Ensemble-based analyses are useful to compare equiprobable scenarios of the reservoir models.However,they require a large suite of reservoir models to cover high uncertainty in heterogeneous and complex reservoir mode...Ensemble-based analyses are useful to compare equiprobable scenarios of the reservoir models.However,they require a large suite of reservoir models to cover high uncertainty in heterogeneous and complex reservoir models.For stable convergence in ensemble Kalman filter(EnKF),increasing ensemble size can be one of the solutions,but it causes high computational cost in large-scale reservoir systems.In this paper,we propose a preprocessing of good initial model selection to reduce the ensemble size,and then,EnKF is utilized to predict production performances stochastically.In the model selection scheme,representative models are chosen by using principal component analysis(PCA)and clustering analysis.The dimension of initial models is reduced using PCA,and the reduced models are grouped by clustering.Then,we choose and simulate representative models from the cluster groups to compare errors of production predictions with historical observation data.One representative model with the minimum error is considered as the best model,and we use the ensemble members near the best model in the cluster plane for applying EnKF.We demonstrate the proposed scheme for two 3D models that EnKF provides reliable assimilation results with much reduced computation time.展开更多
Traumatic brain injury(TBI) at a young age can lead to the development of long-term functional impairments. Severity of injury is well demonstrated to have a strong influence on the extent of functional impairments;ho...Traumatic brain injury(TBI) at a young age can lead to the development of long-term functional impairments. Severity of injury is well demonstrated to have a strong influence on the extent of functional impairments;however, identification of specific magnetic resonance imaging(MRI) biomarkers that are most reflective of injury severity and functional prognosis remain elusive. Therefore, the objective of this study was to utilize advanced statistical approaches to identify clinically relevant MRI biomarkers and predict functional outcomes using MRI metrics in a translational large animal piglet TBI model. TBI was induced via controlled cortical impact and multiparametric MRI was performed at 24 hours and 12 weeks post-TBI using T1-weighted, T2-weighted, T2-weighted fluid attenuated inversion recovery, diffusion-weighted imaging, and diffusion tensor imaging. Changes in spatiotemporal gait parameters were also assessed using an automated gait mat at 24 hours and 12 weeks post-TBI. Principal component analysis was performed to determine the MRI metrics and spatiotemporal gait parameters that explain the largest sources of variation within the datasets. We found that linear combinations of lesion size and midline shift acquired using T2-weighted imaging explained most of the variability of the data at both 24 hours and 12 weeks post-TBI. In addition, linear combinations of velocity, cadence, and stride length were found to explain most of the gait data variability at 24 hours and 12 weeks post-TBI. Linear regression analysis was performed to determine if MRI metrics are predictive of changes in gait. We found that both lesion size and midline shift are significantly correlated with decreases in stride and step length. These results from this study provide an important first step at identifying relevant MRI and functional biomarkers that are predictive of functional outcomes in a clinically relevant piglet TBI model. This study was approved by the University of Georgia Institutional Animal Care and Use Committee(AUP: A2015 11-001) on December 22, 2015.展开更多
Molten iron temperature as well as Si, P, and S contents is the most essential molten iron quality （MIQ） indices in the blast furnace （BF） ironmaking, which requires strict monitoring during the whole ironmaking p...Molten iron temperature as well as Si, P, and S contents is the most essential molten iron quality （MIQ） indices in the blast furnace （BF） ironmaking, which requires strict monitoring during the whole ironmaking production. However, these MIQ parameters are difficult to be directly measured online, and large-time delay exists in off-line analysis through laboratory sampling. Focusing on the practical challenge, a data-driven modeling method was presented for the prediction of MIQ using the improved muhivariable incremental random vector functional-link net- works （M-I-RVFLNs）. Compared with the conventional random vector functional-link networks （RVFLNs） and the online sequential RVFLNs, the M-I-RVFLNs have solved the problem of deciding the optimal number of hidden nodes and overcome the overfitting problems. Moreover, the proposed M I RVFLNs model has exhibited the potential for multivariable prediction of the MIQ and improved the terminal condition for the multiple-input multiple-out- put （MIMO） dynamic system, which is suitable for the BF ironmaking process in practice. Ultimately, industrial experiments and contrastive researches have been conducted on the BF No. 2 in Liuzhou Iron and Steel Group Co. Ltd. of China using the proposed method, and the results demonstrate that the established model produces better estima ting accuracy than other MIQ modeling methods.展开更多
We consider a functional partially linear additive model that predicts a functional response by a scalar predictor and functional predictors. The B-spline and eigenbasis least squares estimator for both the parametric...We consider a functional partially linear additive model that predicts a functional response by a scalar predictor and functional predictors. The B-spline and eigenbasis least squares estimator for both the parametric and the nonparametric components proposed. In the final of this paper, as a result, we got the variance decomposition of the model and establish the asymptotic convergence rate for estimator.展开更多
