基于Shadowed Sets的连续属性离散化

基于Shadowed Sets理论研究了粗糙集连续属性离散化问题,提出一种新的基于Shadowed Sets 理论的候选断点集提取算法.该算法根据实例在单属性上的分布,对数据样本进行分类,采用Shadowed Sets计算出各类的上下近似,最终提取出候选断点集.使用多组UCI数据对此算法的性能进行检验,同时还与其它候选断点集提取算法做了对比实验.实验结果表明,此算法能有效地减少数据集候选断点的数目,提高离散化算法运行速度和识别率.     

离散与连续的相互转化

离散系统的教学模型可推广至连续系统;但为了便于计算,连续变量又常常被离散化处理。     

房地产业上市公司的统计数据挖掘分析研究

应用统计类数据挖掘技术对房地产业上市公司财务进行了分析。即搜集十五个房地产业上市公司的主要财务指标进行因子分析,用提取主成份的方法缩减变数,归纳出影响公司财务状况的四个主要因素。然后,对十五家房地产上市公司进行聚类分析,划分各公司的经营等级。最后,结合因子分析与聚类分析的结果对各公司的经营状况进行了综合评价,并以此指导投资者和经营管理者做出正确的决策。     

数据挖掘技术的理论及应用

数据挖掘是近年来国际上智能信息处理和决策支持分析领域的最前沿的研究方向之一.本文综合介绍了数据挖掘的主要概念和新技术,并展示了其丰富的应用领域.     

基于粗糙集与模糊集的连续值域决策表的离散化算法

将粗糙集理论与模糊集理论结合起来,给出一种连续值域决策表的离散化算法。该算法从已知数据的初始决策系统出发,首先构造对像的相似矩阵,然后根据相似矩阵的传递闭包及粗糙集正域的思想得出决策表的条件类,再根据条件类将连续值决策表化为区间值决策表,最后根据各区间值将连续值域决策表化为离散决策表。     

既不离散也不连续的随机变量

讨论了既不离散也不连续的随机变量 ,并纠正了有关文献中关于连续型随机变量定义中的错误 .     

离散优化与连续优化的复杂性概念

问题的复杂性概念起源于离散的图灵计算机理论的研究,在离散优化问题的研究中被广泛的接受.近期连续优化领域的很多文章中提及NP难这个概念.从而来对比介绍离散优化和连续优化研究中这两个概念的差异.     

数据挖掘中数据排序及其应用

本文从统计学的角度对事务性数据库进行了描述,提出了加权构造综合属性函数方法,对事务项进行了排序分析,并用该方法对某些区中国移动手机用户的消费情况进行了综合评价,得到了许多有意义的结果。     

专家知识库粗集建模中基于熵的数据离散化

首先分析了专家知识库粗集建模中连续数据离散化存在的问题 ,指出允许引入少量的冲突对专家知识库的建模分析是有益的 ;提出了一种基于信息熵的数据离散化方法 ,并分析了数据离散化的熵的度量 ,根据求解问题设计了一种问题求解的遗传算法 ;最后以基于多 Agent车间调度系统中调度 Agent任务分派知识库的粗集建模为例说明了方法的应用过程     

非线性整规划的连续化

本文讨论了非线性整规划问题的连续化途径．结论是可以将无约束和有约束的非线性整规划全局解问题化为非线性连续规划问题求解．     

可拓数据挖掘研究进展

可拓学研究用形式化模型解决矛盾问题的理论与方法,可拓数据挖掘是可拓学和数据挖掘结合的产物,它探讨利用可拓学方法和数据挖掘技术,去挖掘数据库中与可拓变换有关的知识,包括可拓分类知识、传导知识等可拓知识.随着经济全球化的推进,环境的多变促使了信息和知识的更新周期缩短,创新和解决矛盾问题越来越成为各行各业的重要工作.因此,如何挖掘可拓知识就成为数据挖掘研究的重要任务.研究表明,可拓数据挖掘将具有广阔的应用前景.将介绍可拓数据挖掘的集合论基础、基本知识和目前研究的主要内容,并提出今后需要进一步探讨的问题及其发展前景.     

模糊聚类挖掘在综合评价中的应用研究

探讨了聚类分析这一重要的数据挖掘方法在综合评价中的应用,将模糊聚类与综合评价相结合以解决待评价方案数较多的排序问题,并且文中还改进了建立模糊相似矩阵的方法.     

