以Tor网络为代表的匿名网络在带来强隐私性保护的同时也为网络违法犯罪活动提供了温床,因此,开展实时、高精度的Tor网络流量识别研究具有重要的现实意义。为此,针对现有研究存在泛化性不强和实时性差等问题,提出了一种基于多模态特征融...以Tor网络为代表的匿名网络在带来强隐私性保护的同时也为网络违法犯罪活动提供了温床,因此,开展实时、高精度的Tor网络流量识别研究具有重要的现实意义。为此,针对现有研究存在泛化性不强和实时性差等问题,提出了一种基于多模态特征融合和Stacking集成学习技术的Tor网络流量识别方法rtTorTIM。具体来讲,该方法首先提取Tor网络流量的主机级、流级和包级3种模态相关特征并构造特征数据集;随后,rtTorTIM选取随机森林、线性回归和K-近邻方法作为基学习器,并使用一个线性神经网络进行决策融合,从而构建起一个2层Stacking流量分类器。基于ISCX Tor 2016公开数据集的对比实验结果表明,rtTorTIM方法在Tor流量识别上的准确率、精确率和召回率均达到了99%,同时该方法在分类实时性上也展现出更优的性能。展开更多
At present,the emerging solid-phase friction-based additive manufacturing technology,including friction rolling additive man-ufacturing(FRAM),can only manufacture simple single-pass components.In this study,multi-laye...At present,the emerging solid-phase friction-based additive manufacturing technology,including friction rolling additive man-ufacturing(FRAM),can only manufacture simple single-pass components.In this study,multi-layer multi-pass FRAM-deposited alumin-um alloy samples were successfully prepared using a non-shoulder tool head.The material flow behavior and microstructure of the over-lapped zone between adjacent layers and passes during multi-layer multi-pass FRAM deposition were studied using the hybrid 6061 and 5052 aluminum alloys.The results showed that a mechanical interlocking structure was formed between the adjacent layers and the adja-cent passes in the overlapped center area.Repeated friction and rolling of the tool head led to different degrees of lateral flow and plastic deformation of the materials in the overlapped zone,which made the recrystallization degree in the left and right edge zones of the over-lapped zone the highest,followed by the overlapped center zone and the non-overlapped zone.The tensile strength of the overlapped zone exceeded 90%of that of the single-pass deposition sample.It is proved that although there are uneven grooves on the surface of the over-lapping area during multi-layer and multi-pass deposition,they can be filled by the flow of materials during the deposition of the next lay-er,thus ensuring the dense microstructure and excellent mechanical properties of the overlapping area.The multi-layer multi-pass FRAM deposition overcomes the limitation of deposition width and lays the foundation for the future deposition of large-scale high-performance components.展开更多
Emerging two-dimensional MXenes have been extensively studied in a wide range of fields thanks to their superior electrical and hydrophilic attributes as well as excellent chemical stability and mechanical flexibility...Emerging two-dimensional MXenes have been extensively studied in a wide range of fields thanks to their superior electrical and hydrophilic attributes as well as excellent chemical stability and mechanical flexibility.Among them,the ultrahigh electrical conductivity(σ)and tunable band structures of benchmark Ti_(3)C_(2)T_(x) MXene demonstrate its good potential as thermoelectric(TE)materials.However,both the large variation ofσreported in the literature and the intrinsically low Seebeck coefficient(S)hinder the practical applications.Herein,this study has for the first time systematically investigated the TE properties of neat Ti_(3)C_(2)T_(x) films,which are finely modulated by exploiting different dispersing solvents,controlling nanosheet sizes and constructing composites.First,deionized water is found to be superior for obtaining closely packed MXene sheets relative to other polar solvents.Second,a simultaneous increase in both S andσis realized via elevating centrifugal speed on MXene aqueous suspensions to obtain small-sized nanosheets,thus yielding an ultrahigh power factor up to~156μW m^(-1) K^(-2).Third,S is significantly enhanced yet accompanied by a reduction inσwhen constructing MXene-based nanocomposites,the latter of which is originated from the damage to the intimate stackings of MXene nanosheets.Together,a correlation between the TE properties of neat Ti_(3)C_(2)T_(x) films and the stacking of nanosheets is elucidated,which would stimulate further exploration of MXene TEs.展开更多
随着互联网和电子商务的蓬勃发展,网络购物成为人们生活的常态。精准预测用户的网络购物行为,能为相关行业提供有价值的决策参考。基于此,文章基于集成学习法进行预测,为改进传统Stacking模型中只能结合基分类器预测结果的情况,在构建St...随着互联网和电子商务的蓬勃发展,网络购物成为人们生活的常态。精准预测用户的网络购物行为,能为相关行业提供有价值的决策参考。基于此,文章基于集成学习法进行预测,为改进传统Stacking模型中只能结合基分类器预测结果的情况,在构建Stacking模型时融入贝叶斯模型平均(bayesian model averaging,BMA),体现各基分类器对预测结果的贡献程度,有效结合多个模型优势。利用累积重要性筛选出有代表性的特征变量,评估模型性能以确定合适的基分类器组合,并结合逻辑回归元学习器构建最终的Stacking模型,基于构建好的模型融合BMA进行预测。实验结果表明,融入BMA后的Stacking模型预测用户网络购物行为效果较好。展开更多
