Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Classification of EEG signals based on mean-square error optimal time-frequency features

Anderson, Rachele LU orcid and Sandsten, Maria LU (2018) 26th European Signal Processing Conference, EUSIPCO 2018 2018-September. p.106-110
Abstract

This paper illustrates the improvement in accuracy of classification for electroencephalogram (EEG) signals measured during a memory encoding task, by using features based on a mean square error (MSE) optimal time-frequency estimator. The EEG signals are modelled as Locally Stationary Processes, based on the modulation in time of an ordinary stationary covariance function. After estimating the model parameters, we compute the MSE optimal kernel for the estimation of the Wigner-Ville spectrum. We present a simulation study to evaluate the performance of the derived optimal spectral estimator, compared to the single windowed Hanning spectrogram and the Welch spectrogram. Further, the estimation procedure is applied to the measured EEG and... (More)

This paper illustrates the improvement in accuracy of classification for electroencephalogram (EEG) signals measured during a memory encoding task, by using features based on a mean square error (MSE) optimal time-frequency estimator. The EEG signals are modelled as Locally Stationary Processes, based on the modulation in time of an ordinary stationary covariance function. After estimating the model parameters, we compute the MSE optimal kernel for the estimation of the Wigner-Ville spectrum. We present a simulation study to evaluate the performance of the derived optimal spectral estimator, compared to the single windowed Hanning spectrogram and the Welch spectrogram. Further, the estimation procedure is applied to the measured EEG and the time-frequency features extracted from the spectral estimates are used to feed a neural network classifier. Consistent improvement in classification accuracy is obtained by using the features from the proposed estimator, compared to the use of existing methods.

(Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
2018 26th European Signal Processing Conference, EUSIPCO 2018
volume
2018-September
article number
8553130
pages
5 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
26th European Signal Processing Conference, EUSIPCO 2018
conference location
Rome, Italy
conference dates
2018-09-03 - 2018-09-07
external identifiers
  • scopus:85059805925
ISBN
9789082797015
DOI
10.23919/EUSIPCO.2018.8553130
language
English
LU publication?
yes
id
9d550dcd-681d-45d5-b011-e15052ede8f2
date added to LUP
2019-01-24 11:06:35
date last changed
2022-04-25 20:49:21
@inproceedings{9d550dcd-681d-45d5-b011-e15052ede8f2,
  abstract     = {{<p>This paper illustrates the improvement in accuracy of classification for electroencephalogram (EEG) signals measured during a memory encoding task, by using features based on a mean square error (MSE) optimal time-frequency estimator. The EEG signals are modelled as Locally Stationary Processes, based on the modulation in time of an ordinary stationary covariance function. After estimating the model parameters, we compute the MSE optimal kernel for the estimation of the Wigner-Ville spectrum. We present a simulation study to evaluate the performance of the derived optimal spectral estimator, compared to the single windowed Hanning spectrogram and the Welch spectrogram. Further, the estimation procedure is applied to the measured EEG and the time-frequency features extracted from the spectral estimates are used to feed a neural network classifier. Consistent improvement in classification accuracy is obtained by using the features from the proposed estimator, compared to the use of existing methods.</p>}},
  author       = {{Anderson, Rachele and Sandsten, Maria}},
  booktitle    = {{2018 26th European Signal Processing Conference, EUSIPCO 2018}},
  isbn         = {{9789082797015}},
  language     = {{eng}},
  month        = {{11}},
  pages        = {{106--110}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{Classification of EEG signals based on mean-square error optimal time-frequency features}},
  url          = {{http://dx.doi.org/10.23919/EUSIPCO.2018.8553130}},
  doi          = {{10.23919/EUSIPCO.2018.8553130}},
  volume       = {{2018-September}},
  year         = {{2018}},
}