| 一种基于超盒表示的规则提取方法 |
| |
| 引用本文： | 陈曦,靳东明,李志坚. 一种基于超盒表示的规则提取方法[J]. 电子学报, 2002, 30(9): 1379-1383 |
| |
| 作者姓名： | 陈曦 靳东明 李志坚 |
| |
| 作者单位： | 清华大学微电子学研究所,北京 100084 |
| |
| 基金项目： | 高等学校博士学科点专项科研基金资助课题（No.98000338） |
| |
| 摘 要： | 提出一种从训练样本提取基于超盒表示的模糊规则的方法,用于模式分类.这种方法把模式空间划分成模糊超盒,作为模糊规则的前件,规则的后件是相应的类别名称,同时给出每一条模糊规则的置信度.模糊分类规则从训练样本通过学习算法提取.规则提取方法可以分为,对于单个训练模式进行规则前件和后件的局部在线学习,和对于全部训练模式进行循环学习.实验显示规则提取的过程,说明通过这种方法能够获得有效的模式分类规则.
|
| 关 键 词： | 模式分类 模糊规则 规则提取 超盒 |
| 文章编号： | 0372-2112(2002)09-1379-05 |
A Method for Rule Extraction Based on Hyper-Box Representation |
| |
| CHEN Xi,JIN Dong-ming,LI Zhi-jian. A Method for Rule Extraction Based on Hyper-Box Representation[J]. Acta Electronica Sinica, 2002, 30(9): 1379-1383 |
| |
| Authors: | CHEN Xi JIN Dong-ming LI Zhi-jian |
| |
| Affiliation: | Institute of Microelectronics Tsinghua University,Beijing 100084,China |
| |
| Abstract: | In this paper,we discuss a new method for rule extraction based on hyper-box representation.The method is deducted from the MRCC model,used for pattern classification.The method partitions the pattern space with multi-dimensional fuzzy hyper-boxes , and assigns a class label with certainty degree for each variable fuzzy region. These rules are extracted from numerical data through a recursive learning procedure. Experiment shows the efficiency of rule extraction procedure. |
| |
| Keywords: | pattern classification fuzzy rule-based classifier rule generation hyper-box |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《电子学报》浏览原始摘要信息 |
|
点击此处可从《电子学报》下载全文 |
