• 9 Citations

Abstract

Brain–computer interfaces (BCIs) are known to suffer from spontaneous changes in the brain activity. If changes in the mental state of the user are reflected in the brain signals used for control, the behavior of a BCI is directly influenced by these states. We investigate the influence of a state of loss of control in a variant of Pacman on the performance of BCIs based on motor control. To study the effect a temporal loss of control has on the BCI performance, BCI classifiers were trained on electroencephalography (EEG) recorded during the normal control condition, and the classification performance on segments of EEG from the normal and loss of control condition was compared. Classifiers based on event-related desynchronization unexpectedly performed significantly better during the loss of control condition; for the event-related potential classifiers there was no significant difference in performance.
Original languageUndefined
Pages (from-to)628-637
Number of pages10
JournalIEEE transactions on neural systems and rehabilitation engineering
Volume19
Issue number6
DOIs
StatePublished - 5 Dec 2011

Fingerprint

Brain-Computer Interfaces
Brain computer interface
Classifiers
Electroencephalography
Brain
Behavior Control
Evoked Potentials

Keywords

  • lateralized readiness potential
  • common spatial patterns
  • loss of control
  • EWI-20682
  • HMI-CI: Computational Intelligence
  • Event-related desynchronization
  • non-stationarity
  • electroencephalogram
  • METIS-281541
  • IR-78884
  • Brain-Computer Interfaces
  • HMI-MI: MULTIMODAL INTERACTIONS

Cite this

Reuderink, B.; Poel, Mannes; Nijholt, Antinus / The Impact of Loss of Control on Movement BCIs.

In: IEEE transactions on neural systems and rehabilitation engineering, Vol. 19, No. 6, 05.12.2011, p. 628-637.

Research output: Scientific - peer-reviewArticle

@article{7ce5bc7fd2bc4af9bd9374b0988924d7,
title = "The Impact of Loss of Control on Movement BCIs",
abstract = "Brain–computer interfaces (BCIs) are known to suffer from spontaneous changes in the brain activity. If changes in the mental state of the user are reflected in the brain signals used for control, the behavior of a BCI is directly influenced by these states. We investigate the influence of a state of loss of control in a variant of Pacman on the performance of BCIs based on motor control. To study the effect a temporal loss of control has on the BCI performance, BCI classifiers were trained on electroencephalography (EEG) recorded during the normal control condition, and the classification performance on segments of EEG from the normal and loss of control condition was compared. Classifiers based on event-related desynchronization unexpectedly performed significantly better during the loss of control condition; for the event-related potential classifiers there was no significant difference in performance.",
keywords = "lateralized readiness potential, common spatial patterns, loss of control, EWI-20682, HMI-CI: Computational Intelligence, Event-related desynchronization, non-stationarity, electroencephalogram, METIS-281541, IR-78884, Brain-Computer Interfaces, HMI-MI: MULTIMODAL INTERACTIONS",
author = "B. Reuderink and Mannes Poel and Antinus Nijholt",
note = "10.1109/TNSRE.2011.2166562",
year = "2011",
month = "12",
doi = "10.1109/TNSRE.2011.2166562",
volume = "19",
pages = "628--637",
journal = "IEEE transactions on neural systems and rehabilitation engineering",
issn = "1534-4320",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

The Impact of Loss of Control on Movement BCIs. / Reuderink, B.; Poel, Mannes; Nijholt, Antinus.

In: IEEE transactions on neural systems and rehabilitation engineering, Vol. 19, No. 6, 05.12.2011, p. 628-637.

Research output: Scientific - peer-reviewArticle

TY - JOUR

T1 - The Impact of Loss of Control on Movement BCIs

AU - Reuderink,B.

AU - Poel,Mannes

AU - Nijholt,Antinus

N1 - 10.1109/TNSRE.2011.2166562

PY - 2011/12/5

Y1 - 2011/12/5

N2 - Brain–computer interfaces (BCIs) are known to suffer from spontaneous changes in the brain activity. If changes in the mental state of the user are reflected in the brain signals used for control, the behavior of a BCI is directly influenced by these states. We investigate the influence of a state of loss of control in a variant of Pacman on the performance of BCIs based on motor control. To study the effect a temporal loss of control has on the BCI performance, BCI classifiers were trained on electroencephalography (EEG) recorded during the normal control condition, and the classification performance on segments of EEG from the normal and loss of control condition was compared. Classifiers based on event-related desynchronization unexpectedly performed significantly better during the loss of control condition; for the event-related potential classifiers there was no significant difference in performance.

AB - Brain–computer interfaces (BCIs) are known to suffer from spontaneous changes in the brain activity. If changes in the mental state of the user are reflected in the brain signals used for control, the behavior of a BCI is directly influenced by these states. We investigate the influence of a state of loss of control in a variant of Pacman on the performance of BCIs based on motor control. To study the effect a temporal loss of control has on the BCI performance, BCI classifiers were trained on electroencephalography (EEG) recorded during the normal control condition, and the classification performance on segments of EEG from the normal and loss of control condition was compared. Classifiers based on event-related desynchronization unexpectedly performed significantly better during the loss of control condition; for the event-related potential classifiers there was no significant difference in performance.

KW - lateralized readiness potential

KW - common spatial patterns

KW - loss of control

KW - EWI-20682

KW - HMI-CI: Computational Intelligence

KW - Event-related desynchronization

KW - non-stationarity

KW - electroencephalogram

KW - METIS-281541

KW - IR-78884

KW - Brain-Computer Interfaces

KW - HMI-MI: MULTIMODAL INTERACTIONS

U2 - 10.1109/TNSRE.2011.2166562

DO - 10.1109/TNSRE.2011.2166562

M3 - Article

VL - 19

SP - 628

EP - 637

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 - 6

ER -