基于多时窗共空间模式的HMM运动想象脑电识别  

Motor Imagination EEG Recognition Based on HMM of Multi-Time Window Common Spatial Pattern

作　　者：蔡霄仙 陈顺芝 王江辉 丁洋 费克玲 CAI Xiaoxian;CHEN Shunzhi;WANG Jianghui;DING Yang;FEI Keling(School of Mechanical Engineering and Rail Transit,Changzhou University,Changzhou 213164,China)

机构地区：[1]常州大学机械与轨道交通学院,江苏常州213164

出　　处：《计算机测量与控制》2023年第12期277-283,共7页Computer Measurement &Control

基　　金：常州大学教育教学研究课题(GJY2021070);2022年江苏省研究生实践创新计划项目(YPC22020099)。

摘　　要：运动想象脑电具有识别效果不佳及复杂时序信号建模困难的问题,因此提出一种基于多时窗共空间模式的隐马尔可夫模型运动想象脑电识别方法;首先将运动想象脑电划分为多个短时窗信号,然后使用共空间模式提取特征序列,以滤除脑电通道间的冗余信息,最后采用前向-后相算法与Viterbi算法求解隐马尔可夫模型并完成分类识别;将该方法在公开运动想象脑电数据集上进行实验,得到77.17%的分类正确率,相较隐马尔可夫模型算法提升了5.74%,验证了所提方法的有效性。Aiming at the poor performance of motor imagery electroencephalogram(EEG)recognition and difficulty in modeling complex signals,a motor imagery EEG recognition method based on a hidden Markov model(HMM)of multi-time window common spatial pattern is proposed.Firstly,the motor imagery EEG is divided into different short time window signals,and then the common spatial pattern is used to extract the feature sequences,which can filter out the redundant information between EEG channels.Final-ly,the forward-backward algorithm and Viterbi algorithm are used to solve the hidden Markov model and complete the classification recognition.The proposed method is validated on a publicly available motor imagery EEG dataset,and the classification accuracy rate of the proposed method is 77.17%,which is 5.74%higher than that of the HHM algorithm,verifying the effectiveness of the pro-posed method.

关 键 词：多时窗 共空间模式 隐马尔可夫模型 运动想象 脑电识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]