Scale-Dependent Signal Identification in Low-Dimensional Subspace: Motor Imagery Task Classification
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 int...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2016-01-01
|
| Series: | Neural Plasticity |
| Online Access: | http://dx.doi.org/10.1155/2016/7431012 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832563671289561088 |
|---|---|
| author | Qingshan She Haitao Gan Yuliang Ma Zhizeng Luo Tom Potter Yingchun Zhang |
| author_facet | Qingshan She Haitao Gan Yuliang Ma Zhizeng Luo Tom Potter Yingchun Zhang |
| author_sort | Qingshan She |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-ee56519de9b74233887b07c78fb40441 |
| institution | Kabale University |
| issn | 2090-5904 1687-5443 |
| language | English |
| publishDate | 2016-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Neural Plasticity |
| spelling | doaj-art-ee56519de9b74233887b07c78fb404412025-02-03T01:12:57ZengWileyNeural Plasticity2090-59041687-54432016-01-01201610.1155/2016/74310127431012Scale-Dependent Signal Identification in Low-Dimensional Subspace: Motor Imagery Task ClassificationQingshan She0Haitao Gan1Yuliang Ma2Zhizeng Luo3Tom Potter4Yingchun Zhang5Institute of Intelligent Control and Robotics, Hangzhou Dianzi University, Hangzhou, Zhejiang 310018, ChinaInstitute of Intelligent Control and Robotics, Hangzhou Dianzi University, Hangzhou, Zhejiang 310018, ChinaInstitute of Intelligent Control and Robotics, Hangzhou Dianzi University, Hangzhou, Zhejiang 310018, ChinaInstitute of Intelligent Control and Robotics, Hangzhou Dianzi University, Hangzhou, Zhejiang 310018, ChinaDepartment of Biomedical Engineering, University of Houston, Houston, TX 77204, USADepartment of Biomedical Engineering, University of Houston, Houston, TX 77204, USAMotor 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.http://dx.doi.org/10.1155/2016/7431012 |
| spellingShingle | Qingshan She Haitao Gan Yuliang Ma Zhizeng Luo Tom Potter Yingchun Zhang Scale-Dependent Signal Identification in Low-Dimensional Subspace: Motor Imagery Task Classification Neural Plasticity |
| title | Scale-Dependent Signal Identification in Low-Dimensional Subspace: Motor Imagery Task Classification |
| title_full | Scale-Dependent Signal Identification in Low-Dimensional Subspace: Motor Imagery Task Classification |
| title_fullStr | Scale-Dependent Signal Identification in Low-Dimensional Subspace: Motor Imagery Task Classification |
| title_full_unstemmed | Scale-Dependent Signal Identification in Low-Dimensional Subspace: Motor Imagery Task Classification |
| title_short | Scale-Dependent Signal Identification in Low-Dimensional Subspace: Motor Imagery Task Classification |
| title_sort | scale dependent signal identification in low dimensional subspace motor imagery task classification |
| url | http://dx.doi.org/10.1155/2016/7431012 |
| work_keys_str_mv | AT qingshanshe scaledependentsignalidentificationinlowdimensionalsubspacemotorimagerytaskclassification AT haitaogan scaledependentsignalidentificationinlowdimensionalsubspacemotorimagerytaskclassification AT yuliangma scaledependentsignalidentificationinlowdimensionalsubspacemotorimagerytaskclassification AT zhizengluo scaledependentsignalidentificationinlowdimensionalsubspacemotorimagerytaskclassification AT tompotter scaledependentsignalidentificationinlowdimensionalsubspacemotorimagerytaskclassification AT yingchunzhang scaledependentsignalidentificationinlowdimensionalsubspacemotorimagerytaskclassification |