Three-dimensional ocean subsurface temperature and salinity structures(OST/OSS)in the South China Sea(SCS)play crucial roles in oceanic climate research and disaster mitigation.Traditionally,real-time OST and OSS are ...Three-dimensional ocean subsurface temperature and salinity structures(OST/OSS)in the South China Sea(SCS)play crucial roles in oceanic climate research and disaster mitigation.Traditionally,real-time OST and OSS are mainly obtained through in-situ ocean observations and simulation by ocean circulation models,which are usually challenging and costly.Recently,dynamical,statistical,or machine learning models have been proposed to invert the OST/OSS from sea surface information;however,these models mainly focused on the inversion of monthly OST and OSS.To address this issue,we apply clustering algorithms and employ a stacking strategy to ensemble three models(XGBoost,Random Forest,and LightGBM)to invert the real-time OST/OSS based on satellite-derived data and the Argo dataset.Subsequently,a fusion of temperature and salinity is employed to reconstruct OST and OSS.In the validation dataset,the depth-averaged Correlation(Corr)of the estimated OST(OSS)is 0.919(0.83),and the average Root-Mean-Square Error(RMSE)is0.639°C(0.087 psu),with a depth-averaged coefficient of determination(R~2)of 0.84(0.68).Notably,at the thermocline where the base models exhibit their maximum error,the stacking-based fusion model exhibited significant performance enhancement,with a maximum enhancement in OST and OSS inversion exceeding 10%.We further found that the estimated OST and OSS exhibit good agreement with the HYbrid Coordinate Ocean Model(HYCOM)data and BOA_Argo dataset during the passage of a mesoscale eddy.This study shows that the proposed model can effectively invert the real-time OST and OSS,potentially enhancing the understanding of multi-scale oceanic processes in the SCS.展开更多
The safety factor is a crucial quantitative index for evaluating slope stability.However,the traditional calculation methods suffer from unreasonable assumptions,complex soil composition,and inadequate consideration o...The safety factor is a crucial quantitative index for evaluating slope stability.However,the traditional calculation methods suffer from unreasonable assumptions,complex soil composition,and inadequate consideration of the influencing factors,leading to large errors in their calculations.Therefore,a stacking ensemble learning model(stacking-SSAOP)based on multi-layer regression algorithm fusion and optimized by the sparrow search algorithm is proposed for predicting the slope safety factor.In this method,the density,cohesion,friction angle,slope angle,slope height,and pore pressure ratio are selected as characteristic parameters from the 210 sets of established slope sample data.Random Forest,Extra Trees,AdaBoost,Bagging,and Support Vector regression are used as the base model(inner loop)to construct the first-level regression algorithm layer,and XGBoost is used as the meta-model(outer loop)to construct the second-level regression algorithm layer and complete the construction of the stacked learning model for improving the model prediction accuracy.The sparrow search algorithm is used to optimize the hyperparameters of the above six regression models and correct the over-and underfitting problems of the single regression model to further improve the prediction accuracy.The mean square error(MSE)of the predicted and true values and the fitting of the data are compared and analyzed.The MSE of the stacking-SSAOP model was found to be smaller than that of the single regression model(MSE=0.03917).Therefore,the former has a higher prediction accuracy and better data fitting.This study innovatively applies the sparrow search algorithm to predict the slope safety factor,showcasing its advantages over traditional methods.Additionally,our proposed stacking-SSAOP model integrates multiple regression algorithms to enhance prediction accuracy.This model not only refines the prediction accuracy of the slope safety factor but also offers a fresh approach to handling the intricate soil composition and other influencing factors,making it a precise and reliable method for slope stability evaluation.This research holds importance for the modernization and digitalization of slope safety assessments.展开更多
文摘以Tor网络为代表的匿名网络在带来强隐私性保护的同时也为网络违法犯罪活动提供了温床,因此,开展实时、高精度的Tor网络流量识别研究具有重要的现实意义。为此,针对现有研究存在泛化性不强和实时性差等问题,提出了一种基于多模态特征融合和Stacking集成学习技术的Tor网络流量识别方法rtTorTIM。具体来讲,该方法首先提取Tor网络流量的主机级、流级和包级3种模态相关特征并构造特征数据集;随后,rtTorTIM选取随机森林、线性回归和K-近邻方法作为基学习器,并使用一个线性神经网络进行决策融合,从而构建起一个2层Stacking流量分类器。基于ISCX Tor 2016公开数据集的对比实验结果表明,rtTorTIM方法在Tor流量识别上的准确率、精确率和召回率均达到了99%,同时该方法在分类实时性上也展现出更优的性能。
基金supported by the National Key Research and Development Program of China(No.2022YFB3404700)the National Natural Science Foundation of China(Nos.52105313 and 52275299)+2 种基金the Research and Development Program of Beijing Municipal Education Commission,China(No.KM202210005036)the Natural Science Foundation of Chongqing,China(No.CSTB2023NSCQ-MSX0701)the National Defense Basic Research Projects of China(No.JCKY2022405C002).
