组稀疏贝叶斯逻辑回归的P300信号通道自动选择算法

doi:10.12068/j.issn.1005-3026.2019.09.006

东北大学学报:自然科学版 ›› 2019, Vol. 40 ›› Issue (9): 1245-1251.DOI: 10.12068/j.issn.1005-3026.2019.09.006

组稀疏贝叶斯逻辑回归的P300信号通道自动选择算法

冯宝^1,2，张绍荣²

(1. 中山大学生物医学工程学院，广东广州510640; 2. 桂林航天工业学院自动化系，广西桂林541004)

收稿日期:2018-07-25 修回日期:2018-07-25 出版日期:2019-09-15 发布日期:2019-09-17
通讯作者: 冯宝
作者简介:冯宝(1986-)，男，山西太原人，中山大学博士后研究人员，桂林航天工业学院副教授.
基金资助:
国家自然科学基金地区科学基金资助项目(81960324)；广西壮族自治区自然科学基金资助项目(2016GXNSFBA380160)；广西壮族自治区自动检测技术与仪器重点实验室基金资助项目(YQ19209).

Channel Automatic Selection Algorithm for P300 Signal with Group Sparsity Bayesian Logistic Regression

FENG Bao^1,2， ZHANG Shao-rong²

1. School of Biomedical Engineering， Sun Yat-sen University， Guangzhou 510640， China; 2. Department of Automation， Guilin University of Aerospace Technology， Guilin 541004， China.

Received:2018-07-25 Revised:2018-07-25 Online:2019-09-15 Published:2019-09-17
Contact: FENG Bao
About author:-
Supported by:
-

摘要/Abstract

摘要： 为了提高脑机接口中P300脑电信号的分类准确率和计算速度，提出一种组稀疏贝叶斯逻辑回归的P300脑电信号通道自动选择算法.该算法首先在贝叶斯框架下建立P300脑电信号的解码模型，其次提出先验的组自动相关确定(GARD)方法构建组稀疏约束下的P300脑电通道权重系数，最后通过最大似然估计来求解超参数并选出P300脑电通道最优子集，避免了大量的交叉验证过程.所提方法在BCI竞赛数据和自采集数据上进行了验证分析.实验结果表明，所提的方法能够自动选择P300脑电通道子集，提高了P300特征分类准确率.

Abstract: In order to improve the classification accuracy and calculation speed of P300 electroencephalogram(EEG)signals in the brain-computer interface(BCI)， a channel automatic selection algorithm of P300 EEG signal based on group sparsity Bayesian logistic regression was proposed. First， the algorithm established the decoding model of P300 EEG signals under the Bayesian framework， and then， a priori group automatic relevance determination(GARD)was proposed to determine the weight coefficients of P300 EEG channels under group sparse constraints. Finally， the maximum likelihood estimation was used to solve the hyperparameters and select the optimal subset of P300 EEG channels， avoiding a large number of cross-validation processes. The proposed method was verified on the BCI competition dataset and self-acquisition dataset. The experimental results showed that the proposed method can automatically select P300 related channels and may improve the accuracy of P300 feature classification.

Key words: automatic relevance determination(ARD), group sparsity Bayesian, channel selection, P300, brain-computer interface(BCI)

中图分类号:

TP931.41

冯宝，张绍荣. 组稀疏贝叶斯逻辑回归的P300信号通道自动选择算法[J]. 东北大学学报:自然科学版, 2019, 40(9): 1245-1251.

FENG Bao， ZHANG Shao-rong. Channel Automatic Selection Algorithm for P300 Signal with Group Sparsity Bayesian Logistic Regression[J]. Journal of Northeastern University Natural Science, 2019, 40(9): 1245-1251.

