摘要
在实际应用中,当利用多种粗糙集构造算法所得到的多个粗糙集的误判率差异小时,误判率小的粗糙集并不总是具有最高预测准确度。利用粗糙集的分类规则构建Logistic模型,将拟合Logistic模型的AIC值作为该粗糙集的AIC值,用于粗糙集的择优。实例分析结果表明,采用新方法能够筛选出预测准确度较高的粗糙集。当多个粗糙集的误判率差异小时,新方法更可能选出预测准确度最高的粗糙集。
In practical application, when there is small difference of misclassifieation error among many rough sets constructed by multiple rough set construction algorithms, the rough set with least misclassification error does not always have the highest prediction accuracy. Using classification rules as the explained variable, establish a Logistic model, the AIC value of the rough set is defined as the AIC value of the fitted model that the AIC criterion is provided to choice rough sets. The case analysis results show that the new algorithm can choice out rough set with high prediction accuracy. When there is small difference of misclassification error among many rough sets, new algorithm has bigger probability to choice out rough set with the highest prediction accuracy than misclassification criterion.
出处
《模糊系统与数学》
北大核心
2018年第1期165-171,共7页
Fuzzy Systems and Mathematics
基金
国家自然科学基金资助项目(11471239)
国家社会科学基金青年项目(17CTJ002)
2016年度重庆市社会科学规划重大委托项目(2016WT03)
全国统计科学研究重点项目(2017LZ25)
全国统计科学研究项目(2017LZ30)
天津财经大学研究生科研资助计划项目(2016TCB03)
天津财经大学学位与研究生教育教学改革研究一般项目(2014YJY14)
