Stimuli and Feature Extraction Algorithms for Brain-Computer Interfaces
Autor: | Natasha M. Maurits, Mayra Bittencourt-Villalpando |
---|---|
Přispěvatelé: | Movement Disorder (MD), Basic and Translational Research and Imaging Methodology Development in Groningen (BRIDGE) |
Jazyk: | angličtina |
Rok vydání: | 2018 |
Předmět: |
Adult
Male Computer science Interface (computing) Speech recognition Biomedical Engineering Electroencephalography 050105 experimental psychology 03 medical and health sciences Communication Aids for Disabled Young Adult 0302 clinical medicine Evoked Potentials Somatosensory SSVEP-BASED BCIS Internal Medicine medicine Humans 0501 psychology and cognitive sciences P300 Brain–computer interface Graphical user interface medicine.diagnostic_test business.industry General Neuroscience 05 social sciences Rehabilitation Neurofeedback Event-Related Potentials P300 Healthy Volunteers Task (computing) Brain stimulation Brain-Computer Interfaces Task analysis Female business 030217 neurology & neurosurgery Algorithms Psychomotor Performance MENTAL PROSTHESIS |
Zdroj: | IEEE Transactions on Neural Systems and Rehabilitation Engineering, 26(9), 1669-1679. IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
ISSN: | 1534-4320 |
Popis: | A brain-computer interface (BCI) is a system that allows communication between the central nervous system and an external device. The BCIs developed by various research groups differ in their main features and the comparison across studies is therefore challenging. Here, in the same group of 19 healthy participants, we investigate three different tasks (SSVEP, P300 and hybrid) that allowed four choices to the user without previous neurofeedback training. We used the same 64-channel EEG equipment to acquire data while participantsperformed each of the tasks. We systematically compared the participants’ offline performance on the following parameters: a) accuracy, b) BCI Utility (in bits/min) and, c) inefficiency/illiteracy. Additionally, we evaluated the accuracy as a function of the number of electrodes. In our study, the SSVEP task outperformed the other tasks in bit rate, reaching an average and maximum BCI Utility of 63.4 bits/min and 91.3 bits/min, respectively. All participants achieved an accuracy level above 70% on both SSVEP and P300 tasks. Further, the average accuracy of all tasks was highest if a reduced subset with four to 12 electrodes was used. These results are relevant for the development of online BCIs intended for real-life applications. |
Databáze: | OpenAIRE |
Externí odkaz: |