chemical properties of octane isomers,such as boiling point,of formation are found to be better measured by the ABS index than by the Randi,atom-bond connectivity(ABC),and sum-connectivity(SC)indices.One important source of information for researching the molecular structure is the bounds for its topological indices.The extrema of the ABS index of the line,total,and Mycielski graphs are calculated in this work.Moreover,the pertinent extremal graphs were illustrated.展开更多
The Gabes aquifer system,located in southeastern Tunisia,is a crucial resource for supporting local socio-economic activities.Due to its dual porosity structure,is particularly vulnerable to pollution.This study aims ...The Gabes aquifer system,located in southeastern Tunisia,is a crucial resource for supporting local socio-economic activities.Due to its dual porosity structure,is particularly vulnerable to pollution.This study aims to develop a hybrid model that combines the Fracture Aquifer Index(FAI)with the conventional GOD(Groundwater occurrence,Overall lithology,Depth to water table)method,to assess groundwater vulnerability in fractured aquifer.To develop the hybrid model,the classical GOD method was integrated with FAI to produce a single composite index.Each parameter within both GOD and FAI was scored,and a final index was calculated to delineate vulnerable areas.The results show that the study area can be classified into four vulnerability levels:Very low,low,moderate,and high,indicating that approximately 8%of the area exhibits very low vulnerability,29%has low vulnerability,25%falls into the moderate category,and 38%is considered highly vulnerable.The FAI-GOD model further incorporates fracture network characteristics.This refinement reduces the classification to three vulnerability classes:Low,medium,and high.The outcomes demonstrate that 46%of the area is highly vulnerable due to a dense concentration of fractures,while 17%represents an intermediate zone characterized by either shallow or deeper fractures.In contrast,37%corresponds to areas with lightly fractured rock,where the impact on vulnerability is minimal.Multivariate statistical analysis was employed using Principal Components Analysis(PCA)and Hierarchical Cluster Analysis(HCA)on 24 samples across six variables.The first three components account for over 76%of the total variance,reinforcing the significance of fracture dynamics in classifying vulnerability levels.The FAI-GOD model removes the very-low-vulnerability class and expands the spatial extent of low-and high-vulnerability zones,reflecting the dominant influence of fracture networks on aquifer sensitivity.While both indices use a five-class system,FAI-GOD redistributes vulnerability by eliminating very-low-vulnerability areas and amplifying low/high categories,highlighting the critical role of fractures.A strong correlation(R2=0.94)between the GOD and FAI-GOD indices,demonstrated through second-order polynomial regression,confirms the robustness of the FAI-GOD model in accurately predicting vulnerability to pollution.This model provides a useful framework for assessing the vulnerability of complex aquifers and serves as a decision-making tool for groundwater managers in similar areas.展开更多
Chain graphs are{2K_(2),C_(3),C_(5)}-free graphs.Balaban index and sum-Balaban index are two important topological indices.In this paper,we concentrate on the subclass of bicyclic connected chain graphs,identifying th...Chain graphs are{2K_(2),C_(3),C_(5)}-free graphs.Balaban index and sum-Balaban index are two important topological indices.In this paper,we concentrate on the subclass of bicyclic connected chain graphs,identifying the extremal graphs that exhibit the minimum or maximum Balaban index and sum-Balaban index within this class.Moreover,we provide a systematic ordering of all bicyclic connected chain graphs according to the magnitude of their Balaban index and sum-Balaban index.展开更多
This commentary critically appraises the study by Li et al which pioneered the exploration of the triglyceride-glucose(TyG)index as a prognostic marker in hepatitis B virus-related advanced hepatocellular carcinoma pa...This commentary critically appraises the study by Li et al which pioneered the exploration of the triglyceride-glucose(TyG)index as a prognostic marker in hepatitis B virus-related advanced hepatocellular carcinoma patients undergoing combined camrelizumab and lenvatinib therapy.While we acknowledge the study’s clinical relevance in proposing an easily accessible metabolic biomarker,we delve into the mechanistic plausibility linking insulin resistance to immunotherapy response and angiogenic inhibition.We further critically examine the methodological limitations,including the retrospective design,the populationspecific TyG cut-off value,and unaddressed metabolic confounders.We highlight the imperative for future research to validate its utility across diverse etiologies and treatment settings,and to unravel the underlying immunometabolic pathways.展开更多
BACKGROUND Timely and accurate evaluation of mental disorders in adolescents using appropriate mental health literacy assessment tools is essential for improving their mental health literacy levels.AIM To develop an e...BACKGROUND Timely and accurate evaluation of mental disorders in adolescents using appropriate mental health literacy assessment tools is essential for improving their mental health literacy levels.AIM To develop an evaluation index system for the mental health literacy of adolescent patients with mental disorders,providing a scientific,comprehensive,and reliable tool for the monitoring and intervention of mental health literacy of such patients.METHODS From December 2022 to June 2023,the evaluation index system for mental health literacy of adolescents with mental disorders was developed through literature reviews,semi-structured interviews,expert letter consultations,and the analytic hierarchy process.Based on this index system,a self-assessment questionnaire was compiled and administered to 305 adolescents with mental disorders to test the reliability and validity of the index system.RESULTS The final evaluation index system for mental health literacy of adolescents with mental disorders included 4 first-level indicators,10 second-level indicators,and 52 third-level indicators.The overall Cronbach’sαcoefficient of the index system was 0.957,with a partial reliability of 0.826 and a content validity index of 0.975.The cumulative variance contribution rate of 10 common factors was 66.491%.The correlation coefficients between each dimension and the total questionnaire ranged from 0.672 to 0.724,while the correlation coefficients in each dimension ranged from 0.389 to 0.705.CONCLUSION The evaluation index system for mental health literacy of adolescents with mental disorders,developed in this study,demonstrated notable reliability and validity,making it a valuable tool for evaluating mental health literacy in this population.展开更多
