An offline/real-time artifact rejection strategy to improve the classification of multi-channel evoked potentials

Hyunseok Kook, Lalit Gupta, Srinivas Kota, Dennis L Molfese, H. Lyytinen

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

The primary goal of this paper is to improve the classification of multi-channel evoked potentials (EPs) by introducing a temporal domain artifact detection strategy and using this strategy to (a) evaluate how the performance of classifiers is affected by artifacts and (b) show how the performance can be improved by detecting and rejecting artifacts in offline and real-time classification experiments. Using a pattern recognition approach, an artifact is defined in this study as any signal that may lead to inaccurate classifier parameter estimation and inaccurate testing. The temporal domain artifact detection tests include: a within-channel standard deviation (STD) test that can detect signals with little or abnormal variations in each channel and also detect faulty channels, a within-channel clipping (CL) test to detect amplitude clipped EPs in each channel, and a multi-channel EP median distance (MC-MED) test to detect atypical signals not identified by the STD and CL tests. Because the MC-MED test is class-dependent, a novel "pre-testing" approach is developed to identify artifacts in real-time classification experiments. The performance of the artifact detection strategy is demonstrated on real single-trial EP ensembles and it is shown that the strategy is quite effective in identifying atypical EPs. In order to demonstrate the effects of artifacts on classifier performance, a series of classification experiments are designed using a multi-channel decision fusion classification algorithm. Specifically, the classification performance is evaluated on (a) real EP ensembles with artifact contaminations in the training and test sets and (b) ensembles that are free of artifacts in both the training and test sets. It is shown that the improvement in classification accuracy through the incorporation of the artifact detection strategy can be quite significant in real-time classification trials. Furthermore, the generalized formulation of the artifact rejection classification strategy makes it adaptable to various other problems involving the multi-class classification of multivariate signals of multiple sensors.

Original languageEnglish (US)
Pages (from-to)1985-1996
Number of pages12
JournalPattern Recognition
Volume41
Issue number6
DOIs
StatePublished - Jun 1 2008

Fingerprint

Bioelectric potentials
Classifiers
Experiments
Testing
Parameter estimation
Pattern recognition
Contamination
Fusion reactions

Keywords

  • Artifact detection
  • Decision fusion
  • Evoked potentials

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

An offline/real-time artifact rejection strategy to improve the classification of multi-channel evoked potentials. / Kook, Hyunseok; Gupta, Lalit; Kota, Srinivas; Molfese, Dennis L; Lyytinen, H.

In: Pattern Recognition, Vol. 41, No. 6, 01.06.2008, p. 1985-1996.

Research output: Contribution to journalArticle

Kook, Hyunseok ; Gupta, Lalit ; Kota, Srinivas ; Molfese, Dennis L ; Lyytinen, H. / An offline/real-time artifact rejection strategy to improve the classification of multi-channel evoked potentials. In: Pattern Recognition. 2008 ; Vol. 41, No. 6. pp. 1985-1996.
@article{445c7c3f55254cc0920373c4af6711e7,
title = "An offline/real-time artifact rejection strategy to improve the classification of multi-channel evoked potentials",
abstract = "The primary goal of this paper is to improve the classification of multi-channel evoked potentials (EPs) by introducing a temporal domain artifact detection strategy and using this strategy to (a) evaluate how the performance of classifiers is affected by artifacts and (b) show how the performance can be improved by detecting and rejecting artifacts in offline and real-time classification experiments. Using a pattern recognition approach, an artifact is defined in this study as any signal that may lead to inaccurate classifier parameter estimation and inaccurate testing. The temporal domain artifact detection tests include: a within-channel standard deviation (STD) test that can detect signals with little or abnormal variations in each channel and also detect faulty channels, a within-channel clipping (CL) test to detect amplitude clipped EPs in each channel, and a multi-channel EP median distance (MC-MED) test to detect atypical signals not identified by the STD and CL tests. Because the MC-MED test is class-dependent, a novel {"}pre-testing{"} approach is developed to identify artifacts in real-time classification experiments. The performance of the artifact detection strategy is demonstrated on real single-trial EP ensembles and it is shown that the strategy is quite effective in identifying atypical EPs. In order to demonstrate the effects of artifacts on classifier performance, a series of classification experiments are designed using a multi-channel decision fusion classification algorithm. Specifically, the classification performance is evaluated on (a) real EP ensembles with artifact contaminations in the training and test sets and (b) ensembles that are free of artifacts in both the training and test sets. It is shown that the improvement in classification accuracy through the incorporation of the artifact detection strategy can be quite significant in real-time classification trials. Furthermore, the generalized formulation of the artifact rejection classification strategy makes it adaptable to various other problems involving the multi-class classification of multivariate signals of multiple sensors.",
keywords = "Artifact detection, Decision fusion, Evoked potentials",
author = "Hyunseok Kook and Lalit Gupta and Srinivas Kota and Molfese, {Dennis L} and H. Lyytinen",
year = "2008",
month = "6",
day = "1",
doi = "10.1016/j.patcog.2007.09.001",
language = "English (US)",
volume = "41",
pages = "1985--1996",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "6",

