数据挖掘在银行业风险防范的应用

信息资源的分析、整合在银行业的竞争中起着越来越重要的作用。数据挖掘作为一种有效的数据分析工具,能为决策者从不断积累与更新的数据中提取有价值的信息。因此,数据挖掘在银行业日益受到重视。该文介绍数据挖掘在信贷风险预测方面的应用,从信贷管理信息系统中提取数据建立数据仓库,设计并实现了一个C/S结构的信贷风险预测系统,为经营者提供数字化的决策依据。     

Work flow methodology : A proposed approach for analysis and conceptual design of large scale computer based information systems

The objective of this paper is to explain our approach called “Work Flow Methodology for Analysis and Conceptual Data Base Design of Large Scale Computer Based Information System”. The user fills in, through the different steps of the methodology and in the light of the definition of dynamic adaptive system, a number of forms which relate the topological dimension to the time dimension for each application of a given system. In addition, we obtain the “Unit Subschema” which defines the responsibilities of issuing and authorization of receiving information at the proper time. Finally, we apply our methodology to the Registration System in Kuwait University.     

基于框架语义标注的自由文本信息抽取研究

信息抽取是从自由文本语料库构建数据库,实现信息自动收集的有效途径之一。提出了一种以框架语义标注为基础构建信息抽取规则的信息抽取方法。基于框架语义标注的信息抽取是用统一的方法来指导信息抽取过程。这种方法具有较细的处理粒度,对语义规则性强的领域有一定的普遍适用性。设计了基于框架语义的BAIE（图书内容简介信息抽取）系统,并对图书的内容简介试行信息抽取。抽取结果表明,基于框架语义的信息抽取方式有一定的可行性和适用性。     

The Rotorcraft Pilot''s Associate: design and evaluation of an intelligent user interface for cockpit information management

The US Army's Rotorcraft Pilot's Associate (RPA) program is developing an advanced, intelligent “associate” system for flight demonstration in a future attack/scout helicopter. A significant RPA component is the intelligent user interface known as the Cockpit Information Manager (CIM). This paper describes the high-level architecture of the CIM, with emphasis on its pilot-perceptible behaviors: Crew Intent Estimation, Page Selection, Symbol Selection/Declutter, Intelligent Window Location, Automated Pan and Zoom, and Task Allocation. We then present the subjective results of recent full mission simulation studies using the CIM to illustrate pilots' attitudes toward these behaviors and their perceived effectiveness.     

基于最大联合条件互信息的特征选择

在高维数据如图像数据、基因数据、文本数据等的分析过程中,当样本存在冗余特征时会大大增加问题分析复杂难度,因此在数据分析前从中剔除冗余特征尤为重要。基于互信息（MI）的特征选择方法能够有效地降低数据维数,提高分析结果精度,但是,现有方法在特征选择过程中评判特征是否冗余的标准单一,无法合理排除冗余特征,最终影响分析结果。为此,提出一种基于最大联合条件互信息的特征选择方法（MCJMI）。MCJMI选择特征时考虑整体联合互信息与条件互信息两个因素,两个因素融合增强特征选择约束。在平均预测精度方面,MCJMI与信息增益（IG）、最小冗余度最大相关性（mRMR）特征选择相比提升了6个百分点;与联合互信息（JMI）、最大化联合互信息（JMIM）相比提升了2个百分点;与LW向前搜索方法（SFS-LW）相比提升了1个百分点。在稳定性方面,MCJMI稳定性达到了0.92,优于JMI、JMIM、SFS-LW方法。实验结果表明MCJMI能够有效地提高特征选择的准确率与稳定性。     

Information granules and entropy theory in information systems

Information granulation and entropy theory are two main approaches to research uncertainty of an information system, which have been widely applied in many practical issues. In this paper, the characterizations and representations of information granules under various binary relations are investigated in information systems, an axiom definition of information granulation is presented, and some existing definitions of information granulation become its special forms. Entropy theory in information systems is further developed and the granulation monotonicity of each of them is proved. Moreover, the complement relationship between information granulation and entropy is established. This investigation unifies the results of measures for uncertainties in complete information systems and incomplete information systems.     

