Identification of Number of Brain Signal Sources Using BP Neural Networks

Source localization in the brain is one of the important inverse problems in electrophysiology. We propose a method that applies artificial neural networks approach to identification of the number of dipole sources in the brain from the Electroencephalogram (EEG) recordings. We demonstrate the performance of the neural network system we trained by error backpropagation (BP) algorithm on the discrimination between one dipole source and two dipoles. The results of computer simulation are shown on the network characteristics for some cases of location conditions when the number of dipoles is two.

[1]  D. A. Driscoll,et al.  Current Distribution in the Brain From Surface Electrodes , 1968, Anesthesia and analgesia.

[2]  Udantha R. Abeyratne,et al.  Artificial neural networks for source localization in the human brain , 2005, Brain Topography.

[3]  U Moström,et al.  Location of electric current sources in the human brain estimated by the dipole tracing method of the scalp-skull-brain (SSB) head model. , 1994, Electroencephalography and clinical neurophysiology.

[4]  J.C. Mosher,et al.  Recursive MUSIC: A framework for EEG and MEG source localization , 1998, IEEE Transactions on Biomedical Engineering.

[5]  Y Okamoto,et al.  Moving multiple dipole model for cardiac activity. , 1982, Japanese heart journal.

[6]  Qinyu Zhang,et al.  Accuracy of single dipole source localization by BP neural networks from 18-channel EEGs , 2003 .

[7]  Philipp Slusallek,et al.  Introduction to real-time ray tracing , 2005, SIGGRAPH Courses.

[8]  B. N. Cuffin,et al.  Eccentric spheres models of the head , 1991, IEEE Transactions on Biomedical Engineering.

[9]  J. P. Ary,et al.  Location of Sources of Evoked Scalp Potentials: Corrections for Skull and Scalp Thicknesses , 1981, IEEE Transactions on Biomedical Engineering.

[10]  J Z Wang,et al.  On cortical folds and neuromagnetic fields. , 1991, Electroencephalography and clinical neurophysiology.

[11]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .