Soil organic carbon in forest affects nutrient availability,microbial processes,and organic matter inputs.Dominant tree species have increasingly shifted from ectomycorrhizal to arbuscular mycorrhizal associations in ...Soil organic carbon in forest affects nutrient availability,microbial processes,and organic matter inputs.Dominant tree species have increasingly shifted from ectomycorrhizal to arbuscular mycorrhizal associations in subtropical forests.However,the consequences of this shift for soil organic carbon is poorly understood.To address this,a field study was conducted across a natural gradient of arbuscular tree associations to investigate how different mycorrhizal associations affect soil organic carbon quantity,composition,chemical stability,and related soil properties.Soil organic carbon fractions,functional groups,microbial enzyme activities were analyzed.Results showed that increasing arbuscular mycorrhizal dominance was associated with declines in total soil organic carbon,particularly in recalcitrant and aromatic carbon forms.Ectomycorrhizaldominated forests exhibited higher nitrogen availability and elevated nitrogen-hydrolyzing enzyme activity,suggesting enhanced nitrogen acquisition strategies that suppress soil organic carbon decomposition and promote carbon retention.These findings indicate that mycorrhizal-mediated shifts in tree composition may significantly alter soil carbon sequestration potential.Incorporating mycorrhizal functional traits into forest management and carbon modeling could improve predictions of soil organic carbon responses under future environmental change.展开更多
Allometric equations are fundamental tools in ecological research and forestry management,widely used for estimating above-ground biomass and production,serving as the core foundations of dynamic vegetation models.Usi...Allometric equations are fundamental tools in ecological research and forestry management,widely used for estimating above-ground biomass and production,serving as the core foundations of dynamic vegetation models.Using global datasets from Tallo(a tree allometry and crown architecture database encompassing thousands of species)and TRY(a plant traits database),we fit B ayesian hierarchical models with three alternative functional forms(powerlaw,generalized Michaelis-Menten(gMM),and Weibull)to characterize how diameter at breast height(DBH),tree height(H),and crown radius(CR)scale with and without wood density as a species-level predictor.Our analysis revealed that the saturating Weibull function best captured the relationship between tree height and DBH in both functional groups,whereas the CR-DBH relationship was best predicted by a power-law function in angiosperms and by the gMM function in gymnosperms.Although including wood density did not significantly improve predictive performance,it revealed important ecological trade-offs:lighter-wood angiosperms achieve taller mature heights more rapidly,and denser wood promotes wider crown expansion across clades.We also found that accurately estimating DBH required considering both height and crown size,highlighting how these variables together distinguish trees of similar height but differing trunk diameters.Our results emphasize the importance of applying saturating functions for large trees to improve forest biomass estimates and show that wood density,though not always predictive at broad scales,helps illuminate the biomechanical and ecological constraints underlying diverse tree architectures.These findings offer practical pathways for integrating height-and crown-based metrics into existing carbon monitoring programs worldwide.展开更多
Background 3D botanical tree reconstruction from a single image plays a vital role in the field of computer graphics.However,accurately capturing the intricate branching patterns and detailed morphologies of trees rem...Background 3D botanical tree reconstruction from a single image plays a vital role in the field of computer graphics.However,accurately capturing the intricate branching patterns and detailed morphologies of trees remains a challenge.Methods In this study,we proposed a novel approach for single-image tree reconstruction using a conditional generative adversarial network to infer the 3D skeleton of a tree in the form of a 2D skeleton depth map.Based on the 2D skeleton depth map,a corresponding branching structure(3D skeleton)that inherits the tree shape in the input image and leaves can be generated using a procedural modeling technique.Result Experimental results show that the proposed method accurately reconstructs diverse tree structures across species.Both quantitative and qualitative evaluations demonstrate improved skeleton completeness,branching accuracy,and visual realism over baseline methods,while requiring no user input.Conclusions Our proposed approach for generating lifelike 3D tree models from a single image with no user input shows its proficiency in achieving efficient and reliable reconstruction.These results showcase the capability of the proposed model to recreate complex tree architectures while capturing their visual authenticity.展开更多