文摘At present,the emerging solid-phase friction-based additive manufacturing technology,including friction rolling additive man-ufacturing(FRAM),can only manufacture simple single-pass components.In this study,multi-layer multi-pass FRAM-deposited alumin-um alloy samples were successfully prepared using a non-shoulder tool head.The material flow behavior and microstructure of the over-lapped zone between adjacent layers and passes during multi-layer multi-pass FRAM deposition were studied using the hybrid 6061 and 5052 aluminum alloys.The results showed that a mechanical interlocking structure was formed between the adjacent layers and the adja-cent passes in the overlapped center area.Repeated friction and rolling of the tool head led to different degrees of lateral flow and plastic deformation of the materials in the overlapped zone,which made the recrystallization degree in the left and right edge zones of the over-lapped zone the highest,followed by the overlapped center zone and the non-overlapped zone.The tensile strength of the overlapped zone exceeded 90%of that of the single-pass deposition sample.It is proved that although there are uneven grooves on the surface of the over-lapping area during multi-layer and multi-pass deposition,they can be filled by the flow of materials during the deposition of the next lay-er,thus ensuring the dense microstructure and excellent mechanical properties of the overlapping area.The multi-layer multi-pass FRAM deposition overcomes the limitation of deposition width and lays the foundation for the future deposition of large-scale high-performance components.
基金supported by the China Postdoctoral Science Foundation(grant No.2024M750511,J.T.)National Key R&D Program of China(grant No.2022YFB3603804,Y.Z.)National Natural Science Foundation of China(NSFC)under grant Nos.82172470(C.X.)and 22375050(Z.L.).
文摘Emerging two-dimensional MXenes have been extensively studied in a wide range of fields thanks to their superior electrical and hydrophilic attributes as well as excellent chemical stability and mechanical flexibility.Among them,the ultrahigh electrical conductivity(σ)and tunable band structures of benchmark Ti_(3)C_(2)T_(x) MXene demonstrate its good potential as thermoelectric(TE)materials.However,both the large variation ofσreported in the literature and the intrinsically low Seebeck coefficient(S)hinder the practical applications.Herein,this study has for the first time systematically investigated the TE properties of neat Ti_(3)C_(2)T_(x) films,which are finely modulated by exploiting different dispersing solvents,controlling nanosheet sizes and constructing composites.First,deionized water is found to be superior for obtaining closely packed MXene sheets relative to other polar solvents.Second,a simultaneous increase in both S andσis realized via elevating centrifugal speed on MXene aqueous suspensions to obtain small-sized nanosheets,thus yielding an ultrahigh power factor up to~156μW m^(-1) K^(-2).Third,S is significantly enhanced yet accompanied by a reduction inσwhen constructing MXene-based nanocomposites,the latter of which is originated from the damage to the intimate stackings of MXene nanosheets.Together,a correlation between the TE properties of neat Ti_(3)C_(2)T_(x) films and the stacking of nanosheets is elucidated,which would stimulate further exploration of MXene TEs.