AIM:To explore the repeatability,reproducibility,and agreement in the measurement of the choroidal vascularity index(CVI)for different swept-source optical coherence tomography(OCT)devices and between OCT and OCT angi...AIM:To explore the repeatability,reproducibility,and agreement in the measurement of the choroidal vascularity index(CVI)for different swept-source optical coherence tomography(OCT)devices and between OCT and OCT angiography(OCTA)images.METHODS:Two swept-source OCT imaging systems,VG200I and Topcon DRI OCT Triton,were used to capture OCT and OCTA images in triplicate.The first and third images were taken by one operator,and the second image was taken by another operator.The built-in software was used to calculate the CVI from the OCTA images(CVI-OCTA),and a custom-designed algorithm was used to calculate the CVI from the OCT images(CVI-OCT).Repeatability and reproducibility were assessed with the intraclass correlation coefficient(ICC),and agreement between devices and between OCT and OCTA were evaluated with Bland-Altman analysis.RESULTS:Sixty-eight eyes from 35 adults(17 females)were included in the analysis.The average age of the participants was 23.6±2.3y,with an average spherical equivalent refraction of-3.08±2.47 D and an average AL of 25.21±1.20 mm.Both OCT devices demonstrated high repeatability and reproducibility in measuring the CVI-OCTA(all ICCs>0.894 across five choroidal regions)and CVI-OCT(all ICCs>0.838).Furthermore,the between-device agreement in measuring the CVI-OCT was good[mean difference(MD)ranging from-2.32%to-3.07%],but that in measuring the CVI-OCTA was poor(MD,1.48%to-7.43%).Additionally,the between-imaging agreement(CVI-OCTA versus CVI-OCT)was poor for both devices(Triton,MD,6.05%to 12.68%;VG200I,MD,6.67%to 12.09%).CONCLUSION:Both OCT devices and the two analytical methods demonstrate good stability.The inter-device consistency of CVI-OCT is good,while the inter-device consistency of CVI-OCTA and the consistency between the two analytical methods in the same device are both poor.展开更多
Let G be a finite group and H a subgroup of G.The normal index of H in G is defined as the order of K/H_(G),where K is a normal supplement of H in G such that|K|is minimal and H_(G)≤K■G.Let p be a prime which divide...Let G be a finite group and H a subgroup of G.The normal index of H in G is defined as the order of K/H_(G),where K is a normal supplement of H in G such that|K|is minimal and H_(G)≤K■G.Let p be a prime which divides the order of a group G.In this paper,some characterizations of G being p-solvable or p-supersolvable were obtained by analyzing the normal index of certain subgroups of G.These results can be viewed as local version of recent results in the literature.展开更多
BACKGROUND:Rapid identification of patients at risk of clinical deterioration(in-hospital mortality) in emergency settings is essential for timely and appropriate care.Existing prognostic scores,such as the Acute Phys...BACKGROUND:Rapid identification of patients at risk of clinical deterioration(in-hospital mortality) in emergency settings is essential for timely and appropriate care.Existing prognostic scores,such as the Acute Physiology and Chronic Health Evaluation IV(APACHE IV),Simplified Acute Physiology Score 3(SAPS 3),Sequential Organ Failure Assessment(SOFA),and National Early Warning Score 2(NEWS 2),have limitations in emergency scenarios,particularly in resource-limited settings.We aimed to develop a simple and efficient tool tailored to the Brazilian healthcare system.METHODS:This retrospective,multicenter,cohort study analyzed data from 50,709 adult patients admitted to 12 hospitals in southern and southeastern Brazil between 2019 and 2020.The BRASIL score(Brazilian Risk Assessment Severity Index and Length of stay) was constructed using demographic and clinical variables available at admission.Logistic regression was used to determine the weight of each variable,and each variable was assigned a point value based on its β-coefficient and clinical relevance,with thresholds defined according to established medical cutoffs and statistical performance.The score's predictive accuracy was validated using the area under the receiver operating characteristic curve(AUC) with comparative analysis against NEWS 2.RESULTS:The BRASIL score,including age,sex,respiratory rate,heart rate,oxygen saturation,blood pressure,and body temperature,was derived through variables independently associated with in-hospital mortality in a multicenter cohort.The total score was stratified into three risk categories — low(0–3 points),moderate(4–7 points),and high(>7 points) — using observed inflection points in mortality distribution to optimize discrimination.This stratification demonstrated a stepwise increase in mortality rates across categories and the discriminatory performance,with an overall AUC of 0.743(95% CI:0.726–0.761).Compared to NEWS 2(AUC 0.697,95% CI:0.683–0.711),the BRASIL score offered superior early risk identification,supporting timely clinical decisionmaking and resource allocation in the emergency setting.CONCLUSION:The BRASIL score is a novel tool for predicting in-hospital mortality in emergency departments.Its predictive performance and ease of use suggest that it has the potential to improve patient outcomes.展开更多
The associations of co-exposure to per-and polyfluoroalkyl substances(PFAS),polycyclic aromatic hydrocarbons(PAHs),and metals with children’s glycometabolism and the underlying mechanism of immune inflammation are la...The associations of co-exposure to per-and polyfluoroalkyl substances(PFAS),polycyclic aromatic hydrocarbons(PAHs),and metals with children’s glycometabolism and the underlying mechanism of immune inflammation are largely unclear.We conducted a longitudinal panel study to explore the effects of individual and mixture of 27 contaminants on an emerging surrogate indicator of insulin resistance,triglyceride-glucose index(TyG),and the mediation of immunoglobulins and cytokines in children aged 4–6 years and 11–13 years.The results showed robust associations of perfluorooctanoic acid(PFOA),perfluorononanoic acid(PFNA),perfluoroundecanoic acid(PFUnDA),and arsenic(As)with elevated TyG.The interaction of PFNA with PFOA was significant,showing a synergistic effect on TyG.And combined association of each pair of PFOA,PFNA,and As with TyG were enhanced.Meanwhile,the effect of contaminants mixture on TyG was significant for polyfluoroalkyl substances(PFAS)mixture,of which 6:2 Chlorinated polyfluorinated ether sulfonates(Cl-PFESA),PFNA,and PFUnDA weighted more than others.Notably,contaminants were related to immune globulins and cytokines,of which chemokine ligand(CCL)4,interleukin(IL)-1β,IL-9,and tumor necrosis factor(TNF)-α significantly mediated associations of PFOA,PFNA,and PFUnDA with TyG.Accordingly,PFAS and metals were individually and jointly associated with TyG elevation,with 6:2 Cl-PFESA,PFNA,and PFUnDA contributing the most,and CCL4,IL-1β,IL-9,and TNF-α might be the underlying mediators in children.展开更多
