Brain-computer interface speller using hybrid P300 and motor imagery signals

Mohammed Roula; Janusz Kulon; Y. Mamatjan

doi:10.1109/BioRob.2012.6290944

Brain-computer interface speller using hybrid P300 and motor imagery signals

Mohammed Roula, Janusz Kulon, Y. Mamatjan

Faculty of Computing, Engineering and Science

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

Abstract

In this paper we propose a fast brain computer interface speller based on electroencephalography (EEG). The slow performance of conventional BCI spellers is overcome by combining the fast motor evoked potentials (MEPs) with the accuracy of P300 event related potentials. The μ rhythms associated with motor imagery are extracted using morlet wavalet based time-frequency analysis. Selected features were subsequently classified using minimum Mahalanobis distance. A hybrid MEP-P300 algorithm incorporating text prediction was proposed and experiments were conducted to gauge its accuracy and speed. Results show significantly faster performance when compared with conventional P300 spellers while comparable, but reduced accuracy was also noted

Original language	English
Title of host publication	N/A
Pages	224-227
DOIs	https://doi.org/10.1109/BioRob.2012.6290944
Publication status	Published - 27 Jun 2012
Event	Biomedical Robotics and Biomechatronics (BioRob), 2012 4th IEEE RAS and EMBS International - Rome Duration: 24 Jun 2012 → 27 Jun 2012

Conference

Conference	Biomedical Robotics and Biomechatronics (BioRob), 2012 4th IEEE RAS and EMBS International
Period	24/06/12 → 27/06/12

Keywords

.mu rhythms
mahalanobis distance
morlet wavelet based time-frequency analysis
brain-computer interfaces
electroencephalograph
features selection
hybrid mep-p300 algorithm
hybrid p300 event related potentials
motor evoked potentials
motor imagery signals
text prediction
spellers
eeg

Access to Document

10.1109/BioRob.2012.6290944

Cite this

@inproceedings{820fdc8b3a364167a17718e131946e54,

title = "Brain-computer interface speller using hybrid P300 and motor imagery signals",

abstract = "In this paper we propose a fast brain computer interface speller based on electroencephalography (EEG). The slow performance of conventional BCI spellers is overcome by combining the fast motor evoked potentials (MEPs) with the accuracy of P300 event related potentials. The μ rhythms associated with motor imagery are extracted using morlet wavalet based time-frequency analysis. Selected features were subsequently classified using minimum Mahalanobis distance. A hybrid MEP-P300 algorithm incorporating text prediction was proposed and experiments were conducted to gauge its accuracy and speed. Results show significantly faster performance when compared with conventional P300 spellers while comparable, but reduced accuracy was also noted",

keywords = ".mu rhythms, mahalanobis distance, morlet wavelet based time-frequency analysis, brain-computer interfaces, electroencephalograph, features selection, hybrid mep-p300 algorithm, hybrid p300 event related potentials, motor evoked potentials, motor imagery signals, text prediction, spellers, eeg",

author = "Mohammed Roula and Janusz Kulon and Y. Mamatjan",

year = "2012",

month = jun,

day = "27",

doi = "10.1109/BioRob.2012.6290944",

language = "English",

pages = "224--227",

booktitle = "N/A",

note = " Biomedical Robotics and Biomechatronics (BioRob), 2012 4th IEEE RAS and EMBS International ; Conference date: 24-06-2012 Through 27-06-2012",

}

TY - GEN

T1 - Brain-computer interface speller using hybrid P300 and motor imagery signals

AU - Roula, Mohammed

AU - Kulon, Janusz

AU - Mamatjan, Y.

PY - 2012/6/27

Y1 - 2012/6/27

N2 - In this paper we propose a fast brain computer interface speller based on electroencephalography (EEG). The slow performance of conventional BCI spellers is overcome by combining the fast motor evoked potentials (MEPs) with the accuracy of P300 event related potentials. The μ rhythms associated with motor imagery are extracted using morlet wavalet based time-frequency analysis. Selected features were subsequently classified using minimum Mahalanobis distance. A hybrid MEP-P300 algorithm incorporating text prediction was proposed and experiments were conducted to gauge its accuracy and speed. Results show significantly faster performance when compared with conventional P300 spellers while comparable, but reduced accuracy was also noted

AB - In this paper we propose a fast brain computer interface speller based on electroencephalography (EEG). The slow performance of conventional BCI spellers is overcome by combining the fast motor evoked potentials (MEPs) with the accuracy of P300 event related potentials. The μ rhythms associated with motor imagery are extracted using morlet wavalet based time-frequency analysis. Selected features were subsequently classified using minimum Mahalanobis distance. A hybrid MEP-P300 algorithm incorporating text prediction was proposed and experiments were conducted to gauge its accuracy and speed. Results show significantly faster performance when compared with conventional P300 spellers while comparable, but reduced accuracy was also noted

KW - .mu rhythms

KW - mahalanobis distance

KW - morlet wavelet based time-frequency analysis

KW - brain-computer interfaces

KW - electroencephalograph

KW - features selection

KW - hybrid mep-p300 algorithm

KW - hybrid p300 event related potentials

KW - motor evoked potentials

KW - motor imagery signals

KW - text prediction

KW - spellers

KW - eeg

U2 - 10.1109/BioRob.2012.6290944

DO - 10.1109/BioRob.2012.6290944

M3 - Conference contribution

SP - 224

EP - 227

BT - N/A

T2 - Biomedical Robotics and Biomechatronics (BioRob), 2012 4th IEEE RAS and EMBS International

Y2 - 24 June 2012 through 27 June 2012

ER -

Brain-computer interface speller using hybrid P300 and motor imagery signals

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this