Convolutional Neural Networks for P300 Detection with Application to Brain-Computer Interfaces

Hubert Cecotti, Axel Graeser

    Research output: Contribution to journalArticle

    253 Citations (Scopus)

    Abstract

    A Brain-Computer Interface (BCI) is a specific type of human-computer interface that enables the direct communication between human and computers by analyzing brain measurements. Oddball paradigms are used in BCI to generate event-related potentials (ERPs), like the P300 wave, on targets selected by the user. A P300 speller is based on this principle, where the detection of P300 waves allows the user to write characters. The P300 speller is composed of two classification problems. The first classification is to detect the presence of a P300 in the electroencephalogram (EEG). The second one corresponds to the combination of different P300 responses for determining the right character to spell. A new method for the detection of P300 waves is presented. This model is based on a convolutional neural network (CNN). The topology of the network is adapted to the detection of P300 waves in the time domain. Seven classifiers based on the CNN are proposed: four single classifiers with different features set and three multiclassifiers. These models are tested and compared on the Data set II of the third BCI competition. The best result is obtained with a multiclassifier solution with a recognition rate of 95.5 percent, without channel selection before the classification. The proposed approach provides also a new way for analyzing brain activities due to the receptive field of the CNN models.
    LanguageEnglish
    Pages433-445
    JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
    Volume33
    Issue number3
    DOIs
    Publication statusPublished - 1 Mar 2011

    Fingerprint

    Brain computer interface
    Neural Networks
    Neural networks
    Brain
    Classifiers
    Classifier
    Event-related Potentials
    Receptive Field
    Human-computer Interface
    Electroencephalography
    Interfaces (computer)
    Neural Network Model
    Classification Problems
    Percent
    Topology
    Time Domain
    Paradigm
    Communication
    Target
    Model

    Cite this

    Cecotti, Hubert ; Graeser, Axel. / Convolutional Neural Networks for P300 Detection with Application to Brain-Computer Interfaces. 2011 ; Vol. 33, No. 3. pp. 433-445.
    @article{452a7bd88a354f4099768203480f778c,
    title = "Convolutional Neural Networks for P300 Detection with Application to Brain-Computer Interfaces",
    abstract = "A Brain-Computer Interface (BCI) is a specific type of human-computer interface that enables the direct communication between human and computers by analyzing brain measurements. Oddball paradigms are used in BCI to generate event-related potentials (ERPs), like the P300 wave, on targets selected by the user. A P300 speller is based on this principle, where the detection of P300 waves allows the user to write characters. The P300 speller is composed of two classification problems. The first classification is to detect the presence of a P300 in the electroencephalogram (EEG). The second one corresponds to the combination of different P300 responses for determining the right character to spell. A new method for the detection of P300 waves is presented. This model is based on a convolutional neural network (CNN). The topology of the network is adapted to the detection of P300 waves in the time domain. Seven classifiers based on the CNN are proposed: four single classifiers with different features set and three multiclassifiers. These models are tested and compared on the Data set II of the third BCI competition. The best result is obtained with a multiclassifier solution with a recognition rate of 95.5 percent, without channel selection before the classification. The proposed approach provides also a new way for analyzing brain activities due to the receptive field of the CNN models.",
    author = "Hubert Cecotti and Axel Graeser",
    year = "2011",
    month = "3",
    day = "1",
    doi = "10.1109/TPAMI.2010.125",
    language = "English",
    volume = "33",
    pages = "433--445",
    number = "3",

    }

    Convolutional Neural Networks for P300 Detection with Application to Brain-Computer Interfaces. / Cecotti, Hubert; Graeser, Axel.

    Vol. 33, No. 3, 01.03.2011, p. 433-445.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Convolutional Neural Networks for P300 Detection with Application to Brain-Computer Interfaces

    AU - Cecotti, Hubert

    AU - Graeser, Axel

    PY - 2011/3/1

    Y1 - 2011/3/1

    N2 - A Brain-Computer Interface (BCI) is a specific type of human-computer interface that enables the direct communication between human and computers by analyzing brain measurements. Oddball paradigms are used in BCI to generate event-related potentials (ERPs), like the P300 wave, on targets selected by the user. A P300 speller is based on this principle, where the detection of P300 waves allows the user to write characters. The P300 speller is composed of two classification problems. The first classification is to detect the presence of a P300 in the electroencephalogram (EEG). The second one corresponds to the combination of different P300 responses for determining the right character to spell. A new method for the detection of P300 waves is presented. This model is based on a convolutional neural network (CNN). The topology of the network is adapted to the detection of P300 waves in the time domain. Seven classifiers based on the CNN are proposed: four single classifiers with different features set and three multiclassifiers. These models are tested and compared on the Data set II of the third BCI competition. The best result is obtained with a multiclassifier solution with a recognition rate of 95.5 percent, without channel selection before the classification. The proposed approach provides also a new way for analyzing brain activities due to the receptive field of the CNN models.

    AB - A Brain-Computer Interface (BCI) is a specific type of human-computer interface that enables the direct communication between human and computers by analyzing brain measurements. Oddball paradigms are used in BCI to generate event-related potentials (ERPs), like the P300 wave, on targets selected by the user. A P300 speller is based on this principle, where the detection of P300 waves allows the user to write characters. The P300 speller is composed of two classification problems. The first classification is to detect the presence of a P300 in the electroencephalogram (EEG). The second one corresponds to the combination of different P300 responses for determining the right character to spell. A new method for the detection of P300 waves is presented. This model is based on a convolutional neural network (CNN). The topology of the network is adapted to the detection of P300 waves in the time domain. Seven classifiers based on the CNN are proposed: four single classifiers with different features set and three multiclassifiers. These models are tested and compared on the Data set II of the third BCI competition. The best result is obtained with a multiclassifier solution with a recognition rate of 95.5 percent, without channel selection before the classification. The proposed approach provides also a new way for analyzing brain activities due to the receptive field of the CNN models.

    U2 - 10.1109/TPAMI.2010.125

    DO - 10.1109/TPAMI.2010.125

    M3 - Article

    VL - 33

    SP - 433

    EP - 445

    IS - 3

    ER -