基于小波变换和神经网络的脑电信号分类方法

毛峡; 孟庆宇

基于小波变换和神经网络的脑电信号分类方法

毛峡,
孟庆宇

北京航空航天大学电子信息工程学院, 北京 100083

基金项目: 北京市自然科学基金资助项目(33033013)

详细信息

中图分类号: TP 391
计量
- 文章访问数: 3142
- HTML全文浏览量: 32
- PDF下载量: 17654
- 被引次数: 0
出版历程
- 收稿日期: 2004-11-12
- 网络出版日期: 2005-10-31

Method of EEG signals classification based on wavelet transform and neural networks

School of Electronics and Information Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100083, China

摘要

摘要: 结合小波变换和神经网络对酒精中毒者和正常清醒者的脑电信号进行分类.通过分析脑电数据找出分类特征;采用一维离散小波变换提取含有分类特征的脑电信号频段,并以小波变换分解系数作为信号特征,实现数据序列长度压缩;对应3种刺激方式建立3个相同结构的学习向量量化(LVQ)神经网络,用于对脑电信号的预分类;根据判决规则得到最终分类结果.对真实脑电数据的分类正确率达到89%.
- 脑电 /
- 小波变换 /
- 神经网络
Abstract: Electroencephalography (EEG) signals of alcoholic subjects and control subjects were classified by combination of wavelet transforms and neural networks. Classification features were discovered through the EEG data analysis. The frequency bands of EEG signals including classification features were extracted by 1-D wavelet transforms. The decomposed coefficients of wavelet transforms were remained as signals characters to accomplish the length compression of data sequences. Three learning vector quantization (LVQ) networks with same structure corresponding to three kinds of stimulations were built for the predictive classification of the EEG signals. The final classification results were acquired by judge rules. The classification accuracy of experiment EEG signals reach 89%.
- electroencephalography /
- wavelet transforms /
- neural networks

HTML全文

参考文献(1)

[1] 刘晓欲, 蒋大宗, 黄远桂. 生物信号模式识别的方法及其在脑电中的应用进展[J] 北京生物医学工程, 1996, 15(3):188~193 Liu Xiaoyu, Jiang Dazong, Huang Yuangui. Biological signal pattern recognition method and application in EEG[J] Beijing Biomedical Engineering, 1996, 15(3):188~193 (in Chinese) [2] 林相波, 邱天爽. 基于EEG信号分析处理的癫痫预报及研究进展[J] 国外医学生物医学工程分册, 2004, 21(1):9~12 Lin Xiangbo, Qiu Tianshuang. EEG signal analysis and processing based prediction of epileptic seizures and research progress[J] Biomedical Engineering Foreign Medical Science, 2004, 21(1):9~12 (in Chinese) [3] 季忠, 秦树人, 彭丽玲. 脑电信号的现代分析方法[J] 重庆大学学报, 2002, 25(9):108~111 Ji Zhong, Qin Shuren, Peng Liling. Signal processing of electroencephalogram and it’s application[J] Journal of Chong Qing University, 2002, 25(9):108~111 (in Chinese) [4] 袁全, 刘兴华, 李大琛,等. 噪声和音乐对脑电功率谱的影响[J] 航天医学与医学工程, 2000, 13(6):401~404 Yuan Quan, Liu Xinghua, Li Dachen, et al. Effects of noise and music on EEG power spectrum[J] Space Medicine & Medical Engineering, 2000, 13(6):401~404(in Chinese) [5] 林高翔. 脑电功率谱分析和双波谱分析在麻醉深度监测中的应用[J] 华夏医学, 2001, 14(6):963~965 Lin Gaoxiang. The study of technique of electroencephalogram power spectrum and bispectral electroencephalogram analysis on the depth of anesthesia[J] Acta Medicinae Sinica, 2001, 14(6):963~965 (in Chinese) [6] Watt R C, Chris S, Ansel K, et al. Artificial neural networks facilitate bispectral analysis of electroencephalographic data[J] IEEE International Conference on Neural Networks, 1995, 5:2596~2599 [7] Mukherjee A, Karayiannis N B, Glover J R, et al. Evaluation of cosine radial basis function neural networks in detection of artifacts in neonatal EEG[J] Proceedings of the 25th Annual International Conference of the IEEE, 2003, 3:2954~2957 [8] Kim S B, Lee Y H, Kim J H, et al. Automatic detection of epileptiform activity using wavelet and expert rule base[J] Proceedings of the 20th Annual International Conference of the IEEE, 1998, 4:2078~2081 [9] Lester Ingber. Raw EEG data . http://www.ingber.com, 2004-07-28/2004-08-1 [10] 杨福生. 小波变换的工程分析与应用[M] 北京:科学出版社, 2001. 42~48 Yang Fusheng. Engineering analysis and application of wavelet transforms[M] Beijing:Science Press, 2001.42~48(in Chinese) [11] Martin T H, Howard B D, Mark H B. Neural network design[M] Stamford:Thomson Learning Company, 1996. 295~299

施引文献

资源附件(0)

访问统计