欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
多变量经验模式分解（MEMD）方法不需要根据先验知识选取基函数,能同时对多通道数据进行自适应分解,适合于分析具有高度相关性和非平稳性的脑电信号。为了判别包含有用信息的内蕴模式函数（IMFs）,提出一种基于噪声辅助多变量经验模式分解（NA-MEMD）和互信息的方法,并用于脑电特征提取。首先使用NA-MEMD算法对多通道信号进行分解得到多尺度IMF分量,然后采用互信息法分别计算各尺度上信号与其IMF分量、噪声与其IMF分量、信号IMF分量与噪声IMF分量之间的相关性,接着根据敏感因子筛选包含有用信息的IMF分量,将其叠加得到对应的重构信号,最后采用共同空间模式（CSP）法对重构信号进行特征提取,再用支持向量机（SVM）实现分类。使用仿真数据和实际数据集BCI Competition IV Data Set 1进行测试,与现有的其他方法比较,验证了所提方法的有效性。
英文摘要：
Multivariate empirical mode decomposition is suitable to analyze electroencephalography（EEG）signals of non-stationary characteristics and high correlation between different channels,due to the fact that it can adaptive？ly decompose multi-channel data and has no need to select basis function using prior knowledge. To identify the in？trinsic mode functions（IMFs）containing available information,a novel identification method is proposed based on noise-assisted multivariate empirical mode decomposition（NA-MEMD）and mutual information,and then used for feature extraction of EEG signals. Firstly,multi-channel EEG signals are decomposed by the NA-MEMD algorithm to obtain the IMFs at each scale. Secondly,mutual information is used to calculate the correlation between cross-channel EEG signals and their IMFs,noise signals and their IMFs,EEG signals’and noise signals’IMFs,respec？tively,and then the information-bearing IMFs are recognized according to sensitive factors and used to obtain corre？sponding reconstructed signals by adding them together. Finally,the common spatial pattern（CSP）approach is em？ployed to extract features of the reconstructed signals and support vector machine（SVM）is then applied for classifi？cation. The efficiency of the propose method has been demonstrated by comparisons with other existing algorithms on both synthetic data and real BCI Competition IV Data Set 1.
同期刊论文项目
同项目期刊论文
期刊信息
位置：