摘要
根据分层递阶的原则 ,提出一种将粗糙集理论与 BP神经网络相结合的分类算法。该算法分别用粗糙集理论和 BP神经网络处理决策表中的离散属性和连续属性 ,可以避免对象连续属性离散化中产生不确定的情况。同时 ,粗糙集对于决策表噪声比较敏感 ,BP神经网络可以克服这个缺点。最后 ,对 3个公共数据库的测试验证了该分类算法的有效性。
According to the hierarchical principle, a classification method is presented based on the combination of rough set theory and BP neural network. In a decision table, the discrete and continue attributes are processed with rough sets and BP neural network respectively, which can avoid the uncertainty caused in the discretization of the continuous attributes. In addition, rough sets is high sensitivity to the noise in the decision table, this weakness can be counterbalance by BP neural network. The test to 3 public databases validates the classification method.
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2003年第1期31-35,共5页
Chinese Journal of Scientific Instrument
基金
20 0 0年国防科技预研跨行业基金项目资助 (No.J1 6.6.3)
