Time varying EEG Bandpower Estimation Improves 3D Hand Motion Trajectory Prediction Accuracy

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

Abstract

Motion trajectory prediction (MTP) employs a time-series of band-pass filtered EEG potentials for reconstructing the three-dimensional (3D) trajectory of limb movements with a multiple linear regression (mLR) block. While traditional multiclass classification methods use power values of mu (8-12Hz) and beta (12-30Hz) bands for limb movement based classification, recent MTP brain-computer interface (BCI) studies report the best accuracy using a 0.5-2Hz band-pass filter. We recently introduced a novel approach for MTP BCIs where the time-series of band-pass filtered EEG potentials were replaced with the time-series of power values of subject-specific frequency band(s) prior to the application of mLR. Here we present an analysis of three subjects performing 3D arm movements and comparing the accuracy rates of the standard EEG potential model and the proposed spectrum power-based approach.
LanguageEnglish
Title of host publicationUnknown Host Publication
Number of pages1
DOIs
Publication statusPublished - 5 Jun 2016
EventThe 6th International Brain-Computer Interface Meeting - Asilomar, California
Duration: 5 Jun 2016 → …

Other

OtherThe 6th International Brain-Computer Interface Meeting
Period5/06/16 → …

Fingerprint

Electroencephalography
Bioelectric potentials
Trajectories
Time series
Linear regression
Brain computer interface
Power spectrum
Bandpass filters
Frequency bands

Keywords

  • 3D motion trajectory prediction
  • brain-computer interface (BCI)
  • imagined hand movement
  • electroencephalography (EEG)
  • motor imagery (MI)
  • sensorimotor rhythms (SMR)

Cite this

@inproceedings{968c5afe56fa409fb8835e84a034cd0e,
title = "Time varying EEG Bandpower Estimation Improves 3D Hand Motion Trajectory Prediction Accuracy",
abstract = "Motion trajectory prediction (MTP) employs a time-series of band-pass filtered EEG potentials for reconstructing the three-dimensional (3D) trajectory of limb movements with a multiple linear regression (mLR) block. While traditional multiclass classification methods use power values of mu (8-12Hz) and beta (12-30Hz) bands for limb movement based classification, recent MTP brain-computer interface (BCI) studies report the best accuracy using a 0.5-2Hz band-pass filter. We recently introduced a novel approach for MTP BCIs where the time-series of band-pass filtered EEG potentials were replaced with the time-series of power values of subject-specific frequency band(s) prior to the application of mLR. Here we present an analysis of three subjects performing 3D arm movements and comparing the accuracy rates of the standard EEG potential model and the proposed spectrum power-based approach.",
keywords = "3D motion trajectory prediction, brain-computer interface (BCI), imagined hand movement, electroencephalography (EEG), motor imagery (MI), sensorimotor rhythms (SMR)",
author = "Attila Korik and Nazmul Siddique and Ronen Sosnik and Damien Coyle",
year = "2016",
month = "6",
day = "5",
doi = "10.3217/978-3-85125-467-9-77",
language = "English",
isbn = "978-3-85125-467-9",
booktitle = "Unknown Host Publication",

}

Korik, A, Siddique, N, Sosnik, R & Coyle, D 2016, Time varying EEG Bandpower Estimation Improves 3D Hand Motion Trajectory Prediction Accuracy. in Unknown Host Publication. The 6th International Brain-Computer Interface Meeting, 5/06/16. https://doi.org/10.3217/978-3-85125-467-9-77

Time varying EEG Bandpower Estimation Improves 3D Hand Motion Trajectory Prediction Accuracy. / Korik, Attila; Siddique, Nazmul; Sosnik, Ronen; Coyle, Damien.

Unknown Host Publication. 2016.

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

TY - GEN

T1 - Time varying EEG Bandpower Estimation Improves 3D Hand Motion Trajectory Prediction Accuracy

AU - Korik, Attila

AU - Siddique, Nazmul

AU - Sosnik, Ronen

AU - Coyle, Damien

PY - 2016/6/5

Y1 - 2016/6/5

N2 - Motion trajectory prediction (MTP) employs a time-series of band-pass filtered EEG potentials for reconstructing the three-dimensional (3D) trajectory of limb movements with a multiple linear regression (mLR) block. While traditional multiclass classification methods use power values of mu (8-12Hz) and beta (12-30Hz) bands for limb movement based classification, recent MTP brain-computer interface (BCI) studies report the best accuracy using a 0.5-2Hz band-pass filter. We recently introduced a novel approach for MTP BCIs where the time-series of band-pass filtered EEG potentials were replaced with the time-series of power values of subject-specific frequency band(s) prior to the application of mLR. Here we present an analysis of three subjects performing 3D arm movements and comparing the accuracy rates of the standard EEG potential model and the proposed spectrum power-based approach.

AB - Motion trajectory prediction (MTP) employs a time-series of band-pass filtered EEG potentials for reconstructing the three-dimensional (3D) trajectory of limb movements with a multiple linear regression (mLR) block. While traditional multiclass classification methods use power values of mu (8-12Hz) and beta (12-30Hz) bands for limb movement based classification, recent MTP brain-computer interface (BCI) studies report the best accuracy using a 0.5-2Hz band-pass filter. We recently introduced a novel approach for MTP BCIs where the time-series of band-pass filtered EEG potentials were replaced with the time-series of power values of subject-specific frequency band(s) prior to the application of mLR. Here we present an analysis of three subjects performing 3D arm movements and comparing the accuracy rates of the standard EEG potential model and the proposed spectrum power-based approach.

KW - 3D motion trajectory prediction

KW - brain-computer interface (BCI)

KW - imagined hand movement

KW - electroencephalography (EEG)

KW - motor imagery (MI)

KW - sensorimotor rhythms (SMR)

UR - http://isrc.ulster.ac.uk/dcoyle/contact.html

UR - http://isrc.ulster.ac.uk/dcoyle/contact.html

U2 - 10.3217/978-3-85125-467-9-77

DO - 10.3217/978-3-85125-467-9-77

M3 - Conference contribution

SN - 978-3-85125-467-9

BT - Unknown Host Publication

ER -