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

基于自适应无参经验小波变换和选择集成分类模型的运动想象

何群 王煜文 杜硕 陈晓玲 谢平

引用本文:
Citation:

基于自适应无参经验小波变换和选择集成分类模型的运动想象

何群, 王煜文, 杜硕, 陈晓玲, 谢平

Motor imagery based on adaptive parameterless empirical wavelet transform and selective integrated classification

He Qun, Wang Yu-Wen, Du Shuo, Chen Xiao-Ling, Xie Ping
PDF
导出引用
  • 运动想象模式识别率的提高对脑机接口(BCI)技术的应用具有重要意义,本文采用自适应无参经验小波变换(APEWT)和选择集成分类模型相结合的方法提高脑电(EEG)信号的分类识别准确率.首先,通过APEWT将EEG信号分解成不同的模态;然后,使用最优模态重构后的信号计算其能量谱(ES)特征,使用最优模态分量计算其边际谱(MS)特征;最后,将不同时间段的ES特征和不同频段的MS特征输入到构建的选择集成分类模型中,从而得到其分类结果,并将该方法与其他4种组合方法进行比较.实验结果表明,本文方法具有较好分类准确率和实时性,其平均分类正确率高于其他4种方法,同时较近期使用相同数据的文献也有优势.本文为在线运动想象类BCI的应用提供了新的方法和思路.
    Improving recognition rate of motor imagery (MI)-related electroencephalography (EEG) is of great importance for numerous brain computer interface (BCI) applications. However, the performance of a typical BCI system greatly relies on the effectiveness of the extracted features from raw EEG signals and the ability of the classifier to correctly identify different MI patterns. Therefore, in this paper, a new recognition method based on adaptive parameterless empirical wavelet transform (APEWT) and selective integrated classification model is proposed to enhance the classification accuracy of MI-related EEG signal. First, the APEWT is used to decompose EEG signals from different MI patterns into several intrinsic mode functions (IMFs), each of which contains different rhythm information over different frequency bands. Then several related modes are optimally selected based on the correlation coefficients calculated between each IMF component and the original signal to reconstruct EEG signals. Next, in order to further extract useful pattern information from both the time domain and frequency domain, the energy spectrum features of multiple time segments from the reconstructed signals and marginal spectrum features of different frequency bands corresponding to those selected modes are investigated, respectively. Finally, the extracted multiple features from time domain and frequency domain are input into the selective integrated classification model to build an MI recognition system. The selective integrated classification model consists of several extreme learning machines (ELMs) as the basic classifiers, different weights are assigned, respectively, to ELM basic classifiers based on their corresponding classification performances, and several basic ELM classifiers with good performances are selected to construct the final integrated model. The proposed method is evaluated on two public datasets, including BCI Competition Ⅱ dataset Ⅲ and BCI Competition IV dataset 2 b, and is compared with four different combination methods where different features in time domain or frequency domain in the feature extraction stage and different ELMs based classification models are considered. Experimental results demonstrate that the proposed method outperformed four combination methods and the existing methods recently reported in the literature using the same datasets in terms of classification accuracy and area under the ROC curve receiver operating characteristic metric. Specifically, our proposed method achieves the highest average classification accuracy (89.95%) in the compared methods, which indicates its better classification performance and generalization capability. In addition, the proposed method exhibits high computational efficiency, thus providing a new solution for online recognition of MI-related BCI and having the potential to be embedded in a practical system for controlling an external device.
      通信作者: 谢平, pingx@ysu.edu.cn
    • 基金项目: 国家自然科学基金(批准号:61673336)和河北省自然科学基金(批准号:F2015203372)资助的课题.
      Corresponding author: Xie Ping, pingx@ysu.edu.cn
    • Funds: Project supported by the National Natural Science Foundation of China (Grant No. 61673336) and the Natural Science Foundation of Hebei Province, China (Grant No. F2015203372).
    [1]

    Zhang D, Li J W 2017 Sci. Technol. Rev. 35 62(in Chinese) [张丹, 李佳蔚 2017 科技导报 35 62]

    [2]

    Gao S, Wang Y, Gao X, Hong B 2014 Trans. Biomed. Eng. 61 1436

    [3]

    Abdulkader S N, Atia A, Mostafa M S M 2015 Egy. Inf. J. 16 213

    [4]

