Mixed effects models for eeg evoked response detection

Yonghong Huang, Deniz Erdogmus, Misha Pavel, Santosh Mathan

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

7 Citations (Scopus)

Abstract

Human brain signals associated with perceptual processes have been shown to be useful for visual target image search. For the purpose of online training, we develop a novel mixed effects evoked response detector, which is capable of combining individual random effects and population fixed effects, for the analysis of neural signatures associated with targets. To avoid numerical problems in high dimensional matrix computations, we develop equivalent dimension reduced expressions for the mixed models. We construct the mixed effects evoked response model using principal component analysis to provide bases for the population model and linear discriminant analysis (LDA) to provide bases for the individual models. In addition, the LDA is adopted for Elecroencephalography channel dimensionality reduction. Data collected at different time and experimental conditions from two subjects performing image search tasks are utilized to assess the quality of the models. We also compare the proposed model with the support vector machine (SVM). The results demonstrate that the mixed models approach the SVM and provide reliable inference on cross session evaluation for the single-trial evoked response detection.

Original languageEnglish (US)
Title of host publicationProceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008
Pages91-96
Number of pages6
DOIs
StatePublished - 2008
Event2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008 - Cancun, Mexico
Duration: Oct 16 2008Oct 19 2008

Other

Other2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008
CountryMexico
CityCancun
Period10/16/0810/19/08

Fingerprint

Discriminant analysis
Support vector machines
Principal component analysis
Brain
Detectors

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Electrical and Electronic Engineering

Cite this

Huang, Y., Erdogmus, D., Pavel, M., & Mathan, S. (2008). Mixed effects models for eeg evoked response detection. In Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008 (pp. 91-96). [4685461] https://doi.org/10.1109/MLSP.2008.4685461

Mixed effects models for eeg evoked response detection. / Huang, Yonghong; Erdogmus, Deniz; Pavel, Misha; Mathan, Santosh.

Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008. 2008. p. 91-96 4685461.

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

Huang, Y, Erdogmus, D, Pavel, M & Mathan, S 2008, Mixed effects models for eeg evoked response detection. in Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008., 4685461, pp. 91-96, 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008, Cancun, Mexico, 10/16/08. https://doi.org/10.1109/MLSP.2008.4685461
Huang Y, Erdogmus D, Pavel M, Mathan S. Mixed effects models for eeg evoked response detection. In Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008. 2008. p. 91-96. 4685461 https://doi.org/10.1109/MLSP.2008.4685461
Huang, Yonghong ; Erdogmus, Deniz ; Pavel, Misha ; Mathan, Santosh. / Mixed effects models for eeg evoked response detection. Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008. 2008. pp. 91-96
@inproceedings{13ba04df6bd8464b8e3508fc770bffc8,
title = "Mixed effects models for eeg evoked response detection",
abstract = "Human brain signals associated with perceptual processes have been shown to be useful for visual target image search. For the purpose of online training, we develop a novel mixed effects evoked response detector, which is capable of combining individual random effects and population fixed effects, for the analysis of neural signatures associated with targets. To avoid numerical problems in high dimensional matrix computations, we develop equivalent dimension reduced expressions for the mixed models. We construct the mixed effects evoked response model using principal component analysis to provide bases for the population model and linear discriminant analysis (LDA) to provide bases for the individual models. In addition, the LDA is adopted for Elecroencephalography channel dimensionality reduction. Data collected at different time and experimental conditions from two subjects performing image search tasks are utilized to assess the quality of the models. We also compare the proposed model with the support vector machine (SVM). The results demonstrate that the mixed models approach the SVM and provide reliable inference on cross session evaluation for the single-trial evoked response detection.",
author = "Yonghong Huang and Deniz Erdogmus and Misha Pavel and Santosh Mathan",
year = "2008",
doi = "10.1109/MLSP.2008.4685461",
language = "English (US)",
isbn = "9781424423767",
pages = "91--96",
booktitle = "Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008",

}

TY - GEN

T1 - Mixed effects models for eeg evoked response detection

AU - Huang, Yonghong

AU - Erdogmus, Deniz

AU - Pavel, Misha

AU - Mathan, Santosh

PY - 2008

Y1 - 2008

N2 - Human brain signals associated with perceptual processes have been shown to be useful for visual target image search. For the purpose of online training, we develop a novel mixed effects evoked response detector, which is capable of combining individual random effects and population fixed effects, for the analysis of neural signatures associated with targets. To avoid numerical problems in high dimensional matrix computations, we develop equivalent dimension reduced expressions for the mixed models. We construct the mixed effects evoked response model using principal component analysis to provide bases for the population model and linear discriminant analysis (LDA) to provide bases for the individual models. In addition, the LDA is adopted for Elecroencephalography channel dimensionality reduction. Data collected at different time and experimental conditions from two subjects performing image search tasks are utilized to assess the quality of the models. We also compare the proposed model with the support vector machine (SVM). The results demonstrate that the mixed models approach the SVM and provide reliable inference on cross session evaluation for the single-trial evoked response detection.

AB - Human brain signals associated with perceptual processes have been shown to be useful for visual target image search. For the purpose of online training, we develop a novel mixed effects evoked response detector, which is capable of combining individual random effects and population fixed effects, for the analysis of neural signatures associated with targets. To avoid numerical problems in high dimensional matrix computations, we develop equivalent dimension reduced expressions for the mixed models. We construct the mixed effects evoked response model using principal component analysis to provide bases for the population model and linear discriminant analysis (LDA) to provide bases for the individual models. In addition, the LDA is adopted for Elecroencephalography channel dimensionality reduction. Data collected at different time and experimental conditions from two subjects performing image search tasks are utilized to assess the quality of the models. We also compare the proposed model with the support vector machine (SVM). The results demonstrate that the mixed models approach the SVM and provide reliable inference on cross session evaluation for the single-trial evoked response detection.

UR - http://www.scopus.com/inward/record.url?scp=58049149870&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58049149870&partnerID=8YFLogxK

U2 - 10.1109/MLSP.2008.4685461

DO - 10.1109/MLSP.2008.4685461

M3 - Conference contribution

AN - SCOPUS:58049149870

SN - 9781424423767

SP - 91

EP - 96

BT - Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008

ER -