基于BP_K-C4.5算法的高血脂辅助诊断系统  

High blood lipid assisted diagnosis system based on BP_K-C4.5 algorithm

作　　者：方克邦 张云华[1] FANG Kebang;ZHANG Yunhua(School of Information Science and Technology,Zhejiang Sci-Tech University,Hangzhou 310018,China)

机构地区：[1]浙江理工大学信息学院,杭州310018

出　　处：《智能计算机与应用》2020年第2期83-88,共6页Intelligent Computer and Applications

摘　　要：随着社会发展,人们生活方式的变化,疾病也伴随而来。针对这一情况优质的医疗服务已必不可少了。因此基于BP_K-C4.5算法设计了一款高血脂辅助诊断系统。本系统理论基础是:首先用BP神经网络算法对数据集进行特征选择,然后构建K-C4.5分类预测模型。由于BP神经网络算法具有强自适应、容错性和自组织性等优点,综合改进后的分类预测模型降低了算法的复杂度,增强了算法的稳定性。实验结果表明改进后的算法具有较高的分类精度和效率。基于改进的算法设计的高血脂辅助诊断系统,能很好地辅助医疗进行诊断,给医护人员带来便利。With the development of society and changes in people’s lifestyles,the emergence of disease cannot be ignored.Quality medical services for this situation were essential.Therefore,a hyperlipidemia-assisted diagnosis system is designed based on the BP_K-C4.5 algorithm.The theoretical basis of this system is:first,use the BP neural network algorithm to select features for the data set,and then build a K-C4.5 classification prediction model.Because BP neural network algorithm has the advantages of strong self-adaptation,fault tolerance and self-organization,the comprehensive improved classification prediction model reduces the complexity of the algorithm and enhances the stability of the algorithm.Experimental results show that the improved algorithm has higher classification accuracy and efficiency.The hyperlipidemia assisted diagnosis system designed based on the improved algorithm can well assist in medical diagnosis and bring convenience to medical staff.

关 键 词：BP 特征选择 C4.5 KNN 分类预测 辅助系统 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]