Gradient refractive index(GRIN)metalenses are increasingly valued in high-frequency communication due to their exceptional radiation performance.Ceramics with high dielectric constants and low dielectric losses are id...Gradient refractive index(GRIN)metalenses are increasingly valued in high-frequency communication due to their exceptional radiation performance.Ceramics with high dielectric constants and low dielectric losses are ideal candidates for GRIN metalenses.Digital light processing(DLP)3D printing provides a feasible and efficient approach for manufacturing ceramic GRIN metalenses.However,the scattering of ultraviolet(UV)light by ceramic particles in the slurry reduces the printing accuracy of DLP technology,making it difficult to achieve the intricate structural features required for GRIN metalenses in high-frequency communication.In this work,we propose an approach to improve printing accuracy by optimizing the ceramic slurry composition and implementing a dimensional compensation design strategy.Utilizing geometric optics and the S-parameter inversion method,we design a GRIN metalens consisting of two distinct types of subwavelength unit cells(Y-shaped and circular hole geometries)with a minimum feature size of 160μm.Through a refined slurry formulation and precise design parameter compensation,high-fidelity ceramic GRIN metalenses are successfully fabricated.The fabricated metalens exhibits a maximum gain enhancement of 18.4 dBi and a deflection angle of±30°over a bandwidth of 37.84% in the W-band(75-110 GHz).The highly directional far-field beam radiation and efficient beam steering capabilities highlight the potential of ceramic GRIN metalenses for applications in satellite communications,radar systems,and other high-frequency technologies.展开更多
数控多轴车床的核心优势在于较短的加工节拍以及强大的多工序加工能力,能够高精度加工复杂零件,即使面对无铅黄铜等难加工材料,亦能实现高效稳定的加工。INDEX数控多轴车床在多个技术维度上已显著超越传统的凸轮多轴车床。这一结论得到...数控多轴车床的核心优势在于较短的加工节拍以及强大的多工序加工能力,能够高精度加工复杂零件,即使面对无铅黄铜等难加工材料,亦能实现高效稳定的加工。INDEX数控多轴车床在多个技术维度上已显著超越传统的凸轮多轴车床。这一结论得到了精密车削零件制造商Firner Trautwein公司的验证,该公司在德国Zeil am Main及Dunningen的生产基地均使用INDEX数控多轴车床,并表示其生产能力已为应对未来市场需求做好了充分准备。展开更多
Surface polaritons,as surface electromagnetic waves propagating along the surface of a medium,have played a crucial role in enhancing photonic spin Hall effect(PSHE)and developing highly sensitive refractive index(RI)...Surface polaritons,as surface electromagnetic waves propagating along the surface of a medium,have played a crucial role in enhancing photonic spin Hall effect(PSHE)and developing highly sensitive refractive index(RI)sensors.Among them,the traditional surface plasmon polariton(SPP)based on noble metals limits its application beyond the near-infrared(IR)regime due to the large negative permittivity and optical losses.In this contribution,we theoretically proposed a highly sensitive PSHE sensor with the structure of Ge prism-SiC-Si:InAs-sensing medium,by taking advantage of the hybrid surface plasmon phonon polariton(SPPhP)in mid-IR regime.Here,heavily Si-doped InAs(Si:InAs)and SiC excite the SPP and surface phonon polariton(SPhP),and the hybrid SPPhP is realized in this system.More importantly,the designed PSHE sensor based on this SPPhP mechanism achieves the multi-stage RI measurements from 1.00025-1.00225 to 1.70025-1.70225,and the maximal intensity sensitivity and angle sensitivity can be up to 9.4×10^(4)μm/RIU and245°/RIU,respectively.These findings provide a new pathway for the enhancement of PSHE in mid-IR regime,and offer new opportunities to develop highly sensitive RI sensors in multi-scenario applications,such as harmful gas monitoring and biosensing.展开更多
This study presents a hybrid methodology for predicting building collapses within the Intelligent Circular Resilience(ICR)framework.This uses a supervised Machine Learning(ML)approach,earthquake damage re-ports,and th...This study presents a hybrid methodology for predicting building collapses within the Intelligent Circular Resilience(ICR)framework.This uses a supervised Machine Learning(ML)approach,earthquake damage re-ports,and the Simplified Resilience Index(SRI),derived from existing earthquake damage models(EDM)-based on fragility and vulnerability functions-used in the probabilistic seismic risk assessment(PSRA).A curated building damage database comprising 89 structures(71 collapsed and 18 non-collapsed)from ten countries affected by major earthquakes(Mw 6.1-8.1,epicentral distances of 3-125 km,and PGA values ranging from 0.14 g to 0.82 g)was developed,including attributes related to exposure:occupancy,main structural material,number of stories,construction year,and hazard:magnitude,epicentral distance,intensity measures(Peak-ground acceleration,PGA,and elastic spectral acceleration).The dataset includes events such as the 2017 Puebla-Morelos earthquake(Mw 7.1,Mexico),the 1999 Kocaeli earthquake(Mw 7.6,Turkey),and the 2011 Christchurch earthquake(Mw 6.1,New Zealand),among others.Likewise,dependent attributes such as time elapsed and SRI(under 120-,180-,and 365-day recovery scenarios)were calculated using 2-EDMs.Eight Random Forest models were trained and tested for collapse and non-collapse classification using combinations of independent and dependent attributes.The results indicate that models incorporating exposure-related varia-bles-such as structural material,number of stories,construction year,and occupancy-alongside the SRI significantly improve collapse classification performance,achieving recall and F1 scores above 95%.Notably,many collapsed buildings exhibited low intensities(PGA≤0.25 g),emphasizing the influence of local site effects-particularly in Mexico City.The findings demonstrate that incorporating SRI enhances the reliability of collapse prediction and supports its use as an interpretable resilience proxy during early ICR stages.This hybrid methodology bridges empirical data,traditional PSRA models,and ML techniques,contributing to more accurate and scalable post-earthquake resilience assessments.展开更多
Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario.It has gradually become a core technology of int...Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario.It has gradually become a core technology of intelligent transportation system.Most existing vehicle re-identification models adopt the joint learning of global and local features.However,they directly use the extracted global features,resulting in insufficient feature expression.Moreover,local features are primarily obtained through advanced annotation and complex attention mechanisms,which require additional costs.To solve this issue,a multi-feature learning model with enhanced local attention for vehicle re-identification(MFELA)is proposed in this paper.The model consists of global and local branches.The global branch utilizes both middle and highlevel semantic features of ResNet50 to enhance the global representation capability.In addition,multi-scale pooling operations are used to obtain multiscale information.While the local branch utilizes the proposed Region Batch Dropblock(RBD),which encourages the model to learn discriminative features for different local regions and simultaneously drops corresponding same areas randomly in a batch during training to enhance the attention to local regions.Then features from both branches are combined to provide a more comprehensive and distinctive feature representation.Extensive experiments on VeRi-776 and VehicleID datasets prove that our method has excellent performance.展开更多
基金funded by the Science and Technology Project of China Southern Power Grid(YNKJXM20210175)the National Natural Science Foundation of China(52177070).
文摘Most ground faults in distribution network are caused by insulation deterioration of power equipment.It is difficult to find the insulation deterioration of the distribution network in time,and the development trend of the initial insulation fault is unknown,which brings difficulties to the distribution inspection.In order to solve the above problems,a situational awareness method of the initial insulation fault of the distribution network based on a multi-feature index comprehensive evaluation is proposed.Firstly,the insulation situation evaluation index is selected by analyzing the insulation fault mechanism of the distribution network,and the relational database of the distribution network is designed based on the data and numerical characteristics of the existing distribution management system.Secondly,considering all kinds of fault factors of the distribution network and the influence of the power supply region,the evaluation method of the initial insulation fault situation of the distribution network is proposed,and the development situation of the distribution network insulation fault is classified according to the evaluation method.Then,principal component analysis was used to reduce the dimension of the training samples and test samples of the distribution network data,and the support vector machine(SVM)was trained.The optimal parameter combination of the SVM model was found by the grid search method,and a multi-class SVM model based on 1-v-1 method was constructed.Finally,the trained multi-class SVM was used to predict 6 kinds of situation level prediction samples.The results of simulation examples show that the average prediction accuracy of 6 situation levels is above 95%,and the perception accuracy of 4 situation levels is above 96%.In addition,the insulation maintenance decision scheme under different situation levels is able to be given when no fault occurs or the insulation fault is in the early stage,which can meet the needs of power distribution and inspection for accurately sensing the insulation fault situation.The correctness and effectiveness of this method are verified.
基金supported by Postgraduate Research&Practice Innovation Program of Jiangsu Province,China(Grant No.SJCX24_1332)Jiangsu Province Education Science Planning Project in 2024(Grant No.B-b/2024/01/122)High-Level Talent Scientific Research Foundation of Jinling Institute of Technology,China(Grant No.jit-b-201918).
文摘Digital watermarking technology plays an important role in detecting malicious tampering and protecting image copyright.However,in practical applications,this technology faces various problems such as severe image distortion,inaccurate localization of the tampered regions,and difficulty in recovering content.Given these shortcomings,a fragile image watermarking algorithm for tampering blind-detection and content self-recovery is proposed.The multi-feature watermarking authentication code(AC)is constructed using texture feature of local binary patterns(LBP),direct coefficient of discrete cosine transform(DCT)and contrast feature of gray level co-occurrence matrix(GLCM)for detecting the tampered region,and the recovery code(RC)is designed according to the average grayscale value of pixels in image blocks for recovering the tampered content.Optimal pixel adjustment process(OPAP)and least significant bit(LSB)algorithms are used to embed the recovery code and authentication code into the image in a staggered manner.When detecting the integrity of the image,the authentication code comparison method and threshold judgment method are used to perform two rounds of tampering detection on the image and blindly recover the tampered content.Experimental results show that this algorithm has good transparency,strong and blind detection,and self-recovery performance against four types of malicious attacks and some conventional signal processing operations.When resisting copy-paste,text addition,cropping and vector quantization under the tampering rate(TR)10%,the average tampering detection rate is up to 94.09%,and the peak signal-to-noise ratio(PSNR)of the watermarked image and the recovered image are both greater than 41.47 and 40.31 dB,which demonstrates its excellent advantages compared with other related algorithms in recent years.
基金supported by the National Natural Science Foundation of China(Nos.12072027,62103052,61603346 and 62103379)the Henan Key Laboratory of General Aviation Technology,China(No.ZHKF-230201)+3 种基金the Funding for the Open Research Project of the Rotor Aerodynamics Key Laboratory,China(No.RAL20200101)the Key Research and Development Program of Henan Province,China(Nos.241111222000 and 241111222900)the Key Science and Technology Program of Henan Province,China(No.232102220067)the Scholarship Funding from the China Scholarship Council(No.202206030079).
