ERP SOURCE RECONSTRUCTION BY USING PARTICLE SWARM OPTIMIZATION


Creative Commons License

Alp Y. K., Arikan O., Karakas S.

IEEE International Conference on Acoustics, Speech and Signal Processing, Taipei, Taiwan, 19 - 24 April 2009, pp.365-366 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/icassp.2009.4959596
  • City: Taipei
  • Country: Taiwan
  • Page Numbers: pp.365-366
  • Hacettepe University Affiliated: Yes

Abstract

Localization of the sources of Event Related Potentials (ERP) is a challenging inverse problem, especially to resolve sources of neural activity occurring simultaneously. By using an effective dipole source model, we propose a new technique for accurate source localization of ER-P signals. The parameters of the dipole ERP sources are optimally chosen by using Particle Swarm Optimization technique. Obtained results on synthetic data sets show that proposed method well localizes the dipoles on their actual locations. On real data sets, the fit error between the actual and reconstructed data is successfully reduced to noise level by localizing a few dipoles in the brain.