融合共空间模式与脑网络特征的EEG抑郁识别  

EEG Depression Recognition Based on Feature Fusion of Common Spatial Pattern and Brain Connectivity

作　　者：王怡忻 朱湘茹[2] 杨利军 WANG Yixin;ZHU Xiangru;YANG Lijun(School of Mathematics and Statistics,Henan University,Kaifeng,Henan 475004,China;Institute of Cognition,Brain and Health,Henan University,Kaifeng,Henan 475004,China;Henan Engineering Research Center for Artificial Intelligence Theory and Algorithms,Kaifeng,Henan 475004,China)

机构地区：[1]河南大学数学与统计学院,河南开封475004 [2]河南大学认知、脑与健康研究所,河南开封475004 [3]河南省人工智能理论及算法工程研究中心,河南开封475004

出　　处：《计算机工程与应用》2022年第22期150-158,共9页Computer Engineering and Applications

基　　金：国家自然科学基金(11701144,11971149);河南省重点研发与推广专项(科技攻关)项目(212102310305,192102210255);河南大学一流学科交叉学科建设计划(2019YLXKJC03)。

摘　　要：提出共空间模式算法和脑网络拓扑属性融合的脑电信号(electroencephalography,EEG)特征,结合深度学习模型时序卷积网络(temporal convolution network,TCN)对抑郁组和对照组进行分类。根据相位锁值构建电极通道间相位同步性功能网络,分析不同频段下两种类别的功能连接模式。采用多特征融合方法将共空间模式特征和脑网络拓扑特征结合起来,最后结合Fisher score特征选择方法和分类器依赖结构,得到低维高效的特征子集并应用TCN进行分类。在抑郁数据集上的实验结果验证了所提策略的有效性。This paper extracts the features of electroencephalography(EEG)signals based on common spatial pattern and brain connectivity.The depression group and the control group are recognized by using a deep learning model temporal convolution network(TCN)based on these EEG features.The phase synchronization functional network between chan-nels is constructed according to the phase locking values,and the functional connection modes of two classes under differ-ent frequency bands are also analyzed.To contain more comprehensive information,the features between common spatial pattern and brain connectivity are combined.Finally,the Fisher score and classifier dependent structure are used for fea-ture selection.As a result,these low-dimensional and efficient features are fed into a TCN classifier to detect depression.Experimental results on a depression dataset validate the effectiveness of the proposed strategy.

关 键 词：抑郁识别 脑电信号(EEG) 共空间模式 时序卷积网络(TCN) 特征选择 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]