| 一种新的分类规则提取算法 |
| |
| 引用本文： | 赵旭俊,张继福,马洋,蔡江辉.一种新的分类规则提取算法[J].小型微型计算机系统,2012,33(5):1126-1130. |
| |
| 作者姓名： | 赵旭俊 张继福 马洋 蔡江辉 |
| |
| 作者单位： | 太原科技大学计算机科学与技术学院,太原,030024 |
| |
| 基金项目： | 国家自然科学基金，国家自然基金主任基金，山西省青年科技基金 |
| |
| 摘 要： | 约束概念格是概念格的特化结构,构造时具有较低的时空复杂度,能从中快速提取比较丰富的信息和知识.为了提取分类规则,在充分分析约束概念格结点外延与数据集等价划分之间关系的前提下,引入了分类支持度和记录支持度的概念,提出了一种面向约束概念格的分类规则提取算法(Classification Rule Acquisition Algorithm based on Constrained Concept Lattice,CRACCL),并采用UCI数据集作为实验集,验证了本算法能够提取更加实用和准确的分类规则.
|
| 关 键 词： | 约束概念格 分类规则 分类支持度 记录支持度 相容结点 |
Novel Classification Rule Acquisition Algorithm |
| |
| ZHAO Xu-jun
,
ZHANG Ji-fu
,
MA Yang
,
CAI Jiang-hui.Novel Classification Rule Acquisition Algorithm[J].Mini-micro Systems,2012,33(5):1126-1130. |
| |
| Authors: | ZHAO Xu-jun ZHANG Ji-fu MA Yang CAI Jiang-hui |
| |
| Affiliation: | (School of Computer Science and Technology,Taiyuan University of Science & Technology,Taiyuan 030024,China) |
| |
| Abstract: | Constrained concept lattice,with the characteristics of higher constructing efficiency,practicability and pertinence,is a new concept lattice structure.Abundant information and knowledge can be quickly extracted from concept lattice.For classification rule acquisition,a classification rule acquisition algorithm CRACCL based on the constrained concept lattice is presented by using the concept of classification support and record support according to the relationship between node′s extent of constrained concept lattice and equivalence partition of data set.The experiment results validate the higher classification efficiency and correctness of the algorithm by taking the UCI data sets as the formal contexts. |
| |
| Keywords: | constrained concept lattice classification rule classification support record support consistent node |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
