| 基于支持向量机和人工神经网络的心血管疾病中医证候分类识别研究 |
| |
| 引用本文： | 许朝霞,王忆勤,颜建军,郭睿,刘国萍,燕海霞,李福凤,徐琎,郝一鸣,钱鹏.基于支持向量机和人工神经网络的心血管疾病中医证候分类识别研究[J].北京中医药大学学报,2011,34(8). |
| |
| 作者姓名： | 许朝霞 王忆勤 颜建军 郭睿 刘国萍 燕海霞 李福凤 徐琎 郝一鸣 钱鹏 |
| |
| 作者单位： | 上海中医药大学基础医学院 上海201203;华东理工大学机械电子工程中心 |
| |
| 基金项目： | 上海市优秀学科带头人项目(No.09XD0314700); 上海市重点学科经费资助项目(No.S30302); 上海市科委择优委托项目(No.09DZ1907902) |
| |
| 摘 要： | 目的探讨心血管疾病的中医证候分类识别方法,为中医证候的规范化研究提供一定的方法和依据。方法利用统一的中医问诊采集量表,采集临床心血管疾病的病例;然后根据信息的有、无分别赋值为1、0,建立心血管疾病的中医临床信息数据库。基于支持向量机(径向基函数与多项式函数2种算法)和人工神经网络(ACON与OCON 2种结构的网络)对心血管疾病的中医临床信息和证候类别之间的关系进行分析,建立模型,观察其证候预测的准确性。结果经过比较,对于心气虚、心阳虚、心阴虚、痰浊、气滞、血瘀等心血管疾病常见中医证型,OCON网络的识别准确率最高,均在60%以上,其中心气虚和心阳虚证分别高达92.4%、82.9%。结论支持向量机和人工神经网络能为心血管疾病的临床中医证候识别提供一定的客观依据,其中OCON结构网络具有较高的识别准确率。
|
| 关 键 词： | 支持向量机 人工神经网络 心血管疾病 证候识别 |
Recognition of TCM syndrome types of cardiovascular diseases based on support vector machine and artificial neural networks |
| |
| XU Zhao-xia,WANG Yi-qin,YAN Jian-jun,GUO Rui,LIU Guo-ping,YAN Hai-xia,LI Fu-feng,XU Jin,HAO Yi-ming,QIAN Peng.Recognition of TCM syndrome types of cardiovascular diseases based on support vector machine and artificial neural networks[J].Journal of Beijing University of Traditional Chinese Medicine,2011,34(8). |
| |
| Authors: | XU Zhao-xia WANG Yi-qin YAN Jian-jun GUO Rui LIU Guo-ping YAN Hai-xia LI Fu-feng XU Jin HAO Yi-ming QIAN Peng |
| |
| Institution: | XU Zhao-xia1,WANG Yi-qin1,YAN Jian-jun2,GUO Rui1,LIU Guo-ping1,YAN Hai-xia1,LI Fu-feng1,XU Jin1,HAO Yi-ming1,QIAN Peng1(1 School of Preclinical Medicine,Shanghai University of Traditional Chinese Medicine,Shanghai 201203,2 Electromechanical Engineering Center,East China University of Science and Technology) |
| |
| Abstract: | Objective To discuss the recognition method of TCM syndrome types of cardiovascular diseases,and provide some methods and evidences for the standardization of TCM syndrome research.Methods The cases of cardiovascular diseases were selected by using unified scale of TCM inquiry.A database of TCM clinical information was established through assigning yes to 1 and assigning no to 0 according to the information by inquiry.The clinical information and relation among syndrome types were analysed and model was est... |
| |
| Keywords: | support vector machine artificial neural networks cardiovascular diseases recognition of syndrome types |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
