Button Press Detection from EEG Signals Using Deep Learning

Standard

Button Press Detection from EEG Signals Using Deep Learning. / Kuzucu, Enes E.

Proceedings of the 2022 IEEE 23rd International Conference of Young Professionals in Electron Devices and Materials, EDM 2022. IEEE Computer Society, 2022. p. 538-542 (International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices, EDM; Vol. 2022-June).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review

Harvard

Kuzucu, EE 2022, Button Press Detection from EEG Signals Using Deep Learning. in Proceedings of the 2022 IEEE 23rd International Conference of Young Professionals in Electron Devices and Materials, EDM 2022. International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices, EDM, vol. 2022-June, IEEE Computer Society, pp. 538-542, 23rd IEEE International Conference of Young Professionals in Electron Devices and Materials, EDM 2022, Altai, Russian Federation, 30.06.2022. https://doi.org/10.1109/EDM55285.2022.9855191

APA

Kuzucu, E. E. (2022). Button Press Detection from EEG Signals Using Deep Learning. In Proceedings of the 2022 IEEE 23rd International Conference of Young Professionals in Electron Devices and Materials, EDM 2022 (pp. 538-542). (International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices, EDM; Vol. 2022-June). IEEE Computer Society. https://doi.org/10.1109/EDM55285.2022.9855191

Vancouver

Kuzucu EE. Button Press Detection from EEG Signals Using Deep Learning. In Proceedings of the 2022 IEEE 23rd International Conference of Young Professionals in Electron Devices and Materials, EDM 2022. IEEE Computer Society. 2022. p. 538-542. (International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices, EDM). doi: 10.1109/EDM55285.2022.9855191

Author

Kuzucu, Enes E. / Button Press Detection from EEG Signals Using Deep Learning. Proceedings of the 2022 IEEE 23rd International Conference of Young Professionals in Electron Devices and Materials, EDM 2022. IEEE Computer Society, 2022. pp. 538-542 (International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices, EDM).

BibTeX

@inproceedings{394941ff0c254d8bb84b92b5d391d991,

title = "Button Press Detection from EEG Signals Using Deep Learning",

abstract = "Electroencephalogram (EEG) signals are mainly used for neuroscience studies and for brain-computer interface applications with a rising trend. Majority of studies include conducting experiments with different paradigms, and studying the results of experiments for scientific discoveries or various practical applications. It is likely that in the near future, all EEG related scientific discoveries will combine into one comprehensive automated EEG analysis framework where different paradigms can be analyzed in terms of detection of events, markers and signals of interest. In this study we created an application which estimates time of button press actions from stop-signal paradigm EEG recordings, using deep learning methods. Current results indicate that the proposed solution has low intra-subject and inter-subject variability and the work can be further investigated with different applications as well as different paradigms. We are hoping that this work will be the first step to a complete paradigm analysis framework, which aims to automatically extract experiment related information from single-trial EEG signals and facilitates the overall research and analysis process as well being used as a part of various brain-computer interface applications. ",

keywords = "button press detection, convolutional neural networks, deep learning, EEG, stop-signal",

author = "Kuzucu, {Enes E.}",

note = "Funding Information: ACKNOWLEDGMENT Financial support: The EEG data collection was supported by grant № 22-15-00142 of Russian Science Foundation. Publisher Copyright: {\textcopyright} 2022 IEEE.; 23rd IEEE International Conference of Young Professionals in Electron Devices and Materials, EDM 2022 ; Conference date: 30-06-2022 Through 04-07-2022",

year = "2022",

doi = "10.1109/EDM55285.2022.9855191",

language = "English",

isbn = "9781665498043",

series = "International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices, EDM",

publisher = "IEEE Computer Society",

pages = "538--542",

booktitle = "Proceedings of the 2022 IEEE 23rd International Conference of Young Professionals in Electron Devices and Materials, EDM 2022",

address = "United States",

}

RIS

TY - GEN

T1 - Button Press Detection from EEG Signals Using Deep Learning

AU - Kuzucu, Enes E.

PY - 2022

Y1 - 2022

N2 - Electroencephalogram (EEG) signals are mainly used for neuroscience studies and for brain-computer interface applications with a rising trend. Majority of studies include conducting experiments with different paradigms, and studying the results of experiments for scientific discoveries or various practical applications. It is likely that in the near future, all EEG related scientific discoveries will combine into one comprehensive automated EEG analysis framework where different paradigms can be analyzed in terms of detection of events, markers and signals of interest. In this study we created an application which estimates time of button press actions from stop-signal paradigm EEG recordings, using deep learning methods. Current results indicate that the proposed solution has low intra-subject and inter-subject variability and the work can be further investigated with different applications as well as different paradigms. We are hoping that this work will be the first step to a complete paradigm analysis framework, which aims to automatically extract experiment related information from single-trial EEG signals and facilitates the overall research and analysis process as well being used as a part of various brain-computer interface applications.

AB - Electroencephalogram (EEG) signals are mainly used for neuroscience studies and for brain-computer interface applications with a rising trend. Majority of studies include conducting experiments with different paradigms, and studying the results of experiments for scientific discoveries or various practical applications. It is likely that in the near future, all EEG related scientific discoveries will combine into one comprehensive automated EEG analysis framework where different paradigms can be analyzed in terms of detection of events, markers and signals of interest. In this study we created an application which estimates time of button press actions from stop-signal paradigm EEG recordings, using deep learning methods. Current results indicate that the proposed solution has low intra-subject and inter-subject variability and the work can be further investigated with different applications as well as different paradigms. We are hoping that this work will be the first step to a complete paradigm analysis framework, which aims to automatically extract experiment related information from single-trial EEG signals and facilitates the overall research and analysis process as well being used as a part of various brain-computer interface applications.

KW - button press detection

KW - convolutional neural networks

KW - deep learning

KW - EEG

KW - stop-signal

UR - http://www.scopus.com/inward/record.url?scp=85137320878&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/798eb59a-3ae7-3f61-a9b6-36a150b8b3db/

U2 - 10.1109/EDM55285.2022.9855191

DO - 10.1109/EDM55285.2022.9855191

M3 - Conference contribution

AN - SCOPUS:85137320878

SN - 9781665498043

T3 - International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices, EDM

SP - 538

EP - 542

BT - Proceedings of the 2022 IEEE 23rd International Conference of Young Professionals in Electron Devices and Materials, EDM 2022

PB - IEEE Computer Society

T2 - 23rd IEEE International Conference of Young Professionals in Electron Devices and Materials, EDM 2022

Y2 - 30 June 2022 through 4 July 2022

ER -

ID: 37142094