| Presentation | 2010-07-27 Hierarchical Bayes method for NIRS-DOT inverse problem and its phase diagrams Atsushi MIYAMOTO, Kazuho WATANABE, Kazushi IKEDA, Masa-aki SATO, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | NIRS-DOT is a method to reconstruct tomographic images from the data by solving the linear equations, which have ambiguity. In a previous study, a solution to this problem is obtained by the minimum-norm estimation. However, this gives poor results because it does not take into account the localization of brain activity. The hierarchical Bayes framework is convenient to introduce the localization or sparsity into the model. In fact, it works well in the inverse problem of Magnetoencephalography (MEG) current source estimation. In this study, we apply the hierarchical Bayes framework to the inverse problem of the NIRS-DOT. The framework has the two prior hyperparameters that influence the reconstruction accuracy and sparsity. We observed that the phase transition occurs with respect to the hyperparameters, which causes a sudden change in the estimation. Numerical experiments show phase diagrams and the relationship between the hyperparameters and the estimation. This study gives the insight into how to set hyperparameters of the hierarchical Bayes. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | variational Bayes / phase transition / phase diagram / sparseness / NIRS-DOT / inverse problem |
| Paper # | NC2010-38 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 2010/7/20(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Neurocomputing (NC) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Hierarchical Bayes method for NIRS-DOT inverse problem and its phase diagrams |
| Sub Title (in English) | |
| Keyword(1) | variational Bayes |
| Keyword(2) | phase transition |
| Keyword(3) | phase diagram |
| Keyword(4) | sparseness |
| Keyword(5) | NIRS-DOT |
| Keyword(6) | inverse problem |
| 1st Author's Name | Atsushi MIYAMOTO |
| 1st Author's Affiliation | Nara Institute of Science and Technology() |
| 2nd Author's Name | Kazuho WATANABE |
| 2nd Author's Affiliation | Nara Institute of Science and Technology |
| 3rd Author's Name | Kazushi IKEDA |
| 3rd Author's Affiliation | Nara Institute of Science and Technology |
| 4th Author's Name | Masa-aki SATO |
| 4th Author's Affiliation | Computational Neuroscience Labs, ATR International |
| Date | 2010-07-27 |
| Paper # | NC2010-38 |
| Volume (vol) | vol.110 |
| Number (no) | 149 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |