Groundwater inverse modeling is a vital technique for estimating unmeasurable model parameters and enhancing numerical simulation accuracy.This paper comprehensively reviews the current advances and future prospects o...Groundwater inverse modeling is a vital technique for estimating unmeasurable model parameters and enhancing numerical simulation accuracy.This paper comprehensively reviews the current advances and future prospects of metaheuristic algorithm-based groundwater model parameter inversion.Initially,the simulation-optimization parameter estimation framework is introduced,which involves the integration of simulation models with metaheuristic algorithms.The subsequent sections explore the fundamental principles of four widely employed metaheuristic algorithms-genetic algorithm(GA),particle swarm optimization(PSO),simulated annealing(SA),and differential evolution(DE)-highlighting their recent applications in water resources research and related areas.Then,a solute transport model is designed to illustrate how to apply and evaluate these four optimization algorithms in addressing challenges related to model parameter inversion.Finally,three noteworthy directions are presented to address the common challenges among current studies,including balancing the diverse exploration and centralized exploitation within metaheuristic algorithms,local approxi-mate error of the surrogate model,and the curse of dimensionality in spatial variational heterogeneous pa-rameters.In summary,this review paper provides theoretical insights and practical guidance for further advancements in groundwater inverse modeling studies.展开更多
Due to the increasing cyber-attacks,various Intrusion Detection Systems(IDSs)have been proposed to identify network anomalies.Most existing machine learning-based IDSs learn patterns from the features extracted from n...Due to the increasing cyber-attacks,various Intrusion Detection Systems(IDSs)have been proposed to identify network anomalies.Most existing machine learning-based IDSs learn patterns from the features extracted from network traffic flows,and the deep learning-based approaches can learn data distribution features from the raw data to differentiate normal and anomalous network flows.Although having been used in the real world widely,the above methods are vulnerable to some types of attacks.In this paper,we propose a novel attack framework,Anti-Intrusion Detection AutoEncoder(AIDAE),to generate features to disable the IDS.In the proposed framework,an encoder transforms features into a latent space,and multiple decoders reconstruct the continuous and discrete features,respectively.Additionally,a generative adversarial network is used to learn the flexible prior distribution of the latent space.The correlation between continuous and discrete features can be kept by using the proposed training scheme.Experiments conducted on NSL-KDD,UNSW-NB15,and CICIDS2017 datasets show that the generated features indeed degrade the detection performance of existing IDSs dramatically.展开更多
To have uniform nanoparticles individually dispersed on substrate before single-walled carbon nanotubes(SWNTs)growth at high temperature is the key for controlling the diameter of the SWNTs.In this letter,a facile app...To have uniform nanoparticles individually dispersed on substrate before single-walled carbon nanotubes(SWNTs)growth at high temperature is the key for controlling the diameter of the SWNTs.In this letter,a facile approach to control the diameter and distribution of the SWNTs by improving the dispersion of the uniform Fe/Mo nanoparticles on silicon wafers with silica layer chemically modified by 1,1,1,3,3,3-hexamethyldisilazane under different conditions is reported.It is found that the dispersion of the catalyst nanoparticles on Si wafer surface can be improved greatly from hydrophilic to hydrophobic,and the diameter and distribution of the SWNTs depend strongly on the dispersion of the catalyst on the substrate surface.Well dispersion of the catalyst results in relatively smaller diameter and narrower distribution of the SWNTs due to the decrease of aggregation and enhancement of dispersion of the catalyst nanoparticles before growth.It is also found that the diameter of the superlong aligned SWNTs is smaller with more narrow distribution than that of random nanotubes.展开更多
