We present a gain adaptive tuning method for fiber Raman amplifier(FRA) using two-stage neural networks(NNs) and double weights updates. After training the connection weights of two-stage NNs separately in training ph...We present a gain adaptive tuning method for fiber Raman amplifier(FRA) using two-stage neural networks(NNs) and double weights updates. After training the connection weights of two-stage NNs separately in training phase, the connection weights of the unified NN are updated again in verification phase according to error between the predicted and target gains to eliminate the inherent error of the NNs. The simulation results show that the mean of root mean square error(RMSE) and maximum error of gains are 0.131 d B and 0.281 d B, respectively. It shows that the method can realize adaptive adjustment function of FRA gain with high accuracy.展开更多
In this paper,it is shown that the harmonic Bergman projection P_(ω)^(h),induced by a radial,induced by a radial weightω,is bounded and onto from L^(∞)(D)to the harmonic Bloch space B_(h)if and only ifω∈D,,which ...In this paper,it is shown that the harmonic Bergman projection P_(ω)^(h),induced by a radial,induced by a radial weightω,is bounded and onto from L^(∞)(D)to the harmonic Bloch space B_(h)if and only ifω∈D,,which is a class of radial weights satisfying the two-sided doubling conditions.As an application,the bounded and compact positive Toeplitz operators T_(μ,ω)on the endpoint case weighted harmonic Bergman space L_(h,ω)^(1)(D)are characterized.展开更多
Grain filling is a critical determinant of yield and quality in rice.This study aims to clarify the association between grain photosynthesis and the filling rate of rice varieties with different grain weights,providin...Grain filling is a critical determinant of yield and quality in rice.This study aims to clarify the association between grain photosynthesis and the filling rate of rice varieties with different grain weights,providing a theoretical foundation for optimizing grain-filling processes.Two rice varieties with similar growth duration but different grain weights were selected:a large-grain variety,Lingliangyou 268(L268),and a small-grain variety,Ruiliangyou 1053(R1053).Differences in grain filling,grain photosynthetic rate,and grain chlorophyll content were systematically examined during the filling stage.Results showed significant differences in grain-filling,grain photosynthetic rate,and grain chlorophyll content between large-grain and small-grain rice varieties.The grain photosynthetic rate of L268 was a significantly higher than R1053.L268 also exhibited significantly higher initial grain filling rate,maximum grainfilling rate,and mean grain filling rate compared to R1053.Throughout the grain filling period,L268 showed higher grain chlorophyll content(including chlorophyll a,chlorophyll b,and total chlorophyll)than R1053.The increase in chlorophyll content,particularly total chlorophyll,enhanced the grain photosynthetic rate during the early and middle stages of grain filling significantly.These findings suggested that rice varieties with higher grain weights exhibited stronger panicle photosynthetic capacity due to their higher chlorophyll content.The enhanced grain photosynthetic rate contributed to improved grain filling and increased grain weight.展开更多
In this work,we proposed a strategy for the hydrolysis of native corn starch after the treatment of corn starch in an ionic liquid aqueous solution,and it is an awfully“green”and simple means to obtain starch with l...In this work,we proposed a strategy for the hydrolysis of native corn starch after the treatment of corn starch in an ionic liquid aqueous solution,and it is an awfully“green”and simple means to obtain starch with low molecular weight and amorphous state.X-ray diffraction results revealed that the natural starch crystalline region was largely disrupted by ionic liquid owing to the broken intermolecular and intramolecular hydrogen bonds.After hydrolysis,the morphology of starch changed from particles of native corn starch into little pieces,and their molecular weight could be effectively regulated during the hydrolysis process,and also the hydrolyzed starch samples exhibited decreased thermal stability with the extension of hydrolysis time.This work would counsel as a powerful tool for the development of native starch in realistic applications.展开更多
In this paper,we present a necessary and sufficient condition for hyponormal block Toeplitz operators T on the vector-valued weighted Bergman space with symbolsΦ(z)=G^(*)(z)+F(z),where F(z)=∑^(N)_(i)=1 A_(i)z^(i)and...In this paper,we present a necessary and sufficient condition for hyponormal block Toeplitz operators T on the vector-valued weighted Bergman space with symbolsΦ(z)=G^(*)(z)+F(z),where F(z)=∑^(N)_(i)=1 A_(i)z^(i)and G(z)=∑^(N)_(i)=1 A_(−i)z^(i),A_(i)ae culants.展开更多
Machinery condition monitoring is beneficial to equipment maintenance and has been receiving much attention from academia and industry.Machine learning,especially deep learning,has become popular for machinery conditi...Machinery condition monitoring is beneficial to equipment maintenance and has been receiving much attention from academia and industry.Machine learning,especially deep learning,has become popular for machinery condition monitoring because that can fully use available data and computational power.Since significant accidents might be caused if wrong fault alarms are given for machine condition monitoring,interpretable machine learning models,integrate signal processing knowledge to enhance trustworthiness of models,are gradually becoming a research hotspot.A previous spectrum-based and interpretable optimized weights method has been proposed to indicate faulty and fundamental frequencies when the analyzed data only contains a healthy type and a fault type.Considering that multiclass fault types are naturally met in practice,this work aims to explore the interpretable optimized weights method for multiclass fault type scenarios.Therefore,a new multiclass optimized weights spectrum(OWS)is proposed and further studied theoretically and numerically.It is found that the multiclass OWS is capable of capturing the characteristic components associated with different conditions and clearly indicating specific fault characteristic frequencies(FCFs)corresponding to each fault condition.This work can provide new insights into spectrum-based fault classification models,and the new multiclass OWS also shows great potential for practical applications.展开更多
