| 基于交叉熵和新转移函数的模糊神经网络分类器 |
| |
| 引用本文： | 毛玲,孙即祥,季虎.基于交叉熵和新转移函数的模糊神经网络分类器[J].国防科技大学学报,2004,26(5):52-56. |
| |
| 作者姓名： | 毛玲 孙即祥 季虎 |
| |
| 作者单位： | 国防科技大学电子科学与工程学院,湖南,长沙,410073;国防科技大学电子科学与工程学院,湖南,长沙,410073;国防科技大学电子科学与工程学院,湖南,长沙,410073 |
| |
| 摘 要： | 针对目前普遍采用的误差平方和准则及Sigmoid转移函数在BP算法应用中存在的缺陷和不足,提出了基于交叉熵准则和新的S型转移函数构建的模糊神经网络分类器,并将这种分类器应用于心肌梗死的定位诊断,结果表明其训练效率和识别性能都明显优于传统的模糊神经网络。
|
| 关 键 词： | 交叉熵 转移函数 模糊神经网络分类器 心肌梗死 |
| 文章编号： | 1001-2486(2004)05-0052-05 |
| 收稿时间： | 2004/6/19 0:00:00 |
| 修稿时间： | 2004年6月19日 |
Fuzzy Neural Network Classifier Based on the Cross Entropy Rule and the New Transfer Function |
| |
| MAO Ling,SUN Jixiang and JI Hu.Fuzzy Neural Network Classifier Based on the Cross Entropy Rule and the New Transfer Function[J].Journal of National University of Defense Technology,2004,26(5):52-56. |
| |
| Authors: | MAO Ling SUN Jixiang and JI Hu |
| |
| Institution: | College of Electronic Science and Engineering, National Univ. of Defense Technology, Changsha 410073, China;College of Electronic Science and Engineering, National Univ. of Defense Technology, Changsha 410073, China;College of Electronic Science and Engineering, National Univ. of Defense Technology, Changsha 410073, China |
| |
| Abstract: | In view of the fact that BP algorithm based on the common used error square sum rule and Sigmoid transfer function have some limitation and shortcomings, the cross entropy rule and a new transfer function are adopted for constructing and training process of the fuzzy neural network classifier. It is used to realize the orientation of myocardial infarction, and the results prove that this classifier has the capability of outperforming the traditional fuzzy neural network in training efficiency and recognizing ability obviously. |
| |
| Keywords: | cross entropy transfer function fuzzy neural network classifier myocardial infarction |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《国防科技大学学报》浏览原始摘要信息 |
| 点击此处可从《国防科技大学学报》下载免费的PDF全文 |
|
