Application of Partial Least Squares Regression Model in EEG Feature Selection

doi:10.3778/j.issn.1002-8331.2102-0216

Abstract

Abstract: When the principal component analysis（PCA） algorithm reduces the dimensionality of the EEG signal features extracted from the common spatial pattern（CSP）, it only considers the representation ability of the principal component to the input variables, and ignores the interpretation of the output variables. To overcome this shortcoming, this paper proposes a dimensionality reduction method of partial least squares regression（PLS）. Firstly, CSP extracts the feature of signal dealt with data augmentation, and then PLS performs dimensionality reduction on the extracted features. In particular, the paper takes the features that includes a higher level interpretation for the dependent variable in principal component as feature vectors. Finally, PSO-SVM is used to classify. The proposed algorithm is applied on the data set IIIa of the 2005 BCI competition, and the average classification accuracy rate of the three subjects’ imagination movement is 91.71%. The classification result has reached the highest average classification accuracy rate in comparison with algorithms such as CSP-LDS, WL-CSP and CSP, which verifies the effectiveness of the algorithm.

Key words: electroencephalogram（EEG）, common spatial pattern（CSP）, partial least squares regression（PLS）, data augmentation

摘要： 为了克服主成分分析（PCA）对共空间模式（CSP）提取脑电信号特征进行降维时，仅考虑主成分对输入变量的表征能力，而忽略了对输出变量进行解释的这一个缺点，提出偏最小二乘回归（PLS）进行降维，通过CSP对数据增强后的信号进行特征提取，采用PLS进行降维，将提取的主成分信息包含对因变量解释程度高的特征作为特征向量，使用PSO-SVM进行分类，用2005 BCI竞赛的数据集IIIa进行分类测试，结果得到3位被试的想象运动平均分类正确率91.71%，通过与CSP-LDS、WL-CSP和CSP等算法的比较，3位被试的平均分类正确率最高，验证了该算法的有效性。

关键词: 脑电信号, 共空间模式（CSP）, 偏最小二乘回归（PLS）, 数据增强

LIU Yanjun , WANG Li. Application of Partial Least Squares Regression Model in EEG Feature Selection[J]. Computer Engineering and Applications, 2022, 58(19): 218-223.

刘彦俊, 王力. 偏最小二乘回归模型在EEG特征选择的应用[J]. 计算机工程与应用, 2022, 58(19): 218-223.

References

[1] 张洺华.脑机接口技术对脑卒中偏瘫患者上肢及手功能的影响[D].石家庄：河北师范大学，2020.
ZHANG M H.The effect of brain-computer interface technology on upper limb and hand function of stroke patients with hemiplegia[D].Shijiazhuang：Hebei Normal University，2020.
[2] ZHANG Y，LIU B，JI X，et al.Classification of EEG signals based on autoregressive model and wavelet packet decomposition[J].Neural Processing Letters，2017，45（2）：1-14.
[3] MISHUHINA V，JIANG X.Feature weighting and regularization of common spatial patterns in EEG-based motor imagery BCI[J].IEEE Signal Processing Letters，2018，25（6）：1.
[4] KEVRIC J，SUBASI A.Comparison of signal decomposition methods in classification of EEG signals for motor-imagery BCI system[J].Biomedical Signal Processing & Control，2017，31：398-406.
[5] KOLES Z J.The quantitative extraction and topographic mapping of the abnormal components in the clinical EEG[J].Electroencephalography & Clinical Neurophysiology，1991，79（6）：440.
[6] MüLLER-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.
[7] JOLLIFFE I T.Principal component analysis[J].Journal of Marketing Research，2002，87（4）：513.
[8] FAWZI A，SAMULOWITZ H，TURAGA D，et al.Adaptive data augmentation for image classification[C]//Proceedings of IEEE International Conference on Image Processing，2016.
[9] 刘冲，赵海滨，李春胜，等.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.
LIU C，ZHAO H B，LI C S，et al.CSP/SVM-based EEG classification of imagiued hand movements[J].Journal of Northeastern University（Natural Science），2010，31（8）：1098-1101.
[10] SHI Y.A modified particle swarm optimizer[C]//Proceedings of IEEE ICEC Conference，1998.
[11] WU J，SHI L C，LU B L.Removing unrelated features based on linear dynamical system for motor-imagery-based brain-computer interface[C]//Proceedings of the 18th International Conference on Neural Information Processing，2011.
[12] LOTTE F，GUAN C.Regularizing common spatial patterns to improve BCI designs：Unified theory and new algorithms[J].IEEE Transactions on Biomedical Engineering，2011，58（2）：355-362.
[13] WANG H，LI X.Regularized filters for L1-norm-based common spatial patterns[J].IEEE Transactions on Neural Systems & Rehabilitation Engineering，2016，24（2）：201-211.

