搜索

x

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于频率切片小波变换和支持向量机的癫痫脑电信号自动检测

张涛 陈万忠 李明阳

引用本文:
Citation:

基于频率切片小波变换和支持向量机的癫痫脑电信号自动检测

张涛, 陈万忠, 李明阳

Automatic seizure detection of electroencephalogram signals based on frequency slice wavelet transform and SVM

Zhang Tao, Chen Wan-Zhong, Li Ming-Yang
PDF
导出引用
  • 实现癫痫脑电信号的自动检测对癫痫的临床诊断和治疗具有重要意义. 本文提出先使用频率切片小波变换分离出5个不同频段的节律信号, 再分别计算每个节律信号的近似熵和相邻节律的波动指数, 最后使用遗传算法优化的支持向量机进行分类. 实验结果表明, 所提出的方法能够对正常、癫痫发作间期和癫痫发作期三种脑电信号进行准确分类, 分类准确率为98.33%.
    Over 50 million people all over the world are suffering from epilepsy It is of great significance to achieve automatic seizure detection in electroencephalogram (EEG) signal for clinical diagnosis and treatment. In order to achieve automatic diagnosis of epilepsy, a multitude of automated computer aided diagnostic techniques have been proposed. However, only a few of studies lay emphasis on the effects of different rhythm signals. To explore the influence of rhythm signals on classification accuracy, a newly-developed time-frequency analysis method called frequency slice wavelet transform (FSWT), which is able to locate arbitrary time-frequency range with the use of frequency slice function and whose inverse transformation only relies on fast Fourier transform, is employed to extract five different rhythm signals, namely (0.5-4 Hz), (4-8 Hz), (8-13 Hz), (13-30 Hz) and (30-50 Hz) from original EEG signal. Subsequently, for extracting the nonlinear and linear features, the approximate entropy of each rhythm signal and fluctuation index of adjacent rhythm signals are calculated to reflect the variation characteristics of rhythm signals and they are flocked together to form the nine-dimensional feature vectors. Finally, the extracted vectors are fed into a support vector machine (SVM) which is optimized by genetic algorithms (GA) for classification. Specifically, since the parameters of SVM are associated with the final classification accuracy and appropriate parameters could lead to a remarkable result, GA is applied to parameter optimization, half of the obtained vectors are randomly selected as a training set for training, and the remaining vectors constitute a testing set to test the established model. Experimental results of the proposed approach, which is employed in a public epileptic EEG dataset obtained from department of epitology at Bonn University for validation indicate that the proposed method in this study can carry out the task of classifying normal, inter-ictal and epileptic seizure EEG signals with a high classification accuracy (98.33%), a sensitivity of 99%, a specificity of 99%, and a positive predictive value of 99.5%. The presented approach provides an outstanding scheme for the automatic diagnosis of epilepsy, and the directions of our further research may include the application of the proposed method to the diagnosis of other disorders.
      通信作者: 陈万忠, chenwz@jlu.edu.cn
    • 基金项目: 吉林省科技发展计划自然基金项目(批准号: 20150101191JC)、高等学校博士学科点专项科研基金(批准号: 20100061110029)和吉林省科技发展计划重点项目(批准号: 20090350)资助的课题.
      Corresponding author: Chen Wan-Zhong, chenwz@jlu.edu.cn
    • Funds: Project supported by the Natural Science Foundation for Science and Technology Development Plan of Jilin Province, China (Grant No. 20150101191JC), the Specialized Research Fund for the Doctoral Program of Higher Education of China (Grant No. 20100061110029) and Key Project of Jilin Province Science and Technology Development Plan, China (Grant No. 20090350).
    [1]

    Wang Y, Hou F Z, Dai J F, Liu X F, Li J, Wang J 2014 Acta Phys. Sin. 63 218701 (in Chinese) [王莹, 侯凤贞, 戴加飞, 刘新峰, 李锦, 王俊 2014 物理学报 63 218701]

    [2]

    Zhang T, Chen W Z, Li M Y 2015 Acta Phys. Sin. 64 128701 (in Chinese) [张涛, 陈万忠, 李明阳 2015 物理学报 64 128701]