This paper investigates the reliability of internal marine combustion engines using an integrated approach that combines Fault Tree Analysis(FTA)and Bayesian Networks(BN).FTA provides a structured,top-down method for ...This paper investigates the reliability of internal marine combustion engines using an integrated approach that combines Fault Tree Analysis(FTA)and Bayesian Networks(BN).FTA provides a structured,top-down method for identifying critical failure modes and their root causes,while BN introduces flexibility in probabilistic reasoning,enabling dynamic updates based on new evidence.This dual methodology overcomes the limitations of static FTA models,offering a comprehensive framework for system reliability analysis.Critical failures,including External Leakage(ELU),Failure to Start(FTS),and Overheating(OHE),were identified as key risks.By incorporating redundancy into high-risk components such as pumps and batteries,the likelihood of these failures was significantly reduced.For instance,redundant pumps reduced the probability of ELU by 31.88%,while additional batteries decreased the occurrence of FTS by 36.45%.The results underscore the practical benefits of combining FTA and BN for enhancing system reliability,particularly in maritime applications where operational safety and efficiency are critical.This research provides valuable insights for maintenance planning and highlights the importance of redundancy in critical systems,especially as the industry transitions toward more autonomous vessels.展开更多
Urban forests are highly multifunctional and provide numerous ecological functions.Plant functional traits individually or jointly influence the ecological multifunctionality of tree species(TS-EMF)and can also modify...Urban forests are highly multifunctional and provide numerous ecological functions.Plant functional traits individually or jointly influence the ecological multifunctionality of tree species(TS-EMF)and can also modify TSEMF in response to environmental changes.However,there has been limited exploration of multitrait combinations for predicting TS-EMF across seasons and of trait thresholds that enhance TS-EMF.Here,for 10 dominant tree species in urban forests of Northeast China,14 traits were measured and four aboveground and three belowground ecological functions assessed in three seasons.Ecological functions and TS-EMF differed significantly throughout the seasons(P<0.05).Synergistic relationships were found between carbon sequestration and oxygen release,between cooling and humidification,and between organic carbon accumulation and nutrient cycling.Notably,aboveground multifunctionality played a leading role in TS-EMF.With seasonal changes,resource allocation shifted toward traits related to resource acquisition rather than conservation to maintain TS-EMF.The combination of traits that predicted TS-EMF varied by type,accounting for up to 66.45%of the variation.TS-EMF was primarily driven by leaf structure in spring and by nutrient accumulation in autumn.Leaf carbon content(LCC)consistently served as a stabilizing factor for predicting TS-EMF across seasons.At 36.5-36.8 mg g^(-1),LCC had its optimal effect on TS-EMF.Other traits in combination that positively influence total TS-EMF include leaf nitrogen content(3.43-3.45 mg g^(-1)),leaf phosphorus content(0.80-0.83 mg g^(-1)),and leaf area(65.86-68.43 cm^(2)).Within these specified trait thresholds,Morus alba and Quercus mongolica were identified as key species.These findings suggest that the trade-off between various ecological functions can be managed by altering plant traits across seasons.This approach could provide a theoretical foundation for enhancing the TS-EMF of urban forests through trait-based management,offering practical guidance for selecting tree species.展开更多
We investigated the impact of convexity and isoperimetric deficits on the accuracy of sectional area estimates of tree stems using traditional methods(caliper,tape,formulas based on stem diameter and circumference).In...We investigated the impact of convexity and isoperimetric deficits on the accuracy of sectional area estimates of tree stems using traditional methods(caliper,tape,formulas based on stem diameter and circumference).In two complementary experiments,the use of photographs to estimate cross-sectional areas was first validated,then the use of a caliper and diameter tape was computer-simulated.The results indicated that the photographic method offers high precision,with mean relative errors below 0.1%,minimal deviation,and no significant bias,and the traditional methods led to substantial and systematic errors,with deviations from circularity and convexity significantly increasing the errors in area estimation.展开更多
