基于粗糙集和决策树的规则提取方法研究
|
摘要
粗糙集理论是一种处理不准确、不确定和不完备信息的有效分析工具,能利用现有知识库中的知识对不完备信息进行近似刻画处理。属性约简和决策规则提取是粗糙集的两大核心研究内容,但现有的属性约简算法和决策规则提取方法都存在各种不足。
为了获得更精简的属性约简集并有效提取决策规则,本论文首先针对基于分明矩阵的属性约简算法中构造分明函数时存在的元素重复、化简计算量大、矩阵元素长度不一等缺陷进行了改进。由于决策树技术具有分类速度快、效率高、容易理解等特点,本论文将其与粗糙集理论相结合实现决策规则的提取。利用上述改进的属性约简算法得到约简集,再利用约简集构造一棵具有多变量多集合的决策树,从而提取决策规则。为避免不一致信息的干扰,引入准确度和覆盖度两个评价因素对决策规则进行筛选,最后提取有效的决策规则。通过旋转机械中转子不对中的故障诊断实例对上述改进算法进行验证,实例表明,改进的属性约简算法比改进前的算法在故障规则提取时间上更快,证明了改进算法的有效性;同时也表明用粗糙集与决策树相结合的方法,不仅可以去除噪声,也可以处理不一致信息,最终能得到有效的故障诊断决策规则集。
为了将上述方法更好应用到实践中,本论文在.NET平台上设计和实现了一个基于粗糙集的决策规则提取系统,此系统可对原始决策表进行属性约简、根据约简集构造出决策树进行规则提取、并引入覆盖度对规则进行筛选获得有效规则。
Rough Set theory is a kind of effective analysis tool to deal with inaccurate, incomplete, and uncertain information, which makes use of the existed rules in the knowledge warehouse to character the incomplete information. Attribute reduction and decision rules extraction are two main respects research area of rough set, but there are many defects in the existing the two algorithms.
In order to obtain a more streamlined set of attribute reduction effectively, the paper optimizes the attribute reduction algorithm that based on discernibility matrix firstly. Because there are some defects, such as element duplication, complex calculation, and varying length of discernibility matrix element in constructing the traditional discemibility function. As the decision tree technology is characteristic with fast classification speed, high efficient, easily to be understood, and so on, the paper combines the decision tree and rough set theory to extract decision rules, in which, the optimized attribute reduction algorithm is applied to get reduction sets and then the reduced attribute set is used to construct a multi-variable decision tree to extract decision rules. At last, in order to avoid disturbance of inconsistencies information, the accuracy and coverage degree are introduced to filter the decision rules and extract decision rules effectively. An example of rotating machinery fault diagnosis validated the above optimized algorithm, which shows the methods combines rough set and decision tree can not only wipe off noise, but also deal with inconsistencies information.
In order to put the above optimized method into practice, a decision rule extraction system based on rough set theory and decision tree is developed in this paper. The system is designed based on .NET platform, which can carry out attribute reduction for original decision table, extract decision rules according to the structured decision tree, and obtain the effective decision rules finally.
为了获得更精简的属性约简集并有效提取决策规则,本论文首先针对基于分明矩阵的属性约简算法中构造分明函数时存在的元素重复、化简计算量大、矩阵元素长度不一等缺陷进行了改进。由于决策树技术具有分类速度快、效率高、容易理解等特点,本论文将其与粗糙集理论相结合实现决策规则的提取。利用上述改进的属性约简算法得到约简集,再利用约简集构造一棵具有多变量多集合的决策树,从而提取决策规则。为避免不一致信息的干扰,引入准确度和覆盖度两个评价因素对决策规则进行筛选,最后提取有效的决策规则。通过旋转机械中转子不对中的故障诊断实例对上述改进算法进行验证,实例表明,改进的属性约简算法比改进前的算法在故障规则提取时间上更快,证明了改进算法的有效性;同时也表明用粗糙集与决策树相结合的方法,不仅可以去除噪声,也可以处理不一致信息,最终能得到有效的故障诊断决策规则集。
为了将上述方法更好应用到实践中,本论文在.NET平台上设计和实现了一个基于粗糙集的决策规则提取系统,此系统可对原始决策表进行属性约简、根据约简集构造出决策树进行规则提取、并引入覆盖度对规则进行筛选获得有效规则。
Rough Set theory is a kind of effective analysis tool to deal with inaccurate, incomplete, and uncertain information, which makes use of the existed rules in the knowledge warehouse to character the incomplete information. Attribute reduction and decision rules extraction are two main respects research area of rough set, but there are many defects in the existing the two algorithms.
