Re-finding support system based on user's condition estimation without interrupting creative activity
| Project/Area Number |
24700116
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Media informatics/Database
|
|---|
| Research Institution | Kyoto Institute of Technology |
|---|
Principal Investigator |
YAMAMOTO Keiko 京都工芸繊維大学, 工芸科学研究科, 助教 (10585756)
|
|---|
| Project Period (FY) |
2012-04-01 – 2015-03-31
|
| Project Status |
Completed (Fiscal Year 2014)
|
| Budget Amount *help |
¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2014: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2013: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2012: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
|
|---|
| Keywords | リファインディング / ユーザ状態推定 / ドローイング / 学習システム |
|---|
| Outline of Final Research Achievements |
In this research, I aim to support re-finding a certain product from user’s products based on his/her condition estimation without interrupting the creative activity.
First, I evaluated the accuracy of emotion classification by decision trees classifiers based on some keystroke features when the users write their diary. However, the accuracy is too low to estimate user’s emotion.
Second, in order to clarify the differences in motion between good and bad drawing strokes, I analyzed the stroking motions of experts in the process of drawing circles. With some features of drawing motion, the accuracy is 67% on average. This means that these features may be useful to distinguish between good and bad strokes. Based on the result, I proposed and developed a drawing learning support system that compares a current stroke with one of the ideal strokes by each feature in every quarter and provides improvement points of stroking motion for enhancing learners' skills.
|
Report
(4 results)
Research Products
(7 results)
