Scale-Dependent Signal Identification in Low-Dimensional Subspace: Motor Imagery Task Classification.
Scale-Dependent Signal Identification in Low-Dimensional Subspace: Motor Imagery Task Classification.
复制标题
低维子空间运动想象任务分类中的尺度相关信号识别
DOI：
10.1155/2016/7431012
复制
发表时间：
2016
影响因子：
3.1
通讯作者：
Zhang Y
中科院分区：
文献类型：
--
作者：
She Q;Gan H;Ma Y;Luo Z;Potter T;Zhang Y
运动想象脑电图（EEG）已成功地用于运动康复计划。虽然噪声辅助多变量经验模式分解（NA-MEMD）算法已被用于从所有通道中提取与固有模式函数（IMF）相同尺度的任务特定频带，但识别和提取包含重要信息的特定IMF仍然很困难。本文提出了一种新的方法，在没有先验知识的情况下，在低维子空间中识别信息承载组件。我们的方法训练的高斯混合模型（GMM）的复合数据，这是由IMF从原始信号和噪声，通过采用核谱回归，以减少复合数据的维数。然后使用GMM聚类算法区分信息IMF，利用公共空间模式（CSP）方法从重构信号中提取与任务相关的特征，并将支持向量机（SVM）应用于提取的特征以识别不同运动想象任务期间的EEG信号的类别。所提出的方法的有效性已被计算机仿真和运动想象EEG数据集验证。
Motor imagery electroencephalography (EEG) has been successfully used in locomotor rehabilitation programs. While the noise-assisted multivariate empirical mode decomposition (NA-MEMD) algorithm has been utilized to extract task-specific frequency bands from all channels in the same scale as the intrinsic mode functions (IMFs), identifying and extracting the specific IMFs that contain significant information remain difficult. In this paper, a novel method has been developed to identify the information-bearing components in a low-dimensional subspace without prior knowledge. Our method trains a Gaussian mixture model (GMM) of the composite data, which is comprised of the IMFs from both the original signal and noise, by employing kernel spectral regression to reduce the dimension of the composite data. The informative IMFs are then discriminated using a GMM clustering algorithm, the common spatial pattern (CSP) approach is exploited to extract the task-related features from the reconstructed signals, and a support vector machine (SVM) is applied to the extracted features to recognize the classes of EEG signals during different motor imagery tasks. The effectiveness of the proposed method has been verified by both computer simulations and motor imagery EEG datasets.
登录
查看更多内容
影响因子：
3.1
作者：
Faralli A;Bigoni M;Mauro A;Rossi F;Carulli D
通讯作者：
Carulli D
影响因子：
5.7
作者：
Pfurtscheller, G.;Brunner, C.;da Silva, F. H. Lopes
通讯作者：
da Silva, F. H. Lopes
DOI：
10.1109/tim.2013.2275243
发表时间：
2014-01-01
影响因子：
5.6
作者：
Komaty, Ali;Boudraa, Abdel-Ouahab;Dare-Emzivat, Delphine
通讯作者：
Dare-Emzivat, Delphine
影响因子：
4
作者：
Jrad, N.;Congedo, M.;Rakotomamonjy, A.
通讯作者：
Rakotomamonjy, A.
影响因子：
2.6
作者：
Maria Alonso-Valerdi, Luz;Antonio Salido-Ruiz, Ricardo;Ramirez-Mendoza, Ricardo A.
通讯作者：
Ramirez-Mendoza, Ricardo A.