With the increasing complexity of vehicular networks and the proliferation of connected vehicles,Federated Learning(FL)has emerged as a critical framework for decentralized model training while preserving data privacy...With the increasing complexity of vehicular networks and the proliferation of connected vehicles,Federated Learning(FL)has emerged as a critical framework for decentralized model training while preserving data privacy.However,efficient client selection and adaptive weight allocation in heterogeneous and non-IID environments remain challenging.To address these issues,we propose Federated Learning with Client Selection and Adaptive Weighting(FedCW),a novel algorithm that leverages adaptive client selection and dynamic weight allocation for optimizing model convergence in real-time vehicular networks.FedCW selects clients based on their Euclidean distance from the global model and dynamically adjusts aggregation weights to optimize both data diversity and model convergence.Experimental results show that FedCW significantly outperforms existing FL algorithms such as FedAvg,FedProx,and SCAFFOLD,particularly in non-IID settings,achieving faster convergence,higher accuracy,and reduced communication overhead.These findings demonstrate that FedCW provides an effective solution for enhancing the performance of FL in heterogeneous,edge-based computing environments.展开更多
Ultra-high molecular weight polyethylene(UHMWPE)is a key material for marine applications owing to its outstanding self-lubrication and corrosion resistance.However,its long-term performance is compromised by plastic ...Ultra-high molecular weight polyethylene(UHMWPE)is a key material for marine applications owing to its outstanding self-lubrication and corrosion resistance.However,its long-term performance is compromised by plastic deformation in seawater.In this study,we performed a comparative analysis of the UHMWPE dynamics under seawater and water conditions to investigate the plastic deformation of UHMWPE induced by seawater.The results show that the plastic deformation of UHMWPE is amplified in seawater relative to the water conditions.Under thin fluid conditions,frictional interfaces exhibit a higher interfacial friction force and interaction energy in seawater than in water.Compared to freely diffused water molecules,hydrated ions occupy larger interchain spaces within polyethylene.Furthermore,the diffusion of hydrated ions weakens the interchain interactions,promoting more severe polyethylene chain rearrangement and accelerating seawater-induced plastic deformation in UHMWPE during friction.Furthermore,the diffused seawater accelerated the disentangling of the polyethylene chains and enhanced the orderly orientation distribution of polyethylene.Compared to free water molecules,the water molecules of hydrated ions exhibit enhanced attraction to free-flowing water molecules,thereby accelerating seawater flow across submerged UHMWPE surfaces.This flow enhancement promotes surface polyethylene chain mobility in seawater.展开更多
In image analysis,high-precision semantic segmentation predominantly relies on supervised learning.Despite significant advancements driven by deep learning techniques,challenges such as class imbalance and dynamic per...In image analysis,high-precision semantic segmentation predominantly relies on supervised learning.Despite significant advancements driven by deep learning techniques,challenges such as class imbalance and dynamic performance evaluation persist.Traditional weighting methods,often based on pre-statistical class counting,tend to overemphasize certain classes while neglecting others,particularly rare sample categories.Approaches like focal loss and other rare-sample segmentation techniques introduce multiple hyperparameters that require manual tuning,leading to increased experimental costs due to their instability.This paper proposes a novel CAWASeg framework to address these limitations.Our approach leverages Grad-CAM technology to generate class activation maps,identifying key feature regions that the model focuses on during decision-making.We introduce a Comprehensive Segmentation Performance Score(CSPS)to dynamically evaluate model performance by converting these activation maps into pseudo mask and comparing them with Ground Truth.Additionally,we design two adaptive weights for each class:a Basic Weight(BW)and a Ratio Weight(RW),which the model adjusts during training based on real-time feedback.Extensive experiments on the COCO-Stuff,CityScapes,and ADE20k datasets demonstrate that our CAWASeg framework significantly improves segmentation performance for rare sample categories while enhancing overall segmentation accuracy.The proposed method offers a robust and efficient solution for addressing class imbalance in semantic segmentation tasks.展开更多
The accessibility of urban public transit directly influences residents’quality of life,travel behavior,and social equity.Its correlation with housing prices has garnered significant attention across disciplines such...The accessibility of urban public transit directly influences residents’quality of life,travel behavior,and social equity.Its correlation with housing prices has garnered significant attention across disciplines such as geography,economics,and urban planning.Although much existing research focuses on the impact of individual transportation facilities on housing prices,there is a notable gap in comprehensive analyses that assess the influence of overall urban transit accessibility on housing market dynamics.This study selected the main urban area of Hefei,China,as a case to investigate the spatial distribution of housing prices and evaluate public transit accessibility in 2022.Employing techniques such as the optimized parameter geographical detector and local spatial regression models,the study aimed to elucidate the effects and underlying mechanisms of urban transit accessibility on housing prices.The findings revealed that:1)housing prices in Hefei exhibited a clustered spatial pattern,with high prices concentrated in the city center and lower prices in peripheral areas,forming three distinct high-price hotspots with a‘belt-like’distribution;2)public transit accessibility showed a‘coreperiphery’structure,with accessibility declining in a‘circumferential’pattern around the city center.Based on the‘housing price-accessibility’dimension,four categories were identified:high price-high accessibility(37.25%),high price-low accessibility(19.07%),low price-high accessibility(21.95%),and low price-low accessibility(21.73%);3)the impact of transit accessibility on housing prices was spatially heterogeneous,with bus travel showing the strongest explanatory power(0.692),followed by automobile,subway,and bicycle travel.The interaction of these transportation modes generated a synergistic effect on housing price differentiation,with most influencing factors contributing more than 25%.These findings offer valuable insights for optimizing the spatial distribution of public transit infrastructure and improving both urban housing quality and residents’living standards.展开更多
