段锁林,李伟,潘礼正

• 1:常州大学机器人研究所

摘要(Abstract)：

提出一种粒子群算法(PSO)优化共同空间模式(CSP),结合离散小波变换(DWT)的特征提取算法(DWT-PSOCSP)。使用离散小波变换(DWT)系数均值、方差、能量均值作为时频特征,PSO-CSP算法优化频带作为CSP滤波器输入,得到最优频带的空域特征,即选取脑电信号(EEG)的最优频带。采用串行特征融合策略将二者融合为新的特征,输入支持向量机(C-SVM)分类器。使用BCI2005desc_IIIa中四类运动想象数据进行分类仿真研究,分类正确率最高达到91.25%。仿真结果表明该方法提高了分类器泛化能力,验证了该方法的有效性和实用性。

关键词(KeyWords)： 脑电信号;粒子群算法;共同空间模式;离散小波变换;能量均值;支持向量机

Abstract:

Keywords:

基金项目(Foundation): 江苏省科技支撑计划项目(社会发展)(BEK2013671)~~

作者(Author): 段锁林,李伟,潘礼正

DOI: 10.16652/j.issn.1004-373x.2018.23.012

参考文献(References)：

• [1]MINGUILLON J,LOPEZ-GORDO M A,PELAYO F.Trends in EEG-BCI for daily-life:requirements for artifact removal[J].Biomedical signal processing&control,2017,31:407-418.
• [2]杨建平,孔翠香,帅晓勇,等.基于信号处理技术的正念脑电信息提取方法[J].现代电子技术,2017,40(17):70-74.YANG Jianping,KONG Cuixiang,SHUAI Xiaoyong,et al.Extraction of mindfulness EEG information based on signal processing technology[J].Modern electronics technique,2017,40(17):70-74.
• [3]DIEZ P F,LACIAR E,TORRES A,et al.Adaptive bands on EEG signals extracted with empirical mode decomposition[C]//American Congress on Biomedical Engineering.Habana:Springer,2011:1138-1141.
• [4]HUANG N E.A study of the characteristics of white noise using the empirical mode decomposition method[J].Mathematical physical&engineering sciences,2004,460(2046):1597-1611.
• [5]ZHANG Y,ZHOU G,JIN J,et al.Optimizing spatial patterns with sparse filter bands for motor-imagery based brain-computer interface[J].Journal of neuroscience methods,2015,255:85-91.
• [6]BELHADJ S A,BENMOUSSAT N,KRACHAI M D.CSP features extraction and FLDA classification of EEG-based motor imagery for brain-computer interaction[C]//2016 International Conference on Electrical Engineering.Boumerdes:IEEE,2016:1-6.
• [7]杨帮华,陆文宇,何美燕,等.脑机接口中基于WPD和CSP的特征提取[J].仪器仪表学报,2012,33(11):2560-2565.YANG Banghua,LU Wenyu,HE Meiyan,et al.Feature extraction based on WPD and CSP in brain-computer interface[J].Chinese journal of scientific instrument,2012,33(11):2560-2565.
• [8]SUN J,WU X,PALADE V,et al.Random drift particle swarm optimization algorithm:convergence analysis and parameter selection[J].Machine learning,2015,101(1/3):345-376.
• [9]白雁.基于线性递减系数粒子群优化算法的组卷实现[J].现代电子技术,2014,37(24):41-44.BAI Yan.Implementation of test paper based on linear diminishing coefficient particle swarm optimization algorithm[J].Modern electronics technique,2014,37(24):41-44.
• [10]NAM C S,JEON Y,KIM Y J,et al.Movement imagery-related lateralization of event-related(DE)synchronization(ERD/ERS):motor-imagery duration effects[J].Journal of the International Federation of Clinical Neurophysiology,2011,122(3):567.
• [11]梁宏斌,严正俊.基于支持向量机的模式识别方法[J].现代电子技术,2007,30(16):193-194.LIANG Hongbin,YAN Zhengjun.Pattern recognition method based on support vector machines[J].Modern electronics technique,2007,30(16):193-194.
• [12]王璐,吴小培,高湘萍.四类运动想象任务的脑电特征分析及分类[J].计算机技术与发展,2008,18(10):23-26.WANG Lu,WU Xiaopei,GAO Xiangping.Analysis and classification of EEG characteristics of four kinds of sports imagination tasks[J].Computer technology and development,2008,18(10):23-26.
• [13]施锦河,沈继忠,王攀.四类运动想象脑电信号特征提取与分类算法[J].浙江大学学报,2012,46(2):338-344.SHI Jinhe,SHEN Jizhong,WANG Pan.Feature extraction and classification algorithm for EEG signals in four types of sports imaging[J].Journal of Zhejiang University,2012,46(2):338-344.
• [14]庄玮,段锁林,徐亭婷.基于SVM的4类运动想象的脑电信号分类方法[J].常州大学学报,2014,26(1):42-46.ZHUANG Wei,DUAN Suolin,XU Tingting.Classification of EEG signals based on SVM for four types of motion imaging[J].Journal of Changzhou University,2014,26(1):42-46.