| 用于脑电数据压缩的改进的BP小波神经网络 |
| |
| 引用本文： | 王爱敏,是度芳,郭国际.用于脑电数据压缩的改进的BP小波神经网络[J].华中科技大学学报(自然科学版),2003,31(10):109-110. |
| |
| 作者姓名： | 王爱敏 是度芳 郭国际 |
| |
| 作者单位： | 1. 华中科技大学,物理系
2. 华中科技大学,同济医学院神经科 |
| |
| 摘 要： | 用一种改进的BP小波神经网络对脑电图(EEG)数据信号进行压缩．对小波神经网络采用最速梯度下降法优化网络参数，并对学习率采用自适应学习速率方法自动调节．利用小波神经网络的函数逼近特性，对脑电随机信号进行逼近，最终压缩比可达15以上．实验结果显示，小波神经网络在大量压缩数据的同时，能较好地恢复原有信号。
|
| 关 键 词： | 脑电图 小波神经网络 数据压缩 |
| 文章编号： | 1671-4512(2003)10-0109-02 |
| 修稿时间： | 2002年10月26 |
EEG data compression based on BP wavelet neural network |
| |
| Wang Aimin Shi Dufang Guo Guoji Wang Aimin Master, Dept. of Physics,Huazhong Univ. of Sci. & Tech.,Wuhan ,China..EEG data compression based on BP wavelet neural network[J].JOURNAL OF HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY.NATURE SCIENCE,2003,31(10):109-110. |
| |
| Authors: | Wang Aimin Shi Dufang Guo Guoji Wang Aimin Master Dept of Physics Huazhong Univ of Sci & Tech Wuhan China |
| |
| Institution: | Wang Aimin Shi Dufang Guo Guoji Wang Aimin Master, Dept. of Physics,Huazhong Univ. of Sci. & Tech.,Wuhan 430074,China. |
| |
| Abstract: | A novel method of EEG signals compression based on BP wavelet neural network (WNN) was presented. In WNN the most fast grads descent methodology was adopted to adjust the network parameters and the learning rate by self adapting learning rate method. The function approaching peculiarity of WNN was used to approach the EGG signal. The compression rate is about 15. The experimental results show that the signal can be compressed greatly by the WNN and the original signal can be recovered well. |
| |
| Keywords: | electroencephalograph wavelet neural network data compression |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
