覆盖粒计算及其应用研究 硕士学位论文.docx

1、覆盖粒计算及其应用研究 硕士学位论文学校代码 10345 研究类型 应用基础研究硕 士 学 位 论 文 题 目: 覆盖粒计算及其应用研究 Research on the Covering and Its Application Based on Granular Computing Research on the Covering and Its ApplicationBased on Granular ComputingThesis Submitted toZhejiang Normal Universityfor the degree ofMaster of EngineeringBySh

2、uang Liu(Computer Software and Theory)Thesis Supervisor: Professor Jiyi WangJune, 2011覆盖粒计算及其应用研究摘 要粒计算是研究基于多层次粒结构的思维方法、问题求解方法、信息处理模式及其相关理论、技术和工具的学科。它覆盖了所有和粒度相关的理论、方法和技术，主要用于对不确定、不准确、不完整信息的处理，对大规模海量的数据和对复杂问题的求解。粗糙集作为粒计算的一个重要分支，在理论和应用上不断取得丰硕成果的同时，也得到了广泛有意义的推广。而覆盖广义粗糙集理论是Pawlak粗糙集理论在划分基础上推广到覆盖建立起来的，它是

3、研究与覆盖相关的理论体系及其应用，由于它是在粗糙集理论上的关系推广，有关粗糙集的一些理论和应用并不一定在覆盖广义粗糙集下适用。因此，本文的主要内容是在粒计算思想理论背景下，研究与覆盖相关的理论及其应用。具体研究工作如下：一、在面向基于粗糙集理论的动态信息系统规则挖掘的研究中，利用覆盖粒计算相关理论提出了一种能消除引起差异信息系统规则挖掘中不一致因素的公理化方法。实验结果表明，在保持时间复杂度不变的情况下，利用改进的规则挖掘算法，通过消除不一致因素而获得的规则能更全面和更大程度地反映条件属性值变化与决策变化趋势之间的内在联系。二、在面向冲突分析的研究中，在粒计算思想理论背景下，首次提出了“关联冲

4、突”的概念。利用覆盖冲突分析策略,通过“服务资源”实例建立了关联冲突分析的合理泛化模型，讨论了关联冲突过程中所可能引发异常的阶段，并对不同阶段引发的异常进行了详细的分析，给出了具体的解决方案,从而完善了各个领域冲突的解决。三、在面向分类法准确性（单标签和多标签数据集）的研究中，利用拓扑覆盖邻域理论，给出了寻找覆盖系统上重叠元素的相关公理化方法。在粒计算的思维体系背景下，以实例辅证，给出了独立于数据标签和不同理想分类结果假设（一种假设为划分，另一种假设为覆盖）的评价分类法准确性的统一范式，为提高和评估分类法准确性的计算提供了重要的参考意义。最后，文章是在同一个思想理论背景下，讨论了基于覆盖的相关

5、理论和应用。以上研究工作是覆盖广义粗糙集的理论及其应用的补充和发展，充分的体现出了粒计算背景下知识发现理论和方法的独特性，具有重要的理论意义及潜在的应用价值。 关键词：粒计算；覆盖；动态信息系统；规则挖掘；关联冲突；分类RESEARCH ON THE COVERING AND ITS APPLICATION BASED ON GRANULAR COMPUTINGABSTRACTGranular computing (GrC) is viewed as an interdisciplinary study of computation in nature, society and science

6、, characterized by structured thinking, structured problem solving and structured information processing with an underlying notion of multiple levels of granulation. It consists of all the theories, methodologies, techniques and tools related to the granularity, which is mainly used to deal with unc

7、ertainty, imprecise and incomplete information and seek resolutions from the large-scale massive dataset or complicated problem. Rough set, as a very important branch of GrC, is being improving and perfecting on theory and application as well as is being extending widely and significantly. Generaliz

8、ed rough set on covering is the one that partitions Pawlak rough set theory is extended into coverings. It focuses on the study of covering, so that many theories and applications in the Pawlak rough set are not tenable and suitable in the generalized rough set on covering. Therefore, this dissertat

9、ion will mainly make research on covering theories and its applications under background of GrC, whose content is shown as follows:First of all, for the rules mining based on rough set theory in dynamic information system, a pre-process approach to eliminate the elements that cause inconsistence of

10、rules mining in difference information system is proposed under the background of covering theory based on granular computing. Experiment shows that relationship between the changes of condition attributes values and trend of decision-making can be fully reflected as much as possible by a modified r

11、ules mining algorithm under the same time complexity through this pre-process approach.Secondly, for the conflict analysis, associated-conflict is firstly introduced in the perspective of GrC, and a reasonable and comprehensive approach to its analysis, using covering based on granular computing, is

12、 outlined. We argue that this model of associated-conflict analysis, given by the example of service-resource, will provide more profound insight for the conflict resolution in different fields.Thirdly, for the accuracy of classification method on single label dataset or multi label dataset, a unifi

13、ed paradigm for the accuracy used to evaluate different classification methods, using topological covering based on GrC, is presented, independent on number of data labels and different assumptions of ideal classification result(one assumption is partition, the other is covering). And some correspon

14、ding examples are also discussed to illustrate the accuracy in different classification situations. This unified paradigm will provide important reference value for the evaluation and improvement of accuracy of classification method.In brief, this paper discusses theories and applications related to

15、 the covering under the same theory background, and it can be treated as supplement and development of generalized rough set on covering. And it reflects the specificity on theories, methodologies, techniques and tools of knowledge discovery under the background of GrC, with significant referred and

16、 applied value in the future. KEY WORDS: GrC; Covering; Dynamic Information System; Rules Mining; Associated-conflict; Classification目 录摘 要 IABSTRACT III目 录 V第一章 绪 论 11.1粒计算 11.1.1粒计算提出背景 11.1.2粒计算任务和目标 21.1.3粒计算基本要素和理论构成 21.1.4粒计算研究方向与方法 51.1.5粒计算基本思想和实质 61.2覆盖广义粗糙集理论 61.2.1覆盖广义粗糙集的研究背景 71.2.2覆盖广义粗糙集的国内外研究现状 81.3本文研究的意义、目标、方法和主要内容以及创新点 81.3.1本文研究的意义 81.3.2本文研究的目标 81.3.3本文研究的方