    [3]

    Meng Q F, Chen S S, Chen Y H, Feng Z Q 2014 Acta Phys. Sin. 63 050506 (in Chinese) [孟庆芳, 陈珊珊, 陈月辉, 冯志全 2014 物理学报 63 050506]

    [4]

    Acharya U R, Sree S V, Swapna G, Martis R J, Suri J S 2013 Knowl-Based Syst. 45 147

    [5]

    Sasankari K, Thanushkodi K 2014 J. Electr. Eng. Technol. 9 1060

    [6]

    Kumar Y, Dewal M L, Anand R S 2014 Signal Image Video Process 8 1323

    [7]

    Li S F, Zhou W D, Yuan Q, Geng S J, Cai D M 2013 Comput. Biol. Med. 43 807

    [8]

    Khoa T Q D, Huong N T M, Toi V V 2012 Comput. Math. Meth. Med. 1 259

    [9]

    Geng S J, Zhou W D, Yuan Q, Cai D M, Zeng Y J 2011 Neurol. Res. 33 908

    [10]

    Ahmadlou M, Adeli H, Adeli A 2010 J. Neural T. 117 1099

    [11]

    Ahmadlou M, Adeli H, Adeli A 2012 Int. J. Psycp. 85 206

    [12]

    Yuan Q, Zhou W D, Li S F, Cai D M 2012 Chin. J. Sci. Inst. 33 514 (in Chinses) [袁琦, 周卫东, 李淑芳, 蔡冬梅 2012 仪器仪表学报 33 514]

    [13]

    Song Y D, Crowcroft J, Zhang J X 2012 J. Neurosci. Meth. 210 132

    [14]

    Acharya U R, Sree S V, Chattopadhyay S, Yu W W, PENG C A A 2011 Int. J. Neur. Syst. 21 199

    [15]

    Acharya U R, Yanti R, Zheng J W, Krishnan M M R, Tan J H, Martis R J, Lim C M 2013 Int. J. Neur. Syst. 23 1001

    [16]

    Yan Z, Miyamoto A, Jiang Z W 2009 Mech. Syst. Signal Pr. 23 1474

    [17]

    Yan Z H, Miyamoto A, Jiang Z W, Liu X L 2010 Mech. Syst. Signal Pr. 24 491

    [18]

    Yan Z H, Miyamoto A, Jiang Z W 2011 Comput. Struct. 89 14

    [19]

    Zhang Y H, Liu M J, Huang N T, Duan W R, Li T Y 2015 High Volt. Eng. 41 2283 (in Chinses) [张宇辉, 刘梦婕, 黄南天, 段伟润, 李天云 2015 高电压技术 41 2283]

    [20]

    Sun D S 2004 Ph. D. Dissertation (Changsha: Central South University) (in Chinses) [孙德山 2004 博士学位论文 (长沙: 中南大学)]

    [21]

    Xue N J 2011 Comput. Eng. Design 32 1792 (in Chinses) [薛宁静 2011计算机工程与设计 32 1792]

    [22]

    Chen S T, Yu P S 2007 J. Hydrol. 347 67

    [23]

    Andrzejak R G, Lehnertz K, Rieke C, Mormann F, David P, Elger C E 2001 Phys. Rev. E 64 061907

    [24]

    Li S F, Zhou W D, Yuan Q, Geng S J, Cai D M 2013 Comput. Biol. Med. 43 807

    [25]

    Pachori R B, Patidar S 2014 Comput. Meth. Prog. Bio. 113 494

    [26]

    Kumar Y, Dewal M L, Anand R S 2014 Neurocomputing 8 3

    [27]

    Yuan Q, Zhou W D, Yuan S S, Li X L, Wang J W, Jia G J 2014 Int. J. Neur. Syst. 24 1450015

  • [1]

    Wang Y, Hou F Z, Dai J F, Liu X F, Li J, Wang J 2014 Acta Phys. Sin. 63 218701 (in Chinese) [王莹, 侯凤贞, 戴加飞, 刘新峰, 李锦, 王俊 2014 物理学报 63 218701]

