3D Hand Movement Velocity Reconstruction using Power Spectral Density of EEG Signals and Neural Network

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

Abstract

Three dimensional (3D) limb motion trajectory is predictable with a non-invasive brain-computer interface (BCI). To date, most non-invasive motion trajectory prediction BCIs use potential values of electroencephalographic (EEG) signals as the input to a multiple linear regression (mLR) based kinetic data estimator. We investigated the possible improvement in accuracy of 3D hand movement prediction (i.e., the correlation of registered and reconstructed hand velocities) by replacing raw EEG potentials with spectrum power values of specific EEG bands. We also investigated if a non-linear neural network based estimator outperformed the mLR approach. The spectrum power model provided significantly higher accuracy (R~0.60) compared to the similar EEG potentials based approach (R~0.45). Additionally, when replacing the mLR based kinetic data estimation module with a feed-forward neural network (NN) we found the NN based spectrum power model provided higher accuracy (R~0.70) compared to the similar mLR based approach (R~0.60).
LanguageEnglish
Title of host publicationUnknown Host Publication
Number of pages4
Publication statusPublished - 2015
Event37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Milan, Italy
Duration: 1 Jan 2015 → …

Conference

Conference37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Period1/01/15 → …

Fingerprint

Power spectral density
Linear regression
Power spectrum
Neural networks
Trajectories
Brain computer interface
Kinetics
Feedforward neural networks

Keywords

  • EEG
  • neural network
  • BCI
  • brain-computer interface
  • motion trajectory
  • hand movement
  • 3d
  • prediction

Cite this

@inproceedings{669bf2ae5e6949a6a377e2dba94625c1,
title = "3D Hand Movement Velocity Reconstruction using Power Spectral Density of EEG Signals and Neural Network",
abstract = "Three dimensional (3D) limb motion trajectory is predictable with a non-invasive brain-computer interface (BCI). To date, most non-invasive motion trajectory prediction BCIs use potential values of electroencephalographic (EEG) signals as the input to a multiple linear regression (mLR) based kinetic data estimator. We investigated the possible improvement in accuracy of 3D hand movement prediction (i.e., the correlation of registered and reconstructed hand velocities) by replacing raw EEG potentials with spectrum power values of specific EEG bands. We also investigated if a non-linear neural network based estimator outperformed the mLR approach. The spectrum power model provided significantly higher accuracy (R~0.60) compared to the similar EEG potentials based approach (R~0.45). Additionally, when replacing the mLR based kinetic data estimation module with a feed-forward neural network (NN) we found the NN based spectrum power model provided higher accuracy (R~0.70) compared to the similar mLR based approach (R~0.60).",
keywords = "EEG, neural network, BCI, brain-computer interface, motion trajectory, hand movement, 3d, prediction",
author = "Attila Korik and NH Siddique and Ronen Sosnik and Damien Coyle",
year = "2015",
language = "English",
booktitle = "Unknown Host Publication",

}

Korik, A, Siddique, NH, Sosnik, R & Coyle, D 2015, 3D Hand Movement Velocity Reconstruction using Power Spectral Density of EEG Signals and Neural Network. in Unknown Host Publication. 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 1/01/15.

3D Hand Movement Velocity Reconstruction using Power Spectral Density of EEG Signals and Neural Network. / Korik, Attila; Siddique, NH; Sosnik, Ronen; Coyle, Damien.

Unknown Host Publication. 2015.

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

TY - GEN

T1 - 3D Hand Movement Velocity Reconstruction using Power Spectral Density of EEG Signals and Neural Network

AU - Korik, Attila

AU - Siddique, NH

AU - Sosnik, Ronen

AU - Coyle, Damien

PY - 2015

Y1 - 2015

N2 - Three dimensional (3D) limb motion trajectory is predictable with a non-invasive brain-computer interface (BCI). To date, most non-invasive motion trajectory prediction BCIs use potential values of electroencephalographic (EEG) signals as the input to a multiple linear regression (mLR) based kinetic data estimator. We investigated the possible improvement in accuracy of 3D hand movement prediction (i.e., the correlation of registered and reconstructed hand velocities) by replacing raw EEG potentials with spectrum power values of specific EEG bands. We also investigated if a non-linear neural network based estimator outperformed the mLR approach. The spectrum power model provided significantly higher accuracy (R~0.60) compared to the similar EEG potentials based approach (R~0.45). Additionally, when replacing the mLR based kinetic data estimation module with a feed-forward neural network (NN) we found the NN based spectrum power model provided higher accuracy (R~0.70) compared to the similar mLR based approach (R~0.60).

AB - Three dimensional (3D) limb motion trajectory is predictable with a non-invasive brain-computer interface (BCI). To date, most non-invasive motion trajectory prediction BCIs use potential values of electroencephalographic (EEG) signals as the input to a multiple linear regression (mLR) based kinetic data estimator. We investigated the possible improvement in accuracy of 3D hand movement prediction (i.e., the correlation of registered and reconstructed hand velocities) by replacing raw EEG potentials with spectrum power values of specific EEG bands. We also investigated if a non-linear neural network based estimator outperformed the mLR approach. The spectrum power model provided significantly higher accuracy (R~0.60) compared to the similar EEG potentials based approach (R~0.45). Additionally, when replacing the mLR based kinetic data estimation module with a feed-forward neural network (NN) we found the NN based spectrum power model provided higher accuracy (R~0.70) compared to the similar mLR based approach (R~0.60).

KW - EEG

KW - neural network

KW - BCI

KW - brain-computer interface

KW - motion trajectory

KW - hand movement

KW - 3d

KW - prediction

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

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

M3 - Conference contribution

BT - Unknown Host Publication

ER -