Optimizing Motor Imagery Parameters for Robotic Arm Control by Brain-Computer Interface
Brain-Computer Interface (BCI) technology has been shown to provide new communication possibilities, conveying brain information externally. BCI-based robot control has started to play an important role, especially in medically assistive robots but not only there. For example, a BCI-controlled robot...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Brain Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3425/12/7/833 |
| _version_ | 1797407240527806464 |
|---|---|
| author | Ünal Hayta Danut Constantin Irimia Christoph Guger İbrahim Erkutlu İbrahim Halil Güzelbey |
| author_facet | Ünal Hayta Danut Constantin Irimia Christoph Guger İbrahim Erkutlu İbrahim Halil Güzelbey |
| author_sort | Ünal Hayta |
| collection | DOAJ |
| description | Brain-Computer Interface (BCI) technology has been shown to provide new communication possibilities, conveying brain information externally. BCI-based robot control has started to play an important role, especially in medically assistive robots but not only there. For example, a BCI-controlled robotic arm can provide patients diagnosed with neurodegenerative diseases such as Locked-in syndrome (LIS), Amyotrophic lateral sclerosis (ALS), and others with the ability to manipulate different objects. This study presents the optimization of the configuration parameters of a three-class Motor Imagery (MI) -based BCI for controlling a six Degrees of Freedom (DOF) robotic arm in a plane. Electroencephalography (EEG) signals are recorded from 64 positions on the scalp according to the International 10-10 System. In terms of the resulting classification of error rates, we investigated twelve time windows for the spatial filter and classifier calculation and three time windows for the variance smoothing time. The lowest error rates were achieved when using a 3 s time window for creating the spatial filters and classifier, for a variance time window of 1.5 s. |
| first_indexed | 2024-03-09T03:38:47Z |
| format | Article |
| id | doaj.art-c7bd7a6b3c8743dabdf27263828d079b |
| institution | Directory Open Access Journal |
| issn | 2076-3425 |
| language | English |
| last_indexed | 2024-03-09T03:38:47Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Brain Sciences |
| spelling | doaj.art-c7bd7a6b3c8743dabdf27263828d079b2023-12-03T14:44:46ZengMDPI AGBrain Sciences2076-34252022-06-0112783310.3390/brainsci12070833Optimizing Motor Imagery Parameters for Robotic Arm Control by Brain-Computer InterfaceÜnal Hayta0Danut Constantin Irimia1Christoph Guger2İbrahim Erkutlu3İbrahim Halil Güzelbey4Pilotage Department, Faculty of Aeronautics and Aerospace, Gaziantep University, 27310 Gaziantep, TurkeyDepartment of Energy Utilization, Faculty of Electrical Engineering, Electrical Drives and Industrial Automation (EUEDIA), “Gheorghe Asachi” Technical University of Iasi, 700050 Iași, Romaniag.tec Medical Engineering GmbH, 4521 Schiedlberg, AustriaBrain and Nerve Surgery Clinic, Liv Hospital Gaziantep, 27080 Gaziantep, TurkeyFaculty of Aeronautics and Aerospace, Hasan Kalyoncu University, 27010 Gaziantep, TurkeyBrain-Computer Interface (BCI) technology has been shown to provide new communication possibilities, conveying brain information externally. BCI-based robot control has started to play an important role, especially in medically assistive robots but not only there. For example, a BCI-controlled robotic arm can provide patients diagnosed with neurodegenerative diseases such as Locked-in syndrome (LIS), Amyotrophic lateral sclerosis (ALS), and others with the ability to manipulate different objects. This study presents the optimization of the configuration parameters of a three-class Motor Imagery (MI) -based BCI for controlling a six Degrees of Freedom (DOF) robotic arm in a plane. Electroencephalography (EEG) signals are recorded from 64 positions on the scalp according to the International 10-10 System. In terms of the resulting classification of error rates, we investigated twelve time windows for the spatial filter and classifier calculation and three time windows for the variance smoothing time. The lowest error rates were achieved when using a 3 s time window for creating the spatial filters and classifier, for a variance time window of 1.5 s.https://www.mdpi.com/2076-3425/12/7/833Brain-Computer InterfaceEEGmotor imagerycommon spatial patterns (CSP)robot control |
| spellingShingle | Ünal Hayta Danut Constantin Irimia Christoph Guger İbrahim Erkutlu İbrahim Halil Güzelbey Optimizing Motor Imagery Parameters for Robotic Arm Control by Brain-Computer Interface Brain Sciences Brain-Computer Interface EEG motor imagery common spatial patterns (CSP) robot control |
| title | Optimizing Motor Imagery Parameters for Robotic Arm Control by Brain-Computer Interface |
| title_full | Optimizing Motor Imagery Parameters for Robotic Arm Control by Brain-Computer Interface |
| title_fullStr | Optimizing Motor Imagery Parameters for Robotic Arm Control by Brain-Computer Interface |
| title_full_unstemmed | Optimizing Motor Imagery Parameters for Robotic Arm Control by Brain-Computer Interface |
| title_short | Optimizing Motor Imagery Parameters for Robotic Arm Control by Brain-Computer Interface |
| title_sort | optimizing motor imagery parameters for robotic arm control by brain computer interface |
| topic | Brain-Computer Interface EEG motor imagery common spatial patterns (CSP) robot control |
| url | https://www.mdpi.com/2076-3425/12/7/833 |
| work_keys_str_mv | AT unalhayta optimizingmotorimageryparametersforroboticarmcontrolbybraincomputerinterface AT danutconstantinirimia optimizingmotorimageryparametersforroboticarmcontrolbybraincomputerinterface AT christophguger optimizingmotorimageryparametersforroboticarmcontrolbybraincomputerinterface AT ibrahimerkutlu optimizingmotorimageryparametersforroboticarmcontrolbybraincomputerinterface AT ibrahimhalilguzelbey optimizingmotorimageryparametersforroboticarmcontrolbybraincomputerinterface |