    [2]

    Zhang T, Chen W Z, Li M Y 2015 Acta Phys. Sin. 64 128701 (in Chinese) [张涛, 陈万忠, 李明阳 2015 物理学报 64 128701]

    [3]

    Meng Q F, Chen S S, Chen Y H, Feng Z Q 2014 Acta Phys. Sin. 63 050506 (in Chinese) [孟庆芳, 陈珊珊, 陈月辉, 冯志全 2014 物理学报 63 050506]

    [4]

    Acharya U R, Sree S V, Swapna G, Martis R J, Suri J S 2013 Knowl-Based Syst. 45 147

    [5]

    Sasankari K, Thanushkodi K 2014 J. Electr. Eng. Technol. 9 1060

    [6]

    Kumar Y, Dewal M L, Anand R S 2014 Signal Image Video Process 8 1323

    [7]

    Li S F, Zhou W D, Yuan Q, Geng S J, Cai D M 2013 Comput. Biol. Med. 43 807

    [8]

    Khoa T Q D, Huong N T M, Toi V V 2012 Comput. Math. Meth. Med. 1 259

    [9]

    Geng S J, Zhou W D, Yuan Q, Cai D M, Zeng Y J 2011 Neurol. Res. 33 908

    [10]

    Ahmadlou M, Adeli H, Adeli A 2010 J. Neural T. 117 1099

    [11]

    Ahmadlou M, Adeli H, Adeli A 2012 Int. J. Psycp. 85 206

    [12]

    Yuan Q, Zhou W D, Li S F, Cai D M 2012 Chin. J. Sci. Inst. 33 514 (in Chinses) [袁琦, 周卫东, 李淑芳, 蔡冬梅 2012 仪器仪表学报 33 514]

    [13]

    Song Y D, Crowcroft J, Zhang J X 2012 J. Neurosci. Meth. 210 132

    [14]

    Acharya U R, Sree S V, Chattopadhyay S, Yu W W, PENG C A A 2011 Int. J. Neur. Syst. 21 199

    [15]

    Acharya U R, Yanti R, Zheng J W, Krishnan M M R, Tan J H, Martis R J, Lim C M 2013 Int. J. Neur. Syst. 23 1001

    [16]

    Yan Z, Miyamoto A, Jiang Z W 2009 Mech. Syst. Signal Pr. 23 1474

    [17]

    Yan Z H, Miyamoto A, Jiang Z W, Liu X L 2010 Mech. Syst. Signal Pr. 24 491

    [18]

    Yan Z H, Miyamoto A, Jiang Z W 2011 Comput. Struct. 89 14

    [19]

    Zhang Y H, Liu M J, Huang N T, Duan W R, Li T Y 2015 High Volt. Eng. 41 2283 (in Chinses) [张宇辉, 刘梦婕, 黄南天, 段伟润, 李天云 2015 高电压技术 41 2283]

    [20]

    Sun D S 2004 Ph. D. Dissertation (Changsha: Central South University) (in Chinses) [孙德山 2004 博士学位论文 (长沙: 中南大学)]

    [21]

    Xue N J 2011 Comput. Eng. Design 32 1792 (in Chinses) [薛宁静 2011计算机工程与设计 32 1792]

    [22]

    Chen S T, Yu P S 2007 J. Hydrol. 347 67

    [23]

    Andrzejak R G, Lehnertz K, Rieke C, Mormann F, David P, Elger C E 2001 Phys. Rev. E 64 061907

    [24]

    Li S F, Zhou W D, Yuan Q, Geng S J, Cai D M 2013 Comput. Biol. Med. 43 807

    [25]

    Pachori R B, Patidar S 2014 Comput. Meth. Prog. Bio. 113 494

    [26]

    Kumar Y, Dewal M L, Anand R S 2014 Neurocomputing 8 3

    [27]

    Yuan Q, Zhou W D, Yuan S S, Li X L, Wang J W, Jia G J 2014 Int. J. Neur. Syst. 24 1450015