}

TY - JOUR

T1 - An offline/real-time artifact rejection strategy to improve the classification of multi-channel evoked potentials

AU - Kook, Hyunseok

AU - Gupta, Lalit

AU - Kota, Srinivas

AU - Molfese, Dennis L

AU - Lyytinen, H.

PY - 2008/6/1

Y1 - 2008/6/1

N2 - The primary goal of this paper is to improve the classification of multi-channel evoked potentials (EPs) by introducing a temporal domain artifact detection strategy and using this strategy to (a) evaluate how the performance of classifiers is affected by artifacts and (b) show how the performance can be improved by detecting and rejecting artifacts in offline and real-time classification experiments. Using a pattern recognition approach, an artifact is defined in this study as any signal that may lead to inaccurate classifier parameter estimation and inaccurate testing. The temporal domain artifact detection tests include: a within-channel standard deviation (STD) test that can detect signals with little or abnormal variations in each channel and also detect faulty channels, a within-channel clipping (CL) test to detect amplitude clipped EPs in each channel, and a multi-channel EP median distance (MC-MED) test to detect atypical signals not identified by the STD and CL tests. Because the MC-MED test is class-dependent, a novel "pre-testing" approach is developed to identify artifacts in real-time classification experiments. The performance of the artifact detection strategy is demonstrated on real single-trial EP ensembles and it is shown that the strategy is quite effective in identifying atypical EPs. In order to demonstrate the effects of artifacts on classifier performance, a series of classification experiments are designed using a multi-channel decision fusion classification algorithm. Specifically, the classification performance is evaluated on (a) real EP ensembles with artifact contaminations in the training and test sets and (b) ensembles that are free of artifacts in both the training and test sets. It is shown that the improvement in classification accuracy through the incorporation of the artifact detection strategy can be quite significant in real-time classification trials. Furthermore, the generalized formulation of the artifact rejection classification strategy makes it adaptable to various other problems involving the multi-class classification of multivariate signals of multiple sensors.

AB - The primary goal of this paper is to improve the classification of multi-channel evoked potentials (EPs) by introducing a temporal domain artifact detection strategy and using this strategy to (a) evaluate how the performance of classifiers is affected by artifacts and (b) show how the performance can be improved by detecting and rejecting artifacts in offline and real-time classification experiments. Using a pattern recognition approach, an artifact is defined in this study as any signal that may lead to inaccurate classifier parameter estimation and inaccurate testing. The temporal domain artifact detection tests include: a within-channel standard deviation (STD) test that can detect signals with little or abnormal variations in each channel and also detect faulty channels, a within-channel clipping (CL) test to detect amplitude clipped EPs in each channel, and a multi-channel EP median distance (MC-MED) test to detect atypical signals not identified by the STD and CL tests. Because the MC-MED test is class-dependent, a novel "pre-testing" approach is developed to identify artifacts in real-time classification experiments. The performance of the artifact detection strategy is demonstrated on real single-trial EP ensembles and it is shown that the strategy is quite effective in identifying atypical EPs. In order to demonstrate the effects of artifacts on classifier performance, a series of classification experiments are designed using a multi-channel decision fusion classification algorithm. Specifically, the classification performance is evaluated on (a) real EP ensembles with artifact contaminations in the training and test sets and (b) ensembles that are free of artifacts in both the training and test sets. It is shown that the improvement in classification accuracy through the incorporation of the artifact detection strategy can be quite significant in real-time classification trials. Furthermore, the generalized formulation of the artifact rejection classification strategy makes it adaptable to various other problems involving the multi-class classification of multivariate signals of multiple sensors.

KW - Artifact detection

KW - Decision fusion

KW - Evoked potentials

UR - http://www.scopus.com/inward/record.url?scp=38849102361&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38849102361&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2007.09.001

DO - 10.1016/j.patcog.2007.09.001

M3 - Article

VL - 41

SP - 1985

EP - 1996

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 6

ER -