期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

信息表的离散格研究 被引量：3

STUDY ON THE DISCRETIZATION LATTICE OF INFORMATION TABLE
原文传递
导出
摘要 定义离散化方案之间的偏序关系以及交、并运算,将一个信息表的各种离散化方案组织成一个格空间,称为离散格,分析了离散格与划分格之间的关系,证明了离散格是一个布尔代数,而划分格不是布尔代数,分析了一类离散化算法,指出这类算法的求解过程正是对离散格的搜索过程。 This paper analyzes the discretization schemes of a given numeric information table, and constructs a discretization lattice with these schemes. We compare the partition lattice of the object set with the discretization lattice and find that, the latter is a Boolean Algebra while the former is not. Based on the indiscernibility relation on attribute set, we define a function from discretization lattice to the partition lattice. The insight into a class of discretization algorithms shows that they get the final discretized table by searching the discretization lattice.
作者 王立宏 吴耿锋
机构地区 上海大学计算机学院
出处 《模式识别与人工智能》 EI CSCD 北大核心 2004年第1期11-16,共6页 Pattern Recognition and Artificial Intelligence
基金 国家自然科学基金(No.60275022 60203011) 上海市教委重点学科建设资助项目
关键词 机器学习 数据挖掘 离散化算法 信息表 离散格 Discretization Lattice, Partition Lattice, Discretization Algorithms
分类号 TP311.13 [自动化与计算机技术—计算机软件与理论]
  • 相关文献

参考文献9

  • 1李刚,童頫.基于混合概率模型的无监督离散化算法[J].计算机学报,2002,25(2):158-164. 被引量：16
  • 2Grzymala-Busse J W. Stefanowski J, Three Discretization Methods for Rule Induction. Intemational Journal of Intelligent System.s, 2001, 16:29-38.
  • 3Clarke E 1, Barton B A. Entropy and MDL Diseretization of Continuous Variables for Bayesian Belief Networks. International Journal of Intelligent Systems, 2000, 15 : 61 - 92.
  • 4Francis E H T, Shen Lixiang. A Modified Chi2 Algorithm for Discretization. 1EEE Trails on Knowledge and Data Engineering,2002, 14(3): 666-670.
  • 5Silverstein C, Brin S, Motwani R. Beyond Market Baskets: Generalizing Association Rules to Dependence Rules. Data Mining and Knowledge Discovery, 1998, 2:39-68.
  • 6Bay S D. Detecting Group Differences: Mining Contrast Sets. Data Mining and Knowledge Discovery, 2001, 5:213 - 246.
  • 7Bay S D. Multivariant Diseretization for Set Mining. Knowledge and Information Systems, 2001, 3:491-512.
  • 8Yao Y Y, Yao J T. Granular Computing as a Basis for Consistent Classification Problems. Communications of Institute of Information and Computing Machinery, 2002. 5(2): 101-106.
  • 9欧俊豪 王家生.应用概率统计(第二版)[M].天津:天津大学出版社,2001.264-268.

二级参考文献14

  • 1[1]Catlett J. On changing continuous attributes into ordered discreteattributes. In: Proc European Working Session on Learning (EWSL91). LNAI-482, Porto,Portugal, 1991. 164-178
  • 2[2]Dougherty J, Kohavi R, Sahami M. Supervised and unsupervised discretizationof continuous features. In: Proc the 12th International Conference, Morgan KaufmannPublishers, 1995.194-202
  • 3[3]Quinlan J R. C4.5: Programs for Machine Learning. San Mateo: Morgan Kaufmann,1993
  • 4[4]Fayyad U, Irani K. Multi-interval discretizaton of continuous-valuedattributes for classification learning. In: Proc the 13th International JointConference on Artificial Intelligence, San Mateo, CA. Morgan Kaufmann Publishers,1993. 1022-1027
  • 5[5]Li G, Tong F. WILD: Weighted information-loss discretization algorithm forordinal attributes. In: Proc Conference on Intelligent Information Processing, the16th IFIP World Computer Congress 2000, Beijing, China, 2000.254-527
  • 6[6]Quinlan J R. Improved use of continuous attributes in C4.5. Journal ofArtificial Intelligence Research, 1996,4(1):77-90
  • 7[7]Wong A K C, Chiu D K Y. Synthesizing statistical knowledge from incompletemixed-mode data. IEEE Trans Pattern Analysis and Machine Intelligence, 1987,PAMI-9(6):796-805
  • 8[8]Banfield J D, Raftery A E. Model based Gaussian and non-Gaussian clustering.Biometrics, 1993,49(3):803-821
  • 9[9]Mackay D J C. Information Theory, Inference and Learning Algorithms.Cambridge: Cambridge University Press, 2000
  • 10[10]Dempster A P, Laird N M, Rubin D B. Maximum likelihood for incomplete data viathe EM algorithm. Journal of the Royal Statistical Society, Series B, 1977,39(1):1-38

共引文献15

同被引文献18

  • 1王立宏,吴耿锋.信息表离散格的进一步研究[J].模式识别与人工智能,2005,18(1):25-30. 被引量：2
  • 2Liu Li-li,Wong A K C.A global optimal algorithm for Class-dependent discretization of continuous data[J].Intelligent Data Analysis, 2004,8: 151-170.
  • 3Yao Y Y,Yao J T.Granular computing as a basis for consistent classification problems[C]//PAKDD Workshop on Foundation of Data Mining, Taipei, Taiwan, 2002 ,5 ( 2 ) : 101-106.
  • 4Greco S,Matarazzo B,Slowinski R.Rough approximation by dominance relations[J].International Journal of Intelligent Systems,2002,17: 153-171.
  • 5[1]Grzymala-Busse JW, Stefanowski J. Three Discretization Methods for Rule Induction[J]. International Journal of Intelligent Systems, 2001,16(1):29-38 .
  • 6[2]Clarke EI, Barton BA. Entropy and MDL Discretization of Continuous Variables for Bayesian Belief Networks[J]. International Journal of Intelligent Systems, 2000,15(1):61-92.
  • 7[3]Susmaga R. Analyzing Discretizations of Continuous Attributes Given a Monotonic Discrimination Function[J]. Intelligent Data Analysis, 1997,1(3):157-179.
  • 8[6]Wang L, Zhang S, Fan H, et al. The Information Granulation in Discretization[A]. The Second International Conference on Machine Learning and Cybernetics (ICMLC2003)[C], 2003.2620-2623.
  • 9[8]Nguyen, Son H, Skowron A. Quantization of real value attributes[A]. Second Annual Joint Conference on Information Sciences(JCIS'95)[C], 1995.34-37.
  • 10Bay S D. Detecting Group Differences: Mining Contrast Sets.Data Mining and Knowledge Discovery, 2001, 5 : 213-246.

引证文献3

二级引证文献4

模式识别与人工智能
2004年 第1期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部