消费者信用评估中的PCALWM方法研究

设计了一种基于主成分线性加权模型(PCALWM)的消费者信用评估方法,具有评估的客观性、可行性、适应性等优点。使用真实信用卡数据的实证检验表明模型分类效果比较好,具有较好的应用价值。     

Building Strategic Technology Alliances for Teaching and Learning

There is a major need for higher education to confront intense competition, enhance academic programs to meet the challenges of this competition, and to develop new teaching and learning strategies to meet the demands of the global marketplace. Technology and the Internet are intended to break down the barriers of time and space and enable more students to participate and collaborate with faculty and other students. Critical thresholds must be met in order to use technology to communicate, collaborate, and transform teaching and learning. Strategic technology alliances establish a partnership between technology vendors and higher education that will achieve these thresholds to meet the teaching and learning needs of the 21st century student. This revised version was published online in July 2006 with corrections to the Cover Date.     

关于技术作业能力与铁路精益生产的探讨

精益生产起源于汽车制造业，如果把精益生产应用于提供无形空间位移服务的铁路运输企业，还必须符合铁路运输生产的技术经济特征，才能取得理想的效果。铁路运输资源具有一定的技术作业能力，主要表现为随着运输资源空间作业距离的延长，以及与作业距离相关的密度、速度、时效、重量等运输指标的改善，铁路平均生产成本出现了递远递减的基本特征。精益生产通过资源整合、组织边界调整、激励约束机制设计等手段，能够充分实现运输距离经济性，改善精益生产的实施效果。     

关于技术作业能力与铁路精益生产的探讨

精益生产起源于汽车制造业，如果把精益生产应用于提供无形空间位移服务的铁路运输企业，还必须符合铁路运输生产的技术经济特征，才能取得理想的效果。铁路运输资源具有一定的技术作业能力，主要表现为随着运输资源空间作业距离的延长，以及与作业距离相关的密度、速度、时效、重量等运输指标的改善，铁路平均生产成本出现了递远递减的基本特征。精益生产通过资源整合、组织边界调整、激励约束机制设计等手段，能够充分实现运输距离经济性，改善精益生产的实施效果。     

粗糙集-神经网络集成的WSN节点故障诊断

提出一种粗糙集?神经网络集成的无线传感器网络(WSN)节点故障诊断新方法。根据无线传感器网络的应用环境和故障特征得到诊断决策表,利用改进的粗糙集中的归纳属性约简算法对诊断决策表进行属性约简,用Hamming网络建立一套故障分类的方法。仿真实验结果显示,该诊断算法在进行WSN节点故障诊断时,诊断准确性高,通信代价小,能耗低,鲁棒性高。     

一种基于密度的无监督联系发现方法

在数据挖掘过程中,利用K-近邻(KNN)算法搜索新颖节点往往具有一定的局限性和偏差性。针对此问题,本文提出了加权距离和相对密度的概念,采用基于加权距离的相对密度来度量一个对象的局部离群程度。在此基础上,提出了一种基于密度的无监督联系发现方法,并进行了实验。实验结果表明,该方法能够较准确地描述对象的异常程度,具有更高的精确度。     

商业银行综合评价与分类

基于商业银行传统的加权综合评价方法存在权数确定不科学的缺陷 ,确定了商业银行综合评价指标的选择依据并构建了商业银行综合评价指标体系 ,指标包括 :资产收益率、贷款收益率、资产损失率、不良贷款率、非生息资产率、存款付息率、费用利润率、利息实收率。把考核指标转化为正指标后 ,按主分量分析进行综合评价 ,用方差极大化进行正交旋转 ,提取特征根大于 1的公共因子作为综合评价指标。选择平方欧氏距离作为样本相似性测度 ,用类间平均法作为聚类算法 ,按系统聚类法进行聚类分析 ,得到分类谱系图后 ,再恰当分类。并就综合评价结论与实际考核结果做了实证比较。     

Origin and evolution of endemic plants of the Bonin (Ogasawara) Islands

The Bonin Islands are typical oceanic islands, located at the western part of the North Pacific Ocean and approximately 1,000 km south of mainland Japan. This archipelago consists of about 20 small islands. Although floristic diversity is low due to the small area and limited environmental diversity, the Bonin Islands harbor unique endemic flora as in other well-known oceanic islands. This paper presents a brief summary of the results obtained from recent studies on the endemic flora of the Bonin Islands. The results are reviewed in relation to the four stages of the evolution of endemic flora in the oceanic islands; migration, establishment, enlargement and diversification. The ancestors of the flora originated mostly from tropical and subtropical Southeast Asia or mainland Japan by rare events of long distance dispersal. The proportion of bird-dispersed species is relatively high as for other oceanic islands. Genetic data sets obtained from allozyme variation in some endemic species suggest that migration occurred several million years ago and genetic diversity is correlated with current population size. At the time of establishment, self-compatible plants are expected to have an advantage. However, the percentage of dioecious plants is relatively high. This is partly due to evolutionary changes from hermaphroditic ancestors to dioecy which occurred in two genera in the Bonin Islands. In addition, there are some examples of evolutionary changes from herbaceous ancestors to woody endemics. Adaptive radiation is found in some genera, although the number of congeneric endemic species is less than five. Studies of allozyme variation inPittosporum, Symplocos andCrepidiastrum showed that genetic identity is generally very high between congeneric species in spite of their distinct morphologies. This result suggests that divergence of these species occurred rather recently and distinct morphological differences are based on a limited number of genetic changes.     

Regression Diagnostic under Model Misspecification

We propose two novel diagnostic measures for the detection of influential observations for regression parameters in linear regression. Traditional diagnostic statistics focus on the effect of deletion of data points either on parameter estimates, or on predicted values. A data point is regarded as influential by the new methods if its inclusion determines a significantly different likelihood function for the parameter of interest. The concerned likelihood function is asymptotically valid for practically all underlying distributions whose second moments exist.     

The performance of diagnostic-robust generalized potentials for the identification of multiple high leverage points in linear regression

Leverage values are being used in regression diagnostics as measures of influential observations in the $X$-space. Detection of high leverage values is crucial because of their responsibility for misleading conclusion about the fitting of a regression model, causing multicollinearity problems, masking and/or swamping of outliers, etc. Much work has been done on the identification of single high leverage points and it is generally believed that the problem of detection of a single high leverage point has been largely resolved. But there is no general agreement among the statisticians about the detection of multiple high leverage points. When a group of high leverage points is present in a data set, mainly because of the masking and/or swamping effects the commonly used diagnostic methods fail to identify them correctly. On the other hand, the robust alternative methods can identify the high leverage points correctly but they have a tendency to identify too many low leverage points to be points of high leverages which is not also desired. An attempt has been made to make a compromise between these two approaches. We propose an adaptive method where the suspected high leverage points are identified by robust methods and then the low leverage points (if any) are put back into the estimation data set after diagnostic checking. The usefulness of our newly proposed method for the detection of multiple high leverage points is studied by some well-known data sets and Monte Carlo simulations.