Partition-based clustering with weighted feature is developed in the framework of shadowed sets. The objects in the core and boundary regions, generated by shadowed sets-based clustering, have different impact on the ...Partition-based clustering with weighted feature is developed in the framework of shadowed sets. The objects in the core and boundary regions, generated by shadowed sets-based clustering, have different impact on the prototype of each cluster. By integrating feature weights, a formula for weight calculation is introduced to the clustering algorithm. The selection of weight exponent is crucial for good result and the weights are updated iteratively with each partition of clusters. The convergence of the weighted algorithms is given, and the feasible cluster validity indices of data mining application are utilized. Experimental results on both synthetic and real-life numerical data with different feature weights demonstrate that the weighted algorithm is better than the other unweighted algorithms.展开更多
Based on the properties of ordered weighted averaging (OWA) operator and regular increasing monotone (RIM) quantifier, three methods for generating monotonic OWA operator weights are proposed. They are geometric OWA o...Based on the properties of ordered weighted averaging (OWA) operator and regular increasing monotone (RIM) quantifier, three methods for generating monotonic OWA operator weights are proposed. They are geometric OWA operator weights, equidifferent OWA operator weights and the modified RIM quantifier OWA weights. Compared with most of the common OWA methods for generating weights, the methods proposed in this paper are more intuitive and efficient in computation. And as there are more than one solution in most cases, the decision maker can set some initial condition and chooses the appropriate solution in the real decision process, which increases the flexibility of decision making to some extent. All these three OWA methods for generating weights are illustrated by numerical examples.展开更多
Based on the quantifier guided method,an ordered weighted averaging(OWA)weights generating method under given orness level with regular increasing monotone(RIM)quantifiers is proposed.Then the RIM quantifier based OWA...Based on the quantifier guided method,an ordered weighted averaging(OWA)weights generating method under given orness level with regular increasing monotone(RIM)quantifiers is proposed.Then the RIM quantifier based OWA weights generating method is modified to make the generated weights be monotonic,which can be used to express the decision maker's consistent preference information.Finally,both of these weights generating methods are extended to their generic forms,so that they can generate the OWA weights for any ordinary elements set with any given aggregated value.展开更多
Porcine carcass traits and organ weights have important economic roles in the swine industry. A total of 576 animals from a Large White×Minzhu intercross population were genotyped using the Illumina PorcineSNP60K...Porcine carcass traits and organ weights have important economic roles in the swine industry. A total of 576 animals from a Large White×Minzhu intercross population were genotyped using the Illumina PorcineSNP60K Beadchip and were phenotyped for 10 traits, speciifcally, backfat thickness （6-7 libs）, carcass length, carcass weight, foot weight, head weight, heart weight, leaf fat weight, liver weight, lung weight and slaughter body weight. The genome-wide association study （GWAS） was assessed by Genome Wide Rapid Association using the mixed model and regression-genomic control approach. A total of 31 single nucleotide polymorphisms （SNPs） （with the most signiifcant SNP being MARC0033464, P value=6.80×10-13） were located in a 9.76-Mb （31.24-41.00 Mb） region on SSC7 and were found to be signiifcantly associated with one or more carcass traits and organ weights. High percentage of phenotypic variance explanation was observed for each trait ranging from 31.21 to 67.42%. Linkage analysis revealed one haplotype block of 495 kb, in which the most signiifcant SNP being MARC0033464 was contained, on SSC7 at complete linkage disequilibrium. Annotation of the pig reference genome suggested 6 genes （GRM4, HMGA1, NUDT3, RPS10, SPDEF and PACSIN1） in this candidate linkage disequilibrium （LD） interval. Functional analysis indicated that the HMGA1 gene presents the prime biological candidate for carcass traits and organ weights in pig, with potential application in breeding programs.展开更多
The multiple attribute decision making problems are studied, in which the information about attribute weights is partly known and the attribute values take the form of intuitionistic fuzzy numbers. The operational law...The multiple attribute decision making problems are studied, in which the information about attribute weights is partly known and the attribute values take the form of intuitionistic fuzzy numbers. The operational laws of intuitionistic fuzzy numbers are introduced, and the score function and accuracy function are presented to compare the intuitionistic fuzzy numbers. The intuitionistic fuzzy ordered weighted averaging （IFOWA） operator which is an extension of the well-known ordered weighted averaging （OWA） operator is investigated to aggregate the intuitionistic fuzzy information. In order to determine the weights of intuitionistic fuzzy ordered weighted averaging operator, a linear goal programming procedure is proposed for learning the weights from data. Finally, an example is illustrated to verify the effectiveness and practicability of the developed method.展开更多
The objective of the research is to evaluate spatial groundwater quality based on improved fuzzy comprehensive assessment model with entropy weights(FCAEW)in geographical information system(GIS)environment.This paper ...The objective of the research is to evaluate spatial groundwater quality based on improved fuzzy comprehensive assessment model with entropy weights(FCAEW)in geographical information system(GIS)environment.This paper explores the method of comprehensive evaluation of groundwater and sets up an evaluation model applying GIS and FCAEW.Groundwater samples were collected and analyzed from 29 wells in Zhenping County,China.Six parameters were chosen including chloride,sulfate,total hardness,nitrate,fluoride and color.Better spatial interpolation methods for evaluated parameters are found out and selected according to the minimum cross-validation errors from the interpolation methods.FCAEW model was carried out with the help of GIS which makes the evaluating process simpler and easier and more automatically,effectively,efficiently and intelligently.The result embodies the feasibility and effectiveness of FCAEW in GIS when compared with other comprehensive evaluation methods.展开更多
