基于特征向量法和支持向量机的抑郁症脑电信号分类  

Application of Eigenvector Methods and SVM for EEG Signals Classification

作　　者：楼恩平[1] 张胜[1] 

机构地区：[1]浙江师范大学数理与信息工程学院,浙江金华321004

出　　处：《中国医学物理学杂志》2009年第5期1415-1417,1451,共4页Chinese Journal of Medical Physics

基　　金：浙江省自然科学基金资助项目(No.Y207738)

摘　　要：目的:从抑郁症患者EEG信号中提取与疾病相关的信息以实现对抑郁症患者与健康人的自动分类。方法:用特征向量法对抑郁症患者与健康人脑电进行特征提取,得到脑电信号功率谱幅度的最大值、最小值、平均值和标准偏差等特征参数,然后用支持向量机分类器进行训练和分类,并进行测试验证。结果:相对于用小波变换提取的频率相关参数作为分类特征,采用本文特征向量法功率谱估计提取的特征参数为分类特征的分类器具有更好的分类效果,其抑郁症患者和健康人脑电信号的分类准确率可以达到95.6%。结论:该研究成果为抑郁症疾病的物理诊断提供了一种新的途径。Objective： To realize the automatic classification between melancholic and healthy persons by extracting the disease features from the melancholic＇s EEG signals. Methods： 1. Extracting the features from the EEG signals of melancholic and healthy persons; 2. Obtaining the characteristic parameters such as the maximum, minimum, mean and standard deviation of EEG power spectrum amplitude; 3. Training the classifier and realizing the classification based on Support Vector Machines; 4. Test and validation. Results： The present classifier, which uses power spectrum characteristic parameters extracted by eigenvector methods as classification features, has better classification accuracy comparing with the one which uses frequency feature parameters extracted by wavelet methods as classification features. It achieves the classification accuracy of 95.6%.Conclusions： This paper presented a new method for melancholia diagnose.

关 键 词：特征向量法 分类 支持向量机 抑郁症 

分 类 号：TP301.06[自动化与计算机技术—计算机系统结构]