A dynamic multi-channel decision-fusion strategy to classify differential brain activity

Hyunseok Kook, Lalit Gupta, Srinivas Kota, Dennis Molfese

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

2 Citations (Scopus)

Abstract

A strategy is developed to dynamically fuse classification information from multiple channels in order to accurately classify brain activity elicited by external stimuli. The strategy is dynamic in the sense that different channels are selected at different time-instants. The channels are ranked at different time-instants according to their classification accuracies. Although the brain signals are multivariate signals, the classifiers are simple univariate classifiers. A rule is formulated to dynamically select different channels at different time-instants during the testing phase. The independent decisions of the selected channels are fused into a decision fusion vector. The resulting decision fusion vector is optimally classified using a discrete Bayes classifier. The dynamic decision fusion strategy is tested on 3 evoked potential (EP) data sets of 2 different paradigms using univariate mean and Gaussian classifiers. It is shown that the strategy yields high classification accuracies especially for high noise cases. Furthermore, the generalized formulation of the strategy makes it applicable to a wide range of multi-category classification problems involving multivariate signals collected from multiple sensors.

Original languageEnglish (US)
Title of host publication29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07
Pages3212-3215
Number of pages4
DOIs
StatePublished - Dec 1 2007
Event29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07 - Lyon, France
Duration: Aug 23 2007Aug 26 2007

Publication series

NameAnnual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
ISSN (Print)0589-1019

Conference

Conference29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07
CountryFrance
CityLyon
Period8/23/078/26/07

Fingerprint

Brain
Classifiers
Fusion reactions
Bioelectric potentials
Electric fuses
Sensors
Testing

Keywords

  • Decision fusion
  • Evoked potentials
  • Multi-sensor fusion
  • Parametric classification

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Kook, H., Gupta, L., Kota, S., & Molfese, D. (2007). A dynamic multi-channel decision-fusion strategy to classify differential brain activity. In 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07 (pp. 3212-3215). [4353013] (Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings). https://doi.org/10.1109/IEMBS.2007.4353013

A dynamic multi-channel decision-fusion strategy to classify differential brain activity. / Kook, Hyunseok; Gupta, Lalit; Kota, Srinivas; Molfese, Dennis.

29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07. 2007. p. 3212-3215 4353013 (Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings).

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

Kook, H, Gupta, L, Kota, S & Molfese, D 2007, A dynamic multi-channel decision-fusion strategy to classify differential brain activity. in 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07., 4353013, Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, pp. 3212-3215, 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07, Lyon, France, 8/23/07. https://doi.org/10.1109/IEMBS.2007.4353013
Kook H, Gupta L, Kota S, Molfese D. A dynamic multi-channel decision-fusion strategy to classify differential brain activity. In 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07. 2007. p. 3212-3215. 4353013. (Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings). https://doi.org/10.1109/IEMBS.2007.4353013
Kook, Hyunseok ; Gupta, Lalit ; Kota, Srinivas ; Molfese, Dennis. / A dynamic multi-channel decision-fusion strategy to classify differential brain activity. 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07. 2007. pp. 3212-3215 (Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings).
@inproceedings{a5f80a4ffb8246b2870e6b4cff559dce,
title = "A dynamic multi-channel decision-fusion strategy to classify differential brain activity",
abstract = "A strategy is developed to dynamically fuse classification information from multiple channels in order to accurately classify brain activity elicited by external stimuli. The strategy is dynamic in the sense that different channels are selected at different time-instants. The channels are ranked at different time-instants according to their classification accuracies. Although the brain signals are multivariate signals, the classifiers are simple univariate classifiers. A rule is formulated to dynamically select different channels at different time-instants during the testing phase. The independent decisions of the selected channels are fused into a decision fusion vector. The resulting decision fusion vector is optimally classified using a discrete Bayes classifier. The dynamic decision fusion strategy is tested on 3 evoked potential (EP) data sets of 2 different paradigms using univariate mean and Gaussian classifiers. It is shown that the strategy yields high classification accuracies especially for high noise cases. Furthermore, the generalized formulation of the strategy makes it applicable to a wide range of multi-category classification problems involving multivariate signals collected from multiple sensors.",
keywords = "Decision fusion, Evoked potentials, Multi-sensor fusion, Parametric classification",
author = "Hyunseok Kook and Lalit Gupta and Srinivas Kota and Dennis Molfese",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/IEMBS.2007.4353013",
language = "English (US)",
isbn = "1424407885",
series = "Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings",
pages = "3212--3215",
booktitle = "29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07",

}

TY - GEN

T1 - A dynamic multi-channel decision-fusion strategy to classify differential brain activity

AU - Kook, Hyunseok

AU - Gupta, Lalit

AU - Kota, Srinivas

AU - Molfese, Dennis

PY - 2007/12/1

Y1 - 2007/12/1

N2 - A strategy is developed to dynamically fuse classification information from multiple channels in order to accurately classify brain activity elicited by external stimuli. The strategy is dynamic in the sense that different channels are selected at different time-instants. The channels are ranked at different time-instants according to their classification accuracies. Although the brain signals are multivariate signals, the classifiers are simple univariate classifiers. A rule is formulated to dynamically select different channels at different time-instants during the testing phase. The independent decisions of the selected channels are fused into a decision fusion vector. The resulting decision fusion vector is optimally classified using a discrete Bayes classifier. The dynamic decision fusion strategy is tested on 3 evoked potential (EP) data sets of 2 different paradigms using univariate mean and Gaussian classifiers. It is shown that the strategy yields high classification accuracies especially for high noise cases. Furthermore, the generalized formulation of the strategy makes it applicable to a wide range of multi-category classification problems involving multivariate signals collected from multiple sensors.

AB - A strategy is developed to dynamically fuse classification information from multiple channels in order to accurately classify brain activity elicited by external stimuli. The strategy is dynamic in the sense that different channels are selected at different time-instants. The channels are ranked at different time-instants according to their classification accuracies. Although the brain signals are multivariate signals, the classifiers are simple univariate classifiers. A rule is formulated to dynamically select different channels at different time-instants during the testing phase. The independent decisions of the selected channels are fused into a decision fusion vector. The resulting decision fusion vector is optimally classified using a discrete Bayes classifier. The dynamic decision fusion strategy is tested on 3 evoked potential (EP) data sets of 2 different paradigms using univariate mean and Gaussian classifiers. It is shown that the strategy yields high classification accuracies especially for high noise cases. Furthermore, the generalized formulation of the strategy makes it applicable to a wide range of multi-category classification problems involving multivariate signals collected from multiple sensors.

KW - Decision fusion

KW - Evoked potentials

KW - Multi-sensor fusion

KW - Parametric classification

UR - http://www.scopus.com/inward/record.url?scp=57649185075&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57649185075&partnerID=8YFLogxK

U2 - 10.1109/IEMBS.2007.4353013

DO - 10.1109/IEMBS.2007.4353013

M3 - Conference contribution

C2 - 18002679

AN - SCOPUS:57649185075

SN - 1424407885

SN - 9781424407880

T3 - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

SP - 3212

EP - 3215

BT - 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07

ER -