In order to obtain a more streamlined set of attribute reduction effectively, the paper optimizes the attribute reduction algorithm that based on discernibility matrix firstly. Because there are some defects, such as element duplication, complex calculation, and varying length of discernibility matrix element in constructing the traditional discemibility function. As the decision tree technology is characteristic with fast classification speed, high efficient, easily to be understood, and so on, the paper combines the decision tree and rough set theory to extract decision rules, in which, the optimized attribute reduction algorithm is applied to get reduction sets and then the reduced attribute set is used to construct a multi-variable decision tree to extract decision rules. At last, in order to avoid disturbance of inconsistencies information, the accuracy and coverage degree are introduced to filter the decision rules and extract decision rules effectively. An example of rotating machinery fault diagnosis validated the above optimized algorithm, which shows the methods combines rough set and decision tree can not only wipe off noise, but also deal with inconsistencies information.
In order to put the above optimized method into practice, a decision rule extraction system based on rough set theory and decision tree is developed in this paper. The system is designed based on .NET platform, which can carry out attribute reduction for original decision table, extract decision rules according to the structured decision tree, and obtain the effective decision rules finally.
引文
[1].Z.Pawlak.Rough Sets[J].International Journal of Computer and Information Science,1982,11(5):341-356
[2].吴福保.基于粗糙集理论信息系统的分析方法及其应用的研究[博士学位论文].南京:东南大学,2000
[3].S.K.M Wong,W.Ziarko.On Optional decision rules in decision tables[J].Bulletin of polish Academy of Sciences,1985,33(6):663-676
[4].Hu X H,Cercone N.Learning in relational databases:A Rough Set approach [J].Computational Intelligence,1995,11(2):323-338
[5].Jelonek J et al.Rough Set reduction of attributes and their domains for neural networks[J].Computational Intelligence,1995,11(2):339-347
[6].刘少辉,盛秋戬,吴斌.Rough集高效算法的研究[J].计算机学报,2003,26(5):524-529
[7].江娟等.基于粒计算的规则发现研究[J].杭州电子科技大学学报,2005,25(6):60-63
[8].郑书富,林克明.非一致决策系统的规则获取算法[J].三明学院学报,2006,23(2):195-198
[9].QuinlanJ.R.Induetion of Deeision Trees[J].Machine leaming.1986,12(1):81-106
[10].Breiman.L,Friedman.J,Olshen.R.et al.Classification and Regression Trees.Monterey,CA.Wadsworth International Group.1994
[11].谭天乐,宋执环,李平.基于粗糙集的故障诊断方法[J].浙江大学学报,2003,37:47-50
[12].袁小宏,赵仲生,屈梁生.粗糙集理论在机械故障诊断中的应用研究[J].西安交通大学学报,2001,38(11):89-95