文摘In global navigation satellite system denial environment,cross-view geo-localization based on image retrieval presents an exceedingly critical visual localization solution for Unmanned Aerial Vehicle(UAV)systems.The essence of cross-view geo-localization resides in matching images containing the same geographical targets from disparate platforms,such as UAV-view and satellite-view images.However,images of the same geographical targets may suffer from occlusions and geometric distortions due to variations in the capturing platform,view,and timing.The existing methods predominantly extract features by segmenting feature maps,which overlook the holistic semantic distribution and structural information of objects,resulting in loss of image information.To address these challenges,dilated neighborhood attention Transformer is employed as the feature extraction backbone,and Multi-feature representations based on Multi-scale Hierarchical Contextual Aggregation(MMHCA)is proposed.In the proposed MMHCA method,the multiscale hierarchical contextual aggregation method is utilized to extract contextual information from local to global across various granularity levels,establishing feature associations of contextual information with global and local information in the image.Subsequently,the multi-feature representations method is utilized to obtain rich discriminative feature information,bolstering the robustness of model in scenarios characterized by positional shifts,varying distances,and scale ambiguities.Comprehensive experiments conducted on the extensively utilized University-1652 and SUES-200 benchmarks indicate that the MMHCA method surpasses the existing techniques.showing outstanding results in UAV localization and navigation.
基金This work is supported by the Ministry of Education of Humanities and Social Science projects in China(No.20YJCZH124)Guangdong Province Education and Teaching Reform Project No.640:Research on the Teaching Practice and Application of Online Peer Assessment Methods in the Context of Artificial Intelligence.
文摘This study proposes a learner profile framework based on multi-feature fusion,aiming to enhance the precision of personalized learning recommendations by integrating learners’static attributes(e.g.,demographic data and historical academic performance)with dynamic behavioral patterns(e.g.,real-time interactions and evolving interests over time).The research employs Term Frequency-Inverse Document Frequency(TF-IDF)for semantic feature extraction,integrates the Analytic Hierarchy Process(AHP)for feature weighting,and introduces a time decay function inspired by Newton’s law of cooling to dynamically model changes in learners’interests.Empirical results demonstrate that this framework effectively captures the dynamic evolution of learners’behaviors and provides context-aware learning resource recommendations.The study introduces a novel paradigm for learner modeling in educational technology,combining methodological innovation with a scalable technical architecture,thereby laying a foundation for the development of adaptive learning systems.
基金supported by National Natural Science Foundation of China(No.61761027)Gansu Young Doctor’s Fund for Higher Education Institutions(No.2021QB-053)。
文摘The traditional EnFCM(Enhanced fuzzy C-means)algorithm only considers the grey-scale features in image segmentation,resulting in less than satisfactory results when the algorithm is used for remote sensing woodland image segmentation and extraction.An EnFCM remote sensing forest land extraction method based on PCA multi-feature fusion was proposed.Firstly,histogram equalization was applied to improve the image contrast.Secondly,the texture and edge features of the image were extracted,and a multi-feature fused pixel image was generated using the PCA technique.Moreover,the fused feature was used as a feature constraint to measure the difference of pixels instead of a single grey-scale feature.Finally,an improved feature distance metric calculated the similarity between the pixel points and the cluster center to complete the cluster segmentation.The experimental results showed that the error was between 1.5%and 4.0%compared with the forested area counted by experts’hand-drawing,which could obtain a high accuracy segmentation and extraction result.
基金Supported by Ningbo NSF(No.2021J234)Zhejiang Provincial Philosophy and Social Sciences Planning Project(No.24NDJC057YB)。
文摘The atom-bond sum-connectivity(ABS)index,put forward by[J.Math.Chem.,2022,60(10):20812093],exhibits a strong link with the acentric factor of octane isomers.The experimental physico-chemical properties of octane isomers,such as boiling point,of formation are found to be better measured by the ABS index than by the Randi,atom-bond connectivity(ABC),and sum-connectivity(SC)indices.One important source of information for researching the molecular structure is the bounds for its topological indices.The extrema of the ABS index of the line,total,and Mycielski graphs are calculated in this work.Moreover,the pertinent extremal graphs were illustrated.
文摘The Gabes aquifer system,located in southeastern Tunisia,is a crucial resource for supporting local socio-economic activities.Due to its dual porosity structure,is particularly vulnerable to pollution.This study aims to develop a hybrid model that combines the Fracture Aquifer Index(FAI)with the conventional GOD(Groundwater occurrence,Overall lithology,Depth to water table)method,to assess groundwater vulnerability in fractured aquifer.To develop the hybrid model,the classical GOD method was integrated with FAI to produce a single composite index.Each parameter within both GOD and FAI was scored,and a final index was calculated to delineate vulnerable areas.The results show that the study area can be classified into four vulnerability levels:Very low,low,moderate,and high,indicating that approximately 8%of the area exhibits very low vulnerability,29%has low vulnerability,25%falls into the moderate category,and 38%is considered highly vulnerable.The FAI-GOD model further incorporates fracture network characteristics.This refinement reduces the classification to three vulnerability classes:Low,medium,and high.The outcomes demonstrate that 46%of the area is highly vulnerable due to a dense concentration of fractures,while 17%represents an intermediate zone characterized by either shallow or deeper fractures.In contrast,37%corresponds to areas with lightly fractured rock,where the impact on vulnerability is minimal.Multivariate statistical analysis was employed using Principal Components Analysis(PCA)and Hierarchical Cluster Analysis(HCA)on 24 samples across six variables.The first three components account for over 76%of the total variance,reinforcing the significance of fracture dynamics in classifying vulnerability levels.The FAI-GOD model removes the very-low-vulnerability class and expands the spatial extent of low-and high-vulnerability zones,reflecting the dominant influence of fracture networks on aquifer sensitivity.While both indices use a five-class system,FAI-GOD redistributes vulnerability by eliminating very-low-vulnerability areas and amplifying low/high categories,highlighting the critical role of fractures.A strong correlation(R2=0.94)between the GOD and FAI-GOD indices,demonstrated through second-order polynomial regression,confirms the robustness of the FAI-GOD model in accurately predicting vulnerability to pollution.This model provides a useful framework for assessing the vulnerability of complex aquifers and serves as a decision-making tool for groundwater managers in similar areas.
