A Self-Paced and Calibration-Less SSVEP-Based Brain–Computer Interface Speller

Hubert Cecotti

    Research output: Contribution to journalArticle

    145 Citations (Scopus)

    Abstract

    A brain–computer interface (BCI) is a communication system based on neural activity. Its goal is to provide a new output channel for the brain that requires voluntary control. We propose a new self-paced BCI speller based on the detection of steady-state visual evoked potential (SSVEP). The speller does not require any training from the user or from the signal processing part. The system is ready once the subject is prepared. The speller introduces a selection based on a decision tree and an undo command for correcting eventual errors. It was tested on eight healthy subjects who had no prior experience with the application. The average accuracy and information transfer rate are 92.25% and 37.62 bits per minute, which is translated in the speller with an average speed of 5.51 letters per minute.
    LanguageEnglish
    Pages127-133
    JournalIEEE Transactions on Neural Systems and Rehabilitation Engineering
    Volume18
    Issue number2
    DOIs
    Publication statusPublished - 1 Apr 2010

    Fingerprint

    Brain computer interface
    Bioelectric potentials
    Calibration
    Decision trees
    Brain
    Communication systems
    Signal processing

    Cite this

    @article{aee1290ef31a481a88178e19d738d437,
    title = "A Self-Paced and Calibration-Less SSVEP-Based Brain–Computer Interface Speller",
    abstract = "A brain–computer interface (BCI) is a communication system based on neural activity. Its goal is to provide a new output channel for the brain that requires voluntary control. We propose a new self-paced BCI speller based on the detection of steady-state visual evoked potential (SSVEP). The speller does not require any training from the user or from the signal processing part. The system is ready once the subject is prepared. The speller introduces a selection based on a decision tree and an undo command for correcting eventual errors. It was tested on eight healthy subjects who had no prior experience with the application. The average accuracy and information transfer rate are 92.25{\%} and 37.62 bits per minute, which is translated in the speller with an average speed of 5.51 letters per minute.",
    author = "Hubert Cecotti",
    year = "2010",
    month = "4",
    day = "1",
    doi = "10.1109/TNSRE.2009.2039594",
    language = "English",
    volume = "18",
    pages = "127--133",
    journal = "IEEE Transactions on Neural Systems and Rehabilitation Engineering",
    issn = "1534-4320",
    number = "2",

    }

    A Self-Paced and Calibration-Less SSVEP-Based Brain–Computer Interface Speller. / Cecotti, Hubert.

    In: IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol. 18, No. 2, 01.04.2010, p. 127-133.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - A Self-Paced and Calibration-Less SSVEP-Based Brain–Computer Interface Speller

    AU - Cecotti, Hubert

    PY - 2010/4/1

    Y1 - 2010/4/1

    N2 - A brain–computer interface (BCI) is a communication system based on neural activity. Its goal is to provide a new output channel for the brain that requires voluntary control. We propose a new self-paced BCI speller based on the detection of steady-state visual evoked potential (SSVEP). The speller does not require any training from the user or from the signal processing part. The system is ready once the subject is prepared. The speller introduces a selection based on a decision tree and an undo command for correcting eventual errors. It was tested on eight healthy subjects who had no prior experience with the application. The average accuracy and information transfer rate are 92.25% and 37.62 bits per minute, which is translated in the speller with an average speed of 5.51 letters per minute.

    AB - A brain–computer interface (BCI) is a communication system based on neural activity. Its goal is to provide a new output channel for the brain that requires voluntary control. We propose a new self-paced BCI speller based on the detection of steady-state visual evoked potential (SSVEP). The speller does not require any training from the user or from the signal processing part. The system is ready once the subject is prepared. The speller introduces a selection based on a decision tree and an undo command for correcting eventual errors. It was tested on eight healthy subjects who had no prior experience with the application. The average accuracy and information transfer rate are 92.25% and 37.62 bits per minute, which is translated in the speller with an average speed of 5.51 letters per minute.

    U2 - 10.1109/TNSRE.2009.2039594

    DO - 10.1109/TNSRE.2009.2039594

    M3 - Article

    VL - 18

    SP - 127

    EP - 133

    JO - IEEE Transactions on Neural Systems and Rehabilitation Engineering

    T2 - IEEE Transactions on Neural Systems and Rehabilitation Engineering

    JF - IEEE Transactions on Neural Systems and Rehabilitation Engineering

    SN - 1534-4320

    IS - 2

    ER -