[13].Zhong N,Dong J,Ohsuga S.Rough Sets with Heuristics for Feature Selection[J].Journal of Intelligent Information Systems.2001,16(2):200-204
[14].张文修,吴伟志,梁吉业等.粗糙集理论与方法[M].北京:科学出版社,2003:26-39
[15].王国胤.Rough集理论与知识获取[M].西安:西安交通大学出版社,2001
[16].M.Kyrszkiewicz.Rough set approach to incomplete information systems[J].Information Sciences,1998,112:39-49
[17].M.Kryszkiewicz.Rules in incomplete information systems[J].Information Sciences,1999,113:271-292
[18].Z.Pawlak.Rough set theory and its application to data analysis[J].Cybernetics and Systems,1998,29(9):661-668
[19].Skowron A,Rauszer C.The discernibility matrices and function in information system.In:Slowinski R,ed.Dordreecht:Kluwer Academic Publishers,1991:331-362
[20].尹旭日.基于Rough集的连续属性离散化方法[J].计算机工程与设计.2006,27(11):2038-2040
[21].侯利娟,王国胤,聂能.粗糙集理论中的离散化问题[J].计算机科学,2000,89-94
[22].谢宏,程浩忠,牛东晓.基于信息熵的粗糙集连续属性离散化算法[J].计算机学报,2005,28(9):1570-1573
[23].Hu X.H,Cercone N.Learning in relational databases:a rough set approach.International Journal of Computational Intelligence.1995,11(2):323-338
[24].Jelonek J,Krawiec K,Slowinski R.Rough set reduction of attributes and their domains for neural networks.International Journal of Computational.1995,11(2):339-347
[25].刘少辉,盛秋戬,吴斌等.Rough集高效算法的研究[J].计算机学报,2003,26(5):524-529
[26].张腾飞,肖健梅,王锡淮.粗糙集理论中属性相对约简算法[J].电子学报,2005,33(11):2080-2083
[27].王珏,王任,苗夺谦等.基于Rough Set理论的”数据浓缩”[J].计算机学报,1998,21(5):393-399
[28].Wang Jue,Wang Ju.Reduction algorithms based on discernibility matrix:The ordered attributes method[J].Journal of Computer Science & Technology,2001,16(6):489-504
[29].王国胤.Rough集理论与知识获取[M].西安交通大学出版,2001,117-157
[30].苗夺谦,胡桂荣.知识约简的一种启发式算法[J].计算机研究与发展,1999,36(6):681-684
[31].商琳,万琼,姚望舒等.一种连续值属性约简方法ReCA[J].计算机研究与发展,2005,42(7):1217-1224
[32].Renpu Li,Zheng-ou Wang.Mining classification rules using rough sets and neural networks[J].European Journal of Operational Research,2004,157:439-448
[33].任永功,王杨,德勤.基于遗传算法德粗糙集属性约简算法[J].小型微型计算机系统,2006,27(5):862-865
[34].苗夺谦,王珏.粗糙集理论中知识粗糙性与信息熵关系的讨论[J].模式识别与人工智能,1998,11:34-40
[35].陈克兴,李川奇.设备状态监测与故障诊断技术[M].北京:科学技术文献出版社,1989,342-389
[36].Xiaoshu Hang,Honghua Dai.An optimal Strategy for Extracting Probabilistic Rules by Combining Rough Sets and Genetic Algorithm.DS 2003,LNAI 2843:153-165
[37].何伟,刘春亚等.不完备信息系统下的属性约简算法[J].计算机科学,2004,31(2):117-119
[38].罗秋瑾.粗糙集理论在决策树中的应用[D].昆明理工大学,2005
[39].苗夺谦,王珏.基于粗糙集的多变量决策树构造方法[J].软件学报,1997,8(6):425-431
[40].王名扬.基于粗糙集理论的决策树生成与剪树方法[D].东北师范大学,2005
[41].邵峰晶,于忠清.数据挖掘—原理与算法[M].中国水利水电出版社,2003
[42].栗丽华,吉根林.决策树分类技术研究[J].计算机工程,2004,3(9):94-97
[43].洪家荣,丁明峰,李星原.一种新的决策树归纳学习算法[J].计算机学报,1995,18(6):470-474
[44].刘小虎,李生.决策树的优化算法[J].软件学报,1998,9(10):797-800
[45].苗夺谦,王珏.基于粗糙集的多变量决策树构造方法[J].软件学报,1997,8(6):425-431
[46].江娟等.基于粒计算的规则发现研究[J].杭州电子科技大学学报,2005,25(6),60-63
