摘要
规则获取的增量式算法是知识发现领域的一个热点问题 .作者根据粗糙集理论 ,提出 -不可分辨关系的概念 ,建立了 -决策表及其 -决策矩阵 ,在此基础上 ,利用决策函数 ,提出一种在决策表中获取规则的增量式算法 .该算法针对决策表中出现的各种新对象 ,在原有规则集的基础上进行规则和规则参数的增量式更新 。
Incremental acquistion of rules is a topic of general interest in the field of knowledge discovery in database. Based on rough set theory, the concept of -indiscernibility relation is put forward to construct -decision table and -decision matrix. Then, using the decision function, an algorithm of incremental acquisition of decision rules is presented. The algorithm is an incremental methodology for updating the existing decision rules and their parameters when various new objects are appended to the decision table, instead of running the whole learning process again.
出处
《南开大学学报（自然科学版）》
CAS
CSCD
北大核心
2003年第2期98-103,共6页
Acta Scientiarum Naturalium Universitatis Nankaiensis
关键词
粗糙集
决策规则
增量式学习
rough sets
decision rules
incremental learning
