Best practice for single-trial detection of event-related potentials:Application to brain-computer interfaces

Hubert Cecotti, Anthony Ries

    Research output: Contribution to journalArticle

    13 Citations (Scopus)

    Abstract

    The detection of event-related potentials (ERPs) in the electroencephalogram (EEG) signal is a fundamental component in non-invasive brain-computer interface (BCI) research, and in modern cognitive neuroscience studies. Whereas the grand average response across trials provides an estimation of essential characteristics of a brain-evoked response, an estimation of the differences between trials for a particular type of stimulus can provide key insight about the brain dynamics and possible origins of the brain response. The research in ERP single-trial detection has been mainly driven by applications in biomedical engineering, with an interest from machine learning and signal processing groups that test novel methods on noisy signals. Efficient single-trial detection techniques require processing steps that include temporal filtering, spatial filtering, and classification. In this paper, we review the current state-of-the-art methods for single-trial detection of event-related potentials with applications in BCI. Efficient single-trial detection techniques should embed simple yet efficient functions requiring as few hyper-parameters as possible. The focus of this paper is on methods that do not include a large number of hyper-parameters and can be easily implemented with datasets containing a limited number of trials. A benchmark of different classification methods is proposed on a database recorded from sixteen healthy subjects during a rapid serial visual presentation task. The results support the conclusion that single-trial detection can be achieved with an area under the ROC curve superior to 0.9 with less than ten sensors and 20 trials corresponding to the presentation of a target. Whereas the number of sensors is not a key element for efficient single-trial detection, the number of trials must be carefully chosen for creating a robust classifier.
    LanguageEnglish
    Pages156-169
    Number of pages14
    JournalInternational Journal of Psychophysiology
    Volume111
    Early online date22 Jul 2016
    DOIs
    Publication statusPublished - Jan 2017

    Fingerprint

    Brain-Computer Interfaces
    Practice Guidelines
    Evoked Potentials
    Brain
    Biomedical Engineering
    Benchmarking
    Research
    ROC Curve
    Area Under Curve
    Electroencephalography
    Healthy Volunteers
    Databases

    Keywords

    • EEG
    • ERP
    • signal processing
    • event-related potentials

    Cite this

    @article{30e5a9079bab4340a7f2739482818201,
    title = "Best practice for single-trial detection of event-related potentials:Application to brain-computer interfaces",
    abstract = "The detection of event-related potentials (ERPs) in the electroencephalogram (EEG) signal is a fundamental component in non-invasive brain-computer interface (BCI) research, and in modern cognitive neuroscience studies. Whereas the grand average response across trials provides an estimation of essential characteristics of a brain-evoked response, an estimation of the differences between trials for a particular type of stimulus can provide key insight about the brain dynamics and possible origins of the brain response. The research in ERP single-trial detection has been mainly driven by applications in biomedical engineering, with an interest from machine learning and signal processing groups that test novel methods on noisy signals. Efficient single-trial detection techniques require processing steps that include temporal filtering, spatial filtering, and classification. In this paper, we review the current state-of-the-art methods for single-trial detection of event-related potentials with applications in BCI. Efficient single-trial detection techniques should embed simple yet efficient functions requiring as few hyper-parameters as possible. The focus of this paper is on methods that do not include a large number of hyper-parameters and can be easily implemented with datasets containing a limited number of trials. A benchmark of different classification methods is proposed on a database recorded from sixteen healthy subjects during a rapid serial visual presentation task. The results support the conclusion that single-trial detection can be achieved with an area under the ROC curve superior to 0.9 with less than ten sensors and 20 trials corresponding to the presentation of a target. Whereas the number of sensors is not a key element for efficient single-trial detection, the number of trials must be carefully chosen for creating a robust classifier.",
    keywords = "EEG, ERP, signal processing, event-related potentials",
    author = "Hubert Cecotti and Anthony Ries",
    year = "2017",
    month = "1",
    doi = "10.1016/j.ijpsycho.2016.07.500",
    language = "English",
    volume = "111",
    pages = "156--169",
    journal = "International Journal of Psychophysiology",
    issn = "0167-8760",
    publisher = "Elsevier",

    }

    Best practice for single-trial detection of event-related potentials:Application to brain-computer interfaces. / Cecotti, Hubert; Ries, Anthony.

