智能系统学报2017，Vol.12Issue(6)：848-856,9.DOI:10.11992/tis.201706046
中医临床不均衡数据疾病分类方法研究
Research on classification of diseases of clinical imbalanced data in tradi-tional Chinese medicine
摘要
Abstract
An algorithm based on under-sampling unbalanced data classification is a stochastic data optimization al-gorithm. However, in traditional Chinese medicine (TCM), it is difficult to best reflect the distribution of original clinic-al data to solve the problem of feature redundancy in data. Therefore, in this paper, the PRFS-FPUSAB algorithm is pro-posed. In the algorithm, an improved sampling method is proposed based on under-sampling. The original data distribu-tion is reflected as much as possible; then, the classification is improved by combining integrated learning, prediction risk, and feature selection. The experimental results on meridian resistance data collected from TCM show that the al-gorithm improves the area under the curve, and the selected characteristics are also in accordance with TCM theory.关键词
中医临床/不均衡数据分类/原始数据分布/特征选择Key words
Chinese medicine clinical/imbalance data classification/initial data distribution/feature selection分类
信息技术与安全科学引用本文复制引用
潘主强,张林,张磊,李国正,颜仕星..中医临床不均衡数据疾病分类方法研究[J].智能系统学报,2017,12(6):848-856,9.基金项目
国家自然科学基金项目(81503680) （81503680）
中央级公益性科研院所基本科研业务费专项资金项目(ZZ0908032) （ZZ0908032）
全民健康保障信息化工程中医药研究项目(215005). （215005）
