EEG signals feature extraction based on EMD and CSP combined WOSF

doi:10.3778/j.issn.1002-8331.1709-0021

Computer Engineering and Applications ›› 2018, Vol. 54 ›› Issue (24): 149-155.DOI: 10.3778/j.issn.1002-8331.1709-0021

Previous Articles Next Articles

EEG signals feature extraction based on EMD and CSP combined WOSF

ZHANG Xuejun1，2, WANG Longqiang1, HUANG Wanlu1, HUANG Liya1，2, CHENG Xiefeng1，2

1.School of Electronic and Optical Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210023, China
2.Nation-Local Joint Project Engineering Lab of ＲF Integration ＆ Micropackage, Nanjing University of Posts and Telecommunications, Nanjing 210023, China

Online:2018-12-15 Published:2018-12-14

EMD和CSP融合最优波长空间滤波脑电特征提取方法

张学军1，2，王龙强1，黄婉露1，黄丽亚1，2，成谢锋1，2

1.南京邮电大学电子与光学工程学院，南京 210023
2.南京邮电大学射频集成与微组装技术国家地方联合工程实验室，南京 210023

Abstract

Abstract: A feature extraction method based on Empirical Mode Decomposition（EMD）, Common Spatial Pattern（CSP） and Wavelength Optimal Spatial Filter（WOSF） is proposed, Firstly, the EMD is used to decompose the EEG signal, and get a set of stationary time series called Intrinsic Mode Functions（IMFs）. Secondly, selecting the appropriate IMFs for signal reconstruction, then the signal can be transformed into optimal signal through WOSF, the optimal signal is mapped to high-dimensional space through CSP, extracting the corresponding feature vector. Finally, the classification is performed using Support Vector Machine（SVM）. After analyzing the result of the 9 subjects, the average accuracy classification rate obtained is over 95%, confirming the feasibility and availability of this method.

Key words: Empirical Mode Decomposition（EMD）, Common Spatial Pattern（CSP）, Wavelength Optimal Spatial Filter（WOSF）, Intrinsic Mode Functions（IMF）

摘要： 基于经验模式分解和共空间模式，结合最优波长空间滤波，提出了三者相结合的特征提取方法。该方法首先利用经验模式分解进行分解，得到固有模态函数，选择合适的固有模态函数进行信号的重构，然后将重构的信号进行最优波长空间滤波变换，得到最优的波长选择信号，再经共空间模式投影映射，提取相应的特征向量，最后利用支持向量机进行分类。运用该方法对9位受试者进行分类结果分析，平均分类准确率在95%以上，实验表明，提出的算法具有较好的分类识别性。

关键词: 经验模式分解, 共空间滤波模式, 最优波长空间滤波, 固有模态函数

ZHANG Xuejun1，2, WANG Longqiang1, HUANG Wanlu1, HUANG Liya1，2, CHENG Xiefeng1，2. EEG signals feature extraction based on EMD and CSP combined WOSF[J]. Computer Engineering and Applications, 2018, 54(24): 149-155.

张学军1，2，王龙强1，黄婉露1，黄丽亚1，2，成谢锋1，2. EMD和CSP融合最优波长空间滤波脑电特征提取方法[J]. 计算机工程与应用, 2018, 54(24): 149-155.

[1]	GUO Rui, FAN Yamin. Algorithm based on extreme learning machine to restrain the end effect of BS-EMD and its application [J]. Computer Engineering and Applications, 2017, 53(7): 256-262.
[2]	WANG Xia1, WANG Dan1, WANG Guangyan2, ZHANG Yan1. Noisy face mask speech enhancement combining compressed sensing with EMD [J]. Computer Engineering and Applications, 2017, 53(18): 137-140.
[3]	ZHANG Xuejun1，2, HUANG Wanlu1, HUANG Liya1，2, CHENG Xiefeng1，2. EEG signals feature extraction combined with empirical mode decomposition and common spatial pattern [J]. Computer Engineering and Applications, 2017, 53(13): 9-15.
[4]	TAN Yangbo, CHENG Jinjun, LIU Shuai. Liquid solenoid valve fault diagnosis based on EMD and neighborhood rough set [J]. Computer Engineering and Applications, 2017, 53(12): 255-260.
[5]	YANG Hang, GUO Xiaojin. Improved method dealing with end issue of EMD [J]. Computer Engineering and Applications, 2016, 52(8): 266-270.
[6]	ZHANG Yanfei, OUYANG Jianfei, YAO Lifeng. Physiological signals extraction based on ICA and EMD [J]. Computer Engineering and Applications, 2016, 52(6): 167-171.
[7]	JING Bo, JIN Weidong, QIN Na. Track detection of wavelet ridge method based on EMD [J]. Computer Engineering and Applications, 2016, 52(4): 266-270.
[8]	LI Ming, LI Tianrui, CHEN Zhi, YANG Yan. Empirical mode decomposition of high-speed rail data based on Spark computing framework [J]. Computer Engineering and Applications, 2016, 52(20): 103-107.
[9]	XUE Juntao, WENG Yuru, ZHANG Jun. Speech endpoint detection based on EMD and cross-entropy [J]. Computer Engineering and Applications, 2016, 52(20): 149-153.
[10]	ZHAO Taotao, YANG Hongwu. Formant extraction algorithm of speech signal by combining EMD and WMCEP [J]. Computer Engineering and Applications, 2015, 51(9): 207-212.
[11]	YUE Tingming, WANG Jinhai, WANG Huiquan. Integration of accelerometer information and EMD filtering algorithm in dynamic ECG acquisition [J]. Computer Engineering and Applications, 2015, 51(20): 192-197.
[12]	BAO Guangqing, CHANG Yong, YANG Guojin. De-noising of rolling bearing fault vibration signal based on empirical mode decomposition threshold [J]. Computer Engineering and Applications, 2015, 51(10): 205-210.
[13]	PAN Zhengrong, DAI Rui, ZHANG Ning. Improved algorithm for pitch detection [J]. Computer Engineering and Applications, 2015, 51(10): 223-226.
[14]	LIU Shen, ZHANG Xiaoji, NIU Yilong, WANG Pingping. Feature extraction and classification experiment of underwater acoustic signals based on energy spectrum of IMF’s [J]. Computer Engineering and Applications, 2014, 50(3): 203-206.
[15]	XIE Wenjun1，2, QI Rong1, XIAO Lei3. Electromechanical actuation system fault feature extraction based on EMD method [J]. Computer Engineering and Applications, 2014, 50(3): 247-249.

EEG signals feature extraction based on EMD and CSP combined WOSF

EMD和CSP融合最优波长空间滤波脑电特征提取方法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics