• 首页
  • 期刊简介
  • 编委会
  • 投稿指南
  • 收录情况
  • 杂志订阅
  • 联系我们
引用本文:汪林恩,耿晓中,张 茜,岳梦哲,户唯新.基于小波变换和FastICA 的眼电伪迹去除研究[J].软件工程,2023,26(12):29-32.【点击复制】
【打印本页】   【下载PDF全文】   【查看/发表评论】  【下载PDF阅读器】  
←前一篇|后一篇→ 过刊浏览
分享到: 微信 更多
基于小波变换和FastICA 的眼电伪迹去除研究
汪林恩1, 耿晓中2, 张 茜1, 岳梦哲2, 户唯新2
(1.吉林化工学院信息与控制工程学院, 吉林 吉林 132022;
2.长春工程学院计算机技术与工程学院, 吉林 长春 130012)
3172876826@qq.com; dq_ gxz@ccit.edu.cn; 2037273240@qq.com; 614491115@qq.com; 1051090429@qq.com
摘 要: 为了高效去除脑电信号(Electroencephalogram,EEG)中的眼电伪迹,文章提出一种基于小波变换(Wavelet Transform,WT)和快速独立成分分析(Fast Independent Component Analysis,FastICA)相结合的眼电伪迹去除方法。首先,应用小波变换将信号分解成不同频率的小波分量,采用适合的小波基函数和阈值针对高低频噪声做去噪处理;其次,应用FastICA算法分离出各通道的独立成分,获取纯净的脑电信号;最后,对BCI competition IV公共数据集应用融合算法,并输入支持向量机(Support Vector Machine,SVM)进行分类验证。实验结果表明,相较于单一的小波变换和FastICA算法,采用文章提出的融合算法处理后的脑电信号的SVM 分类识别率分别提升了18.9%和15.8%,证明该融合算法对去除脑电信号中的眼电伪迹有较好的效果。
关键词: 脑电信号;眼电伪迹;小波变换;FastICA
中图分类号: TP311.5    文献标识码: A
Research on Removing EOG Artifacts Based on Wavelet Transform and FastICA
WANG Linen1, GENG Xiaozhong2, ZHANG Xi1, YUE Mengzhe2, HU Weixin2
(1.School of In f ormation and Control Engineering, Jilin Institute of Chemical Technology, Jilin 132022, China;
2.School of Computer Technology and Engineering, Changchun Institute of Technology, Changchun 130012, China)
3172876826@qq.com; dq_ gxz@ccit.edu.cn; 2037273240@qq.com; 614491115@qq.com; 1051090429@qq.com
Abstract: In order to efficiently remove EOG ( Electrooculogram) artifacts in EEG ( Electroencephalogram) signals, this paper proposes a method for removing EOG artifacts based on the combination of Wavelet Transform (WT) and Fast Independent Component Analysis (FastICA). Firstly, WT is applied to decompose signals into wavelet components of different frequencies, and suitable wavelet basis functions and thresholds are used to denoise high and low frequency noises. Secondly, the independent components of each channel are separated by the FastICA algorithm, and pure EEG signals are obtained. Finally, fusion algorithm is applied in BCI competition IV public dataset and Support Vector Machine (SVM) is input into it for classification verification. The experimental results show that, compared with the single wavelet transform and FastICA algorithms, the SVM classification recognition rate of EEG signals processed with the proposed fusion algorithm is improved by 18.9% and 15.8% , respectively, which proves that the proposed fusion algorithm has a better effect on removing EOG artifacts in EEG signals.
Keywords: EEG signal; EOG artifact; Wavelet Transform; FastICA


版权所有:软件工程杂志社
地址:辽宁省沈阳市浑南区新秀街2号 邮政编码:110179
电话:0411-84767887 传真:0411-84835089 Email:semagazine@neusoft.edu.cn
备案号:辽ICP备17007376号-1
技术支持:北京勤云科技发展有限公司

用微信扫一扫

用微信扫一扫