| Project/Area Number |
16K16077
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Cognitive science
|
|---|
| Research Institution | Nihon University |
|---|
Principal Investigator |
|
|---|
| Research Collaborator |
SAKATANI Kaoru
CHANG Carl K.
RAHMAN Labiblais
|
|---|
| Project Period (FY) |
2016-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2017: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2016: ¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
|
|---|
| Keywords | 自己組織化マップ / EEG / NIRS / 暗算課題 / 遠隔環境 / ヘルスケアモニタリング / 沈黙 / 脳インタフェース / 機械学習 / 沈黙の種類 |
|---|
| Outline of Final Research Achievements |
This study was conducted to discover the relations between silence during conversation and the corresponding brain activity from the result of simultaneous monitoring of EEG and NIRS signals. To identify the brain states, we cascade a system of two self-organizing maps (SOMs) in which the feature vectors have different segment lengths; that is, the segment length of a sample in the lower SOM is 1 sec and that in the upper is 30 sec. From the experimental results, the brain states of resting and listening were identified in 92% classification accuracy. The brain states of eye-closing, listening, writing answers and writing answers with listening were varied from 67% through 100% in classification accuracy, and we found that the conditions for situation recognition were different by the brain states.
|