Gengma region, Sanjiang district is known to have some large-scale gold deposits. GIS predictive model for hydrothermal gold potential was carried out in this region using weights of evidence modeling technique. Datas...Gengma region, Sanjiang district is known to have some large-scale gold deposits. GIS predictive model for hydrothermal gold potential was carried out in this region using weights of evidence modeling technique. Datasets used include large-scale hydrothermal gold deposit records, geological, geophysical and remote sensing imagery. Based on the geological and mineral characteristics of areas with known gold occurrences in Sanjiang, several geological features were thought to be indicative of areas with potential for the occurrence of hydrothermal gold deposits. Indicative features were extracted from geoexploration datasets for use as input in the predictive model. The features include host rock lithology, geologic structures, wallrock alteration and associated (volcanic-plutonic) igneous rocks. To determine which of the indicative geological features are important spatial predictors of area with potential for gold deposits, spatial analysis was done through the modeling method. The input maps were buffered and the optimum distance of spatial association for each geological feature was determined by calculating the contrast and studentized contrast. Five feature maps were converted to binary predictor patterns and used as evidential layers for predictive modeling. The binary patterns were integrated in two combinations, each of which consists of four patterns in order to avoid over prediction due to the effect of duplicate features in the two structural evidences. The two produced potential maps define almost similar favorable zones. Areas of intersections between these zones in the two potential maps placed the highest predictive favorable zones in the region.展开更多
Multi-attribute group decision-making problems are considered where information on both attribute weights and value scores of consequences is incomplete.In group decision analysis,if preference information about alter...Multi-attribute group decision-making problems are considered where information on both attribute weights and value scores of consequences is incomplete.In group decision analysis,if preference information about alternatives is provided by participants,it should be verified whether there exist compromise weights that can support all the preference relations.The different compromise weight vectors may differ for the ranking of the alternatives.In the case that compromise weights exist,the method is proposed to find out all the compromise weight vectors in order to rank the alternatives.Based on the new feasible domain of attribute weights determined by all the compromise weight vectors and the incomplete information on value scores of consequences,dominance relations between alternatives are checked by a nonlinear goal programming model which can be transformed into a linear one by adopting a transformation.The checked dominance relations uniformly hold for all compromise weight vectors and the incomplete information on value scores of consequences.A final ranking of the alternatives can be obtained by aggregating these dominance relations.展开更多
Weights of evidence （WofE） is an artificial intelligent method for integration of information from diverse sources for predictive purpose in supporting decision making. This method has been commonly used to predict ...Weights of evidence （WofE） is an artificial intelligent method for integration of information from diverse sources for predictive purpose in supporting decision making. This method has been commonly used to predict point events by integrating point training layer and binary or ternary evidential layers （multiclass evidence less commonly used）. Omnibus weights of evidence integrates fuzzy training layer and diverse evidential layers. This method provides new features in comparison with the ordinary Wore method. This new method has been implemented in a geographic information system-geophysical data analysis system and the method includes the following contents： （1） dual fuzzy weights of evidence （DFWofE）, in which training layer and evidential layers can be treated as fuzzy sets. DFWofE can be used to predict not only point events but also area or line events. In this model a fuzzy training layer can be defined based on point, line, and areas using fuzzy membership function; and （2） degree-of-exploration model for WorE is implemented through building a degree of exploration map. This method can be used to assess possible spatial correlations between the degree of exploration and potential evidential layers. Importantly, it would also make it possible to estimate undiscovered resources, if the degree of exploration map is combined with other models that predict where such resources are most likely to occur. These methods and relevant systems were vafidated using a case study of mineral potential prediction in Gejiu （个旧） mineral district, Yunnan （ 云南）, China.展开更多
The veracity of land evaluation is tightly related to the reasonable weights of land evaluation fac- tors. By mapping qualitative linguistic words into a fine-changeable cloud drops and translating the uncertain facto...The veracity of land evaluation is tightly related to the reasonable weights of land evaluation fac- tors. By mapping qualitative linguistic words into a fine-changeable cloud drops and translating the uncertain factor conditions into quantitative values with the uncertain illation based on cloud model, and then, inte- grating correlation analysis, a new way of figuring out the weight of land evaluation factors is proposed. It may solve the limitations of the conventional ways.展开更多
基金supported by the Natural Science Research Project of Colleges and Universities in Anhui Province (No.KJ2021A0479)the Science Research Program of Anhui University of Finance and Economics (No.ACKYC22082)。
文摘We present a gain adaptive tuning method for fiber Raman amplifier(FRA) using two-stage neural networks(NNs) and double weights updates. After training the connection weights of two-stage NNs separately in training phase, the connection weights of the unified NN are updated again in verification phase according to error between the predicted and target gains to eliminate the inherent error of the NNs. The simulation results show that the mean of root mean square error(RMSE) and maximum error of gains are 0.131 d B and 0.281 d B, respectively. It shows that the method can realize adaptive adjustment function of FRA gain with high accuracy.