Statistical downscaling (SD) analyzes relationship between local-scale response and global-scale predictors. The SD model can be used to forecast rainfall (local-scale) using global-scale precipitation from global cir...Statistical downscaling (SD) analyzes relationship between local-scale response and global-scale predictors. The SD model can be used to forecast rainfall (local-scale) using global-scale precipitation from global circulation model output (GCM). The objectives of this research were to determine the time lag of GCM data and build SD model using PCR method with time lag of the GCM precipitation data. The observations of rainfall data in Indramayu were taken from 1979 to 2007 showing similar patterns with GCM data on 1st grid to 64th grid after time shift (time lag). The time lag was determined using the cross-correlation function. However, GCM data of 64 grids showed multicollinearity problem. This problem was solved by principal component regression (PCR), but the PCR model resulted heterogeneous errors. PCR model was modified to overcome the errors with adding dummy variables to the model. Dummy variables were determined based on partial least squares regression (PLSR). The PCR model with dummy variables improved the rainfall prediction. The SD model with lag-GCM predictors was also better than SD model without lag-GCM.展开更多
To solve the increasing model complexity due to several input variables and large correlations under variable load conditions,a dynamic modeling method combining a kernel extreme learning machine(KELM)and principal co...To solve the increasing model complexity due to several input variables and large correlations under variable load conditions,a dynamic modeling method combining a kernel extreme learning machine(KELM)and principal component analysis(PCA)was proposed and applied to the prediction of nitrogen oxide(NO_(x))concentration at the outlet of a selective catalytic reduction(SCR)denitrification system.First,PCA is applied to the feature information extraction of input data,and the current and previous sequence values of the extracted information are used as the inputs of the KELM model to reflect the dynamic characteristics of the NO_(x)concentration at the SCR outlet.Then,the model takes the historical data of the NO_(x)concentration at the SCR outlet as the model input to improve its accuracy.Finally,an optimization algorithm is used to determine the optimal parameters of the model.Compared with the Gaussian process regression,long short-term memory,and convolutional neural network models,the prediction errors are reduced by approximately 78.4%,67.6%,and 59.3%,respectively.The results indicate that the proposed dynamic model structure is reliable and can accurately predict NO_(x)concentrations at the outlet of the SCR system.展开更多
The objective of this paper is to present a review of different calibration and classification methods for functional data in the context of chemometric applications. In chemometric, it is usual to measure certain par...The objective of this paper is to present a review of different calibration and classification methods for functional data in the context of chemometric applications. In chemometric, it is usual to measure certain parameters in terms of a set of spectrometric curves that are observed in a finite set of points (functional data). Although the predictor variable is clearly functional, this problem is usually solved by using multivariate calibration techniques that consider it as a finite set of variables associated with the observed points (wavelengths or times). But these explicative variables are highly correlated and it is therefore more informative to reconstruct first the true functional form of the predictor curves. Although it has been published in several articles related to the implementation of functional data analysis techniques in chemometric, their power to solve real problems is not yet well known. Because of this the extension of multivariate calibration techniques (linear regression, principal component regression and partial least squares) and classification methods (linear discriminant analysis and logistic regression) to the functional domain and some relevant chemometric applications are reviewed in this paper.展开更多
As an extension of linear regression in functional data analysis, functional linear regression has been studied by many researchers and applied in various fields. However, in many cases, data is collected sequentially...As an extension of linear regression in functional data analysis, functional linear regression has been studied by many researchers and applied in various fields. However, in many cases, data is collected sequentially over time, for example the financial series, so it is necessary to consider the autocorrelated structure of errors in functional regression background. To this end, this paper considers a multiple functional linear model with autoregressive errors. Based on the functional principal component analysis, we apply the least square procedure to estimate the functional coefficients and autoregression coefficients. Under some regular conditions, we establish the asymptotic properties of the proposed estimators. A simulation study is conducted to investigate the finite sample performance of our estimators. A real example on China's weather data is applied to illustrate the validity of our model.展开更多
通过融合多个核函数,提出一种多核主成分分析(multi-kernel principal component analysis,MKPCA)和二元Logistic回归耦合的诊断方法(MKPCA-Logistic回归模型)诊断冠心病,较好的解决了单一核函数适应性问题。选取第一舒张波高度U_(1)、...通过融合多个核函数,提出一种多核主成分分析(multi-kernel principal component analysis,MKPCA)和二元Logistic回归耦合的诊断方法(MKPCA-Logistic回归模型)诊断冠心病,较好的解决了单一核函数适应性问题。选取第一舒张波高度U_(1)、第三舒张波高度U_(3)、第一收缩波高度D_(1)、第二收缩波高度D_(2)、第三收缩波高度D_(3)、收缩波的波动值±U_(1)等6个影响因子,建立Logistic回归模型以及MKPCA-Logistic回归模型对冠心病进行诊断。利用预测准确率、误判率和成功率曲线(receiver operating characteristic,ROC)对两种模型的预测精度进行检验。结果表明:MKPCA-Logistic回归模型预测患冠心病的正确率为97%,明显高于Logistic回归模型的正确率92.5%。从ROC曲线分析来看,Logistic回归模型的ROC曲线的曲线下面积(AUC)为0.783,MKPCA-Logistic回归模型的AUC为0.874,耦合模型的分类精度更高。展开更多
基金supported by The Ministry of Trade,Industry,and Energy(20172510102090,20142520100440,20162010201980)Global PhD Fellowship Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(2015H1A2A1030756)supported by the National Research Foundation of Korea(NRF)Grant(No.2018R1C1B5045260).