Transforming urban spatial structures to promote green and low-carbon development is an effective strategy.Although prior studies have examined the impact of urban polycentricity on carbon emissions and economic devel...Transforming urban spatial structures to promote green and low-carbon development is an effective strategy.Although prior studies have examined the impact of urban polycentricity on carbon emissions and economic development,research on its role in the synergistic relationship between these factors regarding carbon emission efficiency is limited.Furthermore,existing literature often overlooks nonlinear effects and interactions with other urban variables.This paper analyzed data from 295 Chinese cities in 2020,calculating urban population polycentricity,population dispersion indices,and carbon emission efficiency.Utilizing local spatial autocorrelation tools,we reveal interactions among urban population polycentricity,dispersion,carbon emissions,and carbon emission efficiency.We then employ a gradient boosting decision tree model(GBDT)to explore nonlinear and synergistic effects of polycentric urbanization.Key findings include:1)polycentric urbanization in Chinese cities exhibits significant spatial differentiation characteristics.The Polycentricity index is relatively high in economically developed eastern coastal regions with an overall low level,carbon emissions are concentrated in industrialized north-central cities and some Yangtze River Delta hubs,and carbon emission efficiency is the highest in the Yangtze River Delta while relatively low in Northeast China;there are significant spatially heterogeneous interaction characteristics among population polycentricity,population dispersion,carbon emissions,and carbon emission efficiency.2)Urban population polycentricity contributes 9.42%to total carbon emissions and 6.24%to carbon emission efficiency.3)The polycentricity index has a nonlinear impact on carbon emissions and carbon emission efficiency:no significant effect when below 0.50 or above 0.55,increased carbon emissions in 0.50-0.53,and reduced carbon emissions with improved efficiency in 0.53-0.55.4)The polycentricity index has an interaction effect with other variables;specifically,when the polycentricity index is between 0.53 and 0.55,its interaction with urban gross domestic product(GDP),urban population,urban built-up area,green coverage rate in built-up areas,urban technological expenditure,and the proportion of the output value of the secondary industry will reduce carbon emissions and improve carbon emission efficiency.These findings enhance the understanding of urban spatial structures and carbon emissions,providing valuable insights for policymakers in developing green and low-carbon strategies.展开更多
Underwater images frequently suffer from chromatic distortion,blurred details,and low contrast,posing significant challenges for enhancement.This paper introduces AquaTree,a novel underwater image enhancement(UIE)meth...Underwater images frequently suffer from chromatic distortion,blurred details,and low contrast,posing significant challenges for enhancement.This paper introduces AquaTree,a novel underwater image enhancement(UIE)method that reformulates the task as a Markov Decision Process(MDP)through the integration of Monte Carlo Tree Search(MCTS)and deep reinforcement learning(DRL).The framework employs an action space of 25 enhancement operators,strategically grouped for basic attribute adjustment,color component balance,correction,and deblurring.Exploration within MCTS is guided by a dual-branch convolutional network,enabling intelligent sequential operator selection.Our core contributions include:(1)a multimodal state representation combining CIELab color histograms with deep perceptual features,(2)a dual-objective reward mechanism optimizing chromatic fidelity and perceptual consistency,and(3)an alternating training strategy co-optimizing enhancement sequences and network parameters.We further propose two inference schemes:an MCTS-based approach prioritizing accuracy at higher computational cost,and an efficient network policy enabling real-time processing with minimal quality loss.Comprehensive evaluations on the UIEB Dataset and Color correction and haze removal comparisons on the U45 Dataset demonstrate AquaTree’s superiority,significantly outperforming nine state-of-the-art methods across five established underwater image quality metrics.展开更多
The increase of competition, economic recession and financial crises has increased business failure and depending on this the researchers have attempted to develop new approaches which can yield more correct and more ...The increase of competition, economic recession and financial crises has increased business failure and depending on this the researchers have attempted to develop new approaches which can yield more correct and more reliable results. The classification and regression tree （CART） is one of the new modeling techniques which is developed for this purpose. In this study, the classification and regression trees method is explained and tested the power of the financial failure prediction. CART is applied for the data of industry companies which is trade in Istanbul Stock Exchange （ISE） between 1997-2007. As a result of this study, it has been observed that, CART has a high predicting power of financial failure one, two and three years prior to failure, and profitability ratios being the most important ratios in the prediction of failure.展开更多