Social Network Discovery by Mining Spatio-Temporal Events

Knowing patterns of relationship in a social network is very useful for law enforcement agencies to investigate collaborations among criminals, for businesses to exploit relationships to sell products, or for individuals who wish to network with others. After all, it is not just what you know, but also whom you know, that matters. However, finding out who is related to whom on a large scale is a complex problem. Asking every single individual would be impractical, given the huge number of individuals and the changing dynamics of relationships. Recent advancement in technology has allowed more data about activities of individuals to be collected. Such data may be mined to reveal associations between these individuals. Specifically, we focus on data having space and time elements, such as logs of people's movement over various locations or of their Internet activities at various cyber locations. Reasoning that individuals who are frequently found together are likely to be associated with each other, we mine from the data instances where several actors co-occur in space and time, presumably due to an underlying interaction. We call these spatio-temporal co-occurrences events, which we use to establish relationships between pairs of individuals. In this paper, we propose a model for constructing a social network from events, and provide an algorithm that mines these events from the data. Experiments on a real-life data tracking people's accesses to cyber locations have also yielded encouraging results. Hady W. Lauw is a graduate student at the School of Computer Engineering, Nanyang Technological University, Singapore. His research interests include spatio-temporal data mining, social network discovery, and link analyisis. He has a BEng in computer engineering from Nanyang Technological University. Ee-Peng Lim is an Associate Professor with the School of Computer Engineering, Nanyang Technological University, Singapore. He received his PhD from the University of Minnesota, Minneapolis in 1994 and B.Sc. in Computer Science from National University of Singapore. Ee-Peng's research interests include information integration, data/text/web mining, digital libraries, and wireless intelligence. He is currently an Associate Editor of the ACM Transactions on Information Systems (TOIS), International Journal of Digital Libraries (IJDL) and International Journal of Data Warehousing and Mining (IJDWM). He was the Program Co-Chair of the ACM/IEEE Joint Conference on Digital Libraries (JCDL 2004), and Conference/Program Co-Chairs of International Conference on Asian Digital Libraries (ICADL 2004). He has also served in the program committee of numerous international conferences. Dr Lim is a Senior Member of IEEE and a Member of ACM. HweeHwa Pang received the B.Sc.—with first class honors—and M.S. degrees from the National University of Singapore in 1989 and 1991, respectively, and the PhD degree from the University of Wisconsin at Madison in 1994, all in Computer Science. He is currently an Associate Professor at the Singapore Management University. His research interests include database management systems, data security and quality, operating systems, and multimedia servers. He has many years of hands-on experience in system implementation and project management. He has also participated in transferring some of his research results to industry. Teck-Tim Tan is an IT Manager (Operations) at the Centre for IT Services, Nanyang Technological University (NTU), Singapore. He administers and oversees NTU's campus-wide wireless LAN infrastructure which facilitates access to the University's vast IT resources and services practically anywhere on campus.     

基于Fuzzy理论的数据挖掘算法研究Ⅱ

"数据挖掘"是数据处理的一个新领域.支持向量机是数据挖掘的一种新方法,该技术在很多领域得到了成功的应用.但是,支持向量机目前还存在许多局限,当支持向量机的训练集中含有模糊信息时,支持向量机将无能为力.为解决一般情况下支持向量机中含有模糊信息(模糊参数)问题,研究了模糊机会约束规划、模糊分类中的模糊特征及其表示方法,建立了模糊支持向量分类机理论,给出了模糊线性可分的模糊支持向量分类机算法.     

基于Fuzzy理论的数据挖掘算法研究(Ⅰ)

“数据挖掘”是数据处理的一个新领域.支持向量机是数据挖掘的一种新方法,该技术在很多领域得到了成功的应用.但是,支持向量机目前还存在许多局限,当支持向量机的训练集中含有模糊信息时,支持向量机将无能为力.为解决一般情况下支持向量机中含有模糊信息(模糊参数)问题,研究了模糊机会约束规划、模糊分类中的模糊特征及其表示方法,建立了模糊支持向量分类机理论,给出了模糊线性可分的模糊支持向量分类机算法.     

移动电话客户流失数据挖掘

本文首先回顾了顾客流失的相关文献,然后利用统计分析方法和数据挖掘技术分析了移动电话号码与移动电话型号对客户流失的影响,对分析结果进行了解释,并给出一些营销建议。     

基于数据挖掘技术的股票收益率方向研究

本文依据数据挖掘技术对股票收益率的变化方向进行探究。通过小波多尺度分解,将股票价格转化为不同频率域下的子序列数据、并对其中的高频序列进行降噪。构建极度梯度提升树(XGBoost)、以及其它主流机器学习算法,对沪深300和中证500指数中成分股的涨跌进行了拟合并预测。研究发现XGBoost的平均准确率分别达到了54.69%和55.13%,同时依据预测信号构建的投资策略可产生稳定收益,表明该方法具备较强的预测能力。在此基础上,对机器学习算法存在的“黑箱”问题进行了阐述和研究,对模型选股的逻辑进行了探析:提出一种因子权重的度量方法,研究发现市净率、市盈率、能量潮等指标在模型中是较为重要的判别指标,并通过偏相依关系度量了模型中各因子对于股价涨跌方向的边际影响,得到模型倾向于选择市盈率、市净率较小的股票等一些结论,使算法的逻辑更为清楚。     

Statistical Analysis of Series System for Masked Data under Successive Censored Life Test

In this paper, considering series system of masked data under simple successive censored and multiple successive censored life test, the likelihood function and maximum likelihood estimate are respectively proposed for series system composed of two units under two kinds of situations. One is the series system composed of two units with constant failure rate, and the other is the series system composed of two units with linear failure rate through the origin. The approximate interval estimates of parameters are given by using the method of likelihood ratio. Besides, the examples show the feasibility of the methods through Monte-Carlo simulations.