摘要
提出一种基于Infomax ICA少次自动提取脑电信号P300成分的方法.为了提高ICA分解的有效性,对原始数据中的自发脑电信号和P300成分进行了均衡.混合信号经过ICA分解后,根据IC的固定时间模式的标准差来自动选择P300成分IC,最后重构得到P300成分.实验结果是:利用6试次实验数据经过本文方法处理后能自动得到P300成分,与29试次平均结果(标准信号)相比,它们之间的Pearson相关系数达0.9035,而6试次实验数据平均的结果与标准信号之间的Pearson相关系数为0.5105.结果表明,该方法能有效的获取P300成分,同时增强了P300成分少次提取的客观性.
This paper puts forward a methtxt for automatically extracting the P300 from electroencephalography (EEG) sig nals within several trials based on Infomax independent component analysis (ICA). An algorithm for signaling equilibrium is pro posed to enhance the effectiveness of ICA decomposition. After the mixed signal is decomposed by Infomax ICA,the independent component (IC) of P300 is automatically selected according to the standard deviation of the fixedtemporalpattern of the IC, and applied in P300 reconstruction. Experimental results show that the P300 can be obtained automatically after six trials on the experi mental data,and the result of its Pearson correlation coefficient (PCC) within the average of 29 trials (standard signal) is 0.9035. However,the PCC of the average result of six trials and standard signal is only 0.5105,dcmomwating the practical applicability of Infomax ICA. This algorithrn enhances the objectivity of P300 cxtracfion within several trials.
出处
《电子学报》
EI
CAS
CSCD
北大核心
2012年第6期1257-1262,共6页
Acta Electronica Sinica
基金
国家863高技术研究发展计划(No.2006AA06Z105)
广西教育厅科研项目(No.201012MA084)
关键词
独立分量分析
P300
脑电
固定时间模式
independent component analysis(ICA)
P300
electroencephaiography(EEG)
fixed-temporal-pattern