基于匹配滤波器和度量学习的脑电信号分类

刘宏马; 王生进

doi:10.16511/j.cnki.qhdxxb.2020.22.024

PDF(1637 KB)

清华大学学报（自然科学版） ›› 2021, Vol. 61 ›› Issue (3) : 248-253. DOI: 10.16511/j.cnki.qhdxxb.2020.22.024

电子工程

基于匹配滤波器和度量学习的脑电信号分类

刘宏马, 王生进

作者信息 +

EEG classification based on a match filter and metric learning

LIU Hongma, WANG Shengjin

Author information +

文章历史 +

摘要

脑电信号识别和脑机接口技术是人机交互领域的热点问题。当前脑电信号分类方法模型复杂，难以实际应用。该文提出基于匹配滤波器的脑电信号分类框架：根据脑电信号特点和假设检验建立生成式模型，并基于Gauss噪声假设推导出一个简单的线性判定算子；利用度量学习方法估计主信号分量和最优协方差矩阵，进一步增强分类器的鉴别力。实验结果表明：所推导出的线性判定算子分类精度和计算复杂度都优于其他算法，能够满足实际应用需求。

Abstract

Brain signal analyses and brain-computer interfaces are key topics in human-computer interaction research. Current electroencephalography (EEG) signal classification methods are complicated and difficult to apply in practice. This paper presents a match filter based classification framework using a hypothesis testing model and a match filter which is a linear function of the signal due to the Gaussian noise assumption. A metric learning based method is then used to estimate the principle component and the optimal covariance matrix to further enhance the model discrimination. The results show that this method provides better recognition accuracy with less computational complexity than other algorithms which makes it more practical.

导出引用

刘宏马, 王生进. 基于匹配滤波器和度量学习的脑电信号分类[J]. 清华大学学报（自然科学版）. 2021, 61(3): 248-253 https://doi.org/10.16511/j.cnki.qhdxxb.2020.22.024

LIU Hongma, WANG Shengjin. EEG classification based on a match filter and metric learning[J]. Journal of Tsinghua University(Science and Technology). 2021, 61(3): 248-253 https://doi.org/10.16511/j.cnki.qhdxxb.2020.22.024

参考文献

[1] BASHASHATI A, FATOURECHI F, WARD R K, et al. A survey of signal processing algorithms in brain-computer interfaces based on electrical brain signals[J]. Journal of Neural Engineering, 2007, 4(2):R32-R57.
[2] LUCK S J. An introduction to the event-related potential technique[M]. 2nd ed. Cambridge, USA:Bradford Books, 2014.
[3] KAMP S M, MURPHY A R, DONCHIN E. The component structure of event-related potentials in the P300 speller paradigm[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2013, 21(6):897-907.
[4] FARWELL L A, DONCHIN E. Talking off the top of your head:Toward a mental prosthesis utilizing event-related brain potentials[J]. Electroencephalography and Clinical Neurophysiology, 1988, 70(6):510-523.
[5] XU N, GAO X R, HONG B, et al. BCI competition 2003-data set Ⅱb:Enhancing P300 wave detection using ICA-based subspace projections for BCI applications[J]. IEEE Transactions on Biomedical Engineering, 2004, 51(6):1067-1072.
[6] QIAO X Y, LI D Z, DONG Y E. P300 feature extraction based on parametric model and FastICA algorithm[C]//Fifth International Conference on Natural Computation. Tianjin, China, 2009:585-589.
[7] BURKE D P, KELLY S P, DE CHAZAL P, et al. A parametric feature extraction and classification strategy for brain-computer interfacing[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2005, 13(1):12-17.
[8] MVLLER-GERKING J, PFURTSCHELLER G, FLYVBJERG H. Designing optimal spatial filters for single-trial EEG classification in a movement task[J]. Clinical Neurophysiology, 1999, 110(5):787-798.
[9] SHI L C, LI Y, SUN R H, et al. A sparse common spatial pattern algorithm for brain-computer interface[C]//International Conference on Neural Information Processing. Berlin, Germany:Springer, 2011:725-733.
[10] KAPER M, MEINICKE P, GROSSEKATHOEFER U, et al. BCI competition 2003-data set Ⅱb:Support vector machines for the P300 speller paradigm[J]. IEEE Transactions on Biomedical Engineering, 2004, 51(6):1073-1076.
[11] LIANG N Y, BOUGRAIN L. Averaging techniques for single-trial analysis of oddball event-related potentials[C]//Proceeding of Fourth International BCI Workshop and Training Course. Graz, Austria, 2008:44-49.
[12] RAKOTOMAMONJY A, GUIGUE V. BCI competition Ⅲ:Dataset Ⅱ-ensemble of SVMs for BCI P300 speller[J]. IEEE Transactions on Biomedical Engineering, 2008, 55(3):1147-1154.
[13] CECOTTI H, GRASER A. Convolutional neural networks for P300 detection with application to brain-computer interfaces[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(3):433-445.
[14] LIU M F, WU W, GU Z H, et al. Deep learning based on batch normalization for P300 signal detection[J]. Neurocomputing, 2018, 275:288-297.
[15] DITTHAPRON A, BANLUESOMBATKUL N, KETRAT S, et al. Universal joint feature extraction for P300 EEG classification using multi-task autoencoder[J]. IEEE Access, 2019, 7:68415-68428.
[16] SHIN Y, LEE S, AHN M, et al. Performance increase by using an EEG sparse representation based classification method[C]//International Symposium on Noninvasive Functional Source Imaging of the Brain and Heart and the 8th International Conference on Bioelectromagnetism. Banff, Canada, 2011:93-97.
[17] LI Z M, ZHANG Z, QIN J, et al. Discriminative Fisher embedding dictionary learning algorithm for object recognition[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 31(3):786-800.
[18] ZHANG Z, JIANG W M, QIN J, et al. Jointly learning structured analysis discriminative dictionary and analysis multiclass classifier[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 29(8):3798-3814.
[19] BLANKERTZ B, MULLER K R, KRUSIENSKI D J, et al. The BCI competition Ⅲ:Validating alternative approaches to actual BCI problems[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2006, 14(2):153-159.
[20] KAY S M. Fundamentals of statistical signal processing[M]. Englewood Cliffs, USA:Prentice Hall, 1993.