Background Dengue fever,a mosquito-borne disease,is influenced by temperature.As global warming intensifies,the frequency of hot nights has increased.However,the relationship between hot nights and dengue transmission...Background Dengue fever,a mosquito-borne disease,is influenced by temperature.As global warming intensifies,the frequency of hot nights has increased.However,the relationship between hot nights and dengue transmission remains unclear.This study aimed to evaluate the impact of hot night exposures on dengue incidence.Methods We collected individual dengue data from Brazil’s SINAN database(2014–2021),covering 5,708,691 patients.Hot night exposures,including the average maximum nighttime temperatures,hot night excess,and hot night duration,were calculated using the ERA5-land dataset.A case-crossover design was employed to assess the association between each hot night exposure and dengue incidence using conditional logistic regression.Results The average maximum nighttime temperature,hot night excess,and hot night duration were all significantly associated with increased risk of dengue,with odds ratios(ORs)of 1.86(95%CI 1.86–1.87),1.01(95%CI 1.01–1.01),and 1.05(95%CI 1.05–1.05),respectively.The attributable risks for each hot night exposure were 14.02%(95%CI 13.49%–14.60%),27.80%(95%CI 27.33%–28.21%),and 26.95%(95%CI 26.58%–27.38%),respectively,when the exposure value was above the 90th percentile of its distribution.Conclusions Hot night exposures were associated with an increased risk of dengue in Brazil.The public health burden of dengue is likely to rise with increasing hot night exposures,especially as hot nights become more frequent worldwide.Implementation of targeted vector control strategies and improved access to cooling equipment,such as air-conditioning,may serve as important mitigation measures.展开更多
The deformability and high degree of freedom of mollusks bring challenges in mathematical modeling and synthesis of motions.Traditional analytical and statistical models are limited by either rigid skeleton assumption...The deformability and high degree of freedom of mollusks bring challenges in mathematical modeling and synthesis of motions.Traditional analytical and statistical models are limited by either rigid skeleton assumptions or model capacity,and have difficulty in generating realistic and multi-pattern mollusk motions.In this work,we present a large-scale dynamic pose dataset of Drosophila larvae and propose a motion synthesis model named Path2Pose to generate a pose sequence given the initial poses and the subsequent guiding path.The Path2Pose model is further used to synthesize long pose sequences of various motion patterns through a recursive generation method.Evaluation analysis results demonstrate that our novel model synthesizes highly realistic mollusk motions and achieves state-of-the-art performance.Our work proves high performance of deep neural networks for mollusk motion synthesis and the feasibility of long pose sequence synthesis based on the customized body shape and guiding path.展开更多
基金supported by the Fundamental Research Funds for the Central Universities(XJ2023005201)the National Natural Science Foundation of China(NSFC:U2267217,42141011,and 42002254).
文摘Groundwater inverse modeling is a vital technique for estimating unmeasurable model parameters and enhancing numerical simulation accuracy.This paper comprehensively reviews the current advances and future prospects of metaheuristic algorithm-based groundwater model parameter inversion.Initially,the simulation-optimization parameter estimation framework is introduced,which involves the integration of simulation models with metaheuristic algorithms.The subsequent sections explore the fundamental principles of four widely employed metaheuristic algorithms-genetic algorithm(GA),particle swarm optimization(PSO),simulated annealing(SA),and differential evolution(DE)-highlighting their recent applications in water resources research and related areas.Then,a solute transport model is designed to illustrate how to apply and evaluate these four optimization algorithms in addressing challenges related to model parameter inversion.Finally,three noteworthy directions are presented to address the common challenges among current studies,including balancing the diverse exploration and centralized exploitation within metaheuristic algorithms,local approxi-mate error of the surrogate model,and the curse of dimensionality in spatial variational heterogeneous pa-rameters.In summary,this review paper provides theoretical insights and practical guidance for further advancements in groundwater inverse modeling studies.
文摘Due to the increasing cyber-attacks,various Intrusion Detection Systems(IDSs)have been proposed to identify network anomalies.Most existing machine learning-based IDSs learn patterns from the features extracted from network traffic flows,and the deep learning-based approaches can learn data distribution features from the raw data to differentiate normal and anomalous network flows.Although having been used in the real world widely,the above methods are vulnerable to some types of attacks.In this paper,we propose a novel attack framework,Anti-Intrusion Detection AutoEncoder(AIDAE),to generate features to disable the IDS.In the proposed framework,an encoder transforms features into a latent space,and multiple decoders reconstruct the continuous and discrete features,respectively.Additionally,a generative adversarial network is used to learn the flexible prior distribution of the latent space.The correlation between continuous and discrete features can be kept by using the proposed training scheme.Experiments conducted on NSL-KDD,UNSW-NB15,and CICIDS2017 datasets show that the generated features indeed degrade the detection performance of existing IDSs dramatically.
基金financial support from NSFC(2117315951420105002)
文摘To have uniform nanoparticles individually dispersed on substrate before single-walled carbon nanotubes(SWNTs)growth at high temperature is the key for controlling the diameter of the SWNTs.In this letter,a facile approach to control the diameter and distribution of the SWNTs by improving the dispersion of the uniform Fe/Mo nanoparticles on silicon wafers with silica layer chemically modified by 1,1,1,3,3,3-hexamethyldisilazane under different conditions is reported.It is found that the dispersion of the catalyst nanoparticles on Si wafer surface can be improved greatly from hydrophilic to hydrophobic,and the diameter and distribution of the SWNTs depend strongly on the dispersion of the catalyst on the substrate surface.Well dispersion of the catalyst results in relatively smaller diameter and narrower distribution of the SWNTs due to the decrease of aggregation and enhancement of dispersion of the catalyst nanoparticles before growth.It is also found that the diameter of the superlong aligned SWNTs is smaller with more narrow distribution than that of random nanotubes.
文摘Background Dengue fever,a mosquito-borne disease,is influenced by temperature.As global warming intensifies,the frequency of hot nights has increased.However,the relationship between hot nights and dengue transmission remains unclear.This study aimed to evaluate the impact of hot night exposures on dengue incidence.Methods We collected individual dengue data from Brazil’s SINAN database(2014–2021),covering 5,708,691 patients.Hot night exposures,including the average maximum nighttime temperatures,hot night excess,and hot night duration,were calculated using the ERA5-land dataset.A case-crossover design was employed to assess the association between each hot night exposure and dengue incidence using conditional logistic regression.Results The average maximum nighttime temperature,hot night excess,and hot night duration were all significantly associated with increased risk of dengue,with odds ratios(ORs)of 1.86(95%CI 1.86–1.87),1.01(95%CI 1.01–1.01),and 1.05(95%CI 1.05–1.05),respectively.The attributable risks for each hot night exposure were 14.02%(95%CI 13.49%–14.60%),27.80%(95%CI 27.33%–28.21%),and 26.95%(95%CI 26.58%–27.38%),respectively,when the exposure value was above the 90th percentile of its distribution.Conclusions Hot night exposures were associated with an increased risk of dengue in Brazil.The public health burden of dengue is likely to rise with increasing hot night exposures,especially as hot nights become more frequent worldwide.Implementation of targeted vector control strategies and improved access to cooling equipment,such as air-conditioning,may serve as important mitigation measures.
基金supported by the Zhejiang Lab,China(No.2020KB0AC02)the Zhejiang Provincial Key R&D Program,China(Nos.2022C01022,2022C01119,and 2021C03003)+2 种基金the National Natural Science Foundation of China(Nos.T2293723 and 61972347)the Zhejiang Provincial Natural Science Foundation,China(No.LR19F020005)the Fundamental Research Funds for the Central Universities,China(No.226-2022-00051)。
文摘The deformability and high degree of freedom of mollusks bring challenges in mathematical modeling and synthesis of motions.Traditional analytical and statistical models are limited by either rigid skeleton assumptions or model capacity,and have difficulty in generating realistic and multi-pattern mollusk motions.In this work,we present a large-scale dynamic pose dataset of Drosophila larvae and propose a motion synthesis model named Path2Pose to generate a pose sequence given the initial poses and the subsequent guiding path.The Path2Pose model is further used to synthesize long pose sequences of various motion patterns through a recursive generation method.Evaluation analysis results demonstrate that our novel model synthesizes highly realistic mollusk motions and achieves state-of-the-art performance.Our work proves high performance of deep neural networks for mollusk motion synthesis and the feasibility of long pose sequence synthesis based on the customized body shape and guiding path.