文摘Chain graphs are{2K_(2),C_(3),C_(5)}-free graphs.Balaban index and sum-Balaban index are two important topological indices.In this paper,we concentrate on the subclass of bicyclic connected chain graphs,identifying the extremal graphs that exhibit the minimum or maximum Balaban index and sum-Balaban index within this class.Moreover,we provide a systematic ordering of all bicyclic connected chain graphs according to the magnitude of their Balaban index and sum-Balaban index.
文摘This commentary critically appraises the study by Li et al which pioneered the exploration of the triglyceride-glucose(TyG)index as a prognostic marker in hepatitis B virus-related advanced hepatocellular carcinoma patients undergoing combined camrelizumab and lenvatinib therapy.While we acknowledge the study’s clinical relevance in proposing an easily accessible metabolic biomarker,we delve into the mechanistic plausibility linking insulin resistance to immunotherapy response and angiogenic inhibition.We further critically examine the methodological limitations,including the retrospective design,the populationspecific TyG cut-off value,and unaddressed metabolic confounders.We highlight the imperative for future research to validate its utility across diverse etiologies and treatment settings,and to unravel the underlying immunometabolic pathways.
基金Supported by Inter Disciplinary Direction Cultivation Project of Hunan University of Chinese Medicine,No.2025JC01032025 Hunan Province Science and Technology Innovation Plan Project,No.2025RC9012+2 种基金2022"Unveiling and Leading"Project of Discipline Construction at Hunan University of Chinese Medicine,No.22JBZ044Changsha Municipal Natural Science Foundation,No.kq2402174Hunan Provincial Science Popularization Fund Project,No.2025ZK4223.
文摘BACKGROUND Timely and accurate evaluation of mental disorders in adolescents using appropriate mental health literacy assessment tools is essential for improving their mental health literacy levels.AIM To develop an evaluation index system for the mental health literacy of adolescent patients with mental disorders,providing a scientific,comprehensive,and reliable tool for the monitoring and intervention of mental health literacy of such patients.METHODS From December 2022 to June 2023,the evaluation index system for mental health literacy of adolescents with mental disorders was developed through literature reviews,semi-structured interviews,expert letter consultations,and the analytic hierarchy process.Based on this index system,a self-assessment questionnaire was compiled and administered to 305 adolescents with mental disorders to test the reliability and validity of the index system.RESULTS The final evaluation index system for mental health literacy of adolescents with mental disorders included 4 first-level indicators,10 second-level indicators,and 52 third-level indicators.The overall Cronbach’sαcoefficient of the index system was 0.957,with a partial reliability of 0.826 and a content validity index of 0.975.The cumulative variance contribution rate of 10 common factors was 66.491%.The correlation coefficients between each dimension and the total questionnaire ranged from 0.672 to 0.724,while the correlation coefficients in each dimension ranged from 0.389 to 0.705.CONCLUSION The evaluation index system for mental health literacy of adolescents with mental disorders,developed in this study,demonstrated notable reliability and validity,making it a valuable tool for evaluating mental health literacy in this population.
基金Supported by the National Key Research and Development Program of China(No.2022YFC3502503)the Medical and Health Science and Technology Project of the Zhejiang Provincial Health Commission of China(No.2022PY072).
文摘AIM:To explore the repeatability,reproducibility,and agreement in the measurement of the choroidal vascularity index(CVI)for different swept-source optical coherence tomography(OCT)devices and between OCT and OCT angiography(OCTA)images.METHODS:Two swept-source OCT imaging systems,VG200I and Topcon DRI OCT Triton,were used to capture OCT and OCTA images in triplicate.The first and third images were taken by one operator,and the second image was taken by another operator.The built-in software was used to calculate the CVI from the OCTA images(CVI-OCTA),and a custom-designed algorithm was used to calculate the CVI from the OCT images(CVI-OCT).Repeatability and reproducibility were assessed with the intraclass correlation coefficient(ICC),and agreement between devices and between OCT and OCTA were evaluated with Bland-Altman analysis.RESULTS:Sixty-eight eyes from 35 adults(17 females)were included in the analysis.The average age of the participants was 23.6±2.3y,with an average spherical equivalent refraction of-3.08±2.47 D and an average AL of 25.21±1.20 mm.Both OCT devices demonstrated high repeatability and reproducibility in measuring the CVI-OCTA(all ICCs>0.894 across five choroidal regions)and CVI-OCT(all ICCs>0.838).Furthermore,the between-device agreement in measuring the CVI-OCT was good[mean difference(MD)ranging from-2.32%to-3.07%],but that in measuring the CVI-OCTA was poor(MD,1.48%to-7.43%).Additionally,the between-imaging agreement(CVI-OCTA versus CVI-OCT)was poor for both devices(Triton,MD,6.05%to 12.68%;VG200I,MD,6.67%to 12.09%).CONCLUSION:Both OCT devices and the two analytical methods demonstrate good stability.The inter-device consistency of CVI-OCT is good,while the inter-device consistency of CVI-OCTA and the consistency between the two analytical methods in the same device are both poor.
基金Supported by the National Natural Science Foundation of China(Grant No.12071092)Guangdong Basic and Applied Basic Research Foundation(Grant No.2025A1515012072)+1 种基金the Natural Science Research Project of Anhui Educational Committee(Grant No.2024AH051298)the Scientific Research Foundation of Bozhou University(Grant No.BYKQ202419).