文摘Ensemble-based analyses are useful to compare equiprobable scenarios of the reservoir models.However,they require a large suite of reservoir models to cover high uncertainty in heterogeneous and complex reservoir models.For stable convergence in ensemble Kalman filter(EnKF),increasing ensemble size can be one of the solutions,but it causes high computational cost in large-scale reservoir systems.In this paper,we propose a preprocessing of good initial model selection to reduce the ensemble size,and then,EnKF is utilized to predict production performances stochastically.In the model selection scheme,representative models are chosen by using principal component analysis(PCA)and clustering analysis.The dimension of initial models is reduced using PCA,and the reduced models are grouped by clustering.Then,we choose and simulate representative models from the cluster groups to compare errors of production predictions with historical observation data.One representative model with the minimum error is considered as the best model,and we use the ensemble members near the best model in the cluster plane for applying EnKF.We demonstrate the proposed scheme for two 3D models that EnKF provides reliable assimilation results with much reduced computation time.
基金Financial support was provided by the University of Georgia Office of the Vice President for Research to FDW。
文摘Traumatic brain injury(TBI) at a young age can lead to the development of long-term functional impairments. Severity of injury is well demonstrated to have a strong influence on the extent of functional impairments;however, identification of specific magnetic resonance imaging(MRI) biomarkers that are most reflective of injury severity and functional prognosis remain elusive. Therefore, the objective of this study was to utilize advanced statistical approaches to identify clinically relevant MRI biomarkers and predict functional outcomes using MRI metrics in a translational large animal piglet TBI model. TBI was induced via controlled cortical impact and multiparametric MRI was performed at 24 hours and 12 weeks post-TBI using T1-weighted, T2-weighted, T2-weighted fluid attenuated inversion recovery, diffusion-weighted imaging, and diffusion tensor imaging. Changes in spatiotemporal gait parameters were also assessed using an automated gait mat at 24 hours and 12 weeks post-TBI. Principal component analysis was performed to determine the MRI metrics and spatiotemporal gait parameters that explain the largest sources of variation within the datasets. We found that linear combinations of lesion size and midline shift acquired using T2-weighted imaging explained most of the variability of the data at both 24 hours and 12 weeks post-TBI. In addition, linear combinations of velocity, cadence, and stride length were found to explain most of the gait data variability at 24 hours and 12 weeks post-TBI. Linear regression analysis was performed to determine if MRI metrics are predictive of changes in gait. We found that both lesion size and midline shift are significantly correlated with decreases in stride and step length. These results from this study provide an important first step at identifying relevant MRI and functional biomarkers that are predictive of functional outcomes in a clinically relevant piglet TBI model. This study was approved by the University of Georgia Institutional Animal Care and Use Committee(AUP: A2015 11-001) on December 22, 2015.
基金Item Sponsored by National Natural Science Foundation of China(61290323,61333007,61473064)Fundamental Research Funds for Central Universities of China(N130108001)+1 种基金National High Technology Research and Development Program of China(2015AA043802)General Project on Scientific Research for Education Department of Liaoning Province of China(L20150186)
文摘Molten iron temperature as well as Si, P, and S contents is the most essential molten iron quality （MIQ） indices in the blast furnace （BF） ironmaking, which requires strict monitoring during the whole ironmaking production. However, these MIQ parameters are difficult to be directly measured online, and large-time delay exists in off-line analysis through laboratory sampling. Focusing on the practical challenge, a data-driven modeling method was presented for the prediction of MIQ using the improved muhivariable incremental random vector functional-link net- works （M-I-RVFLNs）. Compared with the conventional random vector functional-link networks （RVFLNs） and the online sequential RVFLNs, the M-I-RVFLNs have solved the problem of deciding the optimal number of hidden nodes and overcome the overfitting problems. Moreover, the proposed M I RVFLNs model has exhibited the potential for multivariable prediction of the MIQ and improved the terminal condition for the multiple-input multiple-out- put （MIMO） dynamic system, which is suitable for the BF ironmaking process in practice. Ultimately, industrial experiments and contrastive researches have been conducted on the BF No. 2 in Liuzhou Iron and Steel Group Co. Ltd. of China using the proposed method, and the results demonstrate that the established model produces better estima ting accuracy than other MIQ modeling methods.
