|本期目录/Table of Contents|

[1]李冬梅,张洋,杨日东,等.经验模式分解与代价敏感支持向量机在癫痫脑电信号分类中的应用*[J].生物医学工程研究,2017,01:33-37.
 LI Dongmei,ZHANG Yang,YANG Ridong,et al.Classification and Prediction of EEG based on Empirical Mode Decomposition[J].Journal of Biomedical Engineering Research,2017,01:33-37.
点击复制

经验模式分解与代价敏感支持向量机在癫痫脑电信号分类中的应用*(PDF)

《生物医学工程研究》[ISSN:1006-6977/CN:61-1281/TN]

期数:
2017年01期
页码:
33-37
栏目:
出版日期:
2017-03-25

文章信息/Info

Title:
Classification and Prediction of EEG based on Empirical Mode Decomposition
文章编号:
1672-6278 (2017)01-0033-05
作者:
李冬梅1张洋2杨日东3陈子怡4田翔华1董楠3尔西丁·买买提1周毅13
1. 新疆医科大学,新疆 乌鲁木齐 830011;2.新疆医科大学第一附属医院神经内科,新疆 乌鲁木齐 830011;3.中山大学中山医学院生物医学工程系,广东 广州 510080;4.中山大学附属第一医院神经内科,广东 广州 510080
Author(s):
LI Dongmei1ZHANG Yang2YANG Ridong3CHEN Ziyi4TIAN Xianghua1DONG Nan3ALCITIN Mamat1ZHOU Yi13
1. Xinjiang Medical University,Urumqi 830011,China;2. Neurology Departmera,The First Affiliated Hospital of Xinjiang University,Urumqi 830011, Xinjiang;3. Department of Biomedical Engineering,Medical College,Sun Yat-sen University,Guangzhou 510080,China;4. Neurology Departmera,The First Affiliated Hospital of Sun Yat-sen University,Guangzhou 510080
关键词:
脑电信号癫痫经验模式分解代价敏感支持向量机参数寻优
Keywords:
Electroencephalogram Epilepsy Empirical mode decomposition Cost-sensitive SVM Parameter optimization
分类号:
R318
DOI:
10.19529/j.cnki.1672-6278.2017.01.07
文献标识码:
A
摘要:
提取出脑电信号中微弱征兆信息,可以更好地了解脑电信号的特征,但由于各类外界信号的相互混叠,信号呈现出非线性、非平稳性,因此脑电信号的提取是个难题。为此本研究提出了优于小波分解的经验模式分解(EMD)算法对脑电信号进行分解,提取主要IMF分量的特征值,随后采取代价敏感支持向量机(CSVM)进行分类,并对参数进行寻优。在对癫痫患者脑电信号研究的实验中,分类准确率均达到90%以上,验证了本方法的可行性。
Abstract:
EEG signals can be extracted from EEG signals, which can better understand the characteristics of EEG signals. However, due to the aliasing of various types of external signals, the signal exhibits nonlinear and nonstationarity. Therefore, for EEG signals, extraction is a problem. In this paper, an empirical mode decomposition (EMD) algorithm, which is superior to wavelet decomposition, was proposed to decompose the EEG signal and extract the eigenvalues of the main IMF components. Then, the cost-sensitive support vector machine (CSVM) was used to classify the parameters excellent. In the study of EEG signals of epilepsy patients, the accuracy of classification is more than 90%, which verifies the feasibility of this method.

参考文献/References

备注/Memo

备注/Memo:
(收稿日期:2016-11-07)国家自然科学基金资助项目(61263011);中央高校基本业务费项目(15ykcj03d);广东省前沿与关键技术创新专项(2014B010118003,2015B010106008)。△通信作者Email:zhouyi@sysu.edu.cn
更新日期/Last Update: 2017-06-22