基于知网的虚拟人情感建模研究

虚拟人及其和谐交互技术是当前信息科学和生命科学研究的热点。情感信息处理是人工智能和认知科学研究一直关注的问题。本文将研究基于知网的虚拟人情感模型,该模型由冷静、愤怒、快乐、悲伤、放松和恐惧六个维度组成六维空间。通过实例模拟表明,此模型可以很好地对人类的情感进行仿真。     

信息模型驱动的信息系统开发与元信息系统

信息系统开发经历了以计算为中心、数据为中心、对象为中心(数据与处理一体化)和正在发展的以模型为中心的四个阶段。以模型为中心的阶段的出现,使信息系统开发成为一个由信息模型(Information Model)驱动的过程,信息模型将贯穿于信息系统的分析、设计、实现、配置、维护和管理的各个阶段,从而需要一个基于信息模型的、辅助和管理信息系统开发与运行过程的信息系统,即元信息系统。     

基于数据仓库和OLAP技术的证券交易系统的实现方案研究

数据仓库和联机分析处理(OLAP)技术是信息技术领域的新兴技术,而如何应用到证券交易中是证券业面临的问题。建立证券交易数据仓库并使用OLAP技术,可以将大量源数据有效地转化为有用的知识信息,并服务于决策过程。基于数据仓库的证券交易系统就是在面向信息处理的联机事务处理(OLTP)系统的基础上并引入数据仓库和OLAP技术而发展起来的。论文结合证券交易业务提出了系统实现的解决方案,并给出了基于证券交易业务的数据仓库的体系结构、逻辑模型、粒度模型,以及基于证券交易业务的联机分析处理(OLAP)系统的实现方法。     

城市级环境信息化工程数据共享与流量分析实例

本文阐述了城市级环境信息紊统数据共享分析与流量分析的方法,并应用于佛山市南海区环保局环境信息化的建设。在项目前期准备阶段,根据用户画出的流程草图整理、分析得出带泳道的流程图,再依次得出业务数据流图、业务数据UC矩阵和总体信息资源分布利用图。最后总结出业务信息资源管理一览表。实践说明,采用这种总体数据分析过程可以从强调环保业务办理过程仿真实现以及环保专业数据共享、流转、更新的角度,相对科学地宏观分析、解决城市级环境信息系统数据共享问题。     

A usability evaluation toolkit for In-Vehicle Information Systems (IVISs)

Usability must be defined specifically for the context of use of the particular system under investigation. This specific context of use should also be used to guide the definition of specific usability criteria and the selection of appropriate evaluation methods. There are four principles which can guide the selection of evaluation methods, relating to the information required in the evaluation, the stage at which to apply methods, the resources required and the people involved in the evaluation. This paper presents a framework for the evaluation of usability in the context of In-Vehicle Information Systems (IVISs). This framework guides designers through defining usability criteria for an evaluation, selecting appropriate evaluation methods and applying those methods. These stages form an iterative process of design–evaluation–redesign with the overall aim of improving the usability of IVISs and enhancing the driving experience, without compromising the safety of the driver.     

一种基于方差的文本特征选择算法

中文文本分类中传统特征选择算法在低维情况下分类效果不佳。为此,提出一种结合方差思想的评估函数,选出具有较强类别信息的词条,在保证整体分类性能不下降的同时,提高稀有类别的分类精度。采用中心向量分类器,在TanCorpV1.0语料上进行实验,结果表明,该方法在低维空间优势明显,与常用的文档频率、信息增益等9种特征选择算法相比,宏平均值均有较大提高。     

Client-Led Information System Creation (CLIC): navigating the gap

Abstract.  This paper offers a new framework to facilitate an interpretive approach to client-led information system development, referred to as CLIC (Client-Led Information System Creation). The challenge of moving seamlessly through a process of information systems (IS) design is still the subject of much research in the IS field. Attempts to address the difficulties of 'bridging the gap' between a client's business needs and an information system definition have hitherto not provided a coherent and practical approach. Rather than attempting to bridge the gap, this paper describes an approach to managing this gap by facilitating the clients' navigating through the information system design process (or inquiry process) in a coherent manner. The framework has been developed through practice, and the paper provides an example of navigating through the design phase taken from an Action Research field study in a major UK bank.     

