基于EMD和PCA的P300分类算法

提出一种基于经验模态分解(EMD)及主分量分析(PCA)的分类算法，采用支持向量机(SVM)对P300脑电信号字符拼写实验进行分类，通过EMD变换对P300脑电信号分解，从而达到去噪增强特征的效果，使用PCA方法对原始P300信号进行特征提取和集中，并送入SVM中实现分类。实验结果表明，该算法能获得高达96%的分类正确率。

P300 Classification Algorithm Based on EMD and PCA

A classification algorithm based on Empirical Mode Decomposition(EMD) and Principal Component Analysis(PCA) is presented, which uses Support Vector Machine(SVM) to classify the P300 ElectroEncephaloGram(EEG) signals spell experiments. It is decomposed by EMD in order to wipe off noise and strength the useful signals. The signals are extracted and focused in the help of feature scales which contain much P300 information with method of PCA. The signals are send to SVM to be classified. Experimental results show this algorithm can obtain the correct classification rate as high as 96%.