| Project/Area Number |
15K01849
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Brain biometrics
|
|---|
| Research Institution | Tokyo Institute of Technology |
|---|
Principal Investigator |
Yoshimura Natsue 東京工業大学, 科学技術創成研究院, 准教授 (00581315)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
緒方 洋輔 東京工業大学, 科学技術創成研究院, 特任助教 (60641355)
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2017: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2016: ¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
Fiscal Year 2015: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
|
|---|
| Keywords | 脳波 / デコーディング / 機械学習 / 逆問題 / ブレイン・コンピュータ・インタフェース / 機能的MRI |
|---|
| Outline of Final Research Achievements |
Electroencephalography (EEG) has low spatial resolution because it is recorded from sensors placed on the scalp. For this reason, it is considered to be hard to decode imagined characters in the brain from EEG. To solve the problem, EEG cortical current source is calculated using machine learning methods in this research project.
During the research period, decoding performance of vowel classification has enhanced using the EEG current source signals compared to that using EEG sensor signals. This achievement was published in an international journal (Yoshimura et al., Frontiers in Neuroscience, 2016).
The method has showed efficiency also for consonants classification (Under preparation for publish).
|
