A robust sensor selection method for P300 Brain-Computer Interfaces

Hubert Cecotti, Bertrand Rivet, Marco Congedo, Christian Jutten, Olivier Bertrand, Emmanuel Maby, Jeremie Mattout

    Research output: Contribution to journalArticle

    65 Citations (Scopus)

    Abstract

    A brain–computer interface (BCI) is a specific type of human–computer interface that enables direct communication between human and computer through decoding of brain activity. As such, event-related potentials like the P300 can be obtained with an oddball paradigm whose targets are selected by the user. This paper deals with methods to reduce the needed set of EEG sensors in the P300 speller application. A reduced number of sensors yields more comfort for the user, decreases installation time duration, may substantially reduce the financial cost of the BCI setup and may reduce the power consumption for wireless EEG caps. Our new approach to select relevant sensors is based on backward elimination using a cost function based on the signal to signal-plus-noise ratio, after some spatial filtering. We show that this cost function selects sensors’ subsets that provide a better accuracy in the speller recognition rate during the test sessions than selected subsets based on classification accuracy. We validate our selection strategy on data from 20 healthy subjects.
    LanguageEnglish
    Pages1-12
    JournalJournal of Neural Engineering
    Volume8
    DOIs
    Publication statusPublished - 1 Dec 2011

    Fingerprint

    Brain computer interface
    Sensors
    Electroencephalography
    Cost functions
    Set theory
    Interfaces (computer)
    Decoding
    Brain
    Signal to noise ratio
    Electric power utilization
    Communication
    Costs

    Cite this

    Cecotti, H., Rivet, B., Congedo, M., Jutten, C., Bertrand, O., Maby, E., & Mattout, J. (2011). A robust sensor selection method for P300 Brain-Computer Interfaces. Journal of Neural Engineering, 8, 1-12. https://doi.org/10.1088/1741-2560/8/1/016001
    Cecotti, Hubert ; Rivet, Bertrand ; Congedo, Marco ; Jutten, Christian ; Bertrand, Olivier ; Maby, Emmanuel ; Mattout, Jeremie. / A robust sensor selection method for P300 Brain-Computer Interfaces. In: Journal of Neural Engineering. 2011 ; Vol. 8. pp. 1-12.
    @article{a71ced169a69408ca2948d2e2b3aada8,
    title = "A robust sensor selection method for P300 Brain-Computer Interfaces",
    abstract = "A brain–computer interface (BCI) is a specific type of human–computer interface that enables direct communication between human and computer through decoding of brain activity. As such, event-related potentials like the P300 can be obtained with an oddball paradigm whose targets are selected by the user. This paper deals with methods to reduce the needed set of EEG sensors in the P300 speller application. A reduced number of sensors yields more comfort for the user, decreases installation time duration, may substantially reduce the financial cost of the BCI setup and may reduce the power consumption for wireless EEG caps. Our new approach to select relevant sensors is based on backward elimination using a cost function based on the signal to signal-plus-noise ratio, after some spatial filtering. We show that this cost function selects sensors’ subsets that provide a better accuracy in the speller recognition rate during the test sessions than selected subsets based on classification accuracy. We validate our selection strategy on data from 20 healthy subjects.",
    author = "Hubert Cecotti and Bertrand Rivet and Marco Congedo and Christian Jutten and Olivier Bertrand and Emmanuel Maby and Jeremie Mattout",
    year = "2011",
    month = "12",
    day = "1",
    doi = "10.1088/1741-2560/8/1/016001",
    language = "English",
    volume = "8",
    pages = "1--12",
    journal = "Journal of Neural Engineering",
    issn = "1741-2560",

    }

    Cecotti, H, Rivet, B, Congedo, M, Jutten, C, Bertrand, O, Maby, E & Mattout, J 2011, 'A robust sensor selection method for P300 Brain-Computer Interfaces', Journal of Neural Engineering, vol. 8, pp. 1-12. https://doi.org/10.1088/1741-2560/8/1/016001

    A robust sensor selection method for P300 Brain-Computer Interfaces. / Cecotti, Hubert; Rivet, Bertrand; Congedo, Marco; Jutten, Christian; Bertrand, Olivier; Maby, Emmanuel; Mattout, Jeremie.

    In: Journal of Neural Engineering, Vol. 8, 01.12.2011, p. 1-12.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - A robust sensor selection method for P300 Brain-Computer Interfaces

    AU - Cecotti, Hubert

    AU - Rivet, Bertrand

    AU - Congedo, Marco

    AU - Jutten, Christian

    AU - Bertrand, Olivier

    AU - Maby, Emmanuel

    AU - Mattout, Jeremie

    PY - 2011/12/1

    Y1 - 2011/12/1

    N2 - A brain–computer interface (BCI) is a specific type of human–computer interface that enables direct communication between human and computer through decoding of brain activity. As such, event-related potentials like the P300 can be obtained with an oddball paradigm whose targets are selected by the user. This paper deals with methods to reduce the needed set of EEG sensors in the P300 speller application. A reduced number of sensors yields more comfort for the user, decreases installation time duration, may substantially reduce the financial cost of the BCI setup and may reduce the power consumption for wireless EEG caps. Our new approach to select relevant sensors is based on backward elimination using a cost function based on the signal to signal-plus-noise ratio, after some spatial filtering. We show that this cost function selects sensors’ subsets that provide a better accuracy in the speller recognition rate during the test sessions than selected subsets based on classification accuracy. We validate our selection strategy on data from 20 healthy subjects.

    AB - A brain–computer interface (BCI) is a specific type of human–computer interface that enables direct communication between human and computer through decoding of brain activity. As such, event-related potentials like the P300 can be obtained with an oddball paradigm whose targets are selected by the user. This paper deals with methods to reduce the needed set of EEG sensors in the P300 speller application. A reduced number of sensors yields more comfort for the user, decreases installation time duration, may substantially reduce the financial cost of the BCI setup and may reduce the power consumption for wireless EEG caps. Our new approach to select relevant sensors is based on backward elimination using a cost function based on the signal to signal-plus-noise ratio, after some spatial filtering. We show that this cost function selects sensors’ subsets that provide a better accuracy in the speller recognition rate during the test sessions than selected subsets based on classification accuracy. We validate our selection strategy on data from 20 healthy subjects.

    U2 - 10.1088/1741-2560/8/1/016001

    DO - 10.1088/1741-2560/8/1/016001

    M3 - Article

    VL - 8

    SP - 1

    EP - 12

    JO - Journal of Neural Engineering

    T2 - Journal of Neural Engineering

    JF - Journal of Neural Engineering

    SN - 1741-2560

    ER -