粗糙集与Bayes决策规则【毕业论文】.doc

本科毕业论文 （20 届） 粗糙集与Bayes决策规则 专业：数学与应用数学 摘要. 首先, 回顾了此外关键词: Bayes则; 粗糙集; 决策规则; 信息系统Rough Sets with Bayes Decision Rule Abstract Rough set theory is a mathematical tool to study incomplete and uncertain knowledge processing. In recent years, it has been successfully applied in many research fields such as machine learning, knowledge discovery, algorithm research, engineering application, decision support systems, and pattern recognition etc. In this thesis, we mainly focus on the study of rough sets with Bayes decision rules. Basic notions related to rough sets, information systems, and decision tables are first reviewed. The definition of conditional probability and its properties are then introduced. Finally, we investigate the approach of rule acquisition in complete decision tables based on the Bayes probability theory. In the rough set theory, with every decision rule, two conditional probabilities, called certainty factor and coverage factor, are associated. Besides, it is revealed that the two factors satisfy the Bayesian theorem. That means that we can use the two factors to analyze the Bayes’ rules in decision tables without referring to the prior and posterior probabilities of the Bayesian theorem. Keywords: Bayes’ rule; Rough sets; Decision rules; Information system 目录 摘要 I Abstract II 1 前言 1 1.1 粗糙集的由来和发展 1 1.2 Bayes理论的由来和发展 1 1.3 论文的组织结构 2 2 粗糙集理论的基本概念 3 2.1 知识与知识库 3 2.2 不确定范畴, 近似与粗糙集 3 2.3 知识约简 4 2.4 知识表达系统 4 2.5 决策表 6 3 条件概率 7 3.1 条件概率的定义 7 3.2 全概率公式 8 3.3 Bayes公式 8 4 粗糙集与Bayes决策规则 9 4.1 决策规则 9 4.2 决策算法及其性质 10 4.3 决策规则和粗糙集的近似 11 4.4 决策规则和Bayes决策规则 13 4.5 对决策规则的信任因子和覆盖因子决策规则的解释 15 5 小结 25 参考文献 26 致谢 27  1 前言 1.1 粗糙集的由来和发展 粗糙集理论是波兰数学家Pawlak Z于1982年提出的一种数据分析理论. 在这之后, 许多数学家, 计算机研究人员和逻辑学家对粗糙集产生了很大的兴趣, 并且在粗糙集的理论和应用方面做了大量的研究. 1991年Pawlak Z的专著1992年1995年, ACM Communication将其列为新浮现的计算机科学的研究课题. 1998年, 国际信息科学杂志(Infomation Sciences)还为粗糙集理论的研究出了一期专辑. 这些都促进了粗糙集的发展. 粗糙集理论是一种刻不完整性和不确定性的数学工具, 能有效地分析不精确, 不一致, 不完整等各种不完备的信息., 它的主要思想是将不确定或不精确的知识用已知的知识库中