特征可分性显式建模的跨数据库脑电解码方法  

Cross database EEG decoding method with explicit modeling of feature separability

作　　者：李易 张本鑫 莫云 路仲伟 李智 Li Yi;Zhang Benxin;Mo Yun;Lu Zhongwei;Li Zhi(School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China;School of Electronic Information and Automation,Guilin University of Aerospace Technology,Guilin 541004,China)

机构地区：[1]桂林电子科技大学电子工程与自动化学院,桂林541004 [2]桂林航天工业学院电子信息与自动化学院,桂林541004

出　　处：《电子测量技术》2024年第7期95-105,共11页Electronic Measurement Technology

基　　金：广西自动检测技术与仪器重点实验室基金(YQ22209);广西高校中青年教师科研基础能力提升项目(2023KY0813);桂林电子科技大学研究生教育创新计划项目(2023YCXS132)资助。

摘　　要：目前,在运动想象解码领域,研究主要集中在被试依赖和被试独立解码两种方法上。然而,这两种解码方式在脑机接口(BCI)系统的实际使用中存在较大局限性。被试依赖和被试独立解码都依赖于同一中心数据集,当解码模型应用于其他中心的数据集时,性能将显著下降,无法满足BCI系统跨中心使用的需求。为提升运动想象脑电跨数据库解码性能,基于领域泛化的方法框架,提出了一种基于Fisher准则正则化的稀疏选择模型。在最小绝对值收缩和选择算子(LASSO)模型的基础上,引入Fisher准则正则项,以在特征选择过程中显式建模特征的可分性。这有助于提高领域泛化的表示学习能力,从而增强分类模型在不同数据集上的泛化性能。采用两个公开的运动想象脑电数据集,并使用滤波器组共空间模式(FBCSP)和多时频共空间模式(MTFCSP)两种特征提取方法,验证了所提方法的有效性,进一步使用自采集的数据也证实了该方法在实际应用中同样有效。与现有的方法相比,所提方法取得了最高平均分类准确率,达到67.26%。实验结果表明,所提方法在运动想象跨数据库解码中具有更好的泛化能力、更高的特征可分性、更好的鲁棒性。所提方法有望促进BCI系统跨中心使用,提高通用性。Currently,in the field of motor imagery decoding,research has focused on two approaches,subject-dependent and subject-independent decoding.However,these two decoding approaches have major limitations in the practical use of brain-computer interface(BCI)systems.Both subject-dependent and subject-independent decoding rely on the same center dataset,and when the decoding model is applied to datasets from other centers,the performance will be significantly degraded,which cannot satisfy the demand for cross-center use of BCI systems.To improve the cross-database decoding performance of motor imagery Electroencephalogram(EEG),a sparse selection model based on Fisher criterion regularization is proposed based on the methodological framework of domain generalization.Based on the least absolute shrinkage and selection operator(LASSO)model,a Fisher criterion regularization term is introduced to explicitly model feature separability during the feature selection process.This helps to improve the representation learning ability for domain generalization,thus enhancing the generalization performance of the classification model on different datasets.The effectiveness of the proposed method is validated using two publicly available motor imagery EEG datasets and two feature extraction methods,filter bank common spatial pattern(FBCSP)and multiple time frequency common spatial pattern(MTFCSP).Further validation through the utilization of self-collected data also confirmed the effectiveness of the proposed method in practical applications.Compared with existing methods,the proposed method achieved the highest average classification accuracy of 67.26%.The experimental results show that the proposed method has better generalization ability,higher feature separability,and better robustness in motion imagery cross-database decoding.The proposed method is expected to facilitate cross-center use of BCI systems and improve generalizability.

关 键 词：运动想象 脑电解码 稀疏正则化 领域泛化 跨数据库 

分 类 号：TN911.7[电子电信—通信与信息系统] TH77[电子电信—信息与通信工程] R318[机械工程—仪器科学与技术]