A hybrid generative/discriminative method for EEG evoked potential detection

Yonghong Huang, Misha Pavel, Kenneth E. Hild, Deniz Erdogmus, Santosh Mathan

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

5 Scopus citations

Abstract

We propose a new method for the detection of evoked potentials that combines a generative model and a discriminative classifier. The method is a variant of the support vector machine (SVM), which uses the Fisher kernel. The kernel function is derived from a generative statistical model known as mixed effects model (MEM). Instead of arbitrarily selecting the Gaussian kernel for the SVM, we exploit the Fisher kernel derived from the MEM for the SVM. The strength of this approach is that it combines the rich information encoded in the generative model, the MEM, with the discriminative power of the SVM algorithm. Our results show that the new method of combining the two complementary approaches - the generative model (MEM) and the discriminative model (SVM) via the Fisher kernel - achieves substantial improvement over the generative model (MEM) and provides better performance than the discriminative model (Gaussian kernel SVM) on the detection of evoked potentials in neural signals.

Original languageEnglish (US)
Title of host publication2009 4th International IEEE/EMBS Conference on Neural Engineering, NER '09
Pages283-286
Number of pages4
DOIs
Publication statusPublished - 2009
Event2009 4th International IEEE/EMBS Conference on Neural Engineering, NER '09 - Antalya, Turkey
Duration: Apr 29 2009May 2 2009

Other

Other2009 4th International IEEE/EMBS Conference on Neural Engineering, NER '09
CountryTurkey
CityAntalya
Period4/29/095/2/09

    Fingerprint

ASJC Scopus subject areas

  • Biomedical Engineering
  • Clinical Neurology
  • Neuroscience(all)

Cite this

Huang, Y., Pavel, M., Hild, K. E., Erdogmus, D., & Mathan, S. (2009). A hybrid generative/discriminative method for EEG evoked potential detection. In 2009 4th International IEEE/EMBS Conference on Neural Engineering, NER '09 (pp. 283-286). [5109288] https://doi.org/10.1109/NER.2009.5109288