计算机与数字工程2025，Vol.53Issue(4)：926-929,947,5.DOI:10.3969/j.issn.1672-9722.2025.04.002
基于改进统计学独立性的连续属性值划分方法
Continuous Attributes Partition Approach Based on Improved Statistical Independence
摘要
Abstract
A new improved continuous attributes partition approach based on the statistical independence called APA-SI is proposed and described in this paper.APA-SI considers the effect of variance in the two merged intervals.It not only considers the effect of variance on degrees of freedom,but also takes the effect of variance on data distribution into consideration.A series of ex-periments to evaluate the utility of APA-SI method on the credit risk dataset are done.The data mining techniques,such as C4.5 de-cision tree,Naive Bayes and SVM classifiers,to classify and predict the quantified data are applied.The simulation results show that the approach significantly improves the mean accuracy of classification than continuous approval data and other known quantiza-tion methods such as EFD,MDLP,Extended Chi2.关键词
连续属性值/划分方法/分类算法/数据挖掘/机器学习Key words
continuous attributes/partition approach/classification methods/data mining/machine learning分类
计算机与自动化引用本文复制引用
毛明扬..基于改进统计学独立性的连续属性值划分方法[J].计算机与数字工程,2025,53(4):926-929,947,5.基金项目
国家自然科学基金项目(编号:61403219) （编号:61403219）
广州华商学院校级导师制科研项目(编号:2022HSDS07) （编号:2022HSDS07）
广东省普通高校青年创新人才项目"云上-云下互访问服务链安全防护方法研究"(编号:2023KQNCX120)资助. （编号:2023KQNCX120）