[1]	CHEN Yidong, LU Zhonghua. Forecasting CPI Based on Convolutional Neural Network and Long Short-Term Memory Network [J]. Computer Engineering and Applications, 2022, 58(9): 256-262.
[2]	SUN Xiaodong, YANG Dongqiang. Review of Application of Data Augmentation Strategy in English Grammar Error Correction [J]. Computer Engineering and Applications, 2022, 58(7): 43-54.
[3]	WANG Xinpeng, WANG Xiaoqiang, LIN Hao, LI Leixiao, YANG Yanyan, MENG Chuang, GAO Jing. Review on Improvement of Typical Object Detection Algorithms in Deep Learning [J]. Computer Engineering and Applications, 2022, 58(6): 42-57.
[4]	DONG Na, ZHANG Wenqi, WU Zhiqiang. Research on Fuzzy Fusion Control Method for Brain-Controlled Vehicles [J]. Computer Engineering and Applications, 2022, 58(17): 298-305.
[5]	ZHU Xingdong, WANG Ding, FAN Jiali, WANG Zheng, HUANG Kui. Multitarget Detection Based on Enhanced YOLOv3 in Complex Scenarios [J]. Computer Engineering and Applications, 2022, 58(13): 177-184.
[6]	ZHANG Hanyu, WU Zhihao, XU Yong, CHEN Bin. Face Forensics Detection Method Based on Enhanced Convolutional Neural Networks [J]. Computer Engineering and Applications, 2021, 57(8): 220-224.
[7]	ZHU Juntao, YAO Guangle, ZHANG Gexiang, LI Jun, YANG Qiang, WANG Sheng, YE Shaoze. Survey of Few Shot Learning of Deep Neural Network [J]. Computer Engineering and Applications, 2021, 57(7): 22-33.
[8]	LIN Ronglai, TANG Bingying, CHEN Ming. Data Augmentation Algorithm for Bearings Faults Diagnosis [J]. Computer Engineering and Applications, 2021, 57(7): 269-278.
[9]	CAI Dongli, ZHONG Qinghua, ZHU Yongsheng, LIAO Jinxiang, HAN Maizhi. EEG Emotion Recognition Using Convolutional Neural Network with 3D Input [J]. Computer Engineering and Applications, 2021, 57(5): 161-167.
[10]	LUO Qu, FENG Jingwen, LAI Hongyu, LI Tao, DENG Wei, LIU Kai, ZHANG Junpeng. Classification of Rest State EEG in Patients with Schizophrenia or Depression [J]. Computer Engineering and Applications, 2021, 57(13): 138-146.
[11]	SUN Xiao, DING Xiaolong. Data Augmentation Method Based on Generative Adversarial Networks for Facial Expression Recognition Sets [J]. Computer Engineering and Applications, 2020, 56(4): 115-121.
[12]	SHEN Xiaotong, BI Hui, WANG Suhong, LI Wenjie, ZOU Ling. Study on Selection Algorithm of Channels and Classification of EEG in Patients with Depression [J]. Computer Engineering and Applications, 2020, 56(22): 154-159.
[13]	CHEN Jingxia, HAO Wei, ZHANG Pengwei, XIE Jia. RSVP & SSVEP Hybrid EEG Stimulation and Multi-class Event Detection [J]. Computer Engineering and Applications, 2020, 56(15): 132-139.
[14]	WANG Zhong, ZHANG Xueliang, LIU Yaqun, ZHOU Junyu, SHAN Dongsheng. Research on Face Gesture Recognition Based on EEG Sensor [J]. Computer Engineering and Applications, 2020, 56(12): 182-186.
[15]	SU Yusheng, WANG Yafei, LI Xuehua. Depth Estimation of Light Field Based on Improved Densely Connected Convolutional Neural Network [J]. Computer Engineering and Applications, 2020, 56(11): 142-148.