[1]龙佳伟,郑 威,刘 燕,等.基于排列熵和 CSP 融合的脑电信号特征提取[J].计算机技术与发展,2022,32(03):157-162.[doi:10. 3969 / j. issn. 1673-629X. 2022. 03. 026]
　LONG Jia-wei,ZHENG Wei,LIU Yan,et al.EEG Signal Feature Extraction Based on PE and CSP Fusion[J].,2022,32(03):157-162.[doi:10. 3969 / j. issn. 1673-629X. 2022. 03. 026]
点击复制

基于排列熵和 CSP 融合的脑电信号特征提取()
分享到：

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

卷:
32
期数:
2022年03期
页码:
157-162
栏目:
应用前沿与综合
出版日期:
2022-03-10

文章信息/Info

Title:
EEG Signal Feature Extraction Based on PE and CSP Fusion
文章编号:
1673-629X(2022)03-0157-06
作者:
龙佳伟; 郑 威; 刘 燕; 王 玫
江苏科技大学 电子信息学院,江苏 镇江 212100
Author(s):
LONG Jia-wei; ZHENG Wei; LIU Yan; WANG Mei
School of Electronics and Information,Jiangsu University of Science and Technology,Zhenjiang 212100,China
关键词:
运动想象; 离散小波变换; 排列熵; 共空间模式; 支持向量机
Keywords:
motor imagery; discrete wavelet transform; permutation entropy; common spatial pattern; support vector machine
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 03. 026
摘要:
脑电信号( EEG) 是一种在医学领域应用非常广泛的生物电信号。 单一的特征提取方法不能够多方面表示脑电信号特征,从而会给不同意识任务下运动想象脑电信号的分类带来一定困难。 对此,提出一种基于离散小波变换( DWT) 、排列熵(PE) 和共空间模式算法( CSP) 的特征提取方法( DWT-PECSP)。 首先,采用 db4 小波基对原始脑电信号进行 3 层小波分解,根据左右手运动想象所处的频段重构出包含?? 节律(8 Hz-12 Hz)和?β 节律(18 Hz-26 Hz) 的频段信号;然后,分别计算出该频段信号的排列熵值和 CSP 方差作为特征量,并将这两组特征量进行组合;最后,将组合后的特征量输入到支持向量机( SVM) 中进行分类识别。 实验结果表明,该算法在 2003 年脑机接口竞赛的标准数据集( DataSet III) 分类上获得了较高的分类准确率(91. 43% ) ,均高于单一提取排列熵特征的准确率(71. 42% ) 和 CSP 方差特征的准确率(85. 71% ) 。通过对比近年来其他文献的特征提取方法,验证了 DWT-PECSP 算法能够更有效地提取运动想象脑电特征。
Abstract:
The electroencephalogram ( EEG) signal is a kind of bioelectric signal widely used in medical field. A single feature extraction method can’ t represent EEG features in many ways,which will bring some difficulties to the classification of motor imagery EEG signal sunder different conscious tasks. For this,a feature extraction method ( DWT-PECSP) based on discrete wavelet transform ( DWT) ,permutation entropy ( PE) and common space pattern ( CSP) is proposed. Firstly,the original EEG signal is decomposed by three-layer wavelet based on db4 wavelet basis,and the frequency band signal containing ??rhythm (8 Hz-12 Hz) and?β rhythm (18 Hz-26 Hz) is reconstructed according to the frequency band of left and right hand motion imagination. Then,the permutation entropy and CSP variance of the frequency band signals are calculated as feature quantities respectively, and these two sets of feature quantities are combined.Finally,the combined features are input into support vector machine ( SVM) for classification and recognition. The experimental results show that the proposed algorithm achieves high classification accuracy (91. 43% ) on the standard DataSet III of the Brain -Computer Interface Competition in 2003,which is higher than that of extracting permutation entropy feature only (71.42% ) and CSP variance feature only (85. 71% ) . By comparing the feature extraction methods of other literatures in recent years,it is verified that DWT-PECSP algorithm can extract EEG features of motor imagination more effectively.

相似文献/References:

[1]吴柯.图像版权保护与认证的双水印算法[J].计算机技术与发展,2009,(09):136.
　WU Ke.Dual Watermarking Algorithm of Image Copyright Protection and Authentication[J].,2009,(03):136.
[2]王璐 吴小培 高湘萍.四类运动想象任务的脑电特征分析及分类[J].计算机技术与发展,2008,(10):23.
　WANG Lu,WU Xiao-pei,GAO Xiang-ping.Analysis and Classification of Four- Class Motor Imagery EEG Data[J].,2008,(03):23.
[3]于帅珍.一种基于重要系数小波树的数字水印算法[J].计算机技术与发展,2008,(11):152.
　YU Shuai-zhen.Digital Watermark Algorithm Based on Significant Wavelet Tree[J].,2008,(03):152.
[4]李东勤 林克正.基于混沌映射的半脆弱图像水印算法[J].计算机技术与发展,2008,(11):156.
　LI Dong-qin,LIN Ke-zheng.Semi - fragile Image Watermarking Algorithm Based on Chaotic Map[J].,2008,(03):156.
[5]于帅珍.基于DWT可定位和抵御剪切的水印方案[J].计算机技术与发展,2008,(12):150.
　YU Shuai-zhen.Watermark Algorithm Based on DWT Against Cropping[J].,2008,(03):150.
[6]陈美丽 黄士坦.JPEG2000中的EBCOT并行处理方法研究[J].计算机技术与发展,2006,(06):104.
　CFIEN Mei-li,HUANG Shi-tan.Parallel Coding for EBCOT in JPEG2000[J].,2006,(03):104.
[7]李坤 褚蕾蕾 朱世东 吴小培.基于mu节律能量的运动意识分类研究[J].计算机技术与发展,2006,(08):157.
　LI Kun,CHU Lei-lei,ZHU Shi-dong,et al.Study of Classification of Motor Imageries Based on Energy of mu Rhythm of EEG[J].,2006,(03):157.
[8]杜肖山 廖述剑.一种DWT与DCT相结合的图像水印算法[J].计算机技术与发展,2011,(01):147.
　DU Xiao-shan,LIAO Shu-jian.A Novel Image Watermarking Algorithm Based on DWT and DCT[J].,2011,(03):147.
[9]邵婷婷,白宗文,周美丽. 基于离散小波变换的信号分解与重构[J].计算机技术与发展,2014,24(11):159.
　SHAO Ting-ting,BAI Zong-wen,ZHOU Mei-li. Decomposition and Reconstruction of Signal Based on DWT[J].,2014,24(03):159.
[10]詹为,段先华,於跃成.基于小波变换的图像压缩编码方法研究[J].计算机技术与发展,2018,28(06):21.[doi:10.3969/ j. issn.1673-629X.2018.06.005]
　ZHAN Wei,DUAN Xian-hua,YU Yue-cheng.Research on Image Compression Coding Method Based on Wavelet Transform[J].,2018,28(03):21.[doi:10.3969/ j. issn.1673-629X.2018.06.005]

更新日期/Last Update: 2022-03-10