文摘Let G be a finite group and H a subgroup of G.The normal index of H in G is defined as the order of K/H_(G),where K is a normal supplement of H in G such that|K|is minimal and H_(G)≤K■G.Let p be a prime which divides the order of a group G.In this paper,some characterizations of G being p-solvable or p-supersolvable were obtained by analyzing the normal index of certain subgroups of G.These results can be viewed as local version of recent results in the literature.
文摘BACKGROUND:Rapid identification of patients at risk of clinical deterioration(in-hospital mortality) in emergency settings is essential for timely and appropriate care.Existing prognostic scores,such as the Acute Physiology and Chronic Health Evaluation IV(APACHE IV),Simplified Acute Physiology Score 3(SAPS 3),Sequential Organ Failure Assessment(SOFA),and National Early Warning Score 2(NEWS 2),have limitations in emergency scenarios,particularly in resource-limited settings.We aimed to develop a simple and efficient tool tailored to the Brazilian healthcare system.METHODS:This retrospective,multicenter,cohort study analyzed data from 50,709 adult patients admitted to 12 hospitals in southern and southeastern Brazil between 2019 and 2020.The BRASIL score(Brazilian Risk Assessment Severity Index and Length of stay) was constructed using demographic and clinical variables available at admission.Logistic regression was used to determine the weight of each variable,and each variable was assigned a point value based on its β-coefficient and clinical relevance,with thresholds defined according to established medical cutoffs and statistical performance.The score's predictive accuracy was validated using the area under the receiver operating characteristic curve(AUC) with comparative analysis against NEWS 2.RESULTS:The BRASIL score,including age,sex,respiratory rate,heart rate,oxygen saturation,blood pressure,and body temperature,was derived through variables independently associated with in-hospital mortality in a multicenter cohort.The total score was stratified into three risk categories — low(0–3 points),moderate(4–7 points),and high(>7 points) — using observed inflection points in mortality distribution to optimize discrimination.This stratification demonstrated a stepwise increase in mortality rates across categories and the discriminatory performance,with an overall AUC of 0.743(95% CI:0.726–0.761).Compared to NEWS 2(AUC 0.697,95% CI:0.683–0.711),the BRASIL score offered superior early risk identification,supporting timely clinical decisionmaking and resource allocation in the emergency setting.CONCLUSION:The BRASIL score is a novel tool for predicting in-hospital mortality in emergency departments.Its predictive performance and ease of use suggest that it has the potential to improve patient outcomes.
基金supported by the National Key Research and Development Program of China(No.2022YFC3702702)the National Natural Science Foundation of China(No.82404295)the Fundamental Research Funds for the Central Universities,HUST(No.2020kfyXJJS058).
文摘The associations of co-exposure to per-and polyfluoroalkyl substances(PFAS),polycyclic aromatic hydrocarbons(PAHs),and metals with children’s glycometabolism and the underlying mechanism of immune inflammation are largely unclear.We conducted a longitudinal panel study to explore the effects of individual and mixture of 27 contaminants on an emerging surrogate indicator of insulin resistance,triglyceride-glucose index(TyG),and the mediation of immunoglobulins and cytokines in children aged 4–6 years and 11–13 years.The results showed robust associations of perfluorooctanoic acid(PFOA),perfluorononanoic acid(PFNA),perfluoroundecanoic acid(PFUnDA),and arsenic(As)with elevated TyG.The interaction of PFNA with PFOA was significant,showing a synergistic effect on TyG.And combined association of each pair of PFOA,PFNA,and As with TyG were enhanced.Meanwhile,the effect of contaminants mixture on TyG was significant for polyfluoroalkyl substances(PFAS)mixture,of which 6:2 Chlorinated polyfluorinated ether sulfonates(Cl-PFESA),PFNA,and PFUnDA weighted more than others.Notably,contaminants were related to immune globulins and cytokines,of which chemokine ligand(CCL)4,interleukin(IL)-1β,IL-9,and tumor necrosis factor(TNF)-α significantly mediated associations of PFOA,PFNA,and PFUnDA with TyG.Accordingly,PFAS and metals were individually and jointly associated with TyG elevation,with 6:2 Cl-PFESA,PFNA,and PFUnDA contributing the most,and CCL4,IL-1β,IL-9,and TNF-α might be the underlying mediators in children.
基金financial support by the National Key Research and Development Program of China(No.2023YFB4605400)the National Natural Science Foundation of China(No.12472152)the Department of Science and Technology of Guangdong Province(No.2019QN01Z438)。
文摘Gradient refractive index(GRIN)metalenses are increasingly valued in high-frequency communication due to their exceptional radiation performance.Ceramics with high dielectric constants and low dielectric losses are ideal candidates for GRIN metalenses.Digital light processing(DLP)3D printing provides a feasible and efficient approach for manufacturing ceramic GRIN metalenses.However,the scattering of ultraviolet(UV)light by ceramic particles in the slurry reduces the printing accuracy of DLP technology,making it difficult to achieve the intricate structural features required for GRIN metalenses in high-frequency communication.In this work,we propose an approach to improve printing accuracy by optimizing the ceramic slurry composition and implementing a dimensional compensation design strategy.Utilizing geometric optics and the S-parameter inversion method,we design a GRIN metalens consisting of two distinct types of subwavelength unit cells(Y-shaped and circular hole geometries)with a minimum feature size of 160μm.Through a refined slurry formulation and precise design parameter compensation,high-fidelity ceramic GRIN metalenses are successfully fabricated.The fabricated metalens exhibits a maximum gain enhancement of 18.4 dBi and a deflection angle of±30°over a bandwidth of 37.84% in the W-band(75-110 GHz).The highly directional far-field beam radiation and efficient beam steering capabilities highlight the potential of ceramic GRIN metalenses for applications in satellite communications,radar systems,and other high-frequency technologies.
