|
|
|
| 基于递归量化分析与支持向量机的癫痫脑电自动检测方法 |
| 孟庆芳1 2, 陈珊珊1 2, 陈月辉1 2, 冯志全1 2 |
1. 济南大学信息科学与工程学院, 济南 250022; 2. 山东省网络环境智能计算技术重点实验室, 济南 250022 |
| Automatic detection of epileptic EEG based on recurrence quantification analysis and SVM |
| Meng Qing-Fang1 2, Chen Shan-Shan1 2, Chen Yue-Hui1 2, Feng Zhi-Quan1 2 |
1. School of Information Science and Engineering, University of Jinan, Jinan 250022, China; 2. Shandong Provincial Key laboratory of Network Based Intelligent Computing, Jinan 250022, China |
|
|
摘要: 癫痫脑电信号的自动检测对癫痫的临床诊断与治疗具有重要意义. 基于递归图(recurrence plot)的递归量化分析(recurrence quantification analysis,RQA)重现了非线性时间序列的动力学行为,分析了其递归特性,本文提出了基于RQA的癫痫脑电信号特征提取方法. 实验结果表明:直接基于RQA特征的癫痫脑电的检测准确率较高,其中直接基于确定率DET的分类准确率可达到90.25%. 本文还把提取的RQA特征值和变化系数、波动指数相结合组成特征向量,输入到SVM分类器,实现癫痫脑电信号的自动检测;实验结果表明:该方法的分类准确率可达到99%.
关键词:
递归量化分析
递归图
癫痫脑电
支持向量机
|
|
Abstract: Automatic detection and classification of epileptic EEG signals have been a significance method for the clinical diagnosis and treatment of epilepsy. The recurrence quantification analysis (RQA) based on the recurrence plot could visualize the recurrence behaviors of dynamical systems from the nonlinear time series and analysis of the recurrence properties. This paper presents a new feature extraction method for epileptic EEG signals based on the recurrence quantification analysis. Experimental results show that the seizure detection directly based on recurrence quantification analysis features has a higher detection performance; especially the classification accuracy based on the deterministic feature can be up to 90.25%. This paper also combines the RQA features with the variation coefficient and fluctuation index, and then puts the feature vectors into a support vector machine (SVM) to automatically detect the epileptic EEG from EEG recordings. Experimental results shows that the proposed methods could achieve a great classification accuracy of 99%.
Keywords:
recurrence quantification analysis
recurrence plot
epileptic EEG
support vector machine
|
|
收稿日期: 2013-10-11
|
| PACS: |
05.45.Tp
|
(Time series analysis)
|
| |
05.45.Pq
|
(Numerical simulations of chaotic systems)
|
| |
05.45.Ac
|
(Low-dimensional chaos)
|
|
| 基金: 国家自然科学基金(批准号:61201428,61070130,61173079)、山东省自然科学基金(批准号:ZR2010FQ020,ZR2011FZ003)、山东省优秀中青年科学家科研奖励基金(批准号:BS2009SW003)和中国博士后科学基金(批准号:20100470081)资助的课题. |
| 作者简介: |
References
| [1] | Meng Q F, Zhou W D, Chen Y H, Peng Y H 2010 Acta Phys. Sin. 59 123 (in Chinese) [孟庆芳, 周卫东, 陈月辉, 彭玉华 2010 物理学报 59 123]
|
| [2] | Swiderski B, Osowski S, Rysz A 1995 Chaos 5 82
|
| [3] | Kannathal N, Min L C, Rajendra A U, Sadasivan P K 2005 Computer Methods and Programs in Biomedicine 80 187
|
| [4] | Kai C H, Sung N Y 2010 Computers in Biology and Medicine 40 823
|
| [5] | Rajendra A U, Molinari F, Vinitha S S, Chattopadhyay S, Hoong N K, Suri J S 2012 Biomedical Signal Processing and Control 7 401
|
| [6] | Yuan Q, Zhou W D, Li S F, Cai D M 2012 Chinese Journal of Scientific Instrument 33 514 (in Chinese) [袁琦, 周卫东, 李淑芳, 蔡冬梅 2012 仪器仪表学报 33 514]
|
