一种基于改进经验模态分解的癫痫脑电识别新方法

doi:10.3969/j.issn.0258-8021. 2013. 06.04

摘要
图/表
参考文献
相关文章 (4)

全文: PDF (941 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要在临床癫痫诊断过程中，为了提高癫痫脑电的识别率，能在癫痫发作前期就预测到癫痫疾病，其特征波的提取至关重要。针对这一问题，提出将平行延拓与镜像延拓相结合来改进EMD算法。首先，使用平行延拓的方法，在原始脑电信号的左、右端点处分别预测出一个极值；然后，使用基于镜像延拓的EMD方法，对信号进行镜像延拓，以避免经验模态分解过程中的端点效应；最后，采用支持向量机进行信号的分类识别。算法验证数据取自德国伯恩大学癫痫研究中心的脑电数据库，其中50例是正常脑电信号、50例是癫痫发作间期的脑电信号。实验研究表明：该方法对总测试脑电信号的识别率达到94%。其中，正常脑电信号和癫痫脑电信号的独立识别率均为94%，比传统EMD算法处理后的脑电识别率提高了5%，可见该方法可以有效地预测癫痫脑电。

	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
	庞春颖^*王小甜孙晓琳

关键词 ：癫痫脑电, 平行延拓, 镜像延拓, 经验模态分解（EMD）, 支持向量机（SVM）

Abstract：In order to improve the recognition rate of epileptic EEG and to predict epileptic disease in the early stage of epileptic seizures, the characteristic wave extraction is very important in the process of clinical diagnosis of epilepsy. To solve this problem, a method that combined parallel extension with mirror extension to improve EMD algorithm was proposed. Firstly, extreme values were predicted respectively in the left and right endpoints of the original EEG using the parallel extension method. Then, the EMD method based on the mirror extension was used in order to avoid the end effect in the process of EMD. Finally, the SVM classifier was used for signal classification and recognition. The algorithm validation data were from EEG database of the Epilepsy Research Center, University of Bonn, Germany (50 cases normal EEG signals and 50 cases epileptic EEG signals). The result shows that the recognition rate (the sum of normal EEG and epileptic EEG) of total test EEG signals by this method can reach 94%, and the recognition rates of normal EEG and epileptic EEG are both 94%. This result is 5% higher than the recognition rate of EEG processed by the traditional EMD algorithm. Therefore the method can predict epileptic EEG effectively.

Key words： epileptic EEG parallel extension mirror extension empirical model decomposition (EMD) support vector machine (SVM)

基金资助:吉林省科技厅项目（20121006）

引用本文:

庞春颖^*王小甜孙晓琳. 一种基于改进经验模态分解的癫痫脑电识别新方法[J]. 中国生物医学工程学报, 2013, 32(6): 663-669.
PANG Chun Ying^*WANG Xiao Tian SUN Xiao Lin. A New Method of Epileptic EEG Identification Based on Improved EMD. journal1, 2013, 32(6): 663-669.

链接本文:

http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021. 2013. 06.04 或 http://cjbme.csbme.org/CN/Y2013/V32/I6/663

［1］雷国亮.为什么癫痫病发病率居高不下［EB/OL］. http://www.haodf.com/zhuanjiaguandian/zxyylgl_410709901.htm,2011-08-10/2013-03-27.
［2］吴晓斌，郭影，邱天爽，等. B样条小波在提取脑电癫痫棘波中的应用［J］. 生物医学工程学杂志，2006, 23(5): 947-950.
［3］Bethesda MD. Seizures and epilepsy: Hope through research national institute of neurological fisorders and stroke［EB/OL］. http://www.ninds.nih.gov/disorders/epilepsy/detail_epilepsy.htm,2004-05/2013-03-27. 
［4］Adeli H, Zhou Z, Dadmehr N. Analysis of EEG records in an epileptic patient using wavelet transform ［J］. J Neurosci Methods, 2003 Feb 15, 123(1): 69-87.［5］Piotr JD. From wavelets to adaptive approximations: Timefrequency parameterization of EEG ［J］. BioMedical Engineering OnLine, 2003, 2(1): 1-30.
［6］Adeli H, GhoshDastidar S, Dadmehr N. A waveletchaos methodology for analysis of EEGs and EEG subbands to detect seizure and epilepsy［J］. IEEE Trans Biomed Eng, 2007 Feb, 54(2): 205-211.
［7］于德介，程军圣，杨宇. 机械故障诊断的HilbertHuang变换方法［M］. 北京：科学出版社，2007: 20-26.
［8］Huang NE, Shen Z, Long SR, et al. The empirical mode decomposition and the hilbert spectrum for nonlinear and nonstationary time series analysis［J］. Proc R Soc Lond, 1998: 903-995.
［9］Ira Pohl. The avoidance of (relative) catastrophe, heuristic competence, genuine dynamic weighting and computational issues in heuristic problem solving ［C］//Proceedings of International Joint Conferences on Artificial Intelligence. Stanford: Morgan Kaufmann, 1973: 12-17.
［10］Pearl J, Kim JH. Study in Semiadmissible Heuristics ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1982, 4(4): 392-399.
［11］Qin SR, Zhong YM. A new envelope algorithm of HilbertHuang transform ［J］. Mechanical Systems and Signal Processing, 2006, 20(8): 1941-1952.
［12］许宝杰，张建民，徐小力，等. 抑制EMD端点效应方法的研究［J］. 北京理工大学学报. 2006, 26(3): 196-200.
［13］郭兴明，袁志会.基于小波变换和经验模式分解的心音信号研究［J］. 中国生物医学工程学报. 2012, 31(1): 39-44.
［14］邓拥军，王伟，钱成春，等. EMD方法及Hilbert变换中边界问题的处理［J］. 科学通报，2001, 46(3): 257-263.
［15］Cheng JS, Yu DJ, Yang Y. Application of support vector regression machines to the recessing of end effects of HilbertHuang transform ［J］. Mechanical System and Signal Processing, 2007(21): 1197-1211.
［16］陈志彬，陈娟，邱天爽. 基于经验模式分解的脑电棘波检测方法［J］. 生物医学工程学杂志.2007,24(5):973-977.
［17］万柏坤，郑旭媛，朱欣，等.癫痫脑电特征波的综合检测分类方法研究［J］.中国生物医学工程学报. 2002， 21(3): 215-218.
［18］Cristianini N, ShaweTaylor J. An Introduction to Support Vector Machine and Other KernelBased Learning Methods［M］. Beijing:Beijing Machinery Industry Press, 2005: 158-172.