Continuous EEG Classification for a Self-paced BCI

A.R. Satti, D Coyle, G Prasad

Research output: Chapter in Book/Report/Conference proceedingConference contribution

19 Citations (Scopus)

Abstract

Transferring electroencephalogram (EEG)-based brain-computer interface (BCI) systems from synchronous laboratory conditions to real-world applications and situations demands the continuous detection of brain patterns in which the user is in control of the timing and pace of the BCI instead of the computer. A self-paced BCI requires continuous analysis of the continuing brain activity, however, not only the intentional-control (IC) states have to be detected (e.g., motor imagery and imagination) but also the inactive periods, where the user is in a non-control state (NC). The nonstationary nature of the brain signals provides a rather unstable input resulting in uncertainty and complexity in the control. Intelligent processing algorithms adapted to the task at hand are a prerequisite for reliable self-paced BCI applications. This work presents a novel intelligent processing strategy for the realization of an effective self-paced BCI which has the capability to reduce noise as well as adaptation to continuous online biasing. A Savitzki-Golay filter has been applied to remove spikes/outliers while preserving the feature set structure. An anti-bias system is introduced which readjusts the classification output based on the brain's current and previous states. Furthermore, a multiple threshold algorithm is applied on the resultant unbiased classifier output for improved accuracy. These algorithms are tested on 4 real and 3 artificial datasets and results shown are considerably promising and demonstrate the significance of the proposed intelligent and adaptive algorithms.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages315-318
Number of pages4
DOIs
Publication statusPublished - Jun 2009
Event2009. NER '09. 4th International IEEE/EMBS Conference on Neural Engineering, -
Duration: 1 Jun 2009 → …

Conference

Conference2009. NER '09. 4th International IEEE/EMBS Conference on Neural Engineering,
Period1/06/09 → …

Fingerprint

Brain computer interface
Electroencephalography
Brain
Processing
Adaptive algorithms
Classifiers

Cite this

Satti, A.R. ; Coyle, D ; Prasad, G. / Continuous EEG Classification for a Self-paced BCI. Unknown Host Publication. 2009. pp. 315-318
@inproceedings{9be6fa5198eb478cb738e2a7b6dd94cd,
title = "Continuous EEG Classification for a Self-paced BCI",
abstract = "Transferring electroencephalogram (EEG)-based brain-computer interface (BCI) systems from synchronous laboratory conditions to real-world applications and situations demands the continuous detection of brain patterns in which the user is in control of the timing and pace of the BCI instead of the computer. A self-paced BCI requires continuous analysis of the continuing brain activity, however, not only the intentional-control (IC) states have to be detected (e.g., motor imagery and imagination) but also the inactive periods, where the user is in a non-control state (NC). The nonstationary nature of the brain signals provides a rather unstable input resulting in uncertainty and complexity in the control. Intelligent processing algorithms adapted to the task at hand are a prerequisite for reliable self-paced BCI applications. This work presents a novel intelligent processing strategy for the realization of an effective self-paced BCI which has the capability to reduce noise as well as adaptation to continuous online biasing. A Savitzki-Golay filter has been applied to remove spikes/outliers while preserving the feature set structure. An anti-bias system is introduced which readjusts the classification output based on the brain's current and previous states. Furthermore, a multiple threshold algorithm is applied on the resultant unbiased classifier output for improved accuracy. These algorithms are tested on 4 real and 3 artificial datasets and results shown are considerably promising and demonstrate the significance of the proposed intelligent and adaptive algorithms.",
author = "A.R. Satti and D Coyle and G Prasad",
year = "2009",
month = "6",
doi = "10.1109/NER.2009.5109296",
language = "English",
pages = "315--318",
booktitle = "Unknown Host Publication",

}

Satti, AR, Coyle, D & Prasad, G 2009, Continuous EEG Classification for a Self-paced BCI. in Unknown Host Publication. pp. 315-318, 2009. NER '09. 4th International IEEE/EMBS Conference on Neural Engineering, 1/06/09. https://doi.org/10.1109/NER.2009.5109296

Continuous EEG Classification for a Self-paced BCI. / Satti, A.R.; Coyle, D; Prasad, G.

Unknown Host Publication. 2009. p. 315-318.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Continuous EEG Classification for a Self-paced BCI

AU - Satti, A.R.

AU - Coyle, D

AU - Prasad, G

PY - 2009/6

Y1 - 2009/6

N2 - Transferring electroencephalogram (EEG)-based brain-computer interface (BCI) systems from synchronous laboratory conditions to real-world applications and situations demands the continuous detection of brain patterns in which the user is in control of the timing and pace of the BCI instead of the computer. A self-paced BCI requires continuous analysis of the continuing brain activity, however, not only the intentional-control (IC) states have to be detected (e.g., motor imagery and imagination) but also the inactive periods, where the user is in a non-control state (NC). The nonstationary nature of the brain signals provides a rather unstable input resulting in uncertainty and complexity in the control. Intelligent processing algorithms adapted to the task at hand are a prerequisite for reliable self-paced BCI applications. This work presents a novel intelligent processing strategy for the realization of an effective self-paced BCI which has the capability to reduce noise as well as adaptation to continuous online biasing. A Savitzki-Golay filter has been applied to remove spikes/outliers while preserving the feature set structure. An anti-bias system is introduced which readjusts the classification output based on the brain's current and previous states. Furthermore, a multiple threshold algorithm is applied on the resultant unbiased classifier output for improved accuracy. These algorithms are tested on 4 real and 3 artificial datasets and results shown are considerably promising and demonstrate the significance of the proposed intelligent and adaptive algorithms.

AB - Transferring electroencephalogram (EEG)-based brain-computer interface (BCI) systems from synchronous laboratory conditions to real-world applications and situations demands the continuous detection of brain patterns in which the user is in control of the timing and pace of the BCI instead of the computer. A self-paced BCI requires continuous analysis of the continuing brain activity, however, not only the intentional-control (IC) states have to be detected (e.g., motor imagery and imagination) but also the inactive periods, where the user is in a non-control state (NC). The nonstationary nature of the brain signals provides a rather unstable input resulting in uncertainty and complexity in the control. Intelligent processing algorithms adapted to the task at hand are a prerequisite for reliable self-paced BCI applications. This work presents a novel intelligent processing strategy for the realization of an effective self-paced BCI which has the capability to reduce noise as well as adaptation to continuous online biasing. A Savitzki-Golay filter has been applied to remove spikes/outliers while preserving the feature set structure. An anti-bias system is introduced which readjusts the classification output based on the brain's current and previous states. Furthermore, a multiple threshold algorithm is applied on the resultant unbiased classifier output for improved accuracy. These algorithms are tested on 4 real and 3 artificial datasets and results shown are considerably promising and demonstrate the significance of the proposed intelligent and adaptive algorithms.

U2 - 10.1109/NER.2009.5109296

DO - 10.1109/NER.2009.5109296

M3 - Conference contribution

SP - 315

EP - 318

BT - Unknown Host Publication

ER -