| 基于自回归模型和关联向量机的癫痫脑电信号自动分类 |
| |
| 引用本文： | 韩敏,孙磊磊,洪晓军,韩杰.基于自回归模型和关联向量机的癫痫脑电信号自动分类[J].中国生物医学工程学报,2011,30(6). |
| |
| 作者姓名： | 韩敏 孙磊磊 洪晓军 韩杰 |
| |
| 作者单位： | 1. 大连理工大学电子信息与电气工程学部,大连,116023
2. 大连医科大学附属第一医院,大连,116011 |
| |
| 摘 要： | 癫痫脑电信号自动分类方法的研究具有重要意义.基于自回归模型和关联向量机,实现癫痫脑电信号的自动分类.采用自回归模型,进行脑电信号特征提取；通过引入主成分分析和线性判别分析两种特征变换方法,降低特征空间维数；采用关联向量机作为分类器,提高模型稀疏性并可以得到概率式输出.在对波恩大学癫痫研究中心脑电信号的分类中,所提出的方法最高准确率可以达到99.875％；在将特征空间维数降至原始维数的1/15时,分类准确率仍可达到99.500％；采用关联向量机作为分类器,模型稀疏性大幅提高,与支持向量机相比,同等条件下关联向量数仅为支持向量数的几十分之一.所提方法可以很好地应用于癫痫脑电信号的自动分类.
|
| 关 键 词： | 癫痫 自回归模型 主成分分析 线性判别分析 关联向量机 |
Automatic Classification of Epileptic EEG Signals Based on AR Model and Relevance Vector Machine |
| |
| HAN Min,SUN Lei-Lei,HONG Xiao-Jun,HAN Jie.Automatic Classification of Epileptic EEG Signals Based on AR Model and Relevance Vector Machine[J].Chinese Journal of Biomedical Engineering,2011,30(6). |
| |
| Authors: | HAN Min SUN Lei-Lei HONG Xiao-Jun HAN Jie |
| |
| Institution: | HAN Min 1 SUN Lei-Lei1 HONG Xiao-Jun2 HAN Jie2 1(School of Electronic and Information Engineering,Dalian University of Technology,Dalian 116023,China) 2(First Affiliated Hospital of Dalian Medical University,Dalian 116011,China) |
| |
| Abstract: | Automatic classification system of epileptic EEG signals is one very important issue.In this paper a new epileptic EEG signal classification method was proposed on the basis of AR model and relevance vector machine.AR model was used to extract EEG features,and then principle components analysis and linear discriminant analysis were adopted to reduce the dimensionality of feature space.In order to obtain a sparser model and a model with probabilistic outputs,relevance vector machine was chosen as classifier.... |
| |
| Keywords: | epilepsy AR model principle components analysis(PCA) linear discriminant analysis(LDA) relevance vector machine |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