美国卫星科学数据处理存档系统S4PA综述

简单的、可扩展的、基于脚本的科学数据处理存档系统S4PA,是NASA Goddard地球科学数据和信息服务中心分布式数据存档中心GES DISC DAAC近年发展和使用的、进行气象卫星遥感数据处理和存储管理的系统。本文全面介绍了S4PA的发展历程、建设原则、系统设计和技术特点。其核心思想是采用成熟技术对气象卫星数据处理和存储进行流程化设计,使资源有效利用率达到最优。S4PA的成功应用,证明了这是一种先进的、低成本的、稳定的、可扩展的数据处理和存档系统。本文有助于将国际先进的数据存档技术应用于我国海量数据的数据处理和存档、数据管理的实际工作中。     

Concepts of model confidence

This exploratory paper discusses the concept of confidence in results obtained from decisionaiding models. Model confidence is viewed not as an attribute of a model, but of the model user. We argue that confidence in a model is a result of the accumulation of information, the sum total of which leads to a judgmental statement by the decision-maker. We offer an approach to the analysis of such information by defining seven criteria against which the information can be interpreted. For each criterion, a minimal level of “information satisfaction” is assumed that represents the decision-maker's threshold value. The meeting of all the criteria values informs the decision-maker that the model results can be used with an acceptable level of confidence.     

Web-based learning programs: Use by learners with various cognitive styles

To consider how Web-based learning program is utilized by learners with different cognitive styles, this study presents a Web-based learning system (WBLS) and analyzes learners’ browsing data recorded in the log file to identify how learners’ cognitive styles and learning behavior are related. In order to develop an adapted WBLS, this study also proposes a design model for system designers to tailor the preferences linked with each cognitive style. The samples comprise 105 third-grade Accounting Information System course students from a technology university in central Taiwan. Analytical results demonstrate that learners with different cognitive styles have similar but linear learning approaches, and learners with different cognitive styles adopt different navigation tools to process learning.     

C4ISR系统信息优势度量研究

信息优势是敌对双方在战场对抗中获取和使用信息的一种优越性,是当前网络中心战和C4ISR系统研究的重要课题.在分析C4ISR系统工作流程的基础上,将信息在物理域、信息域和认知域的转化过程链接起来,形成信息优势价值链;分析了C4ISR系统的信息转换过程,并给出了用信息的完备性、正确性和时效性指标评估信息转换质量的方法;通过定义态势感知,提出一种个体态势感知的评估方法;最后,通过定量描述共享态势感知,建立了信息优势的数学模型.     

Inheritance of workflows: an approach to tackling problems related to change

Inheritance is one of the key issues of object-orientation. The inheritance mechanism allows for the definition of a subclass which inherits the features of a specific superclass. When adapting a workflow process definition to specific needs (ad-hoc change) or changing the structure of the workflow process as a result of reengineering efforts (evolutionary change), inheritance concepts are useful to check whether the new workflow process inherits some desirable properties of the old workflow process. Today's workflow management systems have problems dealing with both ad-hoc changes and evolutionary changes. As a result, a workflow management system is not used to support dynamically changing workflow processes or the workflow processes are supported in a rigid manner, i.e., changes are not allowed or handled outside of the workflow management system. In this paper, we propose inheritance-preserving transformation rules for workflow processes and show that these rules can be used to avoid problems such as the “dynamic-change bug.” The dynamic-change bug refers to errors introduced by migrating a case (i.e., a process instance) from an old process definition to a new one. A transfer from an old process to a new process can lead to duplication of work, skipping of tasks, deadlocks, and livelocks. Restricting change to the inheritance-preserving transformation rules guarantees transfers without any of these problems. Moreover, the transformation rules can also be used to extract aggregate management information in case more than one version of a workflow process cannot be avoided.     

基于语义的智能信息处理技术的研究

智能信息处理是模拟人或者自然界其他生物处理各种信息的行为,是当前信息处理技术向多样化、集成化与智能化方向的发展,具有很高的理论研究和应用价值.经过多年的研究和探索,智能信息处理技术已经取得较大的发展,但在实际应用中还存在许多问题需要解决和完善.分析了基于概念图的语义研究在智能信息处理中的应用,并设计与实现了一个基于概念图的智能答疑系统CGQAS,通过实验结果验证了基于概念图的智能信息处理的可行性和有效性.     

信息集成数据模型研究*

信息集成是指将多个信息源进行整合,为用户提供一个统一访问这些信息的接口或数据视图。公共数据模型是设计信息集成系统的基本出发点,从分类的角度对信息集成公共数据模型进行研究。对各种数据模型的特点、描述能力、应用领域以及发展现状作了分析和比较。