| 神经网络分析方法用于心脏病诊断的研究 |
| |
| 引用本文： | 宁新宝,黄晓林,徐寅林,韩桂明.神经网络分析方法用于心脏病诊断的研究[J].生物医学工程学杂志,2004,21(2):284-287. |
| |
| 作者姓名： | 宁新宝 黄晓林 徐寅林 韩桂明 |
| |
| 作者单位： | 南京大学,电子科学与工程系,近代声学国家重点实验室,生物医学电子工程研究所,南京,210093 |
| |
| 基金项目： | 江苏省自然科学基金资助项目 (BK2 0 0 0 0 14 ) |
| |
| 摘 要： | 神经网络可以很好的拟合任意的非线性函数。我们从 QRS波群的高频三维频谱中提取出一些定量的特征参数 ,用神经网络的方法对这些参数进行有监督的学习训练 ,最终能在由这些特征参数张成的 m维空间中构建出一个 m维的曲面来区分病人和健康人的 QRS波群高频三维频谱 ,从而使得训练后的网络能基于 QRS波群的高频三维频谱自行诊断出病人和健康人
|
| 关 键 词： | 神经网络 BP算法 高频心电图 QRS波群的高频三维频谱 |
Research on the Application of Neural Network to Diagnosis of Cardiopathy |
| |
| Xinbao Ning,Xiaolin Huang,Yinlin Xu,Guiming Han.Research on the Application of Neural Network to Diagnosis of Cardiopathy[J].Journal of Biomedical Engineering,2004,21(2):284-287. |
| |
| Authors: | Xinbao Ning Xiaolin Huang Yinlin Xu Guiming Han |
| |
| Affiliation: | State Key Laboratory of Modern Acoustics, Institute of Biomedical Electronical Engineering, Electronic Science and Engineering Department, Nanjing University, Nanjing 210093, China. xbning@nju.edu.cn |
| |
| Abstract: | Neural networks can fit any nonlinear function. After drawing out several characteristic parameters from the three dimension spectrum for high frequency QRS waves, we input them into the network and trained the network. In this way, we can get a m dimension curved surface in the m dimension space which is constructed by those parameters, and this curved surface divides the space into two parts: the unhealthiness and the health. Now, the network can automatically distinguish between the healthiness and the unhealthiness according to their three dimension spectrum for high frequency QRS waves. |
| |
| Keywords: | Neural networks BP algorithm High frequency ECG(HFECG) Three dimension spectrum for high frequency QRS waves |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