基金supported by the National Natural Science Foundation of China(12171075)the Science and Technology Research Project of Education Department of Jilin Province(JJKH20241406KJ)Zhan’s research was supported by the Doctoral Startup Fund of Liaoning University of Technology(XB2024029).
文摘In this paper,it is shown that the harmonic Bergman projection P_(ω)^(h),induced by a radial,induced by a radial weightω,is bounded and onto from L^(∞)(D)to the harmonic Bloch space B_(h)if and only ifω∈D,,which is a class of radial weights satisfying the two-sided doubling conditions.As an application,the bounded and compact positive Toeplitz operators T_(μ,ω)on the endpoint case weighted harmonic Bergman space L_(h,ω)^(1)(D)are characterized.
基金supported by the Hunan Provincial Natural Science Foundation of China(Grant No.2023JJ40309)the Changsha Outstanding Innovative Youth Training Program(kq2306015).
文摘Grain filling is a critical determinant of yield and quality in rice.This study aims to clarify the association between grain photosynthesis and the filling rate of rice varieties with different grain weights,providing a theoretical foundation for optimizing grain-filling processes.Two rice varieties with similar growth duration but different grain weights were selected:a large-grain variety,Lingliangyou 268(L268),and a small-grain variety,Ruiliangyou 1053(R1053).Differences in grain filling,grain photosynthetic rate,and grain chlorophyll content were systematically examined during the filling stage.Results showed significant differences in grain-filling,grain photosynthetic rate,and grain chlorophyll content between large-grain and small-grain rice varieties.The grain photosynthetic rate of L268 was a significantly higher than R1053.L268 also exhibited significantly higher initial grain filling rate,maximum grainfilling rate,and mean grain filling rate compared to R1053.Throughout the grain filling period,L268 showed higher grain chlorophyll content(including chlorophyll a,chlorophyll b,and total chlorophyll)than R1053.The increase in chlorophyll content,particularly total chlorophyll,enhanced the grain photosynthetic rate during the early and middle stages of grain filling significantly.These findings suggested that rice varieties with higher grain weights exhibited stronger panicle photosynthetic capacity due to their higher chlorophyll content.The enhanced grain photosynthetic rate contributed to improved grain filling and increased grain weight.
文摘In this work,we proposed a strategy for the hydrolysis of native corn starch after the treatment of corn starch in an ionic liquid aqueous solution,and it is an awfully“green”and simple means to obtain starch with low molecular weight and amorphous state.X-ray diffraction results revealed that the natural starch crystalline region was largely disrupted by ionic liquid owing to the broken intermolecular and intramolecular hydrogen bonds.After hydrolysis,the morphology of starch changed from particles of native corn starch into little pieces,and their molecular weight could be effectively regulated during the hydrolysis process,and also the hydrolyzed starch samples exhibited decreased thermal stability with the extension of hydrolysis time.This work would counsel as a powerful tool for the development of native starch in realistic applications.
文摘In this paper,we present a necessary and sufficient condition for hyponormal block Toeplitz operators T on the vector-valued weighted Bergman space with symbolsΦ(z)=G^(*)(z)+F(z),where F(z)=∑^(N)_(i)=1 A_(i)z^(i)and G(z)=∑^(N)_(i)=1 A_(−i)z^(i),A_(i)ae culants.
基金supported by the National Natural Science Foundation of China under Grant Nos.523B2043 and 52475112.
文摘Machinery condition monitoring is beneficial to equipment maintenance and has been receiving much attention from academia and industry.Machine learning,especially deep learning,has become popular for machinery condition monitoring because that can fully use available data and computational power.Since significant accidents might be caused if wrong fault alarms are given for machine condition monitoring,interpretable machine learning models,integrate signal processing knowledge to enhance trustworthiness of models,are gradually becoming a research hotspot.A previous spectrum-based and interpretable optimized weights method has been proposed to indicate faulty and fundamental frequencies when the analyzed data only contains a healthy type and a fault type.Considering that multiclass fault types are naturally met in practice,this work aims to explore the interpretable optimized weights method for multiclass fault type scenarios.Therefore,a new multiclass optimized weights spectrum(OWS)is proposed and further studied theoretically and numerically.It is found that the multiclass OWS is capable of capturing the characteristic components associated with different conditions and clearly indicating specific fault characteristic frequencies(FCFs)corresponding to each fault condition.This work can provide new insights into spectrum-based fault classification models,and the new multiclass OWS also shows great potential for practical applications.