参考文献

[1]Vo K，Pham T，Nguyen D N，et al.Subject-independent ERP-based brain-computer interfaces ［J］.IEEE Transactions on Neural Systems and Rehabilitation Engineering，2018，26(4):719-728.
[2]Polich J.Updating P300:an integrative theory of P3a and P3b ［J］.Clinical Neurophysiology，2007，118(10):2128-2148.
[3]Atum Y V，José B M，Rufiner L，et al.Genetic feature selection for a P300 brain computer interface［J］.IFMBE Proceedings，2015，49(10):603-606.
[4]Corralejo R，Nicolás-Alonso L F，álvarez D，et al.A P300-based brain-computer interface aimed at operating electronic devices at home for severely disabled people［J］.Medical & Biological Engineering & Computing，2014，52(10):861-872.
[5]Simbolon A I，Turnip A，Hutahaean J，et al.An experiment of lie detection based EEG-P300 classified by SVM algorithm［C］// International Conference on Automation，Cognitive Science，Optics，Micro Electro-Mechanical System，and Information Technology.Bandung-Indonesia，2015:68-71.
[6]Momennezhad A，Ebrahimnezhad H，Shamsi M，et al.Brain activity EEG-P300 signal categorization from LPC based estimation of signal using fisher linear discriminant analysis［J］.International Journal of Intelligent Computing in Medical Sciences & Image Processing，2014，6(1):17-26.
[7]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.
[8]Kutsenko D O，Ivonin A A，Shuvaev V T，et al.Spatial structure of EEG in depression patients with co-occurring anxiety disorders［J］.Human Physiology，2015，41(1):34-38.
[9]Tu W，Sun S.Spatial filter selection with LASSO for EEG classification［C］//International Conference on Advanced Data Mining & Applications.Berlin-Heidelberg:Springer， 2010:142-149.
[10]Tomioka R，Müller K R.A regularized discriminative framework for EEG analysis with application to brain-computer interface［J］.Neuroimage，2010，49(1):415-432.
[11]Kondo Y，Hayashi K，Maeda S I.Sparse Bayesian linear regression with latent masking variables［J］.Neurocomputing，2017，258:3-12.
[12]黄璐，王宏.单导联脑电信号分类研究［J］.仪器仪表学报，2014，35(4):814-819.(Huang Lu，Wang Hong.Research on the classification of P300 in single channel EEG［J］.Chinese Journal of Scientific Instrument，2014，35(4):814-819.)
[13]单海军，朱善安.基于Relief-SBS的脑机接口通道选择［J］.生物医学工程学杂志，2016，33(2):350-356.(Shan Hai-jun，Zhu Shan-an.A novel channel selection method for brain-computer interface based on relief-SBS［J］.Journal of Biomedical Engineering，2016，33(2):350-356.).
[14]Castillo I，Schmidt-Hieber J，Aad V D V.Bayesian linear regression with sparse priors［J］.e-Print arXiv，2015，43(5):1986-2018.
[15]Hall M H，Smoller J W，Cook N R，et al.Patterns of deficits in brain function in bipolar disorder and schizophrenia:a cluster analytic study［J］.Psychiatry Research，2012，200(2/3):272-280.
[16]Michael T，Klaus-Robert M，Ad A，et al.Review of the BCI competition IV［J］.Frontiers in Neuroscience，2012，6(55):1-31.
[17]Hwang H J，Hahne J M，Muller K R.Channel selection for simultaneous myoelectric prosthesis control［C］// International Winter Workshop on Brain-Computer Interface.Seoul:IEEE，2014:1-4.
[18]Long J，Li Y，Wang H，et al.Control of a simulated wheelchair based on a hybrid brain computer interface［C］// Annual International Conference of the IEEE Engineering in Medicine and Biology Society.San Diego，2012:6727-6730.

组稀疏贝叶斯逻辑回归的P300信号通道自动选择算法

Channel Automatic Selection Algorithm for P300 Signal with Group Sparsity Bayesian Logistic Regression

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	黄璐，王宏. 基于约束独立分量分析的脑电特征提取[J]. 东北大学学报:自然科学版, 2014, 35(3): 419-423.
[2]	刘冲;赵海滨;李春胜;王宏;. 基于CSP与SVM算法的运动想象脑电信号分类[J]. 东北大学学报(自然科学版), 2010, 31(8): 1098-1101.