文摘随着互联网和电子商务的蓬勃发展,网络购物成为人们生活的常态。精准预测用户的网络购物行为,能为相关行业提供有价值的决策参考。基于此,文章基于集成学习法进行预测,为改进传统Stacking模型中只能结合基分类器预测结果的情况,在构建Stacking模型时融入贝叶斯模型平均(bayesian model averaging,BMA),体现各基分类器对预测结果的贡献程度,有效结合多个模型优势。利用累积重要性筛选出有代表性的特征变量,评估模型性能以确定合适的基分类器组合,并结合逻辑回归元学习器构建最终的Stacking模型,基于构建好的模型融合BMA进行预测。实验结果表明,融入BMA后的Stacking模型预测用户网络购物行为效果较好。
基金jointly supported by the National Key Research and Development Program of China(2022YFC3104304)the National Natural Science Foundation of China(Grant No.41876011)+1 种基金the 2022 Research Program of Sanya Yazhou Bay Science and Technology City(SKJC-2022-01-001)the Hainan Province Science and Technology Special Fund(ZDYF2021SHFZ265)。
文摘Three-dimensional ocean subsurface temperature and salinity structures(OST/OSS)in the South China Sea(SCS)play crucial roles in oceanic climate research and disaster mitigation.Traditionally,real-time OST and OSS are mainly obtained through in-situ ocean observations and simulation by ocean circulation models,which are usually challenging and costly.Recently,dynamical,statistical,or machine learning models have been proposed to invert the OST/OSS from sea surface information;however,these models mainly focused on the inversion of monthly OST and OSS.To address this issue,we apply clustering algorithms and employ a stacking strategy to ensemble three models(XGBoost,Random Forest,and LightGBM)to invert the real-time OST/OSS based on satellite-derived data and the Argo dataset.Subsequently,a fusion of temperature and salinity is employed to reconstruct OST and OSS.In the validation dataset,the depth-averaged Correlation(Corr)of the estimated OST(OSS)is 0.919(0.83),and the average Root-Mean-Square Error(RMSE)is0.639°C(0.087 psu),with a depth-averaged coefficient of determination(R~2)of 0.84(0.68).Notably,at the thermocline where the base models exhibit their maximum error,the stacking-based fusion model exhibited significant performance enhancement,with a maximum enhancement in OST and OSS inversion exceeding 10%.We further found that the estimated OST and OSS exhibit good agreement with the HYbrid Coordinate Ocean Model(HYCOM)data and BOA_Argo dataset during the passage of a mesoscale eddy.This study shows that the proposed model can effectively invert the real-time OST and OSS,potentially enhancing the understanding of multi-scale oceanic processes in the SCS.
基金supported by the Basic Research Special Plan of Yunnan Provincial Department of Science and Technology-General Project(Grant No.202101AT070094)。
文摘The safety factor is a crucial quantitative index for evaluating slope stability.However,the traditional calculation methods suffer from unreasonable assumptions,complex soil composition,and inadequate consideration of the influencing factors,leading to large errors in their calculations.Therefore,a stacking ensemble learning model(stacking-SSAOP)based on multi-layer regression algorithm fusion and optimized by the sparrow search algorithm is proposed for predicting the slope safety factor.In this method,the density,cohesion,friction angle,slope angle,slope height,and pore pressure ratio are selected as characteristic parameters from the 210 sets of established slope sample data.Random Forest,Extra Trees,AdaBoost,Bagging,and Support Vector regression are used as the base model(inner loop)to construct the first-level regression algorithm layer,and XGBoost is used as the meta-model(outer loop)to construct the second-level regression algorithm layer and complete the construction of the stacked learning model for improving the model prediction accuracy.The sparrow search algorithm is used to optimize the hyperparameters of the above six regression models and correct the over-and underfitting problems of the single regression model to further improve the prediction accuracy.The mean square error(MSE)of the predicted and true values and the fitting of the data are compared and analyzed.The MSE of the stacking-SSAOP model was found to be smaller than that of the single regression model(MSE=0.03917).Therefore,the former has a higher prediction accuracy and better data fitting.This study innovatively applies the sparrow search algorithm to predict the slope safety factor,showcasing its advantages over traditional methods.Additionally,our proposed stacking-SSAOP model integrates multiple regression algorithms to enhance prediction accuracy.This model not only refines the prediction accuracy of the slope safety factor but also offers a fresh approach to handling the intricate soil composition and other influencing factors,making it a precise and reliable method for slope stability evaluation.This research holds importance for the modernization and digitalization of slope safety assessments.
文摘为了解决单个神经网络预测的局限性和时间序列的波动性,提出了一种奇异谱分析(singular spectrum analysis,SSA)和Stacking框架相结合的短期负荷预测方法。利用随机森林筛选出与历史负荷相关性强烈的特征因素,采用SSA为负荷数据降噪,简化模型计算过程;基于Stacking框架,结合长短期记忆(long and short-term memory,LSTM)-自注意力机制(self-attention mechanism,SA)、径向基(radial base functions,RBF)神经网络和线性回归方法集成新的组合模型,同时利用交叉验证方法避免模型过拟合;选取PJM和澳大利亚电力负荷数据集进行验证。仿真结果表明,与其他模型比较,所提模型预测精度高。
