Maynooth University

Maynooth University ePrints and eTheses Archive

Maynooth University Library

Subject-Independent Magnetoencephalographic Source Localization by a Multilayer Perceptron

Sung, C. Jun and Pearlmutter, Barak A. (2003) Subject-Independent Magnetoencephalographic Source Localization by a Multilayer Perceptron. Advances in Neural Information Processing Systems, 16. ISSN 1049-5258

[img] Download (99kB)


We describe a system that localizes a single dipole to reasonable accuracy from noisy magnetoencephalographic (MEG) measurements in real time. At its core is a multilayer perceptron (MLP) trained to map sensor signals and head position to dipole location. Including head position overcomes the previous need to retrain the MLP for each subject and session. The training dataset was generated by mapping randomly chosen dipoles and head positions through an analytic model and adding noise from real MEG recordings. After training, a localization took 0.7 ms with an average error of 0.90 cm. A few iterations of a Levenberg-Marquardt routine using the MLP’s output as its initial guess took 15 ms and improved the accuracy to 0.53 cm, only slightly above the statistical limits on accuracy imposed by the noise. We applied these methods to localize single dipole sources from MEG components isolated by blind source separation and compared the estimated locations to those generated by standard manually-assisted commercial software.

Item Type: Article
Keywords: Magnetoencephalographic Source Localization; Multilayer Perceptron;
Subjects: Science & Engineering > Computer Science
Science & Engineering > Hamilton Institute
Item ID: 2050
Depositing User: Dr. Barak Pearlmutter
Date Deposited: 14 Jul 2010 15:46
Journal or Publication Title: Advances in Neural Information Processing Systems
Publisher: Massachusetts Institute of Technology Press (MIT Press)
Refereed: No

Repository Staff Only(login required)

View Item Item control page

Document Downloads

More statistics for this item...