Traditional multivariate parametric control charts often perform inadequately in detecting shifts in the covariance matrix when the data deviate from normality.In this paper,we propose a multivariate nonparametric exp...Traditional multivariate parametric control charts often perform inadequately in detecting shifts in the covariance matrix when the data deviate from normality.In this paper,we propose a multivariate nonparametric exponentially weighted moving average(SGLGEWMA)control chart,incorporating a Sparse Group Lasso penalty,which is capable of detecting shifts in the covariance matrix across a wide range of data types,including discrete,continuous,and mixed distributions.The proposed approach projects multivariate data into a Euclidean space and then computes an approximate Alt’s likelihood ratio,regularized via the Sparse Group Lasso.The resulting EWMA statistic monitors process shifts.Monte Carlo simulations demonstrate that SGLGEWMA outperforms both the Lasso-based LGShewhart and the Ridge-based RGEWMA control charts under various distributions,with enhanced efficacy in high-dimensional scenarios.Sensitivity analyses are performed on the tuning parameters(λ_(1),λ_(2))and smoothing parameterρ,to evaluate their impact on monitoring performance.Additionally,a simulation study and an illustrative example involving covariance monitoring in wafer semiconductor manufacturing are presented to demonstrate the practical application of the proposed chart.Empirical results confirm that the proposed control chart promptly identifies abnormal fluctuations and issues timely alerts,highlighting both its theoretical significance and practical utility.展开更多
Intra-annual climatic variability plays a critical role in regulating wood formation dynamics during the growing season,particularly in seasonally arid regions—such as the Qinling Mountains,China,and Mediterranean fo...Intra-annual climatic variability plays a critical role in regulating wood formation dynamics during the growing season,particularly in seasonally arid regions—such as the Qinling Mountains,China,and Mediterranean forests—where trees exhibit bimodal radial growth patterns as an adaptive response to water stress.While these growth patterns reflect immediate climatic conditions,the role of ecological memory,specifically vegetation growth carryover(VGC)and lagged climate effects(LCEs),remains poorly quantified.We employed the Vaganov–Shashkin(VS)model to analyze intra-annual bimodal growth patterns in two regions and used a vector autoregressive model with impulse response functions to assess the duration and intensity of VGC and LCE on tree-ring growth and remote sensing vegetation indices(leaf area index(LAI)and gross primary productivity(GPP)).Our results revealed bimodal growth patterns with spring and autumn peaks,but the autumn peak occurred earlier in the Qinling Mountains(August–October)than in Mediterranean forests(late September–October).VGC exerted the strongest influence on tree-ring growth in the first year,diminishing significantly after eight years in both regions(p<0.01).Tree-ring growth exhibited positive LCE responses to precipitation and soil moisture but negative responses to temperature(p<0.05).Remote sensing indices(LAI and GPP)displayed stronger VGC effects in the Qinling Mountains than in Mediterranean forests.While both LAI and GPP responded positively to soil moisture,temperature-induced LCE was positive in the Qinling Mountains but negative in the Mediterranean forests(p<0.05).Overall,VGC was the dominant ecological memory effect in both regions.Our results suggest that coupling the VGC and LCE of multiple vegetation growth indicators at multiple scales has the potential to improve the accuracy of global dynamic vegetation models.展开更多
观点分析对于社交媒体这一关键的网络舆论阵地有着重要的现实意义。该文基于非参数模型的文本聚类技术,将社交媒体文本根据用户主张的观点汇总,直观呈现用户群体所持有的不同立场。针对社交媒体文本长度短、数量多、情感丰富等特点,该...观点分析对于社交媒体这一关键的网络舆论阵地有着重要的现实意义。该文基于非参数模型的文本聚类技术,将社交媒体文本根据用户主张的观点汇总,直观呈现用户群体所持有的不同立场。针对社交媒体文本长度短、数量多、情感丰富等特点,该文提出使用情感分布增强(Sentiment Distribution Enhanced,SDE)方法改进现有基于狄利克雷过程混合模型的短文本流聚类算法,以高斯分布建模文本情感,并推导相应的坍缩吉布斯采样算法推断参数。该方法在捕获文本情感特征的同时,能够自动确定聚类簇数量并实现观点聚类。与现有先进方法在Tweets、Google News数据集上的对比实验显示,该文提出的方法在标准化互信息、准确度等指标上取得了超越现有模型的聚类表现,并且在主观性较强的数据集上具有更显著的优势。展开更多
基金Sponsored by the National Natural Science Foundation of China[grant number 12571305]the Natural Science Foundation of Shanghai[grant number 25ZR1401113].
