Research on EEG analysis technique for requiring mixing noise
| Project/Area Number |
24700215
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Sensitivity informatics/Soft computing
|
|---|
| Research Institution | Doshisha University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2012-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2015: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2014: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2013: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2012: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
|
|---|
| Keywords | 感性情報処理 / 脳波 / 雑音 / 感情 / 概念化 |
|---|
| Outline of Final Research Achievements |
The noise mixes with the EEG even if the EEG is measured by maintaining the device and the environment enough. Moreover, even if the signal processing is given to the EEG data, it is impossible to remove the noise. In this study, the association technology of the word that has been researched in the field of the linguistic processing is applied to the analysis of the EEG in the measured brain wave on the assumption that the noise mixes. In this study, presumed emotions were four kinds, and, as a result of the assessment experiment under the severest condition that the EEG data of the subject him/herself is not used, the emotions presumption accuracy became 34.7%. Moreover, it was confirmed to become the accuracy of 55.5% by using the subject's EEG data at the same time. As a result, the finding that was available skills with a real environment was able to be obtained.
|
Report
(5 results)
Research Products
(99 results)