    Fang X L, Jiang Z L 2007 Acta Phys. Sin. 56 7330(in Chinese) [方小玲, 姜宗来 2007 物理学报 56 7330]

    [5]

    Pfurtscheller G, da Silva F H L 1999 Cli. Neurophysiol. 110 1842

    [6]

    Lei M, Meng G, Zhang W M, Nilanjan S 2016 Acta Phys. Sin. 65 108701(in Chinese) [雷敏, 孟光, 张文明, Nilanjan Sarkar 2016 物理学报 65 108701]

    [7]

    Lei M, Meng G, Zhang W M, Joshua W, Nilanjan S 2016 Entropy 18 412

    [8]

    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]

    [9]

    Xu B, Song A 2008 J. Biomed. Sci. Eng. 1 64

    [10]

    Sun H W, Fu Y F, Xiong X, Yang J, Liu C W, Yu Z T 2015 Acta Automatica Sin. 41 1686(in Chinese) [孙会文, 伏云发, 熊馨, 杨俊, 刘传伟, 余正涛 2015 自动化学报 41 1686]

    [11]

    Xie P, Chen X L, Su Y P, Liang Z H, Li X L 2013 Chin. J. Biomed. Eng. 32 641(in Chinese) [谢平, 陈晓玲, 苏玉萍, 梁振虎, 李小俚 2013 中国生物医学工程学报 32 641]

    [12]

    Yang M H, Chen W Z, Li M Y 2017 Acta Automatica Sin. 43 743(in Chinese) [杨默涵, 陈万忠, 李明阳 2017 自动化学报 43 743]

    [13]

    Wu L Y, Lu H, Gao N, Wang T 2017 Chin. J. Biomed. Eng. 36 224(in Chinese) [吴林彦, 鲁昊, 高诺, 王涛 2017 生物医学工程研究 36 224]

    [14]

    Zhang X Q, Liang J 2013 Acta Phys. Sin. 62 050505(in Chinese) [张学清, 梁军 2013 物理学报 62 050505]

    [15]

    Tang Z C, Sun S Q, Zhang K J 2017 Chin. J. Mech. Eng. 53 60(in Chinese) [唐智川, 孙守迁, 张克俊 2017 机械工程学报 53 60]

    [16]

    Gilles J 2013 IEEE Trans. Signal Proc. 61 3999

    [17]

    Gilles J, Heal K 2014 Multiresol. Inf. Proces 12 1450044

    [18]

    Zheng J, Pan H, Yang S, Cheng J 2017 Signal. Proces 130 305

    [19]

    Hou B W 2012 M. S. Dissertation (Xi'an: Xidian University) (in Chinese) 侯秉文 2012 硕士学位论文 (西安: 西安电子科技大学)

    [20]

    Zhao Y, Chen R, Liu W 2016 Comput. Sci. 8 177(in Chinese) [赵宇, 陈锐, 刘蔚 2016计算机科学 8 177]

    [21]

    Lindeberg T, ter Haar R B M 1994 Linear Scale-Space I: Basic Theory (Netherlands: Springer) pp1-38

    [22]

    Cai Y P, Li A H, Wang T, Yao L, Xu P 2010 J. Vibra. Eng. 4 430(in Chinese) [蔡艳平, 李艾华, 王涛, 姚良, 许平 2010 振动工程学报 4 430]

    [23]

    Huang G B, Zhu Q Y, Siew C K 2004 IEEE International Joint Conference on Neural Networks Proceedings Budapest, Hungary, July 25-29, 2004 p985

    [24]

    Huang G B, Zhu Q Y, Siew C K 2006 Neurocomput 70 489

    [25]

    Bentlemsan M, Zemouri E T T, Bouchaffra D, Yahya-Zoubir, B, Ferroudji, K 2014 5th International Conference on Intelligent Systems, Modelling and Simulation, Langkawi, Malaysia, Jan. 27-29, 2014 p235

    [26]

    Suk H I, Lee S W 2013 Trans. Patt. Anal. Mach. Intelli 35 286

  • [1]

    Zhang D, Li J W 2017 Sci. Technol. Rev. 35 62(in Chinese) [张丹, 李佳蔚 2017 科技导报 35 62]

    [2]

