| 基于GMDH型神经网络的EEG分类研究 |
| |
| 引用本文： | 郝冬梅,阮晓钢. 基于GMDH型神经网络的EEG分类研究[J]. 中国生物医学工程学报, 2005, 24(1): 66-69 |
| |
| 作者姓名： | 郝冬梅 阮晓钢 |
| |
| 作者单位： | 北京工业大学电控学院,北京,100022 |
| |
| 基金项目： | 国家自然科学基金资助项目 (60 3 75 0 17)。 |
| |
| 摘 要： | 为了提高对不同认知状态下脑电信号(EEG)的分类正确率，提出一种GMDH型神经网络及改进的训练算法。此网络结构在演化中生成，分类规则由简单多项式表示，训练算法可防止出现过拟合。此网络用于区分算术运算和休息状态下的脑电信号，正确率达到84．5％，与标准前向型神经网络(FNN)比较，显示了较好的分类效果。
|
| 关 键 词： | GMDH型神经网络 前向型神经网络 脑电信号 多项式 |
| 文章编号： | 0258-8021(2005)01-66-04 |
| 修稿时间： | 2003-09-18 |
Research on EEG Classification With GMDH-type Neural Network |
| |
| HAO Dong-mei,RUAN Xiao-Gang. Research on EEG Classification With GMDH-type Neural Network[J]. Chinese Journal of Biomedical Engineering, 2005, 24(1): 66-69 |
| |
| Authors: | HAO Dong-mei RUAN Xiao-Gang |
| |
| Abstract: | A GMDH|type neural network and its modified training algorithm were presented in this paper to improve the classifying accuracy of EEG with different mental tasks. The network was formed through evolution,the classification rules were described by a concise set of polynomials and the training algorithm was able to prevent over|fitting effectively.Experimental resutts showed the GMDH|type nearal could classify the EEG of math or relaxtasks with accuracy of 84.5%.It was indicated that GMDH|type neural network exhibited higher classitying accuracy compared to the feedforward neural network (FNN). |
| |
| Keywords: | GMDH-type network feedforward neural network(FNN) EEG polynomial |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