文摘With the increasing complexity of vehicular networks and the proliferation of connected vehicles,Federated Learning(FL)has emerged as a critical framework for decentralized model training while preserving data privacy.However,efficient client selection and adaptive weight allocation in heterogeneous and non-IID environments remain challenging.To address these issues,we propose Federated Learning with Client Selection and Adaptive Weighting(FedCW),a novel algorithm that leverages adaptive client selection and dynamic weight allocation for optimizing model convergence in real-time vehicular networks.FedCW selects clients based on their Euclidean distance from the global model and dynamically adjusts aggregation weights to optimize both data diversity and model convergence.Experimental results show that FedCW significantly outperforms existing FL algorithms such as FedAvg,FedProx,and SCAFFOLD,particularly in non-IID settings,achieving faster convergence,higher accuracy,and reduced communication overhead.These findings demonstrate that FedCW provides an effective solution for enhancing the performance of FL in heterogeneous,edge-based computing environments.
基金financially supported by the National Natural Science Foundation of China(Nos.51909023 and 51775077)the Natural Science Foundation of Liaoning Province(No.2021-MS-140)the Fundamental Research Funds for the Central Universities(No.3132025114)。
文摘Ultra-high molecular weight polyethylene(UHMWPE)is a key material for marine applications owing to its outstanding self-lubrication and corrosion resistance.However,its long-term performance is compromised by plastic deformation in seawater.In this study,we performed a comparative analysis of the UHMWPE dynamics under seawater and water conditions to investigate the plastic deformation of UHMWPE induced by seawater.The results show that the plastic deformation of UHMWPE is amplified in seawater relative to the water conditions.Under thin fluid conditions,frictional interfaces exhibit a higher interfacial friction force and interaction energy in seawater than in water.Compared to freely diffused water molecules,hydrated ions occupy larger interchain spaces within polyethylene.Furthermore,the diffusion of hydrated ions weakens the interchain interactions,promoting more severe polyethylene chain rearrangement and accelerating seawater-induced plastic deformation in UHMWPE during friction.Furthermore,the diffused seawater accelerated the disentangling of the polyethylene chains and enhanced the orderly orientation distribution of polyethylene.Compared to free water molecules,the water molecules of hydrated ions exhibit enhanced attraction to free-flowing water molecules,thereby accelerating seawater flow across submerged UHMWPE surfaces.This flow enhancement promotes surface polyethylene chain mobility in seawater.
基金supported by the Funds for Central-Guided Local Science and Technology Development(Grant No.202407AC110005)Key Technologies for the Construction of a Whole-Process Intelligent Service System for Neuroendocrine Neoplasm.Supported by 2023 Opening Research Fund of Yunnan Key Laboratory of Digital Communications(YNJTKFB-20230686,YNKLDC-KFKT-202304).
文摘In image analysis,high-precision semantic segmentation predominantly relies on supervised learning.Despite significant advancements driven by deep learning techniques,challenges such as class imbalance and dynamic performance evaluation persist.Traditional weighting methods,often based on pre-statistical class counting,tend to overemphasize certain classes while neglecting others,particularly rare sample categories.Approaches like focal loss and other rare-sample segmentation techniques introduce multiple hyperparameters that require manual tuning,leading to increased experimental costs due to their instability.This paper proposes a novel CAWASeg framework to address these limitations.Our approach leverages Grad-CAM technology to generate class activation maps,identifying key feature regions that the model focuses on during decision-making.We introduce a Comprehensive Segmentation Performance Score(CSPS)to dynamically evaluate model performance by converting these activation maps into pseudo mask and comparing them with Ground Truth.Additionally,we design two adaptive weights for each class:a Basic Weight(BW)and a Ratio Weight(RW),which the model adjusts during training based on real-time feedback.Extensive experiments on the COCO-Stuff,CityScapes,and ADE20k datasets demonstrate that our CAWASeg framework significantly improves segmentation performance for rare sample categories while enhancing overall segmentation accuracy.The proposed method offers a robust and efficient solution for addressing class imbalance in semantic segmentation tasks.
基金Under the auspices of the National Natural Science Foundation of China(No.42271224,41901193)Ministry of Edu cation Humanities and Social Sciences Research Planning Fund Project of China(No.24YJAZH190)+1 种基金Anhui Province Excellent Youth Research Project in Universities(No.2022AH030019)Anhui Social Sciences Innovation Development Research Project(No.2024CXQ503)。
文摘The accessibility of urban public transit directly influences residents’quality of life,travel behavior,and social equity.Its correlation with housing prices has garnered significant attention across disciplines such as geography,economics,and urban planning.Although much existing research focuses on the impact of individual transportation facilities on housing prices,there is a notable gap in comprehensive analyses that assess the influence of overall urban transit accessibility on housing market dynamics.This study selected the main urban area of Hefei,China,as a case to investigate the spatial distribution of housing prices and evaluate public transit accessibility in 2022.Employing techniques such as the optimized parameter geographical detector and local spatial regression models,the study aimed to elucidate the effects and underlying mechanisms of urban transit accessibility on housing prices.The findings revealed that:1)housing prices in Hefei exhibited a clustered spatial pattern,with high prices concentrated in the city center and lower prices in peripheral areas,forming three distinct high-price hotspots with a‘belt-like’distribution;2)public transit accessibility showed a‘coreperiphery’structure,with accessibility declining in a‘circumferential’pattern around the city center.Based on the‘housing price-accessibility’dimension,four categories were identified:high price-high accessibility(37.25%),high price-low accessibility(19.07%),low price-high accessibility(21.95%),and low price-low accessibility(21.73%);3)the impact of transit accessibility on housing prices was spatially heterogeneous,with bus travel showing the strongest explanatory power(0.692),followed by automobile,subway,and bicycle travel.The interaction of these transportation modes generated a synergistic effect on housing price differentiation,with most influencing factors contributing more than 25%.These findings offer valuable insights for optimizing the spatial distribution of public transit infrastructure and improving both urban housing quality and residents’living standards.