    Gao S, Wang Y, Gao X, Hong B 2014 Trans. Biomed. Eng. 61 1436

    [3]

    Abdulkader S N, Atia A, Mostafa M S M 2015 Egy. Inf. J. 16 213

    [4]

    Fang X L, Jiang Z L 2007 Acta Phys. Sin. 56 7330(in Chinese) [方小玲, 姜宗来 2007 物理学报 56 7330]

    [5]

    Pfurtscheller G, da Silva F H L 1999 Cli. Neurophysiol. 110 1842

    [6]

    Lei M, Meng G, Zhang W M, Nilanjan S 2016 Acta Phys. Sin. 65 108701(in Chinese) [雷敏, 孟光, 张文明, Nilanjan Sarkar 2016 物理学报 65 108701]

    [7]

    Lei M, Meng G, Zhang W M, Joshua W, Nilanjan S 2016 Entropy 18 412

    [8]

    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]

    [9]

    Xu B, Song A 2008 J. Biomed. Sci. Eng. 1 64

    [10]

    Sun H W, Fu Y F, Xiong X, Yang J, Liu C W, Yu Z T 2015 Acta Automatica Sin. 41 1686(in Chinese) [孙会文, 伏云发, 熊馨, 杨俊, 刘传伟, 余正涛 2015 自动化学报 41 1686]

    [11]

    Xie P, Chen X L, Su Y P, Liang Z H, Li X L 2013 Chin. J. Biomed. Eng. 32 641(in Chinese) [谢平, 陈晓玲, 苏玉萍, 梁振虎, 李小俚 2013 中国生物医学工程学报 32 641]

    [12]

    Yang M H, Chen W Z, Li M Y 2017 Acta Automatica Sin. 43 743(in Chinese) [杨默涵, 陈万忠, 李明阳 2017 自动化学报 43 743]

    [13]

    Wu L Y, Lu H, Gao N, Wang T 2017 Chin. J. Biomed. Eng. 36 224(in Chinese) [吴林彦, 鲁昊, 高诺, 王涛 2017 生物医学工程研究 36 224]

    [14]

    Zhang X Q, Liang J 2013 Acta Phys. Sin. 62 050505(in Chinese) [张学清, 梁军 2013 物理学报 62 050505]

    [15]

    Tang Z C, Sun S Q, Zhang K J 2017 Chin. J. Mech. Eng. 53 60(in Chinese) [唐智川, 孙守迁, 张克俊 2017 机械工程学报 53 60]

    [16]

    Gilles J 2013 IEEE Trans. Signal Proc. 61 3999

    [17]

    Gilles J, Heal K 2014 Multiresol. Inf. Proces 12 1450044

    [18]

    Zheng J, Pan H, Yang S, Cheng J 2017 Signal. Proces 130 305

    [19]

    Hou B W 2012 M. S. Dissertation (Xi'an: Xidian University) (in Chinese) 侯秉文 2012 硕士学位论文 (西安: 西安电子科技大学)

    [20]

    Zhao Y, Chen R, Liu W 2016 Comput. Sci. 8 177(in Chinese) [赵宇, 陈锐, 刘蔚 2016计算机科学 8 177]

    [21]

    Lindeberg T, ter Haar R B M 1994 Linear Scale-Space I: Basic Theory (Netherlands: Springer) pp1-38

    [22]

    Cai Y P, Li A H, Wang T, Yao L, Xu P 2010 J. Vibra. Eng. 4 430(in Chinese) [蔡艳平, 李艾华, 王涛, 姚良, 许平 2010 振动工程学报 4 430]

    [23]

    Huang G B, Zhu Q Y, Siew C K 2004 IEEE International Joint Conference on Neural Networks Proceedings Budapest, Hungary, July 25-29, 2004 p985

    [24]

    Huang G B, Zhu Q Y, Siew C K 2006 Neurocomput 70 489

    [25]

    Bentlemsan M, Zemouri E T T, Bouchaffra D, Yahya-Zoubir, B, Ferroudji, K 2014 5th International Conference on Intelligent Systems, Modelling and Simulation, Langkawi, Malaysia, Jan. 27-29, 2014 p235

    [26]

