Subject-dependent classification for robust idle state detection using multi-modal neuroimaging and data-fusion techniques in BCI

Min Ho Lee, Siamac Fazli, Jan Mehnert, Seong Whan Lee

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

Abstract Brain-computer interfaces (BCIs) allow users to control external devices by their intentions. Currently, most BCI systems are synchronous. They rely on cues or tasks to which a subject has to react. In order to design an asynchronous BCI one needs to be able to robustly detect an idle class. In this study, we examine whether multi-modal neuroimaging, based on simultaneous EEG and near-infrared spectroscopy (NIRS) measurements, can assist in the robust detection of the idle class within a sensory motor rhythm-based BCI paradigm. We propose two types of subject-dependent classification strategies to combine the information of both modalities. Our results demonstrate that not only idle-state decoding can be significantly improved by exploiting the complementary information of multi-modal recordings, but also it is possible to minimize the delay of the system, caused by the slow inherent hemodynamic response of the NIRS signal.

Original languageEnglish
Article number5378
Pages (from-to)2725-2737
Number of pages13
JournalPattern Recognition
Volume48
Issue number8
DOIs
Publication statusPublished - Aug 1 2015
Externally publishedYes

Fingerprint

Neuroimaging
Brain computer interface
Data fusion
Near infrared spectroscopy
Hemodynamics
Electroencephalography
Decoding

Keywords

  • Classifier combination
  • Combined EEG-NIRS
  • Hybrid brain-computer interfacing
  • Subject-dependent classification

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Subject-dependent classification for robust idle state detection using multi-modal neuroimaging and data-fusion techniques in BCI. / Lee, Min Ho; Fazli, Siamac; Mehnert, Jan; Lee, Seong Whan.

In: Pattern Recognition, Vol. 48, No. 8, 5378, 01.08.2015, p. 2725-2737.

Research output: Contribution to journalArticle

@article{2bd37a5687004c269152b26ab465ed3a,
title = "Subject-dependent classification for robust idle state detection using multi-modal neuroimaging and data-fusion techniques in BCI",
abstract = "Abstract Brain-computer interfaces (BCIs) allow users to control external devices by their intentions. Currently, most BCI systems are synchronous. They rely on cues or tasks to which a subject has to react. In order to design an asynchronous BCI one needs to be able to robustly detect an idle class. In this study, we examine whether multi-modal neuroimaging, based on simultaneous EEG and near-infrared spectroscopy (NIRS) measurements, can assist in the robust detection of the idle class within a sensory motor rhythm-based BCI paradigm. We propose two types of subject-dependent classification strategies to combine the information of both modalities. Our results demonstrate that not only idle-state decoding can be significantly improved by exploiting the complementary information of multi-modal recordings, but also it is possible to minimize the delay of the system, caused by the slow inherent hemodynamic response of the NIRS signal.",
keywords = "Classifier combination, Combined EEG-NIRS, Hybrid brain-computer interfacing, Subject-dependent classification",
author = "Lee, {Min Ho} and Siamac Fazli and Jan Mehnert and Lee, {Seong Whan}",
year = "2015",
month = "8",
day = "1",
doi = "10.1016/j.patcog.2015.03.010",
language = "English",
volume = "48",
pages = "2725--2737",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier",
number = "8",

}

TY - JOUR

T1 - Subject-dependent classification for robust idle state detection using multi-modal neuroimaging and data-fusion techniques in BCI

AU - Lee, Min Ho

AU - Fazli, Siamac

AU - Mehnert, Jan

AU - Lee, Seong Whan

PY - 2015/8/1

Y1 - 2015/8/1

N2 - Abstract Brain-computer interfaces (BCIs) allow users to control external devices by their intentions. Currently, most BCI systems are synchronous. They rely on cues or tasks to which a subject has to react. In order to design an asynchronous BCI one needs to be able to robustly detect an idle class. In this study, we examine whether multi-modal neuroimaging, based on simultaneous EEG and near-infrared spectroscopy (NIRS) measurements, can assist in the robust detection of the idle class within a sensory motor rhythm-based BCI paradigm. We propose two types of subject-dependent classification strategies to combine the information of both modalities. Our results demonstrate that not only idle-state decoding can be significantly improved by exploiting the complementary information of multi-modal recordings, but also it is possible to minimize the delay of the system, caused by the slow inherent hemodynamic response of the NIRS signal.

AB - Abstract Brain-computer interfaces (BCIs) allow users to control external devices by their intentions. Currently, most BCI systems are synchronous. They rely on cues or tasks to which a subject has to react. In order to design an asynchronous BCI one needs to be able to robustly detect an idle class. In this study, we examine whether multi-modal neuroimaging, based on simultaneous EEG and near-infrared spectroscopy (NIRS) measurements, can assist in the robust detection of the idle class within a sensory motor rhythm-based BCI paradigm. We propose two types of subject-dependent classification strategies to combine the information of both modalities. Our results demonstrate that not only idle-state decoding can be significantly improved by exploiting the complementary information of multi-modal recordings, but also it is possible to minimize the delay of the system, caused by the slow inherent hemodynamic response of the NIRS signal.

KW - Classifier combination

KW - Combined EEG-NIRS

KW - Hybrid brain-computer interfacing

KW - Subject-dependent classification

UR - http://www.scopus.com/inward/record.url?scp=84928298407&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84928298407&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2015.03.010

DO - 10.1016/j.patcog.2015.03.010

M3 - Article

VL - 48

SP - 2725

EP - 2737

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 8

M1 - 5378

ER -