This paper presents a supervised learning algorithm for retinal vascular segmentation based on classification and regression tree (CART) algorithm and improved adptive bosting (AdaBoost). Local binary patterns (LBP) t...This paper presents a supervised learning algorithm for retinal vascular segmentation based on classification and regression tree (CART) algorithm and improved adptive bosting (AdaBoost). Local binary patterns (LBP) texture features and local features are extracted by extracting,reversing,dilating and enhancing the green components of retinal images to construct a 17-dimensional feature vector. A dataset is constructed by using the feature vector and the data manually marked by the experts. The feature is used to generate CART binary tree for nodes,where CART binary tree is as the AdaBoost weak classifier,and AdaBoost is improved by adding some re-judgment functions to form a strong classifier. The proposed algorithm is simulated on the digital retinal images for vessel extraction (DRIVE). The experimental results show that the proposed algorithm has higher segmentation accuracy for blood vessels,and the result basically contains complete blood vessel details. Moreover,the segmented blood vessel tree has good connectivity,which basically reflects the distribution trend of blood vessels. Compared with the traditional AdaBoost classification algorithm and the support vector machine (SVM) based classification algorithm,the proposed algorithm has higher average accuracy and reliability index,which is similar to the segmentation results of the state-of-the-art segmentation algorithm.展开更多
Urban tree species provide various essential ecosystem services in cities,such as regulating urban temperatures,reducing noise,capturing carbon,and mitigating the urban heat island effect.The quality of these services...Urban tree species provide various essential ecosystem services in cities,such as regulating urban temperatures,reducing noise,capturing carbon,and mitigating the urban heat island effect.The quality of these services is influenced by species diversity,tree health,and the distribution and the composition of trees.Traditionally,data on urban trees has been collected through field surveys and manual interpretation of remote sensing images.In this study,we evaluated the effectiveness of multispectral airborne laser scanning(ALS)data in classifying 24 common urban roadside tree species in Espoo,Finland.Tree crown structure information,intensity features,and spectral data were used for classification.Eight different machine learning algorithms were tested,with the extra trees(ET)algorithm performing the best,achieving an overall accuracy of 71.7%using multispectral LiDAR data.This result highlights that integrating structural and spectral information within a single framework can improve the classification accuracy.Future research will focus on identifying the most important features for species classification and developing algorithms with greater efficiency and accuracy.展开更多
基金supported by the National Natural Science Foundation of China(grant numbers 32471851,32171759 and 32201533)Double Thousand Plan of Jiangxi Province(jxsq2023201058)Jiangxi Province Ganpo Juncai Support Plan(2024BCE50043).
文摘Soil organic carbon in forest affects nutrient availability,microbial processes,and organic matter inputs.Dominant tree species have increasingly shifted from ectomycorrhizal to arbuscular mycorrhizal associations in subtropical forests.However,the consequences of this shift for soil organic carbon is poorly understood.To address this,a field study was conducted across a natural gradient of arbuscular tree associations to investigate how different mycorrhizal associations affect soil organic carbon quantity,composition,chemical stability,and related soil properties.Soil organic carbon fractions,functional groups,microbial enzyme activities were analyzed.Results showed that increasing arbuscular mycorrhizal dominance was associated with declines in total soil organic carbon,particularly in recalcitrant and aromatic carbon forms.Ectomycorrhizaldominated forests exhibited higher nitrogen availability and elevated nitrogen-hydrolyzing enzyme activity,suggesting enhanced nitrogen acquisition strategies that suppress soil organic carbon decomposition and promote carbon retention.These findings indicate that mycorrhizal-mediated shifts in tree composition may significantly alter soil carbon sequestration potential.Incorporating mycorrhizal functional traits into forest management and carbon modeling could improve predictions of soil organic carbon responses under future environmental change.
基金supported by the Xingdian Talent Support Program of Yunnan Province(E5YNR03B01)the Xishuangbanna State Rainforest Talent Support Program(E4BN041B01)the CAS President’s International Fellowship Initiative(2020FYB0003)。
文摘Allometric equations are fundamental tools in ecological research and forestry management,widely used for estimating above-ground biomass and production,serving as the core foundations of dynamic vegetation models.Using global datasets from Tallo(a tree allometry and crown architecture database encompassing thousands of species)and TRY(a plant traits database),we fit B ayesian hierarchical models with three alternative functional forms(powerlaw,generalized Michaelis-Menten(gMM),and Weibull)to characterize how diameter at breast height(DBH),tree height(H),and crown radius(CR)scale with and without wood density as a species-level predictor.Our analysis revealed that the saturating Weibull function best captured the relationship between tree height and DBH in both functional groups,whereas the CR-DBH relationship was best predicted by a power-law function in angiosperms and by the gMM function in gymnosperms.Although including wood density did not significantly improve predictive performance,it revealed important ecological trade-offs:lighter-wood angiosperms achieve taller mature heights more rapidly,and denser wood promotes wider crown expansion across clades.We also found that accurately estimating DBH required considering both height and crown size,highlighting how these variables together distinguish trees of similar height but differing trunk diameters.Our results emphasize the importance of applying saturating functions for large trees to improve forest biomass estimates and show that wood density,though not always predictive at broad scales,helps illuminate the biomechanical and ecological constraints underlying diverse tree architectures.These findings offer practical pathways for integrating height-and crown-based metrics into existing carbon monitoring programs worldwide.
文摘Background 3D botanical tree reconstruction from a single image plays a vital role in the field of computer graphics.However,accurately capturing the intricate branching patterns and detailed morphologies of trees remains a challenge.Methods In this study,we proposed a novel approach for single-image tree reconstruction using a conditional generative adversarial network to infer the 3D skeleton of a tree in the form of a 2D skeleton depth map.Based on the 2D skeleton depth map,a corresponding branching structure(3D skeleton)that inherits the tree shape in the input image and leaves can be generated using a procedural modeling technique.Result Experimental results show that the proposed method accurately reconstructs diverse tree structures across species.Both quantitative and qualitative evaluations demonstrate improved skeleton completeness,branching accuracy,and visual realism over baseline methods,while requiring no user input.Conclusions Our proposed approach for generating lifelike 3D tree models from a single image with no user input shows its proficiency in achieving efficient and reliable reconstruction.These results showcase the capability of the proposed model to recreate complex tree architectures while capturing their visual authenticity.
基金supported by Istanbul Technical University(Project No.45698)supported through the“Young Researchers’Career Development Project-training of doctoral students”of the Croatian Science Foundation.
文摘This paper investigates the reliability of internal marine combustion engines using an integrated approach that combines Fault Tree Analysis(FTA)and Bayesian Networks(BN).FTA provides a structured,top-down method for identifying critical failure modes and their root causes,while BN introduces flexibility in probabilistic reasoning,enabling dynamic updates based on new evidence.This dual methodology overcomes the limitations of static FTA models,offering a comprehensive framework for system reliability analysis.Critical failures,including External Leakage(ELU),Failure to Start(FTS),and Overheating(OHE),were identified as key risks.By incorporating redundancy into high-risk components such as pumps and batteries,the likelihood of these failures was significantly reduced.For instance,redundant pumps reduced the probability of ELU by 31.88%,while additional batteries decreased the occurrence of FTS by 36.45%.The results underscore the practical benefits of combining FTA and BN for enhancing system reliability,particularly in maritime applications where operational safety and efficiency are critical.This research provides valuable insights for maintenance planning and highlights the importance of redundancy in critical systems,especially as the industry transitions toward more autonomous vessels.