基金Supported by the National Natural Science Foundation of China(61139002)~~
文摘Partition-based clustering with weighted feature is developed in the framework of shadowed sets. The objects in the core and boundary regions, generated by shadowed sets-based clustering, have different impact on the prototype of each cluster. By integrating feature weights, a formula for weight calculation is introduced to the clustering algorithm. The selection of weight exponent is crucial for good result and the weights are updated iteratively with each partition of clusters. The convergence of the weighted algorithms is given, and the feasible cluster validity indices of data mining application are utilized. Experimental results on both synthetic and real-life numerical data with different feature weights demonstrate that the weighted algorithm is better than the other unweighted algorithms.
文摘Based on the properties of ordered weighted averaging (OWA) operator and regular increasing monotone (RIM) quantifier, three methods for generating monotonic OWA operator weights are proposed. They are geometric OWA operator weights, equidifferent OWA operator weights and the modified RIM quantifier OWA weights. Compared with most of the common OWA methods for generating weights, the methods proposed in this paper are more intuitive and efficient in computation. And as there are more than one solution in most cases, the decision maker can set some initial condition and chooses the appropriate solution in the real decision process, which increases the flexibility of decision making to some extent. All these three OWA methods for generating weights are illustrated by numerical examples.
基金The National Key Technology R&D Program of China during the 11th Five-Year Plan Period(No.2006BAH02A06)
文摘Based on the quantifier guided method,an ordered weighted averaging(OWA)weights generating method under given orness level with regular increasing monotone(RIM)quantifiers is proposed.Then the RIM quantifier based OWA weights generating method is modified to make the generated weights be monotonic,which can be used to express the decision maker's consistent preference information.Finally,both of these weights generating methods are extended to their generic forms,so that they can generate the OWA weights for any ordinary elements set with any given aggregated value.
基金supported by the Agricultural Science and Technology Innovation Program, China (ASTIPIAS02)the National Key Technology R&D Program of China (2011BAD28B01)+2 种基金the National Natural Science Foundation of China (31201781)the Earmarked Fund for Modern Agroindustry Technology Research System, National Technology Program of China (2011ZX08006-003)the Chinese Academy of Agricultural Sciences Foundation (2011cj-5, 2012ZL069 and 2014ywf-yb-8)
文摘Porcine carcass traits and organ weights have important economic roles in the swine industry. A total of 576 animals from a Large White×Minzhu intercross population were genotyped using the Illumina PorcineSNP60K Beadchip and were phenotyped for 10 traits, speciifcally, backfat thickness （6-7 libs）, carcass length, carcass weight, foot weight, head weight, heart weight, leaf fat weight, liver weight, lung weight and slaughter body weight. The genome-wide association study （GWAS） was assessed by Genome Wide Rapid Association using the mixed model and regression-genomic control approach. A total of 31 single nucleotide polymorphisms （SNPs） （with the most signiifcant SNP being MARC0033464, P value=6.80×10-13） were located in a 9.76-Mb （31.24-41.00 Mb） region on SSC7 and were found to be signiifcantly associated with one or more carcass traits and organ weights. High percentage of phenotypic variance explanation was observed for each trait ranging from 31.21 to 67.42%. Linkage analysis revealed one haplotype block of 495 kb, in which the most signiifcant SNP being MARC0033464 was contained, on SSC7 at complete linkage disequilibrium. Annotation of the pig reference genome suggested 6 genes （GRM4, HMGA1, NUDT3, RPS10, SPDEF and PACSIN1） in this candidate linkage disequilibrium （LD） interval. Functional analysis indicated that the HMGA1 gene presents the prime biological candidate for carcass traits and organ weights in pig, with potential application in breeding programs.
基金supported by the National Natural Science Foundation of China (70771025)the Fundamental Research Funds for the Central Universities of Hohai University (2009B04514)Humanities and Social Sciences Foundations of Ministry of Education of China(10YJA630067)
文摘The multiple attribute decision making problems are studied, in which the information about attribute weights is partly known and the attribute values take the form of intuitionistic fuzzy numbers. The operational laws of intuitionistic fuzzy numbers are introduced, and the score function and accuracy function are presented to compare the intuitionistic fuzzy numbers. The intuitionistic fuzzy ordered weighted averaging （IFOWA） operator which is an extension of the well-known ordered weighted averaging （OWA） operator is investigated to aggregate the intuitionistic fuzzy information. In order to determine the weights of intuitionistic fuzzy ordered weighted averaging operator, a linear goal programming procedure is proposed for learning the weights from data. Finally, an example is illustrated to verify the effectiveness and practicability of the developed method.
