|本期目录/Table of Contents|

基于EEG去趋势波动分析和极限学习机的癫痫发作自动检测与分类识别(PDF)

《纳米技术与精密工程》[ISSN:1672-6030/CN:12-1351/O3]

期数:
2015年6期
页码:
397-403
栏目:
神经工程学中的精密测量、计算与控制技术
出版日期:
2015-11-15

文章信息/Info

Title:
Automatic Detection and Classification of Epileptic EEG Based on Detrended Fluctuation Analysis and Extreme Learning Machine
作者:
刘小峰12 张 翔3 王 雪12
(1.河海大学物联网工程学院,常州213022; 2. 常州市特种机器人与智能技术重点实验室,常州213022;
3.中国民生银行南昌分行,南昌330000)
Author(s):
Liu Xiaofeng12 Zhang Xiang3 Wang Xue12
(1. College of Internet of Things Enigneering, Hohai University, Changzhou 213022, China;
2. Changzhou Key Laboratory of Advanced Robotics and Intelligent Technology, Changzhou 213022, China;
3. Nanchang Branch of China Minsheng Bank, Nanchang 330000, China)
关键词:
脑电 去趋势波动指数 癫痫发作 极限学习机 自动检测
Keywords:
electroencephalogram detrended fluctuation index epileptic seizures extreme learning machine automatic detection
分类号:
R318
DOI:
10.13494/j.npe. 20150034
文献标识码:
A
摘要:
癫痫是一种常发的中枢神经失调疾病.基于脑电(EEG)的癫痫发作自动检测与准确识别在临床诊断和治疗上具有重要意义.本文首先采用经验模态分解(EMD)将被试者脑电信号分解成多个固有模态函数(IMF),然后计算低尺度IMF的去趋势波动指数、均值和标准差并组成特征向量,再由极限学习机(ELM)进行自动分类.经使用波恩大学和波士顿儿童医院的脑电数据集(含健康志愿者与癫痫患者)检测验证,结果表明本文所提出的自动检测与快速识别方法仅需较少训练样本即可达到较高的癫痫发作准确识别率(≥95%),具有较好临床应用价值.
Abstract:
Epilepsy is one of the most common neurological diseases. Automatic detection and accurate identification of epileptic seizure based on electroencephalogram (EEG) plays an important role in the diagnosis and treatment of epileptic seizures. In this paper, EEG signals were decomposed into a number of intrinsic mode functions (IMFs) by empirical mode decomposition (EMD), and then the detrended fluctuation index, mean and standard deviation (SD) of IMFs of lower scales were calculated. The three parameters were combined into a feature vector and fed into an extreme learning machine (ELM) classifier. The proposed method was validated on the EEG data sets from Bonn University and Boston Children’s Hospital, involving healthy subjects and epileptics. Results show that the proposed method of automatic detection and rapid identification requires fewer training samples while achieving a higher recognition rate (≥95%), indicating that it is a promising tool for automatic detection and classification of epileptic seizures.

参考文献/References

-

备注/Memo

备注/Memo:
收稿日期: 2015-09-17.
基金项目: 国家自然科学基金资助项目(60905060);江苏省自然科学基金资助项目(BK20141157);中央高校科研业务费资助项目(2011B11114,2012B07314).
作者简介: 刘小峰(1974— ),男,教授.
通讯作者: 刘小峰,xfliu@hhu.edu.cn.
更新日期/Last Update: 2015-11-27