  • [1] 张毅军, 慕晓冬, 郭乐勐, 张朋, 赵导, 白文华. 一种基于量子线路的支持向量机训练方案. 物理学报, 2023, 72(7): 070302. doi: 10.7498/aps.72.20222003
    [2] 梁可达, 刘滕飞, 常哲, 张猛, 李志鑫, 黄松松, 王晶. 基于最小二乘法和支持向量机的海洋内孤立波传播速度反演模型. 物理学报, 2023, 72(2): 028301. doi: 10.7498/aps.72.20221633
    [3] 宋堃, 高太长, 刘西川, 印敏, 薛杨. 基于支持向量机的微波链路雨强反演方法. 物理学报, 2015, 64(24): 244301. doi: 10.7498/aps.64.244301
    [4] 赵志刚, 张纯杰, 苟向锋, 桑虎堂. 基于粒子群优化支持向量机的太阳电池温度预测. 物理学报, 2015, 64(8): 088801. doi: 10.7498/aps.64.088801
    [5] 张涛, 陈万忠, 李明阳. 基于AdaBoost算法的癫痫脑电信号识别. 物理学报, 2015, 64(12): 128701. doi: 10.7498/aps.64.128701
    [6] 行鸿彦, 朱清清, 徐伟. 一种混沌海杂波背景下的微弱信号检测方法. 物理学报, 2014, 63(10): 100505. doi: 10.7498/aps.63.100505
    [7] 孟庆芳, 陈珊珊, 陈月辉, 冯志全. 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. 物理学报, 2014, 63(5): 050506. doi: 10.7498/aps.63.050506
    [8] 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. 物理学报, 2013, 62(21): 215201. doi: 10.7498/aps.62.215201
    [9] 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. 物理学报, 2013, 62(12): 120511. doi: 10.7498/aps.62.120511
    [10] 王芳芳, 张业荣. 基于支持向量机的电磁逆散射方法. 物理学报, 2012, 61(8): 084101. doi: 10.7498/aps.61.084101
    [11] 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. 物理学报, 2012, 61(24): 240504. doi: 10.7498/aps.61.240504
    [12] 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. 物理学报, 2010, 59(5): 3043-3048. doi: 10.7498/aps.59.3043
    [13] 王革丽, 杨培才, 毛宇清. 基于支持向量机方法对非平稳时间序列的预测. 物理学报, 2008, 57(2): 714-719. doi: 10.7498/aps.57.714
    [14] 蔡俊伟, 胡寿松, 陶洪峰. 基于选择性支持向量机集成的混沌时间序列预测. 物理学报, 2007, 56(12): 6820-6827. doi: 10.7498/aps.56.6820
    [15] 张家树, 党建亮, 李恒超. 时空混沌序列的局域支持向量机预测. 物理学报, 2007, 56(1): 67-77. doi: 10.7498/aps.56.67
    [16] 叶美盈. 基于最小二乘支持向量机建模的混沌系统控制. 物理学报, 2005, 54(1): 30-34. doi: 10.7498/aps.54.30
    [17] 叶美盈, 汪晓东, 张浩然. 基于在线最小二乘支持向量机回归的混沌时间序列预测. 物理学报, 2005, 54(6): 2568-2573. doi: 10.7498/aps.54.2568
    [18] 崔万照, 朱长纯, 保文星, 刘君华. 基于模糊模型支持向量机的混沌时间序列预测. 物理学报, 2005, 54(7): 3009-3018. doi: 10.7498/aps.54.3009
    [19] 刘 涵, 刘 丁, 任海鹏. 基于最小二乘支持向量机的混沌控制. 物理学报, 2005, 54(9): 4019-4025. doi: 10.7498/aps.54.4019
    [20] 崔万照, 朱长纯, 保文星, 刘君华. 混沌时间序列的支持向量机预测. 物理学报, 2004, 53(10): 3303-3310. doi: 10.7498/aps.53.3303
计量
  • 文章访问数:  5776
  • PDF下载量:  279
  • 被引次数: 0
出版历程
  • 收稿日期:  2015-10-19
  • 修回日期:  2015-11-06
  • 刊出日期:  2016-02-05

/

返回文章
返回