Improving Motor Imagery EEG Classification Based on Channel Selection Using a Deep Learning Architecture
Recently, motor imagery EEG signals have been widely applied in Brain–Computer Interfaces (BCI). These signals are typically observed in the first motor cortex of the brain, resulting from the imagination of body limb movements. For non-invasive BCI systems, it is not apparent how to locate the elec...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/13/2302 |
| _version_ | 1797408679788544000 |
|---|---|
| author | Tat’y Mwata-Velu Juan Gabriel Avina-Cervantes Jose Ruiz-Pinales Tomas Alberto Garcia-Calva Erick-Alejandro González-Barbosa Juan B. Hurtado-Ramos José-Joel González-Barbosa |
| author_facet | Tat’y Mwata-Velu Juan Gabriel Avina-Cervantes Jose Ruiz-Pinales Tomas Alberto Garcia-Calva Erick-Alejandro González-Barbosa Juan B. Hurtado-Ramos José-Joel González-Barbosa |
| author_sort | Tat’y Mwata-Velu |
| collection | DOAJ |
| description | Recently, motor imagery EEG signals have been widely applied in Brain–Computer Interfaces (BCI). These signals are typically observed in the first motor cortex of the brain, resulting from the imagination of body limb movements. For non-invasive BCI systems, it is not apparent how to locate the electrodes, optimizing the accuracy for a given task. This study proposes a comparative analysis of channel signals exploiting the Deep Learning (DL) technique and a public dataset to locate the most discriminant channels. EEG channels are usually selected based on the function and nomenclature of electrode location from international standards. Instead, the most suitable configuration for a given paradigm must be determined by analyzing the proper selection of the channels. Therefore, an EEGNet network was implemented to classify signals from different channel location using the accuracy metric. Achieved results were then contrasted with results from the state-of-the-art. As a result, the proposed method improved BCI classification accuracy. |
| first_indexed | 2024-03-09T04:01:58Z |
| format | Article |
| id | doaj.art-e3cf58480e804d64abf115214ffad973 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T04:01:58Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-e3cf58480e804d64abf115214ffad9732023-12-03T14:12:18ZengMDPI AGMathematics2227-73902022-07-011013230210.3390/math10132302Improving Motor Imagery EEG Classification Based on Channel Selection Using a Deep Learning ArchitectureTat’y Mwata-Velu0Juan Gabriel Avina-Cervantes1Jose Ruiz-Pinales2Tomas Alberto Garcia-Calva3Erick-Alejandro González-Barbosa4Juan B. Hurtado-Ramos5José-Joel González-Barbosa6Telematics and Digital Signal Processing Research Groups (CAs), Electronics Engineering Department, University of Guanajuato, Carr. Salamanca-Valle de Santiago km 3.5 + 1.8, Com. Palo Blanco, Salamanca 36885, MexicoTelematics and Digital Signal Processing Research Groups (CAs), Electronics Engineering Department, University of Guanajuato, Carr. Salamanca-Valle de Santiago km 3.5 + 1.8, Com. Palo Blanco, Salamanca 36885, MexicoTelematics and Digital Signal Processing Research Groups (CAs), Electronics Engineering Department, University of Guanajuato, Carr. Salamanca-Valle de Santiago km 3.5 + 1.8, Com. Palo Blanco, Salamanca 36885, MexicoTelematics and Digital Signal Processing Research Groups (CAs), Electronics Engineering Department, University of Guanajuato, Carr. Salamanca-Valle de Santiago km 3.5 + 1.8, Com. Palo Blanco, Salamanca 36885, MexicoTecnológico Nacional de México/ITS de Irapuato, Carretera Irapuato—Silao km 12.5 Colonia El Copal, Irapuato 36821, MexicoInstituto Politécnico Nacional, Centro de Investigación en Ciencia Aplicada y Tecnología Avanzada—Unidad Querétaro, Av. Cerro Blanco 141, Col. Colinas del Cimatario, Querétaro 76090, MexicoInstituto Politécnico Nacional, Centro de Investigación en Ciencia Aplicada y Tecnología Avanzada—Unidad Querétaro, Av. Cerro Blanco 141, Col. Colinas del Cimatario, Querétaro 76090, MexicoRecently, motor imagery EEG signals have been widely applied in Brain–Computer Interfaces (BCI). These signals are typically observed in the first motor cortex of the brain, resulting from the imagination of body limb movements. For non-invasive BCI systems, it is not apparent how to locate the electrodes, optimizing the accuracy for a given task. This study proposes a comparative analysis of channel signals exploiting the Deep Learning (DL) technique and a public dataset to locate the most discriminant channels. EEG channels are usually selected based on the function and nomenclature of electrode location from international standards. Instead, the most suitable configuration for a given paradigm must be determined by analyzing the proper selection of the channels. Therefore, an EEGNet network was implemented to classify signals from different channel location using the accuracy metric. Achieved results were then contrasted with results from the state-of-the-art. As a result, the proposed method improved BCI classification accuracy.https://www.mdpi.com/2227-7390/10/13/2302motor imageryEEG signalsdeep learningEEGNet10–20 international system |
| spellingShingle | Tat’y Mwata-Velu Juan Gabriel Avina-Cervantes Jose Ruiz-Pinales Tomas Alberto Garcia-Calva Erick-Alejandro González-Barbosa Juan B. Hurtado-Ramos José-Joel González-Barbosa Improving Motor Imagery EEG Classification Based on Channel Selection Using a Deep Learning Architecture Mathematics motor imagery EEG signals deep learning EEGNet 10–20 international system |
| title | Improving Motor Imagery EEG Classification Based on Channel Selection Using a Deep Learning Architecture |
| title_full | Improving Motor Imagery EEG Classification Based on Channel Selection Using a Deep Learning Architecture |
| title_fullStr | Improving Motor Imagery EEG Classification Based on Channel Selection Using a Deep Learning Architecture |
| title_full_unstemmed | Improving Motor Imagery EEG Classification Based on Channel Selection Using a Deep Learning Architecture |
| title_short | Improving Motor Imagery EEG Classification Based on Channel Selection Using a Deep Learning Architecture |
| title_sort | improving motor imagery eeg classification based on channel selection using a deep learning architecture |
| topic | motor imagery EEG signals deep learning EEGNet 10–20 international system |
| url | https://www.mdpi.com/2227-7390/10/13/2302 |
| work_keys_str_mv | AT tatymwatavelu improvingmotorimageryeegclassificationbasedonchannelselectionusingadeeplearningarchitecture AT juangabrielavinacervantes improvingmotorimageryeegclassificationbasedonchannelselectionusingadeeplearningarchitecture AT joseruizpinales improvingmotorimageryeegclassificationbasedonchannelselectionusingadeeplearningarchitecture AT tomasalbertogarciacalva improvingmotorimageryeegclassificationbasedonchannelselectionusingadeeplearningarchitecture AT erickalejandrogonzalezbarbosa improvingmotorimageryeegclassificationbasedonchannelselectionusingadeeplearningarchitecture AT juanbhurtadoramos improvingmotorimageryeegclassificationbasedonchannelselectionusingadeeplearningarchitecture AT josejoelgonzalezbarbosa improvingmotorimageryeegclassificationbasedonchannelselectionusingadeeplearningarchitecture |