    In: International Journal of Psychophysiology, Vol. 111, 01.2017, p. 156-169.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Best practice for single-trial detection of event-related potentials:Application to brain-computer interfaces

    AU - Cecotti, Hubert

    AU - Ries, Anthony

    PY - 2017/1

    Y1 - 2017/1

    N2 - The detection of event-related potentials (ERPs) in the electroencephalogram (EEG) signal is a fundamental component in non-invasive brain-computer interface (BCI) research, and in modern cognitive neuroscience studies. Whereas the grand average response across trials provides an estimation of essential characteristics of a brain-evoked response, an estimation of the differences between trials for a particular type of stimulus can provide key insight about the brain dynamics and possible origins of the brain response. The research in ERP single-trial detection has been mainly driven by applications in biomedical engineering, with an interest from machine learning and signal processing groups that test novel methods on noisy signals. Efficient single-trial detection techniques require processing steps that include temporal filtering, spatial filtering, and classification. In this paper, we review the current state-of-the-art methods for single-trial detection of event-related potentials with applications in BCI. Efficient single-trial detection techniques should embed simple yet efficient functions requiring as few hyper-parameters as possible. The focus of this paper is on methods that do not include a large number of hyper-parameters and can be easily implemented with datasets containing a limited number of trials. A benchmark of different classification methods is proposed on a database recorded from sixteen healthy subjects during a rapid serial visual presentation task. The results support the conclusion that single-trial detection can be achieved with an area under the ROC curve superior to 0.9 with less than ten sensors and 20 trials corresponding to the presentation of a target. Whereas the number of sensors is not a key element for efficient single-trial detection, the number of trials must be carefully chosen for creating a robust classifier.

    AB - The detection of event-related potentials (ERPs) in the electroencephalogram (EEG) signal is a fundamental component in non-invasive brain-computer interface (BCI) research, and in modern cognitive neuroscience studies. Whereas the grand average response across trials provides an estimation of essential characteristics of a brain-evoked response, an estimation of the differences between trials for a particular type of stimulus can provide key insight about the brain dynamics and possible origins of the brain response. The research in ERP single-trial detection has been mainly driven by applications in biomedical engineering, with an interest from machine learning and signal processing groups that test novel methods on noisy signals. Efficient single-trial detection techniques require processing steps that include temporal filtering, spatial filtering, and classification. In this paper, we review the current state-of-the-art methods for single-trial detection of event-related potentials with applications in BCI. Efficient single-trial detection techniques should embed simple yet efficient functions requiring as few hyper-parameters as possible. The focus of this paper is on methods that do not include a large number of hyper-parameters and can be easily implemented with datasets containing a limited number of trials. A benchmark of different classification methods is proposed on a database recorded from sixteen healthy subjects during a rapid serial visual presentation task. The results support the conclusion that single-trial detection can be achieved with an area under the ROC curve superior to 0.9 with less than ten sensors and 20 trials corresponding to the presentation of a target. Whereas the number of sensors is not a key element for efficient single-trial detection, the number of trials must be carefully chosen for creating a robust classifier.

    KW - EEG

    KW - ERP

    KW - signal processing

    KW - event-related potentials

    U2 - 10.1016/j.ijpsycho.2016.07.500

    DO - 10.1016/j.ijpsycho.2016.07.500

    M3 - Article

    VL - 111

    SP - 156

    EP - 169

    JO - International Journal of Psychophysiology

    T2 - International Journal of Psychophysiology

    JF - International Journal of Psychophysiology

    SN - 0167-8760

    ER -