文摘数控多轴车床的核心优势在于较短的加工节拍以及强大的多工序加工能力,能够高精度加工复杂零件,即使面对无铅黄铜等难加工材料,亦能实现高效稳定的加工。INDEX数控多轴车床在多个技术维度上已显著超越传统的凸轮多轴车床。这一结论得到了精密车削零件制造商Firner Trautwein公司的验证,该公司在德国Zeil am Main及Dunningen的生产基地均使用INDEX数控多轴车床,并表示其生产能力已为应对未来市场需求做好了充分准备。
基金Project supported by the National Natural Science Foundation of China(Grant No.12175107)the Qing Lan Project of Jiangsu Province+2 种基金the Hua Li Talents Program of Nanjing University of PostsTelecommunications,Natural Science Foundation of Nanjing Vocational University of Industry Technology(Grant No.YK22-02-08)the Fund from the Research Center of Industrial Perception and Intelligent Manufacturing Equipment Engineering of Jiangsu Province,China(Grant No.ZK21-05-09)。
文摘Surface polaritons,as surface electromagnetic waves propagating along the surface of a medium,have played a crucial role in enhancing photonic spin Hall effect(PSHE)and developing highly sensitive refractive index(RI)sensors.Among them,the traditional surface plasmon polariton(SPP)based on noble metals limits its application beyond the near-infrared(IR)regime due to the large negative permittivity and optical losses.In this contribution,we theoretically proposed a highly sensitive PSHE sensor with the structure of Ge prism-SiC-Si:InAs-sensing medium,by taking advantage of the hybrid surface plasmon phonon polariton(SPPhP)in mid-IR regime.Here,heavily Si-doped InAs(Si:InAs)and SiC excite the SPP and surface phonon polariton(SPhP),and the hybrid SPPhP is realized in this system.More importantly,the designed PSHE sensor based on this SPPhP mechanism achieves the multi-stage RI measurements from 1.00025-1.00225 to 1.70025-1.70225,and the maximal intensity sensitivity and angle sensitivity can be up to 9.4×10^(4)μm/RIU and245°/RIU,respectively.These findings provide a new pathway for the enhancement of PSHE in mid-IR regime,and offer new opportunities to develop highly sensitive RI sensors in multi-scenario applications,such as harmful gas monitoring and biosensing.
基金Vicerrectoría de Inves-tigaciones of the UMNG for the financial support of the IMP-ING-3743 Project.
文摘This study presents a hybrid methodology for predicting building collapses within the Intelligent Circular Resilience(ICR)framework.This uses a supervised Machine Learning(ML)approach,earthquake damage re-ports,and the Simplified Resilience Index(SRI),derived from existing earthquake damage models(EDM)-based on fragility and vulnerability functions-used in the probabilistic seismic risk assessment(PSRA).A curated building damage database comprising 89 structures(71 collapsed and 18 non-collapsed)from ten countries affected by major earthquakes(Mw 6.1-8.1,epicentral distances of 3-125 km,and PGA values ranging from 0.14 g to 0.82 g)was developed,including attributes related to exposure:occupancy,main structural material,number of stories,construction year,and hazard:magnitude,epicentral distance,intensity measures(Peak-ground acceleration,PGA,and elastic spectral acceleration).The dataset includes events such as the 2017 Puebla-Morelos earthquake(Mw 7.1,Mexico),the 1999 Kocaeli earthquake(Mw 7.6,Turkey),and the 2011 Christchurch earthquake(Mw 6.1,New Zealand),among others.Likewise,dependent attributes such as time elapsed and SRI(under 120-,180-,and 365-day recovery scenarios)were calculated using 2-EDMs.Eight Random Forest models were trained and tested for collapse and non-collapse classification using combinations of independent and dependent attributes.The results indicate that models incorporating exposure-related varia-bles-such as structural material,number of stories,construction year,and occupancy-alongside the SRI significantly improve collapse classification performance,achieving recall and F1 scores above 95%.Notably,many collapsed buildings exhibited low intensities(PGA≤0.25 g),emphasizing the influence of local site effects-particularly in Mexico City.The findings demonstrate that incorporating SRI enhances the reliability of collapse prediction and supports its use as an interpretable resilience proxy during early ICR stages.This hybrid methodology bridges empirical data,traditional PSRA models,and ML techniques,contributing to more accurate and scalable post-earthquake resilience assessments.
基金This work was supported,in part,by the National Nature Science Foundation of China under Grant Numbers 61502240,61502096,61304205,61773219in part,by the Natural Science Foundation of Jiangsu Province under grant numbers BK20201136,BK20191401+1 种基金in part,by the Postgraduate Research&Practice Innovation Program of Jiangsu Province under Grant Numbers SJCX21_0363in part,by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)fund.
文摘Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario.It has gradually become a core technology of intelligent transportation system.Most existing vehicle re-identification models adopt the joint learning of global and local features.However,they directly use the extracted global features,resulting in insufficient feature expression.Moreover,local features are primarily obtained through advanced annotation and complex attention mechanisms,which require additional costs.To solve this issue,a multi-feature learning model with enhanced local attention for vehicle re-identification(MFELA)is proposed in this paper.The model consists of global and local branches.The global branch utilizes both middle and highlevel semantic features of ResNet50 to enhance the global representation capability.In addition,multi-scale pooling operations are used to obtain multiscale information.While the local branch utilizes the proposed Region Batch Dropblock(RBD),which encourages the model to learn discriminative features for different local regions and simultaneously drops corresponding same areas randomly in a batch during training to enhance the attention to local regions.Then features from both branches are combined to provide a more comprehensive and distinctive feature representation.Extensive experiments on VeRi-776 and VehicleID datasets prove that our method has excellent performance.
