网站首页            期刊简介             编委会             投稿指南             期刊订阅             下载中心             在线留言            联系我们             English
  2025年4月5日 星期六  
文章快速检索
中国生物医学工程学报  2018, Vol. 37 Issue (6): 665-672    DOI: 10.3969/j.issn.0258-8021.2018.06.004
  论著 本期目录 | 过刊浏览 | 高级检索 |
利用整体经验模态分解和随机森林的脑电信号分类研究
秦喜文1,2*, 吕思奇1, 李巧玲1
1长春工业大学研究生院,长春 130012;
2长春工业大学基础科学学院,长春 130012
Recognition of EEG Based on Ensemble Empirical Mode Decomposition and Random Forest
Qin Xiwen1,2*, Lv Siqi1, Li Qiaoling1
1Graduate School, Changchun University of Technology, Changchun 130012, China;
2School of Basic Sciences, Changchun University of Technology, Changchun 130012, China
全文: PDF (1168 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
摘要 癫痫脑电信号的自动监测与分类在临床医学上具有重要意义。针对脑电信号的非平稳特点,提出一种基于整体经验模态分解和随机森林相结合的脑电信号分类方法。选取波恩大学脑电信号数据集中癫痫发作间期和发作期的200个单通道信号,共819 400个数据作为样本。首先利用整体模态分解将癫痫脑电信号分解成多个固有模态函数,然后对各阶固有模态函数提取有效特征,最后分别用随机森林和最小二乘支持向量机对脑电信号的特征进行分类。将随机森林与最小二乘支持向量机分类正确识别率对比,结果表明,随机森林分类方法对发作期和发作间期的癫痫脑电信号的分类效果比较理想,识别精度为99.60%,高于最小二乘支持向量机的准确性。该方法的提出能有效提高临床癫痫脑电信号分析的效率。
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
秦喜文
吕思奇
李巧玲
关键词 脑电信号整体经验模态分解随机森林特征识别分类    
Abstract:It is of great importance to automaticaly monitor and classify epileptic EEG in clinical medicine. In view of the non-stationary characteristics of EEG signals, a new method for feature extraction and recognition of EEG based on ensemble empirical mode decomposition (EEMD) and random forest (RF) was proposed in this paper. In this study 200 single-channel signals of epileptic ictal and interictal EEG were selected from EEG data of Bonn University, and 819400 data were used as samples. Firstly, the EEG signals were decomposed into several intrinsic mode functions (IMF) by EEMD, and then the effective features were extracted from each IMF component. Finally, the features of each IMF component were classified by RF and least squares support vector machine (LSSVM). We compared the classification results of RF and LSSVM. The results showed that the classification effect of RF algorithm on epileptic EEG signals in ictal and interictal periods was effective. The recognition accuracy was 99.60%, which was higher than the accuracy of LSSVM. The proposed method could effectively improve the efficiency of clinical EEG signal analysis.
Key wordsEEG    ensemble empirical mode decomposition(EEMD)    random forest(RF)    feature extraction and recognition
收稿日期: 2017-06-17     
PACS:  R318  
基金资助:国家自然科学基金(11301036, 11226335, 11571051);吉林省教育厅科研项目(JJKH20170540KJ).
通讯作者: E-mail: qinxiwen@ccut.edu.cn   
引用本文:   
秦喜文, 吕思奇, 李巧玲. 利用整体经验模态分解和随机森林的脑电信号分类研究[J]. 中国生物医学工程学报, 2018, 37(6): 665-672.
Qin Xiwen, Lv Siqi, Li Qiaoling. Recognition of EEG Based on Ensemble Empirical Mode Decomposition and Random Forest. Chinese Journal of Biomedical Engineering, 2018, 37(6): 665-672.
链接本文:  
http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021.2018.06.004     或     http://cjbme.csbme.org/CN/Y2018/V37/I6/665
版权所有 © 2015 《中国生物医学工程学报》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发