[47].郑书富,林克明.非一致决策系统的规则获取算法[J].三明学院学报,2006,23(2):195-198
[48].周庆敏,李永生,殷晨波,陆金桂.基于粗糙集理论的故障诊断规则获取方法研究[J].计算机工程与应用,2003(26):64-66
[49].陈久军,盛颂恩,陈燕飞.Rough集理论在故障诊断专家系统中的应用研究[J].机电工程,2002,19(3):49-51
[50].曾建武.粗糙集理论及故障诊断应用研究[D].浙江大学,2066
[51].王楠,律方成,刘云鹏,李和明.粗糙集理论在变压器故障诊断中的应用[J].北电力大学学报,2003,30(4):21-24
[52].袁小宏,赵仲生,屈梁生.粗糙集理论在机械故障诊断中的应用研究[J].西安交通大学学报,2001,38(11):89-95
[53].ChanP.K,StolfoS.J.Experiments on Multistrategy Leaning by Metaleaming.in Proceeding 2~(nd)[J].International conferences Information and Knowledge Management.1993:314-323
[54].Pawlak Z.Rough sets,decision algorithms and Bayes' theorem[J].European Journal of Operational Research,2002,136(1):181-189
[55].黄文涛,赵学增,王伟杰,代礼周.基于粗糙集理论的故障诊断决策规则提取方法[J] 计算机工程与应用,2003,23(11):150-154
[56].刘清.Rough集及Rough推理[M].北京:科学出版社,2003
[57].周庆敏,李永生,殷晨波,陆金桂.基于粗糙集理论的故障诊断规则获取方法研究[J].计算机工程与应用,2003(26):64-66
[2].吴福保.基于粗糙集理论信息系统的分析方法及其应用的研究[博士学位论文].南京:东南大学,2000
[3].S.K.M Wong,W.Ziarko.On Optional decision rules in decision tables[J].Bulletin of polish Academy of Sciences,1985,33(6):663-676
[4].Hu X H,Cercone N.Learning in relational databases:A Rough Set approach [J].Computational Intelligence,1995,11(2):323-338
[5].Jelonek J et al.Rough Set reduction of attributes and their domains for neural networks[J].Computational Intelligence,1995,11(2):339-347
[6].刘少辉,盛秋戬,吴斌.Rough集高效算法的研究[J].计算机学报,2003,26(5):524-529
[7].江娟等.基于粒计算的规则发现研究[J].杭州电子科技大学学报,2005,25(6):60-63
[8].郑书富,林克明.非一致决策系统的规则获取算法[J].三明学院学报,2006,23(2):195-198
[9].QuinlanJ.R.Induetion of Deeision Trees[J].Machine leaming.1986,12(1):81-106
[10].Breiman.L,Friedman.J,Olshen.R.et al.Classification and Regression Trees.Monterey,CA.Wadsworth International Group.1994
[11].谭天乐,宋执环,李平.基于粗糙集的故障诊断方法[J].浙江大学学报,2003,37:47-50
[12].袁小宏,赵仲生,屈梁生.粗糙集理论在机械故障诊断中的应用研究[J].西安交通大学学报,2001,38(11):89-95
[13].Zhong N,Dong J,Ohsuga S.Rough Sets with Heuristics for Feature Selection[J].Journal of Intelligent Information Systems.2001,16(2):200-204
[14].张文修,吴伟志,梁吉业等.粗糙集理论与方法[M].北京:科学出版社,2003:26-39
[15].王国胤.Rough集理论与知识获取[M].西安:西安交通大学出版社,2001
[16].M.Kyrszkiewicz.Rough set approach to incomplete information systems[J].Information Sciences,1998,112:39-49
[17].M.Kryszkiewicz.Rules in incomplete information systems[J].Information Sciences,1999,113:271-292
[18].Z.Pawlak.Rough set theory and its application to data analysis[J].Cybernetics and Systems,1998,29(9):661-668
[19].Skowron A,Rauszer C.The discernibility matrices and function in information system.In:Slowinski R,ed.Dordreecht:Kluwer Academic Publishers,1991:331-362
[20].尹旭日.基于Rough集的连续属性离散化方法[J].计算机工程与设计.2006,27(11):2038-2040
[21].侯利娟,王国胤,聂能.粗糙集理论中的离散化问题[J].计算机科学,2000,89-94
[22].谢宏,程浩忠,牛东晓.基于信息熵的粗糙集连续属性离散化算法[J].计算机学报,2005,28(9):1570-1573
