[1]邵星翰,林明星.基于多元经验模式分解的 SSVEP 目标识别研究[J].计算机技术与发展,2021,31(02):133-137.[doi:10. 3969 / j. issn. 1673-629X. 2021. 02. 025]
　SHAO Xing-han,LIN Ming-xing.Study on Steady State Visual Evoked Potential Target Recognition Based on Multivariate Empirical Mode Decomposition[J].,2021,31(02):133-137.[doi:10. 3969 / j. issn. 1673-629X. 2021. 02. 025]
点击复制

基于多元经验模式分解的 SSVEP 目标识别研究()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
31
期数:
2021年02期
页码:
133-137
栏目:
应用前沿与综合
出版日期:
2021-02-10

文章信息/Info

Title:
Study on Steady State Visual Evoked Potential Target Recognition Based on Multivariate Empirical Mode Decomposition
文章编号:
1673-629X(2021)02-0133-05
作者:
邵星翰; 林明星
山东大学,山东 济南 250061
Author(s):
SHAO Xing-han; LIN Ming-xing
Shandong University,Jinan 250061,China
关键词:
脑-机接口; 稳态视觉诱发电位; 多元经验模式分解; 本征模式函数; 多元同步指数
Keywords:
brain-computer interface;  steady state visual evoked potential;  multiple empirical mode decomposition;  intrinsic mode function;  multiple synchronous index
分类号:
TP31
DOI:
10. 3969 / j. issn. 1673-629X. 2021. 02. 025
摘要:
在脑-机接口(BCI) 系统中,对稳态视觉诱发电位(SSVEP) 的准确识别在生物医学等领域是至关重要的,而各种伪迹影响了识别准确率。 提出一种基于多元经验模式分解的多元同步指数法(MEMD-MSI) ,首先用白噪声辅助的多元经验模式分解( MEMD) 对原信号进行分解,各通道提取出前 6 个本征模式函数(IMF) 分量,提出通过网格搜索法对 IMF 分量进行加权,从而剔除 EEG 信号中的伪迹,保留脑电信号中的有效信息,6 名受试者的信号数据用来筛选加权系数。 接着用多元同步指数法(MSI)对重构信号进行识别。 另外,选取了 9 名受试者的信号数据,对比了 MEMD-MSI,MSI 及多元经验模态分解典型相关分析(MEMD-CCA)3 种算法在不同时窗的准确性。 结果表明, MEMD-MSI 在三种算法中有着最高的准确率,且在时窗大小为 2s 时,其准确率达到了 95.24% 。 证明该算法有效地剔除了伪迹, 具有高准确率。
Abstract:
In the brain-computer interface (BCI) system,the accurate recognition of steady-state visual evoked potential (SSVEP) is significant in biomedical and other fields,and various artifacts affect the recognition accuracy. We propose a multiple synchronization index based on multiple empirical mode decomposition (MEMD-MSI) . Firstly,the original signal is decomposed by white noise assisted multiple MEMD. The first six intrinsic mode functions (IMF) components are extracted from each channel. A grid search method is proposed to weigh the IMF components so as to eliminate the artifacts in the EEG signal and retain the effective information in the EEG signal. The signal data of the six subjects are used to choose the weighting coefficient. Then,MSI is used to identify the recon-structed signal. Besides, the signal data of 9 subjects are selected to compare the accuracy of the MEMD-MSI,MSI and multiple empirical mode decomposition canonical correlation analysis (MEMD-CCA) in different time windows. The results show that the MEMD-MSI has the highest accuracy among the three algorithms, and the accuracy reaches 95.24% when the time window size is 2s. It is proved that the proposed algorithm can effectively eliminate the artifacts with high accuracy.

相似文献/References:

[1]笪铖璐,陈志阳,黄丽亚. 基于CCA的SSVEP性能研究[J].计算机技术与发展,2015,25(05):52.
　DA Cheng-lu,CHEN Zhi-yang,HUANG Li-ya. Study on Performance of SSVEP Based on CCA[J].,2015,25(02):52.
[2]林文通[],张学军[][],黄丽亚[][],等. 基于ERD和累积能量的脑电特征提取方法[J].计算机技术与发展,2017,27(06):86.
　LIN Wen-tong[],ZHANG Xue-jun[][],HUANG Li-ya[][],et al. EEG Feature Extraction Method Based on ERD and Accumulated Power[J].,2017,27(02):86.
[3]赵丽,薛仲林,王宣方. 基于SSVEP的高传输速率脑机拨号系统[J].计算机技术与发展,2017,27(10):185.
　ZHAO Li,XUE Zhong-lin,WANG Xuan-fang. A High ITR BCI Dial System Based on SSVEP[J].,2017,27(02):185.
[4]张学军,刘定宇,霍 延.EMD 融合 WPT 和 CSP 的脑电特征提取方法[J].计算机技术与发展,2020,30(11):136.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 025]
　ZHANG Xue-jun,LIU Ding-yu,HUO Yan.EEG Feature Extraction of EMD Fusing WPT and CSP[J].,2020,30(02):136.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 025]

更新日期/Last Update: 2020-02-10