    Suk H I, Lee S W 2013 Trans. Patt. Anal. Mach. Intelli 35 286

  • [1] 巴图巴雅尔·欧赟, 赵跃进, 孔令琴, 董立泉, 刘明, 惠梅. 头部旋转运动下自适应非接触鲁棒性心率检测方法. 物理学报, 2022, 71(5): 058704. doi: 10.7498/aps.71.20211634
    [2] 景鹏, 张学军, 孙知信. 基于弹性变分模态分解的癫痫脑电信号分类方法. 物理学报, 2021, 70(1): 018702. doi: 10.7498/aps.70.20200904
    [3] 巴图巴雅尔·欧赟, 赵跃进, 孔令琴. 头部旋转运动下自适应非接触鲁棒性心率检测方法. 物理学报, 2021, (): . doi: 10.7498/aps.70.20211634
    [4] 汪祥莉, 王斌, 王文波, 喻敏. 混沌背景下非平稳谐波信号的自适应同步挤压小波变换提取. 物理学报, 2016, 65(20): 200202. doi: 10.7498/aps.65.200202
    [5] 张涛, 陈万忠, 李明阳. 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. 物理学报, 2016, 65(3): 038703. doi: 10.7498/aps.65.038703
    [6] 王莹, 侯凤贞, 戴加飞, 刘新峰, 李锦, 王俊. 基于自适应模板法的脑电信号转移熵分析. 物理学报, 2015, 64(8): 088701. doi: 10.7498/aps.64.088701
    [7] 赵益波, 张秀再, 孙心宇. 基于Weiner模型超混沌l系统的自适应辨识. 物理学报, 2014, 63(13): 130503. doi: 10.7498/aps.63.130503
    [8] 孟庆芳, 陈月辉, 冯志全, 王枫林, 陈珊珊. 基于局域相关向量机回归模型的小尺度网络流量的非线性预测. 物理学报, 2013, 62(15): 150509. doi: 10.7498/aps.62.150509
    [9] 王跃钢, 文超斌, 杨家胜, 左朝阳, 崔祥祥. 基于无模型方法的混沌系统自适应控制. 物理学报, 2013, 62(10): 100504. doi: 10.7498/aps.62.100504
    [10] 余海军, 杜建明, 张秀兰. 相干态的小波变换. 物理学报, 2012, 61(16): 164205. doi: 10.7498/aps.61.164205
    [11] 高国荣, 刘艳萍, 潘琼. 基于小波域可导阈值函数与自适应阈值的脉冲星信号消噪. 物理学报, 2012, 61(13): 139701. doi: 10.7498/aps.61.139701
    [12] 缪志强, 王耀南. 基于径向小波神经网络的混沌系统鲁棒自适应反演控制. 物理学报, 2012, 61(3): 030503. doi: 10.7498/aps.61.030503
    [13] 韦笃取, 张波. 基于无源性理论自适应镇定具有v/f输入的永磁同步电动机的混沌运动. 物理学报, 2012, 61(3): 030505. doi: 10.7498/aps.61.030505
    [14] 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
    [15] 郑刚, 邹见效, 徐红兵, 秦钢. 直驱型永磁同步风力发电机组中混沌运动的反步自适应控制. 物理学报, 2011, 60(6): 060506. doi: 10.7498/aps.60.060506
    [16] 韦笃取, 张波, 丘东元, 罗晓曙. 基于LaSalle不变集定理自适应控制永磁同步电动机的混沌运动. 物理学报, 2009, 58(9): 6026-6029. doi: 10.7498/aps.58.6026
    [17] 王 凯, 张 会, 常胜江, 申金媛. 用于复杂光谱数据压缩的自适应小波算法. 物理学报, 2007, 56(6): 3613-3618. doi: 10.7498/aps.56.3613
    [18] 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
    [19] 卞保民, 杨 玲, 张 平, 纪运景, 李振华, 倪晓武. 理想气体球面强冲击波一般自模拟运动模型. 物理学报, 2006, 55(8): 4181-4187. doi: 10.7498/aps.55.4181
    [20] 张宗燧. 李模型中极点的运动. 物理学报, 1965, 21(11): 1882-1888. doi: 10.7498/aps.21.1882
计量
  • 文章访问数:  5170
  • PDF下载量:  217
  • 被引次数: 0
出版历程
  • 收稿日期:  2018-01-25
  • 修回日期:  2018-03-13
  • 刊出日期:  2018-06-05

/

返回文章
返回