基金supported by the National Natural Science Foundation(32130068,32271634,and 32071597)CAS Key Laboratory of Forest Ecology and Silviculture,Institute of Applied Ecology,Chinese Academy of Sciences(KLFES-2025)。
文摘Urban forests are highly multifunctional and provide numerous ecological functions.Plant functional traits individually or jointly influence the ecological multifunctionality of tree species(TS-EMF)and can also modify TSEMF in response to environmental changes.However,there has been limited exploration of multitrait combinations for predicting TS-EMF across seasons and of trait thresholds that enhance TS-EMF.Here,for 10 dominant tree species in urban forests of Northeast China,14 traits were measured and four aboveground and three belowground ecological functions assessed in three seasons.Ecological functions and TS-EMF differed significantly throughout the seasons(P<0.05).Synergistic relationships were found between carbon sequestration and oxygen release,between cooling and humidification,and between organic carbon accumulation and nutrient cycling.Notably,aboveground multifunctionality played a leading role in TS-EMF.With seasonal changes,resource allocation shifted toward traits related to resource acquisition rather than conservation to maintain TS-EMF.The combination of traits that predicted TS-EMF varied by type,accounting for up to 66.45%of the variation.TS-EMF was primarily driven by leaf structure in spring and by nutrient accumulation in autumn.Leaf carbon content(LCC)consistently served as a stabilizing factor for predicting TS-EMF across seasons.At 36.5-36.8 mg g^(-1),LCC had its optimal effect on TS-EMF.Other traits in combination that positively influence total TS-EMF include leaf nitrogen content(3.43-3.45 mg g^(-1)),leaf phosphorus content(0.80-0.83 mg g^(-1)),and leaf area(65.86-68.43 cm^(2)).Within these specified trait thresholds,Morus alba and Quercus mongolica were identified as key species.These findings suggest that the trade-off between various ecological functions can be managed by altering plant traits across seasons.This approach could provide a theoretical foundation for enhancing the TS-EMF of urban forests through trait-based management,offering practical guidance for selecting tree species.
文摘We investigated the impact of convexity and isoperimetric deficits on the accuracy of sectional area estimates of tree stems using traditional methods(caliper,tape,formulas based on stem diameter and circumference).In two complementary experiments,the use of photographs to estimate cross-sectional areas was first validated,then the use of a caliper and diameter tape was computer-simulated.The results indicated that the photographic method offers high precision,with mean relative errors below 0.1%,minimal deviation,and no significant bias,and the traditional methods led to substantial and systematic errors,with deviations from circularity and convexity significantly increasing the errors in area estimation.
基金Under the auspices of National Natural Science Foundation of China(No.42571300)。
文摘Transforming urban spatial structures to promote green and low-carbon development is an effective strategy.Although prior studies have examined the impact of urban polycentricity on carbon emissions and economic development,research on its role in the synergistic relationship between these factors regarding carbon emission efficiency is limited.Furthermore,existing literature often overlooks nonlinear effects and interactions with other urban variables.This paper analyzed data from 295 Chinese cities in 2020,calculating urban population polycentricity,population dispersion indices,and carbon emission efficiency.Utilizing local spatial autocorrelation tools,we reveal interactions among urban population polycentricity,dispersion,carbon emissions,and carbon emission efficiency.We then employ a gradient boosting decision tree model(GBDT)to explore nonlinear and synergistic effects of polycentric urbanization.Key findings include:1)polycentric urbanization in Chinese cities exhibits significant spatial differentiation characteristics.The Polycentricity index is relatively high in economically developed eastern coastal regions with an overall low level,carbon emissions are concentrated in industrialized north-central cities and some Yangtze River Delta hubs,and carbon emission efficiency is the highest in the Yangtze River Delta while relatively low in Northeast China;there are significant spatially heterogeneous interaction characteristics among population polycentricity,population dispersion,carbon emissions,and carbon emission efficiency.2)Urban population polycentricity contributes 9.42%to total carbon emissions and 6.24%to carbon emission efficiency.3)The polycentricity index has a nonlinear impact on carbon emissions and carbon emission efficiency:no significant effect when below 0.50 or above 0.55,increased carbon emissions in 0.50-0.53,and reduced carbon emissions with improved efficiency in 0.53-0.55.4)The polycentricity index has an interaction effect with other variables;specifically,when the polycentricity index is between 0.53 and 0.55,its interaction with urban gross domestic product(GDP),urban population,urban built-up area,green coverage rate in built-up areas,urban technological expenditure,and the proportion of the output value of the secondary industry will reduce carbon emissions and improve carbon emission efficiency.These findings enhance the understanding of urban spatial structures and carbon emissions,providing valuable insights for policymakers in developing green and low-carbon strategies.
