多因变量多元线性模型主成分型预测的最优性判别

针对多因变量多元线性模型有偏预测问题,结合主成分估计,构造主成分型预测量。通过主成分型预测与最优线性无偏预测的最优性判别问题进行分析,分别得到了主成分型预测在R(i)(·)准则、MDE-准则及RT(·)下优于最优线性无偏预测的充分条件。结果表明,在一定条件下,有偏的主成分型预测优于最优线性无偏预测。

多因变量线性模型下三类预测的最优性判别

在多因变量多元线性模型中就岭型主成分型预测与最优线性无偏预测、主成分型预测之间的最优性判别问题进行讨论.得到岭型主成分型预测在R(i)(·)准则下优于最优线性无偏预测和主成分型预测的两个充要条件,同时得到了其在MDE-准则和矩阵迹RT(·)意义下优于最优线性无偏预测和主成分型预测的充分条件.

基于事例推理的电力系统短期负荷预测

短期负荷预测对于电力系统安全、稳定、经济地运行有重要意义。将粗糙集信息熵理论和统计学主成分分析方法用在负荷事例属性的约简上，分别针对负荷数据的重要性和相关性进行了有效处理。这样，不仅减少了事例重用过程的训练时间，还有效控制了次要负荷因素对重要因素的干扰；在事例修正过程中，针对非正常日提出一些有效的修正方案。最后，用河北省保定供电公司2000-2004年的负荷数据对该方案验证，结果表明，提出的预测方案是有效，可行的。

基于声发射信号的PE塑料失效PCA预测方法

以聚乙烯(PE)塑料为研究对象,采用声发射监测技术对不同拉伸速度下试样失效过程进行监测,采集相应的声发射信号(持续时间、幅值、事件计数、撞击次数等),通过相关性系数分析确定评价因子,利用三角形隶属函数确定各评语集的失效隶属度,建立了PE塑料失效破坏程度主成分分析(PCA)模糊预测评价模型。另取同型号PE试样进行不同速度拉伸损伤破坏试验,并对损伤过程“力–时间”曲线的弹性阶段、屈服阶段(轻微失效)、颈缩阶段(中度失效)、断裂阶段(严重失效)特征点参数进行统计,破坏过程中所选时间点对应的失效程度与PCA预测评价结果一致,验证了模糊预测评价模型的可行性。

上市公司财务危机识别模型的运用比较

本文以我国沪深两地上市公司为研究对象,根据同行业且总资产规模相近的原则,选取ST板块中71家上市公司及71家非ST上市公司为样本,建立主成分预测模型、二分类变量logistic回归模型和判别分析模型,用来识别上市公司是否出现财务危机。通过模型比较发现,二分类变量logistic回归模型的实证结果总体上优于另外两种模型,具有较高的识别效果。

Forecasting of development of the Jiangsu construction industry and its case analysis

In order to grasp the development path of the Jiangsu construction industry, a multivariable linear regression model for forecasting is proposed. Five factors affecting development of the Jiangsu construction industry are chosen as explanatory variables. They are the construction industry＇s fixed assets K, the gross domestic product （GDP）, real estate added value （REAV）, construction industry export （WS）and investment in construction and installation projects（JA）. The principal component analysis is used to resolve multicollinearity between them. The construction added value （CAV） is chosen as a dependant variable, and the growth model of the Jiangsu construction industry is established. Statistical data from 1990 to 2008 are used to test the prediction accuracy of the model. The predictive results show that from 2009 to 2012, the average annual growth rate of the Jiangsu construction industry added value will be 17. 65% while the GDP growth rate will be 14. 16% . the Jiangsu construction industry will grow faster than the GDP in the near future. The construction output of the GDP continues to rise, and its pillar position will be further strengthened.

Predict typhoon-induced storm surge deviation in a principal component back-propagation neural network model

To reduce typhoon-caused damages, numerical and empirical methods are often used to forecast typhoon storm surge. However, typhoon surge is a complex nonlinear process that is difficult to forecast accurately. We applied a principal component back-propagation neural network (PCBPNN) to predict the deviation in typhoon storm surge, in which data of the typhoon, upstream flood, and historical case studies were involved. With principal component analysis, 15 input factors were reduced to five principal components, and the application of the model was improved. Observation data from Huangpu Park in Shanghai, China were used to test the feasibility of the model. The results indicate that the model is capable of predicting a 12-hour warning before a typhoon surge.

Predicting configuration performance of modular product family using principal component analysis and support vector machine

A novel configuration performance prediction approach with combination of principal component analysis(PCA) and support vector machine(SVM) was proposed.This method can estimate the performance parameter values of a newly configured product through soft computing technique instead of practical test experiments,which helps to evaluate whether or not the product variant can satisfy the customers' individual requirements.The PCA technique was used to reduce and orthogonalize the module parameters that affect the product performance.Then,these extracted features were used as new input variables in SVM model to mine knowledge from the limited existing product data.The performance values of a newly configured product can be predicted by means of the trained SVM models.This PCA-SVM method can ensure that the performance prediction is executed rapidly and accurately,even under the small sample conditions.The applicability of the proposed method was verified on a family of plate electrostatic precipitators.

Estimation of Travel Times on Signalized Arterials

This paper describes procedure for estimation of travel time on signalized arterial roads based on multiple data sources with application of dimensionality reduction. Travel time estimation approach incorporates forecast of transportation nodes impendence and travel time on network links. Forecasting period is two hours and the estimation is based on historical data and real time data on traffic conditions. Travel time estimation combines multivariate regression, principal component analysis, KNN （k-nearest neighbours）, cross validation and EWMA （exponentially weighted moving average） methods. When comparing estimation methodologies, relevantly better results were achieved by KNN method than with EWMA method. This is true for every time interval considered except for evening time interval when signalized arterial roads were uncongested.