• 11 Citations

Abstract

A brain-computer interface (BCI) enables direct communication from the brain to devices, bypassing the traditional pathway of peripheral nerves and muscles. Current BCIs aimed at patients require that the user invests weeks, or even months, to learn the skill to intentionally modify their brain signals. This can be reduced to a calibration session of about half an hour per session if machine learning (ML) methods are used. The laborious recalibration is still needed due to inter-session differences in the statistical properties of the electroencephalography (EEG) signal. Further, the natural variability in spontaneous EEG violates basic assumptions made by the ML methods used to train the BCI classifier, and causes the classification accuracy to fluctuate unpredictably. These fluctuations make the current generation of BCIs unreliable. In this dissertation,we will investigate the nature of these variations in the EEG distributions, and introduce two new, complementary methods to overcome these two key issues. To confirm the problem of non-stationary brain signals, we first show that BCIs based on commonly used signal features are sensitive to changes in the mental state of the user. We proceed by describing a method aimed at removing these changes in signal feature distributions. We have devised a method that uses a second-order baseline (SOB) to specifically isolate these relative changes in neuronal firing synchrony. To the best of our knowledge this is the first BCI classifier that works on out-of-sample subjects without any loss of performance. Still, the assumption made by ML methods that the training data consists of samples that are independent and identically distributed (iid) is violated, because EEG samples nearby in time are highly correlated. Therefore we derived a generalization of the well-known support vector machine (SVM) classifier, that takes the resulting chronological structure of classification errors into account. Both on artificial data and real BCI data, overfitting is reduced with this dependent samples support vector machine (dSVM), leading to BCIs with an increased information throughput.
Original languageUndefined
Awarding Institution
  • University of Twente
Supervisors/Advisors
  • Nijholt, Antinus , Supervisor
  • Poel, Mannes , Advisor
Sponsors
Date of Award21 Oct 2011
Place of PublicationEnschede, The Netherlands
Print ISBNs978-94-6191-058-5
StatePublished - 21 Oct 2011

Fingerprint

Brain computer interface
Electroencephalography
Learning systems
Brain
Classifiers
Support vector machines
Muscle
Throughput
Calibration
Communication

Keywords

  • HMI-MI: MULTIMODAL INTERACTIONS
  • EWI-19995
  • METIS-284894
  • IR-78274

Cite this

Reuderink, B. (2011). Robust Brain-Computer Interfaces Enschede, The Netherlands
Reuderink, B.. / Robust Brain-Computer Interfaces. Enschede, The Netherlands, 2011. 81 p.
@misc{06991e40a25044b391442d9bfcbda33b,
title = "Robust Brain-Computer Interfaces",
abstract = "A brain-computer interface (BCI) enables direct communication from the brain to devices, bypassing the traditional pathway of peripheral nerves and muscles. Current BCIs aimed at patients require that the user invests weeks, or even months, to learn the skill to intentionally modify their brain signals. This can be reduced to a calibration session of about half an hour per session if machine learning (ML) methods are used. The laborious recalibration is still needed due to inter-session differences in the statistical properties of the electroencephalography (EEG) signal. Further, the natural variability in spontaneous EEG violates basic assumptions made by the ML methods used to train the BCI classifier, and causes the classification accuracy to fluctuate unpredictably. These fluctuations make the current generation of BCIs unreliable. In this dissertation,we will investigate the nature of these variations in the EEG distributions, and introduce two new, complementary methods to overcome these two key issues. To confirm the problem of non-stationary brain signals, we first show that BCIs based on commonly used signal features are sensitive to changes in the mental state of the user. We proceed by describing a method aimed at removing these changes in signal feature distributions. We have devised a method that uses a second-order baseline (SOB) to specifically isolate these relative changes in neuronal firing synchrony. To the best of our knowledge this is the first BCI classifier that works on out-of-sample subjects without any loss of performance. Still, the assumption made by ML methods that the training data consists of samples that are independent and identically distributed (iid) is violated, because EEG samples nearby in time are highly correlated. Therefore we derived a generalization of the well-known support vector machine (SVM) classifier, that takes the resulting chronological structure of classification errors into account. Both on artificial data and real BCI data, overfitting is reduced with this dependent samples support vector machine (dSVM), leading to BCIs with an increased information throughput.",
keywords = "HMI-MI: MULTIMODAL INTERACTIONS, EWI-19995, METIS-284894, IR-78274",
author = "B. Reuderink",
year = "2011",
month = "10",
isbn = "978-94-6191-058-5",
school = "University of Twente",

}

Reuderink, B 2011, 'Robust Brain-Computer Interfaces', University of Twente, Enschede, The Netherlands.