文摘We consider a functional partially linear additive model that predicts a functional response by a scalar predictor and functional predictors. The B-spline and eigenbasis least squares estimator for both the parametric and the nonparametric components proposed. In the final of this paper, as a result, we got the variance decomposition of the model and establish the asymptotic convergence rate for estimator.
文摘Statistical downscaling (SD) analyzes relationship between local-scale response and global-scale predictors. The SD model can be used to forecast rainfall (local-scale) using global-scale precipitation from global circulation model output (GCM). The objectives of this research were to determine the time lag of GCM data and build SD model using PCR method with time lag of the GCM precipitation data. The observations of rainfall data in Indramayu were taken from 1979 to 2007 showing similar patterns with GCM data on 1st grid to 64th grid after time shift (time lag). The time lag was determined using the cross-correlation function. However, GCM data of 64 grids showed multicollinearity problem. This problem was solved by principal component regression (PCR), but the PCR model resulted heterogeneous errors. PCR model was modified to overcome the errors with adding dummy variables to the model. Dummy variables were determined based on partial least squares regression (PLSR). The PCR model with dummy variables improved the rainfall prediction. The SD model with lag-GCM predictors was also better than SD model without lag-GCM.
基金The National Natural Science Foundation of China(No.71471060)the Natural Science Foundation of Hebei Province(No.E2018502111)。
文摘To solve the increasing model complexity due to several input variables and large correlations under variable load conditions,a dynamic modeling method combining a kernel extreme learning machine(KELM)and principal component analysis(PCA)was proposed and applied to the prediction of nitrogen oxide(NO_(x))concentration at the outlet of a selective catalytic reduction(SCR)denitrification system.First,PCA is applied to the feature information extraction of input data,and the current and previous sequence values of the extracted information are used as the inputs of the KELM model to reflect the dynamic characteristics of the NO_(x)concentration at the SCR outlet.Then,the model takes the historical data of the NO_(x)concentration at the SCR outlet as the model input to improve its accuracy.Finally,an optimization algorithm is used to determine the optimal parameters of the model.Compared with the Gaussian process regression,long short-term memory,and convolutional neural network models,the prediction errors are reduced by approximately 78.4%,67.6%,and 59.3%,respectively.The results indicate that the proposed dynamic model structure is reliable and can accurately predict NO_(x)concentrations at the outlet of the SCR system.
文摘The objective of this paper is to present a review of different calibration and classification methods for functional data in the context of chemometric applications. In chemometric, it is usual to measure certain parameters in terms of a set of spectrometric curves that are observed in a finite set of points (functional data). Although the predictor variable is clearly functional, this problem is usually solved by using multivariate calibration techniques that consider it as a finite set of variables associated with the observed points (wavelengths or times). But these explicative variables are highly correlated and it is therefore more informative to reconstruct first the true functional form of the predictor curves. Although it has been published in several articles related to the implementation of functional data analysis techniques in chemometric, their power to solve real problems is not yet well known. Because of this the extension of multivariate calibration techniques (linear regression, principal component regression and partial least squares) and classification methods (linear discriminant analysis and logistic regression) to the functional domain and some relevant chemometric applications are reviewed in this paper.
基金supported by National Nature Science Foundation of China(No.11861074,No.11371354 and N0.11301464)Key Laboratory of Random Complex Structures and Data Science,Chinese Academy of Sciences,Beijing 100190,China(No.2008DP173182)Applied Basic Research Project of Yunnan Province(No.2019FB138).
文摘As an extension of linear regression in functional data analysis, functional linear regression has been studied by many researchers and applied in various fields. However, in many cases, data is collected sequentially over time, for example the financial series, so it is necessary to consider the autocorrelated structure of errors in functional regression background. To this end, this paper considers a multiple functional linear model with autoregressive errors. Based on the functional principal component analysis, we apply the least square procedure to estimate the functional coefficients and autoregression coefficients. Under some regular conditions, we establish the asymptotic properties of the proposed estimators. A simulation study is conducted to investigate the finite sample performance of our estimators. A real example on China's weather data is applied to illustrate the validity of our model.
