Three-Class EEG-Based Motor Imagery Classification Using Phase-Space Reconstruction Technique
Over the last few decades, brain signals have been significantly exploited for brain-computer interface (BCI) applications. In this paper, we study the extraction of features using event-related desynchronization/synchronization techniques to improve the classification accuracy for three-class motor...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2016-08-01
|
| Series: | Brain Sciences |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2076-3425/6/3/36 |
| _version_ | 1819212560745889792 |
|---|---|
| author | Ridha Djemal Ayad G. Bazyed Kais Belwafi Sofien Gannouni Walid Kaaniche |
| author_facet | Ridha Djemal Ayad G. Bazyed Kais Belwafi Sofien Gannouni Walid Kaaniche |
| author_sort | Ridha Djemal |
| collection | DOAJ |
| description | Over the last few decades, brain signals have been significantly exploited for brain-computer interface (BCI) applications. In this paper, we study the extraction of features using event-related desynchronization/synchronization techniques to improve the classification accuracy for three-class motor imagery (MI) BCI. The classification approach is based on combining the features of the phase and amplitude of the brain signals using fast Fourier transform (FFT) and autoregressive (AR) modeling of the reconstructed phase space as well as the modification of the BCI parameters (trial length, trial frequency band, classification method). We report interesting results compared with those present in the literature by utilizing sequential forward floating selection (SFFS) and a multi-class linear discriminant analysis (LDA), our findings showed superior classification results, a classification accuracy of 86.06% and 93% for two BCI competition datasets, with respect to results from previous studies. |
| first_indexed | 2024-12-23T06:44:55Z |
| format | Article |
| id | doaj.art-4f6ea912a1cd425f8f8f96c43714a756 |
| institution | Directory Open Access Journal |
| issn | 2076-3425 |
| language | English |
| last_indexed | 2024-12-23T06:44:55Z |
| publishDate | 2016-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Brain Sciences |
| spelling | doaj.art-4f6ea912a1cd425f8f8f96c43714a7562022-12-21T17:56:35ZengMDPI AGBrain Sciences2076-34252016-08-01633610.3390/brainsci6030036brainsci6030036Three-Class EEG-Based Motor Imagery Classification Using Phase-Space Reconstruction TechniqueRidha Djemal0Ayad G. Bazyed1Kais Belwafi2Sofien Gannouni3Walid Kaaniche4EE Department, King Saud University, Riyadh 11421, Saudi ArabiaEE Department, King Saud University, Riyadh 11421, Saudi ArabiaCS Department, King Saud University, Riyadh 11421, Saudi ArabiaCS Department, King Saud University, Riyadh 11421, Saudi ArabiaElectrical Engineering Department, ENISo of Sousse, BP 264 Erriadh 4023, Sousse 4054, TunisiaOver the last few decades, brain signals have been significantly exploited for brain-computer interface (BCI) applications. In this paper, we study the extraction of features using event-related desynchronization/synchronization techniques to improve the classification accuracy for three-class motor imagery (MI) BCI. The classification approach is based on combining the features of the phase and amplitude of the brain signals using fast Fourier transform (FFT) and autoregressive (AR) modeling of the reconstructed phase space as well as the modification of the BCI parameters (trial length, trial frequency band, classification method). We report interesting results compared with those present in the literature by utilizing sequential forward floating selection (SFFS) and a multi-class linear discriminant analysis (LDA), our findings showed superior classification results, a classification accuracy of 86.06% and 93% for two BCI competition datasets, with respect to results from previous studies.http://www.mdpi.com/2076-3425/6/3/36brain-computer interface (BCI)motor imagery (MI)electroencephalogram EEG |
| spellingShingle | Ridha Djemal Ayad G. Bazyed Kais Belwafi Sofien Gannouni Walid Kaaniche Three-Class EEG-Based Motor Imagery Classification Using Phase-Space Reconstruction Technique Brain Sciences brain-computer interface (BCI) motor imagery (MI) electroencephalogram EEG |
| title | Three-Class EEG-Based Motor Imagery Classification Using Phase-Space Reconstruction Technique |
| title_full | Three-Class EEG-Based Motor Imagery Classification Using Phase-Space Reconstruction Technique |
| title_fullStr | Three-Class EEG-Based Motor Imagery Classification Using Phase-Space Reconstruction Technique |
| title_full_unstemmed | Three-Class EEG-Based Motor Imagery Classification Using Phase-Space Reconstruction Technique |
| title_short | Three-Class EEG-Based Motor Imagery Classification Using Phase-Space Reconstruction Technique |
| title_sort | three class eeg based motor imagery classification using phase space reconstruction technique |
| topic | brain-computer interface (BCI) motor imagery (MI) electroencephalogram EEG |
| url | http://www.mdpi.com/2076-3425/6/3/36 |
| work_keys_str_mv | AT ridhadjemal threeclasseegbasedmotorimageryclassificationusingphasespacereconstructiontechnique AT ayadgbazyed threeclasseegbasedmotorimageryclassificationusingphasespacereconstructiontechnique AT kaisbelwafi threeclasseegbasedmotorimageryclassificationusingphasespacereconstructiontechnique AT sofiengannouni threeclasseegbasedmotorimageryclassificationusingphasespacereconstructiontechnique AT walidkaaniche threeclasseegbasedmotorimageryclassificationusingphasespacereconstructiontechnique |