Robust Brain-Computer Interfaces. / Reuderink, B.

Enschede, The Netherlands, 2011. 81 p.

Research output: ScientificPhD Thesis - Research UT, graduation UT

TY - THES

T1 - Robust Brain-Computer Interfaces

AU - Reuderink,B.

PY - 2011/10/21

Y1 - 2011/10/21

N2 - A brain-computer interface (BCI) enables direct communication from the brain to devices, bypassing the traditional pathway of peripheral nerves and muscles. Current BCIs aimed at patients require that the user invests weeks, or even months, to learn the skill to intentionally modify their brain signals. This can be reduced to a calibration session of about half an hour per session if machine learning (ML) methods are used. The laborious recalibration is still needed due to inter-session differences in the statistical properties of the electroencephalography (EEG) signal. Further, the natural variability in spontaneous EEG violates basic assumptions made by the ML methods used to train the BCI classifier, and causes the classification accuracy to fluctuate unpredictably. These fluctuations make the current generation of BCIs unreliable. In this dissertation,we will investigate the nature of these variations in the EEG distributions, and introduce two new, complementary methods to overcome these two key issues. To confirm the problem of non-stationary brain signals, we first show that BCIs based on commonly used signal features are sensitive to changes in the mental state of the user. We proceed by describing a method aimed at removing these changes in signal feature distributions. We have devised a method that uses a second-order baseline (SOB) to specifically isolate these relative changes in neuronal firing synchrony. To the best of our knowledge this is the first BCI classifier that works on out-of-sample subjects without any loss of performance. Still, the assumption made by ML methods that the training data consists of samples that are independent and identically distributed (iid) is violated, because EEG samples nearby in time are highly correlated. Therefore we derived a generalization of the well-known support vector machine (SVM) classifier, that takes the resulting chronological structure of classification errors into account. Both on artificial data and real BCI data, overfitting is reduced with this dependent samples support vector machine (dSVM), leading to BCIs with an increased information throughput.

AB - A brain-computer interface (BCI) enables direct communication from the brain to devices, bypassing the traditional pathway of peripheral nerves and muscles. Current BCIs aimed at patients require that the user invests weeks, or even months, to learn the skill to intentionally modify their brain signals. This can be reduced to a calibration session of about half an hour per session if machine learning (ML) methods are used. The laborious recalibration is still needed due to inter-session differences in the statistical properties of the electroencephalography (EEG) signal. Further, the natural variability in spontaneous EEG violates basic assumptions made by the ML methods used to train the BCI classifier, and causes the classification accuracy to fluctuate unpredictably. These fluctuations make the current generation of BCIs unreliable. In this dissertation,we will investigate the nature of these variations in the EEG distributions, and introduce two new, complementary methods to overcome these two key issues. To confirm the problem of non-stationary brain signals, we first show that BCIs based on commonly used signal features are sensitive to changes in the mental state of the user. We proceed by describing a method aimed at removing these changes in signal feature distributions. We have devised a method that uses a second-order baseline (SOB) to specifically isolate these relative changes in neuronal firing synchrony. To the best of our knowledge this is the first BCI classifier that works on out-of-sample subjects without any loss of performance. Still, the assumption made by ML methods that the training data consists of samples that are independent and identically distributed (iid) is violated, because EEG samples nearby in time are highly correlated. Therefore we derived a generalization of the well-known support vector machine (SVM) classifier, that takes the resulting chronological structure of classification errors into account. Both on artificial data and real BCI data, overfitting is reduced with this dependent samples support vector machine (dSVM), leading to BCIs with an increased information throughput.

KW - HMI-MI: MULTIMODAL INTERACTIONS

KW - EWI-19995

KW - METIS-284894

KW - IR-78274

M3 - PhD Thesis - Research UT, graduation UT

SN - 978-94-6191-058-5

ER -

Reuderink B. Robust Brain-Computer Interfaces. Enschede, The Netherlands, 2011. 81 p.