Name
Title | ||
|---|---|---|
Development of a variational Bayesian expectation maximization (VBEM) method for model inversion of multi-area E/MEG model |
Abstract | ||
|---|---|---|
We develop and evaluate a variational Bayesian expectation maximization (VBEM) method for model inversion of our multi-area extended neural mass model (MEN) using EEG/MEG data. Parameters of MEN have suitable prior distributions that enable us to use properties of a conjugate-exponential model in implementing VBEM. Consequently, VBEM leads to analytically tractable forms that starts with initialization and consists of repeated iterations of a variational Bayesian expectation step (VB E-step) and a variational Bayesian maximization step (VB M-step). Posterior distributions of model parameters are updated in the VB M-step. Distribution of the hidden state is updated in the VB E-step using variational extended Kalman smoother. We evaluate and validate performance of VBEM method for model inversion of MEN using simulation studies in various signal-to-noise ratios. The proposed approach provides a useful technique for analyzing effective connectivity using non-invasive EEG and MEG methods. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/ISBI.2011.5872563 | Chicago, IL |
Keywords | Field | DocType |
belief networks,electroencephalography,expectation-maximisation algorithm,magnetoencephalography,medical computing,neurophysiology,physiological models,conjugate-exponential model,model inversion,multiarea extended neural mass model,noninvasive EEG methods,noninvasive MEG methods,signal-noise ratios,variational Bayesian expectation maximization method,variational extended Kalman smoother,EEG,MEG,Model Inversion,Variational Bayesian Expectation Maximization | Data modeling,Model inversion,Computer science,Artificial intelligence,Kalman smoother,Pattern recognition,Expectation–maximization algorithm,Signal-to-noise ratio,Algorithm,Initialization,Maximization,Machine learning,Bayesian probability | Conference |
ISSN | ISBN | Citations |
1945-7928 E-ISBN : 978-1-4244-4128-0 | 978-1-4244-4128-0 | 1 |
PageRank | References | Authors |
0.35 | 4 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Abbas Babajani-Fermi | 1 | 95 | 6.98 |
| kourosh jafarikhouzani | 2 | 261 | 28.87 |
| Hamid Soltanian-Zadeh | 3 | 613 | 84.11 |
| Babajani-Feremi, A. | 4 | 1 | 0.35 |
| Jafari-Khouzani, K. | 5 | 1 | 0.69 |
| Soltanian-Zadeh, H. | 6 | 1 | 0.35 |