摘要
在膨胀土试验中存在大量相互缺损的试验数据,不利于膨胀土分类规则的提取。基于粗糙集信息不完备系统的决策挖掘可以提取膨胀土分类规则。提出了用膨胀土分类决策系统的可信度作为先验概率,用膨胀土试验数据的支持度作为后验概率,引入贝叶斯方法计算条件概率,然后提取条件概率大于某一阈值的规则,最后通过逻辑合取与析取归并膨胀土分类规则。实例及应用分析表明,基于粗糙集不完备系统的膨胀土分类规则提取概念明确,过程简单,易于编制计算机程序,具有明显的理论意义和使用价值。
Generating expansive soil classification is difficult for incomplete test data when different test indexes are collected. Data mining by rough sets for an incomplete system can applied to generate expansive soil classification rule. The conditional probability calculated by Bayes method is presented that the reliability of expansive soil classify- ing decision system is the priori probability and the support degree of expansive soil test data is posterior probability. Those rules should be preserved whose conditional probability is bigger than a given threshold value. The rule of ex- pansive soil classification is generated by logic conjunction and disjunction to the preserved rules. The example and ap- plication analysis indicate that generating expansive soil classification rule based on rough sets for incomplete decision system is easy to program by computer and has high value in practice.
出处
《铁道科学与工程学报》
CAS
CSCD
北大核心
2005年第4期1-5,共5页
Journal of Railway Science and Engineering
基金
教育部博士点基金项目(20030533043)
关键词
粗糙集
膨胀土分类
不完备系统
规则提取
rough set
expansive soil classification
incomplete system
generating rule
