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AdaBoost算法的癫痫脑电信号识别

张涛 陈万忠 李明阳

引用本文:
Citation:

基于AdaBoost算法的癫痫脑电信号识别

张涛, 陈万忠, 李明阳

Recognition of epilepsy electroencephalography based on AdaBoost algorithm

Zhang Tao, Chen Wan-Zhong, Li Ming-Yang
PDF
导出引用
  • AdaBoost算法作为Boosting算法的经典算法之一, 在人脸检测和目标跟踪等领域得到了广泛应用, 但该算法也有一个缺点-退化问题. 为了解决这个问题, 通过对弱分类器进行筛选、引入平滑因子和权值修正函数三个措施对算法进行优化, 并将优化后的算法与小波包分解相结合应用到癫痫脑电信号的识别上. 结果表明, 本文算法对癫痫脑电信号的识别率为96.11%, 对正常脑电信号的识别率为99.51%, 具有较高的识别率, 为癫痫的正确诊断提供了一种可能有效的解决方案.
    Automatic recognition of epilepsy electroencephalography (EEG) signal has become a research focus because of its high efficiency, and many algorithms have been put forward to achieve it. As one of the classic algorithms of boosting algorithm, AdaBoost algorithm has been widely used in face detection and target tracking fields, but the algorithm also has a disadvantage that is its degradation. In order to solve this problem, this paper puts forward three measures to optimize the algorithm by filtering the weak classifiers whose recognition rates are low, introducing the smoothing factor and a weighted correction function. In order to verify the robustness of optimized algorithm, we choose three main parameters, i.e., the number of weak classifier, which is denoted by T; the base of logarithmic function, which is denoted by α; the threshold of weight, which is denoted by β. The experimental results of optimized AdaBoost show that it has good robustness and high recognition rate. #br#In this paper, we divide the whole process into three steps. The first step is to use the Butterworth digital low-pass filter in which the cutoff frequency of pass band is 40 Hz to filter noise whose frequency is above 40 Hz. The second step is to do feature extraction with the help of wavelet packet decomposition. The third step is to compute the sum of absolute value which are the wavelet packet coefficients of fourth layer, the wavelet package entropy and the sum of signal amplitude square and combine them together to form the feature vector of each EEG. Because the wavelet package entropy is far less than the sum of absolute value and the sum of signal amplitude square, in order to make sure that the entropy reacts in the third step, we use one thousandth of the sum of absolute wavelet packet coefficients, one hundredth of the sum of signal amplitude square and the wavelet package entropy as the weighted feature vector. Finally, we succeed in distinguishing EEGs between epilepsy and normal by using the optimized AdaBoost whose input is the weighted feature vector. The result shows that the presented method has a high recognition rate, it can identify 96.11% epilepsy EEGs and 99.51% normal EEGs, thus it provides an effective solution for the correct diagnosis of epilepsy.
    • 基金项目: 高等学校博士学科点专项科研基金(批准号:20100061110029)、吉林省科技发展计划重点项目(批准号:20090350)和吉林大学研究生创新研究计划(批准号:20121107)资助的课题.
    • Funds: Project supported by the Specialized Research Fund for the Doctoral Program of Higher Education of China (Grant No. 20100061110029), the Key Project of Jilin Province Science and Technology Development Plan, China (Grant No. 20090350), and the Graduate Innovation Research Program of Jilin University, China (Grant No. 20121107).
    [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]

    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]

    [3]

    Cai D M, Zhou W D, Li S F, Wang J W, Jia G J, Liu X W 2011 Acta Biophys. Sin. 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]

    [4]

    Pang C Y, Wang X T, Sun X L 2013 Chin. J. Biomed. Eng. 32 663 (in Chinese) [庞春颖, 王小甜, 孙晓琳 2013 中国生物医学工程学报 32 663]

    [5]

    Zhang Z, Du S H, Chen Z Y, Tian X H, Zhou Y, Zhang Y 2013 J. Biomed. Eng. Res. 32 74 (in Chinese) [张振, 杜守洪, 陈子怡, 田翔华, 周毅, 张洋 2013 生物医学工程研究 32 74]

    [6]

    Tibdewal M N, Manjunatha M, Ray A K, Malokar M 2013 1st IEEE-EMBS Special Topic Conference on Point-of-Care (POCT) Healthcare Technologies (PHT) Bangalore, India, January 16-18, 2013 p72

    [7]

    Sakkalis V, Giannakakis G, Farmaki C, Mousas A, Pediaditis M 2013 35th Annual International Conference of the IEEE EMBS Osaka, Japan, July 3-7, 2013 p6333

    [8]

    Fu Z L 2014 Acta Autom. Sin. 40 1075 (in Chinese) [付忠良 2014 自动化学报 40 1075]

    [9]

    Fu Z L 2013 J. Comput. Res. Dev. 50 861 (in Chinese) [付忠良 2013 计算机研究与发展 50 861]

    [10]

    Schapire R E, Singer Y 1999 11th Annual Conference on Computational Learning Theory Madison, Wisconsin, July 24-26, 1998 p297

    [11]

    Islam M M, Yao X, Murase K 2003 IEEE Trans. Neural Networks 14 820

    [12]

    Cao Y, Miao Q G, Liu J C 2013 Acta Autom. Sin. 39 745 (in Chinese) [曹莹, 苗启广, 刘家辰 2013 自动化学报 39 745]

    [13]

    Fu Z L 2011 J. Comput. Res. Dev. 48 2326 (in Chinese) [付忠良 2011 计算机研究与发展 48 2326]

    [14]

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

    [15]

