Genetic algorithms for dipole location of fetal magnetocardiography.

Journal: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
PMID:

Abstract

In this paper, we explore the use of Maximum Likelihood (ML) method with Genetic Algorithms (GA) as global optimization procedure for source reconstruction in fetal magnetocardiography (fMCG) data. A multiple equivalent current dipole (ECD) model was used for sources active in different time samples. Inverse solutions across time were obtained for a single-dipole approximation to estimate the trajectory of the dipole position. We compared the GA and SIMPLEX methods in a simulation environment under noise conditions. Methods are applied on a real fMCG data. Results show robust estimators of the cardiac sources when GA is used as optimization technique.

Authors

  • D Escalona-Vargas
  • P Murphy
  • C L Lowery
  • H Eswaran