基金supported by the National Natural Science Foundation of China(No.41161020)the Introduction of Talent Project of Ningxia University(No.BQD2012013)the Natural Science Foundation of Ningxia University(No.ZR1209)
文摘The objective of the research is to evaluate spatial groundwater quality based on improved fuzzy comprehensive assessment model with entropy weights(FCAEW)in geographical information system(GIS)environment.This paper explores the method of comprehensive evaluation of groundwater and sets up an evaluation model applying GIS and FCAEW.Groundwater samples were collected and analyzed from 29 wells in Zhenping County,China.Six parameters were chosen including chloride,sulfate,total hardness,nitrate,fluoride and color.Better spatial interpolation methods for evaluated parameters are found out and selected according to the minimum cross-validation errors from the interpolation methods.FCAEW model was carried out with the help of GIS which makes the evaluating process simpler and easier and more automatically,effectively,efficiently and intelligently.The result embodies the feasibility and effectiveness of FCAEW in GIS when compared with other comprehensive evaluation methods.
文摘Gengma region, Sanjiang district is known to have some large-scale gold deposits. GIS predictive model for hydrothermal gold potential was carried out in this region using weights of evidence modeling technique. Datasets used include large-scale hydrothermal gold deposit records, geological, geophysical and remote sensing imagery. Based on the geological and mineral characteristics of areas with known gold occurrences in Sanjiang, several geological features were thought to be indicative of areas with potential for the occurrence of hydrothermal gold deposits. Indicative features were extracted from geoexploration datasets for use as input in the predictive model. The features include host rock lithology, geologic structures, wallrock alteration and associated (volcanic-plutonic) igneous rocks. To determine which of the indicative geological features are important spatial predictors of area with potential for gold deposits, spatial analysis was done through the modeling method. The input maps were buffered and the optimum distance of spatial association for each geological feature was determined by calculating the contrast and studentized contrast. Five feature maps were converted to binary predictor patterns and used as evidential layers for predictive modeling. The binary patterns were integrated in two combinations, each of which consists of four patterns in order to avoid over prediction due to the effect of duplicate features in the two structural evidences. The two produced potential maps define almost similar favorable zones. Areas of intersections between these zones in the two potential maps placed the highest predictive favorable zones in the region.
基金supported by the Humanities and Social Sciences Foundation of Ministry of Education of China(09YJC630229)Scientific Research Foundation of Guangxi University for Nationalities for Talent Introduction(200702YZ01)Science and Technology Project of State Ethnic Affairs Commission(09GX03)
文摘Multi-attribute group decision-making problems are considered where information on both attribute weights and value scores of consequences is incomplete.In group decision analysis,if preference information about alternatives is provided by participants,it should be verified whether there exist compromise weights that can support all the preference relations.The different compromise weight vectors may differ for the ranking of the alternatives.In the case that compromise weights exist,the method is proposed to find out all the compromise weight vectors in order to rank the alternatives.Based on the new feasible domain of attribute weights determined by all the compromise weight vectors and the incomplete information on value scores of consequences,dominance relations between alternatives are checked by a nonlinear goal programming model which can be transformed into a linear one by adopting a transformation.The checked dominance relations uniformly hold for all compromise weight vectors and the incomplete information on value scores of consequences.A final ranking of the alternatives can be obtained by aggregating these dominance relations.
基金supported by the National Natural Science Foundation of China (No. 40638041)National Key Technology R&D Program (No. 2006BAB01A01)+2 种基金Project of China Geological Survey (No. 1212010633910)the National High Technology Research and Development Program of China (Nos. 2006AA06Z115, 2006AA06Z113)State Key Laboratory of Geological Processes and Mineral Resources (No. GPMR2007-12)
文摘Weights of evidence （WofE） is an artificial intelligent method for integration of information from diverse sources for predictive purpose in supporting decision making. This method has been commonly used to predict point events by integrating point training layer and binary or ternary evidential layers （multiclass evidence less commonly used）. Omnibus weights of evidence integrates fuzzy training layer and diverse evidential layers. This method provides new features in comparison with the ordinary Wore method. This new method has been implemented in a geographic information system-geophysical data analysis system and the method includes the following contents： （1） dual fuzzy weights of evidence （DFWofE）, in which training layer and evidential layers can be treated as fuzzy sets. DFWofE can be used to predict not only point events but also area or line events. In this model a fuzzy training layer can be defined based on point, line, and areas using fuzzy membership function; and （2） degree-of-exploration model for WorE is implemented through building a degree of exploration map. This method can be used to assess possible spatial correlations between the degree of exploration and potential evidential layers. Importantly, it would also make it possible to estimate undiscovered resources, if the degree of exploration map is combined with other models that predict where such resources are most likely to occur. These methods and relevant systems were vafidated using a case study of mineral potential prediction in Gejiu （个旧） mineral district, Yunnan （ 云南）, China.
文摘The veracity of land evaluation is tightly related to the reasonable weights of land evaluation fac- tors. By mapping qualitative linguistic words into a fine-changeable cloud drops and translating the uncertain factor conditions into quantitative values with the uncertain illation based on cloud model, and then, inte- grating correlation analysis, a new way of figuring out the weight of land evaluation factors is proposed. It may solve the limitations of the conventional ways.