[23].Hu X.H,Cercone N.Learning in relational databases:a rough set approach.International Journal of Computational Intelligence.1995,11(2):323-338
[24].Jelonek J,Krawiec K,Slowinski R.Rough set reduction of attributes and their domains for neural networks.International Journal of Computational.1995,11(2):339-347
[25].刘少辉,盛秋戬,吴斌等.Rough集高效算法的研究[J].计算机学报,2003,26(5):524-529
[26].张腾飞,肖健梅,王锡淮.粗糙集理论中属性相对约简算法[J].电子学报,2005,33(11):2080-2083
[27].王珏,王任,苗夺谦等.基于Rough Set理论的”数据浓缩”[J].计算机学报,1998,21(5):393-399
[28].Wang Jue,Wang Ju.Reduction algorithms based on discernibility matrix:The ordered attributes method[J].Journal of Computer Science & Technology,2001,16(6):489-504
[29].王国胤.Rough集理论与知识获取[M].西安交通大学出版,2001,117-157
[30].苗夺谦,胡桂荣.知识约简的一种启发式算法[J].计算机研究与发展,1999,36(6):681-684
[31].商琳,万琼,姚望舒等.一种连续值属性约简方法ReCA[J].计算机研究与发展,2005,42(7):1217-1224
[32].Renpu Li,Zheng-ou Wang.Mining classification rules using rough sets and neural networks[J].European Journal of Operational Research,2004,157:439-448
[33].任永功,王杨,德勤.基于遗传算法德粗糙集属性约简算法[J].小型微型计算机系统,2006,27(5):862-865
[34].苗夺谦,王珏.粗糙集理论中知识粗糙性与信息熵关系的讨论[J].模式识别与人工智能,1998,11:34-40
[35].陈克兴,李川奇.设备状态监测与故障诊断技术[M].北京:科学技术文献出版社,1989,342-389
[36].Xiaoshu Hang,Honghua Dai.An optimal Strategy for Extracting Probabilistic Rules by Combining Rough Sets and Genetic Algorithm.DS 2003,LNAI 2843:153-165
[37].何伟,刘春亚等.不完备信息系统下的属性约简算法[J].计算机科学,2004,31(2):117-119
[38].罗秋瑾.粗糙集理论在决策树中的应用[D].昆明理工大学,2005
[39].苗夺谦,王珏.基于粗糙集的多变量决策树构造方法[J].软件学报,1997,8(6):425-431
[40].王名扬.基于粗糙集理论的决策树生成与剪树方法[D].东北师范大学,2005
[41].邵峰晶,于忠清.数据挖掘—原理与算法[M].中国水利水电出版社,2003
[42].栗丽华,吉根林.决策树分类技术研究[J].计算机工程,2004,3(9):94-97
[43].洪家荣,丁明峰,李星原.一种新的决策树归纳学习算法[J].计算机学报,1995,18(6):470-474
[44].刘小虎,李生.决策树的优化算法[J].软件学报,1998,9(10):797-800
[45].苗夺谦,王珏.基于粗糙集的多变量决策树构造方法[J].软件学报,1997,8(6):425-431
[46].江娟等.基于粒计算的规则发现研究[J].杭州电子科技大学学报,2005,25(6),60-63
[47].郑书富,林克明.非一致决策系统的规则获取算法[J].三明学院学报,2006,23(2):195-198
[48].周庆敏,李永生,殷晨波,陆金桂.基于粗糙集理论的故障诊断规则获取方法研究[J].计算机工程与应用,2003(26):64-66
[49].陈久军,盛颂恩,陈燕飞.Rough集理论在故障诊断专家系统中的应用研究[J].机电工程,2002,19(3):49-51
[50].曾建武.粗糙集理论及故障诊断应用研究[D].浙江大学,2066
[51].王楠,律方成,刘云鹏,李和明.粗糙集理论在变压器故障诊断中的应用[J].北电力大学学报,2003,30(4):21-24
[52].袁小宏,赵仲生,屈梁生.粗糙集理论在机械故障诊断中的应用研究[J].西安交通大学学报,2001,38(11):89-95
[53].ChanP.K,StolfoS.J.Experiments on Multistrategy Leaning by Metaleaming.in Proceeding 2~(nd)[J].International conferences Information and Knowledge Management.1993:314-323
[54].Pawlak Z.Rough sets,decision algorithms and Bayes' theorem[J].European Journal of Operational Research,2002,136(1):181-189
[55].黄文涛,赵学增,王伟杰,代礼周.基于粗糙集理论的故障诊断决策规则提取方法[J] 计算机工程与应用,2003,23(11):150-154
[56].刘清.Rough集及Rough推理[M].北京:科学出版社,2003
[57].周庆敏,李永生,殷晨波,陆金桂.基于粗糙集理论的故障诊断规则获取方法研究[J].计算机工程与应用,2003(26):64-66
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |