A convolutional neural network for steady state visual evoked potential classification under ambulatory environment

No Sang Kwak, Klaus Muller, Seong Whan Lee

Research output: Contribution to journalArticle

40 Citations (Scopus)

Abstract

The robust analysis of neural signals is a challenging problem. Here, we contribute a convolutional neural network (CNN) for the robust classification of a steady-state visual evoked potentials (SSVEPs) paradigm. We measure electroencephalogram (EEG)-based SSVEPs for a brain-controlled exoskeleton under ambulatory conditions in which numerous artifacts may deteriorate decoding. The proposed CNN is shown to achieve reliable performance under these challenging conditions. To validate the proposed method, we have acquired an SSVEP dataset under two conditions: 1) a static environment, in a standing position while fixated into a lower-limb exoskeleton and 2) an ambulatory environment, walking along a test course wearing the exoskeleton (here, artifacts are most challenging). The proposed CNN is compared to a standard neural network and other state-of-the-art methods for SSVEP decoding (i.e., a canonical correlation analysis (CCA)-based classifier, a multivariate synchronization index (MSI), a CCA combined with k-nearest neighbors (CCA-KNN) classifier) in an offline analysis. We found highly encouraging SSVEP decoding results for the CNN architecture, surpassing those of other methods with classification rates of 99.28% and 94.03% in the static and ambulatory conditions, respectively. A subsequent analysis inspects the representation found by the CNN at each layer and can thus contribute to a better understanding of the CNN's robust, accurate decoding abilities.

Original languageEnglish
Article numbere0172578
JournalPLoS One
Volume12
Issue number2
DOIs
Publication statusPublished - 2017 Feb 1

Fingerprint

evoked potentials
Visual Evoked Potentials
Bioelectric potentials
neural networks
Neural networks
exoskeleton
Decoding
Artifacts
Classifiers
electroencephalography
Posture
Walking
Electroencephalography
Lower Extremity
Network architecture
limbs (animal)
walking
Brain
Synchronization
methodology

ASJC Scopus subject areas

  • Medicine(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

A convolutional neural network for steady state visual evoked potential classification under ambulatory environment. / Kwak, No Sang; Muller, Klaus; Lee, Seong Whan.

In: PLoS One, Vol. 12, No. 2, e0172578, 01.02.2017.

Research output: Contribution to journalArticle

@article{8718c4165071453c96501ee764af146c,
title = "A convolutional neural network for steady state visual evoked potential classification under ambulatory environment",
abstract = "The robust analysis of neural signals is a challenging problem. Here, we contribute a convolutional neural network (CNN) for the robust classification of a steady-state visual evoked potentials (SSVEPs) paradigm. We measure electroencephalogram (EEG)-based SSVEPs for a brain-controlled exoskeleton under ambulatory conditions in which numerous artifacts may deteriorate decoding. The proposed CNN is shown to achieve reliable performance under these challenging conditions. To validate the proposed method, we have acquired an SSVEP dataset under two conditions: 1) a static environment, in a standing position while fixated into a lower-limb exoskeleton and 2) an ambulatory environment, walking along a test course wearing the exoskeleton (here, artifacts are most challenging). The proposed CNN is compared to a standard neural network and other state-of-the-art methods for SSVEP decoding (i.e., a canonical correlation analysis (CCA)-based classifier, a multivariate synchronization index (MSI), a CCA combined with k-nearest neighbors (CCA-KNN) classifier) in an offline analysis. We found highly encouraging SSVEP decoding results for the CNN architecture, surpassing those of other methods with classification rates of 99.28{\%} and 94.03{\%} in the static and ambulatory conditions, respectively. A subsequent analysis inspects the representation found by the CNN at each layer and can thus contribute to a better understanding of the CNN's robust, accurate decoding abilities.",
author = "Kwak, {No Sang} and Klaus Muller and Lee, {Seong Whan}",
year = "2017",
month = "2",
day = "1",
doi = "10.1371/journal.pone.0172578",
language = "English",
volume = "12",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "2",

}

TY - JOUR

T1 - A convolutional neural network for steady state visual evoked potential classification under ambulatory environment

AU - Kwak, No Sang

AU - Muller, Klaus

AU - Lee, Seong Whan

PY - 2017/2/1

Y1 - 2017/2/1

N2 - The robust analysis of neural signals is a challenging problem. Here, we contribute a convolutional neural network (CNN) for the robust classification of a steady-state visual evoked potentials (SSVEPs) paradigm. We measure electroencephalogram (EEG)-based SSVEPs for a brain-controlled exoskeleton under ambulatory conditions in which numerous artifacts may deteriorate decoding. The proposed CNN is shown to achieve reliable performance under these challenging conditions. To validate the proposed method, we have acquired an SSVEP dataset under two conditions: 1) a static environment, in a standing position while fixated into a lower-limb exoskeleton and 2) an ambulatory environment, walking along a test course wearing the exoskeleton (here, artifacts are most challenging). The proposed CNN is compared to a standard neural network and other state-of-the-art methods for SSVEP decoding (i.e., a canonical correlation analysis (CCA)-based classifier, a multivariate synchronization index (MSI), a CCA combined with k-nearest neighbors (CCA-KNN) classifier) in an offline analysis. We found highly encouraging SSVEP decoding results for the CNN architecture, surpassing those of other methods with classification rates of 99.28% and 94.03% in the static and ambulatory conditions, respectively. A subsequent analysis inspects the representation found by the CNN at each layer and can thus contribute to a better understanding of the CNN's robust, accurate decoding abilities.

AB - The robust analysis of neural signals is a challenging problem. Here, we contribute a convolutional neural network (CNN) for the robust classification of a steady-state visual evoked potentials (SSVEPs) paradigm. We measure electroencephalogram (EEG)-based SSVEPs for a brain-controlled exoskeleton under ambulatory conditions in which numerous artifacts may deteriorate decoding. The proposed CNN is shown to achieve reliable performance under these challenging conditions. To validate the proposed method, we have acquired an SSVEP dataset under two conditions: 1) a static environment, in a standing position while fixated into a lower-limb exoskeleton and 2) an ambulatory environment, walking along a test course wearing the exoskeleton (here, artifacts are most challenging). The proposed CNN is compared to a standard neural network and other state-of-the-art methods for SSVEP decoding (i.e., a canonical correlation analysis (CCA)-based classifier, a multivariate synchronization index (MSI), a CCA combined with k-nearest neighbors (CCA-KNN) classifier) in an offline analysis. We found highly encouraging SSVEP decoding results for the CNN architecture, surpassing those of other methods with classification rates of 99.28% and 94.03% in the static and ambulatory conditions, respectively. A subsequent analysis inspects the representation found by the CNN at each layer and can thus contribute to a better understanding of the CNN's robust, accurate decoding abilities.

UR - http://www.scopus.com/inward/record.url?scp=85013356387&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85013356387&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0172578

DO - 10.1371/journal.pone.0172578

M3 - Article

C2 - 28225827

AN - SCOPUS:85013356387

VL - 12

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 2

M1 - e0172578

ER -