    Ji Z 2003 Ph. D. Dissertation (Chongqing: Chongqing University) (in Chinese) [季忠 2003 博士学位论文 (重庆: 重庆大学)]

    [16]

    Ge Y Z, Xu M Y, Mi J C 2013 Acta Phys. Sin. 62 104701 (in Chinese) [戈阳祯, 徐敏义, 米建春 2013 物理学报 62 104701]

    [17]

    Gao Q, Yi S H, Jiang Z F, ZhaoY X, Xie W K 2012 Chin. Phys. B 21 064701

    [18]

    Wang D M, Wang L, Zhang G M 2012 J. Zhejiang Univ. (Eng. Sci.) 46 837 (in Chinese) [王德明, 王莉, 张广明 2012 浙江大学学报 (工学版) 46 837]

    [19]

    Wang X C, Shi F, Yu L, Li Y 2013 43 Cases of MATLAB Neural Network Analysis (Beijing: Beihang University Press) p1 (in Chinese) [王小川, 史峰, 郁磊, 李洋 2013 MATLAB神经网络 43 个案例分析 (北京: 北京航空航天出版社) 第1页]

  • [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]

    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]

    [3]

    Cai D M, Zhou W D, Li S F, Wang J W, Jia G J, Liu X W 2011 Acta Biophys. Sin. 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]

    [4]

    Pang C Y, Wang X T, Sun X L 2013 Chin. J. Biomed. Eng. 32 663 (in Chinese) [庞春颖, 王小甜, 孙晓琳 2013 中国生物医学工程学报 32 663]

    [5]

    Zhang Z, Du S H, Chen Z Y, Tian X H, Zhou Y, Zhang Y 2013 J. Biomed. Eng. Res. 32 74 (in Chinese) [张振, 杜守洪, 陈子怡, 田翔华, 周毅, 张洋 2013 生物医学工程研究 32 74]

    [6]

    Tibdewal M N, Manjunatha M, Ray A K, Malokar M 2013 1st IEEE-EMBS Special Topic Conference on Point-of-Care (POCT) Healthcare Technologies (PHT) Bangalore, India, January 16-18, 2013 p72

    [7]

    Sakkalis V, Giannakakis G, Farmaki C, Mousas A, Pediaditis M 2013 35th Annual International Conference of the IEEE EMBS Osaka, Japan, July 3-7, 2013 p6333

    [8]

    Fu Z L 2014 Acta Autom. Sin. 40 1075 (in Chinese) [付忠良 2014 自动化学报 40 1075]

    [9]

    Fu Z L 2013 J. Comput. Res. Dev. 50 861 (in Chinese) [付忠良 2013 计算机研究与发展 50 861]

    [10]

    Schapire R E, Singer Y 1999 11th Annual Conference on Computational Learning Theory Madison, Wisconsin, July 24-26, 1998 p297

    [11]

    Islam M M, Yao X, Murase K 2003 IEEE Trans. Neural Networks 14 820

    [12]

    Cao Y, Miao Q G, Liu J C 2013 Acta Autom. Sin. 39 745 (in Chinese) [曹莹, 苗启广, 刘家辰 2013 自动化学报 39 745]

    [13]

    Fu Z L 2011 J. Comput. Res. Dev. 48 2326 (in Chinese) [付忠良 2011 计算机研究与发展 48 2326]

    [14]

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

    [15]

    Ji Z 2003 Ph. D. Dissertation (Chongqing: Chongqing University) (in Chinese) [季忠 2003 博士学位论文 (重庆: 重庆大学)]

    [16]

    Ge Y Z, Xu M Y, Mi J C 2013 Acta Phys. Sin. 62 104701 (in Chinese) [戈阳祯, 徐敏义, 米建春 2013 物理学报 62 104701]

    [17]

    Gao Q, Yi S H, Jiang Z F, ZhaoY X, Xie W K 2012 Chin. Phys. B 21 064701

    [18]

    Wang D M, Wang L, Zhang G M 2012 J. Zhejiang Univ. (Eng. Sci.) 46 837 (in Chinese) [王德明, 王莉, 张广明 2012 浙江大学学报 (工学版) 46 837]

    [19]

    Wang X C, Shi F, Yu L, Li Y 2013 43 Cases of MATLAB Neural Network Analysis (Beijing: Beihang University Press) p1 (in Chinese) [王小川, 史峰, 郁磊, 李洋 2013 MATLAB神经网络 43 个案例分析 (北京: 北京航空航天出版社) 第1页]

计量
  • 文章访问数:  1984
  • PDF下载量:  231
  • 被引次数: 0
出版历程
  • 收稿日期:  2014-11-24
  • 修回日期:  2015-01-10
  • 刊出日期:  2015-06-05

基于AdaBoost算法的癫痫脑电信号识别

  • 1. 吉林大学通信工程学院, 长春 130012
    基金项目: 

    高等学校博士学科点专项科研基金(批准号:20100061110029)、吉林省科技发展计划重点项目(批准号:20090350)和吉林大学研究生创新研究计划(批准号:20121107)资助的课题.

摘要: AdaBoost算法作为Boosting算法的经典算法之一, 在人脸检测和目标跟踪等领域得到了广泛应用, 但该算法也有一个缺点-退化问题. 为了解决这个问题, 通过对弱分类器进行筛选、引入平滑因子和权值修正函数三个措施对算法进行优化, 并将优化后的算法与小波包分解相结合应用到癫痫脑电信号的识别上. 结果表明, 本文算法对癫痫脑电信号的识别率为96.11%, 对正常脑电信号的识别率为99.51%, 具有较高的识别率, 为癫痫的正确诊断提供了一种可能有效的解决方案.

English Abstract

参考文献 (19)

目录

    /

    返回文章
    返回