文章摘要
引用本文:王田,李玉榕,陈建国,陈东毅.小波包分解结合异常值检测自动去除眼电中眨眼干扰的方法[J].福州大学学报(自然科学版),2018,46(6):
小波包分解结合异常值检测自动去除眼电中眨眼干扰的方法
A method for removing blink signals in an electroopticgraph by using wavelet packet decomposition and outlier detection
投稿时间:2017-12-13  修订日期:2018-03-28
DOI:
中文关键词: 眼电图  小波包  异常值检测
英文关键词: EOG  wavelet packet  outlier detection
基金项目:国家自然科学基金(61773124);国家重点研发计划“政府间国际科技创新合作”重点专项(2016YFE0122700);福建省科技厅引导性项目(2016Y1002)
作者单位E-mail
王田 福州大学电气工程与自动化学院 798834816@qq.com 
李玉榕 福州大学电气工程与自动化学院 liyurong@fzu.edu.cn 
陈建国 福州大学电气工程与自动化学院  
陈东毅 福州大学电气工程与自动化学院  
摘要点击次数: 17
全文下载次数: 11
中文摘要:
      由于眼电信号可作为人机交互,脑机接口等领域的一种重要的信息源,所以近年来眼电信号被广泛应用,但当眼电信号作为信号源应用时,无意识眨眼会成为干扰信号使系统产生误操作,因此应该去除无意识眨眼。为了减少有用眼电信号的损失,本文提出了一种小波包分解和异常值检测(WPT-OD)去除眨眼信号的新方法。该算法首先利用小波包方法将原始信号进行分解,得到低频分量进行重构,然后应用异常值检测中三种常用的准则,即Chauvenet Criterion标准,Peirce标准和调整框图法确定眨眼信号的区域,并将该区域其置零。实验发现,WPT-OD的平均正确率达到98.9%,其中调整框图法效果最好,其去眨眼信号与原始信号相关性高达95.33%,损失率仅为4.17%。实验表明:WPT-OD算法能够准确的确定无意识眨眼的起点和终点,并且可以保留更多的有用信号且与原始信号的相关性强。
英文摘要:
      As a vital information source of human-computer interaction and brain-computer interface Eye electrical signal is widely used in recent years, and the unintentional blink of eye removal (EOG) has become a new research hotspot. In order to reduce the loss of useful eye signals, this paper presents a new method of wavelet packet transform and outliers detection (WPT-OD) to remove blink signals. Firstly, the wavelet packet method is used to decompose the high frequency components from the original signal, and then the three commonly used criteria of the anomaly detection are applied. The Chauvenet standard (CC), Peirce (PC) standard and ADJBP (Adjusted box plot) determine the position of the blink signal and set it to zero. It was found that the average correct rate of WPT-OD was 98.9%. The correlation between the blink signal and the original was as high as 95.33% and the loss rate was only 4.17%. The experimental results verify the effectiveness of the algorithm.。
查看全文   查看/发表评论  下载PDF阅读器
关闭