基金supported by theHubei Provincial Technology Innovation Special Project and the Natural Science Foundation of Hubei Province under Grants 2023BEB024,2024AFC066,respectively.
文摘Underwater images frequently suffer from chromatic distortion,blurred details,and low contrast,posing significant challenges for enhancement.This paper introduces AquaTree,a novel underwater image enhancement(UIE)method that reformulates the task as a Markov Decision Process(MDP)through the integration of Monte Carlo Tree Search(MCTS)and deep reinforcement learning(DRL).The framework employs an action space of 25 enhancement operators,strategically grouped for basic attribute adjustment,color component balance,correction,and deblurring.Exploration within MCTS is guided by a dual-branch convolutional network,enabling intelligent sequential operator selection.Our core contributions include:(1)a multimodal state representation combining CIELab color histograms with deep perceptual features,(2)a dual-objective reward mechanism optimizing chromatic fidelity and perceptual consistency,and(3)an alternating training strategy co-optimizing enhancement sequences and network parameters.We further propose two inference schemes:an MCTS-based approach prioritizing accuracy at higher computational cost,and an efficient network policy enabling real-time processing with minimal quality loss.Comprehensive evaluations on the UIEB Dataset and Color correction and haze removal comparisons on the U45 Dataset demonstrate AquaTree’s superiority,significantly outperforming nine state-of-the-art methods across five established underwater image quality metrics.
文摘The increase of competition, economic recession and financial crises has increased business failure and depending on this the researchers have attempted to develop new approaches which can yield more correct and more reliable results. The classification and regression tree （CART） is one of the new modeling techniques which is developed for this purpose. In this study, the classification and regression trees method is explained and tested the power of the financial failure prediction. CART is applied for the data of industry companies which is trade in Istanbul Stock Exchange （ISE） between 1997-2007. As a result of this study, it has been observed that, CART has a high predicting power of financial failure one, two and three years prior to failure, and profitability ratios being the most important ratios in the prediction of failure.
基金National Natural Science Foundation of China(No.61163010)
文摘This paper presents a supervised learning algorithm for retinal vascular segmentation based on classification and regression tree (CART) algorithm and improved adptive bosting (AdaBoost). Local binary patterns (LBP) texture features and local features are extracted by extracting,reversing,dilating and enhancing the green components of retinal images to construct a 17-dimensional feature vector. A dataset is constructed by using the feature vector and the data manually marked by the experts. The feature is used to generate CART binary tree for nodes,where CART binary tree is as the AdaBoost weak classifier,and AdaBoost is improved by adding some re-judgment functions to form a strong classifier. The proposed algorithm is simulated on the digital retinal images for vessel extraction (DRIVE). The experimental results show that the proposed algorithm has higher segmentation accuracy for blood vessels,and the result basically contains complete blood vessel details. Moreover,the segmented blood vessel tree has good connectivity,which basically reflects the distribution trend of blood vessels. Compared with the traditional AdaBoost classification algorithm and the support vector machine (SVM) based classification algorithm,the proposed algorithm has higher average accuracy and reliability index,which is similar to the segmentation results of the state-of-the-art segmentation algorithm.
文摘Urban tree species provide various essential ecosystem services in cities,such as regulating urban temperatures,reducing noise,capturing carbon,and mitigating the urban heat island effect.The quality of these services is influenced by species diversity,tree health,and the distribution and the composition of trees.Traditionally,data on urban trees has been collected through field surveys and manual interpretation of remote sensing images.In this study,we evaluated the effectiveness of multispectral airborne laser scanning(ALS)data in classifying 24 common urban roadside tree species in Espoo,Finland.Tree crown structure information,intensity features,and spectral data were used for classification.Eight different machine learning algorithms were tested,with the extra trees(ET)algorithm performing the best,achieving an overall accuracy of 71.7%using multispectral LiDAR data.This result highlights that integrating structural and spectral information within a single framework can improve the classification accuracy.Future research will focus on identifying the most important features for species classification and developing algorithms with greater efficiency and accuracy.
