Sparse EEG compressive sensing for web-enabled person identification

被引:37
作者
Dai, Yixiang [1 ]
Wang, Xue [1 ]
Li, Xuanping [1 ]
Tan, Yuqi [1 ]
机构
[1] Tsinghua Univ, Dept Precis Instrument, State Key Lab Precis Measurement Technol & Instru, Beijing 100084, Peoples R China
基金
中国国家自然科学基金;
关键词
Person identification; Sparse EEG compressive sensing; Nondirective mental tasks; Wearable consumer-grade EEG headset; Web-enabled applications;
D O I
10.1016/j.measurement.2015.07.008
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Electroencephalogram (EEG) person identification, a relatively new biometric method, aims to distinguish subjects by measuring, extracting and comparing features of EEG signals. This paper introduces sparse EEG compressive sensing to web-enabled EEG person identification and demonstrates the feasibility. Specifically, in order to adjust the person identification system to ubiquitous web-enabled scenarios, a wearable consumer-grade EEG headset with sparsely distributed dry electrodes is used to record EEG signals on the motor cortex and a nondirective short-time mental task is designed to simplify the measuring process. Moreover, the EEG data compression module reduces the volume of data for web transmission dramatically. Then feature vectors are extracted from reconstructed EEG data by analyzing power spectral density (PSD), concentration and meditation index. Lastly, a data segmentation based support vector machine classification method is proposed, which eliminates the classification error caused by unreliable EEG data segments. The final identification accuracy reaches 93.73% and the experimental results also indicate that each of the 16 subjects spends only 60 s and 10 s on training and identification respectively while the transmitted data are cut by 50%. It proves that the person identification based on sparse EEG compressive sensing is viable in consumer-grade and web-enabled applications. (C) 2015 Elsevier Ltd. All rights reserved.
引用
收藏
页码:11 / 20
页数:10
相关论文
共 29 条
[1]   Compressive sensing scalp EEG signals: implementations and practical performance [J].
Abdulghani, Amir M. ;
Casson, Alexander J. ;
Rodriguez-Villegas, Esther .
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, 2012, 50 (11) :1137-1145
[2]  
Abdullah M.K.l., 2010, WORLD ACAD SCI ENG T, V68, P1123
[3]  
Abualsaud K, 2013, INT WIREL COMMUN, P231, DOI 10.1109/IWCMC.2013.6583564
[4]  
Allison BZ, 2010, FRONT COLLECT, P357, DOI 10.1007/978-3-642-02091-9_19
[5]  
Almehmadi A, 2013, INT CONF COMM INF T, P49, DOI 10.1109/ICCITechnology.2013.6579521
[6]  
[Anonymous], P INT C MULT INP ICM
[7]  
Ashby C, 2011, I IEEE EMBS C NEUR E, P442, DOI 10.1109/NER.2011.5910581
[8]   Compressed sensing framework for EEG compression [J].
Aviyente, Selin .
2007 IEEE/SP 14TH WORKSHOP ON STATISTICAL SIGNAL PROCESSING, VOLS 1 AND 2, 2007, :181-184
[9]   A portable wireless biometric multi-channel system [J].
Boquete, Luciano ;
Rodriguez Ascariz, Jose Manuel ;
Cantos, Joaquin ;
Barea, Rafael ;
Miguel, Juan Manuel ;
Ortega, Sergio ;
Peixoto, Nathalia .
MEASUREMENT, 2012, 45 (06) :1587-1598
[10]  
Candès EJ, 2008, IEEE SIGNAL PROC MAG, V25, P21, DOI 10.1109/MSP.2007.914731