文摘Traditional multivariate parametric control charts often perform inadequately in detecting shifts in the covariance matrix when the data deviate from normality.In this paper,we propose a multivariate nonparametric exponentially weighted moving average(SGLGEWMA)control chart,incorporating a Sparse Group Lasso penalty,which is capable of detecting shifts in the covariance matrix across a wide range of data types,including discrete,continuous,and mixed distributions.The proposed approach projects multivariate data into a Euclidean space and then computes an approximate Alt’s likelihood ratio,regularized via the Sparse Group Lasso.The resulting EWMA statistic monitors process shifts.Monte Carlo simulations demonstrate that SGLGEWMA outperforms both the Lasso-based LGShewhart and the Ridge-based RGEWMA control charts under various distributions,with enhanced efficacy in high-dimensional scenarios.Sensitivity analyses are performed on the tuning parameters(λ_(1),λ_(2))and smoothing parameterρ,to evaluate their impact on monitoring performance.Additionally,a simulation study and an illustrative example involving covariance monitoring in wafer semiconductor manufacturing are presented to demonstrate the practical application of the proposed chart.Empirical results confirm that the proposed control chart promptly identifies abnormal fluctuations and issues timely alerts,highlighting both its theoretical significance and practical utility.
基金supported by the National Natural Science Foundation of China(Nos.42277448,42330501,41971104,and 41807431)。
文摘Intra-annual climatic variability plays a critical role in regulating wood formation dynamics during the growing season,particularly in seasonally arid regions—such as the Qinling Mountains,China,and Mediterranean forests—where trees exhibit bimodal radial growth patterns as an adaptive response to water stress.While these growth patterns reflect immediate climatic conditions,the role of ecological memory,specifically vegetation growth carryover(VGC)and lagged climate effects(LCEs),remains poorly quantified.We employed the Vaganov–Shashkin(VS)model to analyze intra-annual bimodal growth patterns in two regions and used a vector autoregressive model with impulse response functions to assess the duration and intensity of VGC and LCE on tree-ring growth and remote sensing vegetation indices(leaf area index(LAI)and gross primary productivity(GPP)).Our results revealed bimodal growth patterns with spring and autumn peaks,but the autumn peak occurred earlier in the Qinling Mountains(August–October)than in Mediterranean forests(late September–October).VGC exerted the strongest influence on tree-ring growth in the first year,diminishing significantly after eight years in both regions(p<0.01).Tree-ring growth exhibited positive LCE responses to precipitation and soil moisture but negative responses to temperature(p<0.05).Remote sensing indices(LAI and GPP)displayed stronger VGC effects in the Qinling Mountains than in Mediterranean forests.While both LAI and GPP responded positively to soil moisture,temperature-induced LCE was positive in the Qinling Mountains but negative in the Mediterranean forests(p<0.05).Overall,VGC was the dominant ecological memory effect in both regions.Our results suggest that coupling the VGC and LCE of multiple vegetation growth indicators at multiple scales has the potential to improve the accuracy of global dynamic vegetation models.
文摘观点分析对于社交媒体这一关键的网络舆论阵地有着重要的现实意义。该文基于非参数模型的文本聚类技术,将社交媒体文本根据用户主张的观点汇总,直观呈现用户群体所持有的不同立场。针对社交媒体文本长度短、数量多、情感丰富等特点,该文提出使用情感分布增强(Sentiment Distribution Enhanced,SDE)方法改进现有基于狄利克雷过程混合模型的短文本流聚类算法,以高斯分布建模文本情感,并推导相应的坍缩吉布斯采样算法推断参数。该方法在捕获文本情感特征的同时,能够自动确定聚类簇数量并实现观点聚类。与现有先进方法在Tweets、Google News数据集上的对比实验显示,该文提出的方法在标准化互信息、准确度等指标上取得了超越现有模型的聚类表现,并且在主观性较强的数据集上具有更显著的优势。
