摘要
为提高医疗数据分类的准确率,将模糊理论引入决策树中构建医疗数据分类模型,并采用粒子群优化算法对模糊决策树模型参数进行优化。结果表明,所提改进方法在关联规则数量、测试准确率、训练准确率三方面表现良好,其中在糖尿病和乳腺癌医疗数据集上分类准确率分别达83.42%和98.14%;相较于FDT模型和CART模型,所提方法的准确率高6.32%和13.39%。通过以上研究得出,改进模糊决策树在医疗数据分类方面有显著优势,可用于医疗大数据分析应用。
In order to improve the accuracy of medical data classification,fuzzy theory is introduced into decision tree to construct medical data classification model,and particle swarm optimization algorithm is used to optimize the parameters of fuzzy decision tree model.The results show that the improved method performs well in three aspects:the number of association rules,the accuracy of testing and the accuracy of training.Among them,the accuracy rate of classification is 83.42%and 98.14%respectively in the diabetes and breast cancer medical datasets.Compared with FDT model and cart model,the accuracy of the proposed method is 6.32%and 13.39%higher.Through the above research,it is concluded that the improved fuzzy decision tree has significant advantages in medical data classification and can be used for medical big data analysis and application.
作者
林军
郭志旭
李函
谢志翔
Lin Jun;Guo Zhixu;Li Han;Xie Zhixiang(Department of Information,the 900th Hospital of Joint Logistics Support Force,Fujian Fuzhou 350025,China)
出处
《现代科学仪器》
2022年第3期173-178,共6页
Modern Scientific Instruments
关键词
ID3算法
医疗大数据
粒子群优化算法
数据分析
ID3 algorithm
Medical big data
Particle swarm optimization algorithm
Data analysis