| [7] | Yuan Q, Zhou W D, Li S F, Cai D M 2011 Epilepsy Research 96 29
|
| [8] | Cai D M, Zhou W D, Liu K, Li S F, Geng S J 2010 Chinese Journal of Biomedical Engineering 29 836 (in Chinese) [蔡冬梅, 周卫东, 刘凯, 李淑芳, 耿淑娟 2010 中国生物医学工程学报 29 836]
|
| [9] | Eckmann J P, Kamphorst S O, Ruelle D 1987 Europhysics Letters 5 973
|
| [10] | Acharya U R, Sree V, Chattopadhyay S, Yu W W, Alvin P C 2011 International Journal of Neural Systems 21 199
|
| [11] | Thomasson N, Hoeppner T J, Webber C L, Zbilut J P 2001 Physics Letters A 279 94
|
| [12] | Rajendra A U, Faustand O, Kannathal N 2005 Computer Methods and Programs in Biomedicine 80 37
|
| [13] | Ouyang G X, Li X L, Dang C Y, Richards D A 2008 Clinical Neurophysiology 119 1747
|
| [14] | Zhong J K, Song Z H, Hao W Q 2002 Acta Biophysica Sinica 18 241 (in Chinese) [钟季康, 宋志怀, 郝为强 2002 生物物理学报 18 241]
|
| [15] | Marwan W N, Kurths J 2002 Phys. Rev. E 66 1539
|
| [16] | Chen X M, Qiu Y H, Zhu Y S 2008 Journal of Biomedical Engineering 25 39 (in Chinese) [陈晓鸣, 邱意弘, 朱贻盛 2008 生物医学工程学杂志 25 39]
|
| [17] | Liu X, Cheng J H, Lu H B, Zhang L P, Ma J, Dong X Z 2006 Space Medicine & Medical Engineering 19 394 (in Chinese) [刘欣, 程九华, 卢虹冰, 张立藩, 马进, 董秀珍 2006 航天医学与医学工程 19 394]
|
| [18] | Deng N Y, Tian Y J 2004 A new method of data mining: support vector machines (Science Press) (in Chinese) [邓乃扬, 田英杰 2004 数据挖掘中的新方法-支持向量机(科学出版社)]
|
| [19] | Cai D M, Zhou W D, Li S F, Wang J W, Jia G J, Liu X W 2011 Acta Biophysica Sinica 27 175 (in Chinese) [蔡冬梅, 周卫东, 李淑芳, 王纪文, 贾桂娟, 刘学伍 2011 生物物理学报 27 175]
|
| [20] | Nicolaou N, Georgiou J 2012 Expert Systems with Applications 39 202
|
| [21] | Ubeyli E D 2009 Digital Signal Processing 2009(19) 297
|
| [22] | Song Y, Lio P 2010 Journal of Biomedical Science and Engineering 3 556
|
|
[1]
|
唐舟进, 任峰, 彭涛, 王文博. 基于迭代误差补偿的混沌时间序列最小二乘支持向量机预测算法[J]. 物理学报, 2014, 63(5): 050505.
|
|
[2]
|
王萍, 潘跃. 基于显著性特征的大冰雹识别模型[J]. 物理学报, 2013, 62(6): 069202.
|
|
[3]
|
火元莲, 张广庶, 吕世华, 袁萍. 闪电的分形特征研究及其在自动识别中的应用[J]. 物理学报, 2013, 62(5): 059201.
|
|
[4]
|
于洋, 郝中骐, 李常茂, 郭连波, 李阔湖, 曾庆栋, 李祥友, 任昭, 曾晓雁. 支持向量机算法在激光诱导击穿光谱技术塑料识别中的应用研究[J]. 物理学报, 2013, 62(21): 215201.
|
|
[5]
|
赵永平, 张丽艳, 李德才, 王立峰, 蒋洪章. 过滤窗最小二乘支持向量机的混沌时间序列预测[J]. 物理学报, 2013, 62(12): 120511.
|
|
[6]
|
王春龙, 刘建国, 赵南京, 马明俊, 王寅, 胡丽, 张大海, 余洋, 孟德硕, 章炜, 刘晶, 张玉钧, 刘文清. 水体重金属激光诱导击穿光谱定量分析方法对比研究[J]. 物理学报, 2013, 62(12): 125201.
|
|
[7]
|
王芳芳,张业荣. 基于支持向量机的电磁逆散射方法[J]. 物理学报, 2012, 61(8): 084101.
|
|
[8]
|
行鸿彦, 祁峥东, 徐伟. 基于选择性支持向量机集成的海杂波背景中的微弱信号检测[J]. 物理学报, 2012, 61(24): 240504.
|
|
[9]
|
于艳华, 宋俊德. 基于信息冗余检验的支持向量机时间序列预测自由参数选取方法[J]. 物理学报, 2012, 61(17): 170516.
|
|
[10]
|
行鸿彦, 程艳燕, 徐伟. 基于广义窗函数和最小二乘支持向量机的混沌背景下微弱信号检测[J]. 物理学报, 2012, 61(10): 100506.
|
|
[11]
|
杨红, 王瑞. 基于反馈和多最小二乘支持向量机的分数阶混沌系统控制[J]. 物理学报, 2011, 60(7): 070508.
|
|
[12]
|
龙文, 焦建军, 龙祖强. 基于PSO优化LSSVM的未知模型混沌系统控制[J]. 物理学报, 2011, 60(11): 110506.
|
|
[13]
|
边洪瑞, 王江, 韩春晓, 邓斌, 魏熙乐, 车艳秋. 基于复杂度的针刺脑电信号特征提取[J]. 物理学报, 2011, 60(11): 118701.
|
|
[14]
|
阎晓妹, 刘丁. 基于最小二乘支持向量机的分数阶混沌系统控制[J]. 物理学报, 2010, 59(5): 3043-3048.
|
|
[15]
|
陈强, 任雪梅. 基于多核最小二乘支持向量机的永磁同步电机混沌建模及其实时在线预测[J]. 物理学报, 2010, 59(4): 2310-2318.
|
|
|
|