BCI image retrieval using fMRI and kernel fuzzy clustering
Project/Area Number |
24500258
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Sensitivity informatics/Soft computing
|
Research Institution | Kochi University of Technology |
Principal Investigator |
|
Co-Investigator(Kenkyū-buntansha) |
HATAKEYAMA Yutaka 高知大学, 医歯学系, 准教授 (00376956)
OKAMOTO Kazushi 千葉大学, 学内共同利用施設等, 助教 (10615032)
SAIKI Sachio 神戸大学, その他の研究科, 助教 (40549408)
|
Project Period (FY) |
2012-04-01 – 2015-03-31
|
Project Status |
Completed (Fiscal Year 2014)
|
Budget Amount *help |
¥5,330,000 (Direct Cost: ¥4,100,000、Indirect Cost: ¥1,230,000)
Fiscal Year 2014: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2013: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2012: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
|
Keywords | ソフトコンピューティング / BCI / fMRI / 機械学習 / 画像検索 / パターン認識 / 脳情報デコーディング |
Outline of Final Research Achievements |
This study aims at image retrieval using brain neural data obtained from fMRI---BCI based image retrieval. In order to construct the foundation of BCI image retrieval, we have conducted four brain decoding experiment, color circle, black-and-white shapes, emotional images, and images which have different semantics. We used and compared four machine learning techniques, SVM, backpropagation, random forest, and sparse logistic regression. The result shows that the accuracy of the estimation of image is around 70%.
|
Report
(4 results)
Research Products
(14 results)
-
-
-
-
[Presentation] Decoding analysis for fMRI based on Deep Brief Network2014
Author(s)
Yutaka Hatakeyama, Hiromi Kataoka, Yoshiyasu Okuhara, Shinichi Yoshida
Organizer
World Automation Congress 2014, 9th International Forum on Multimedia and Image Processing
Place of Presentation
World Automation Congress 2014, 9th International Forum on Multimedia and Image Processing
Year and Date
2014-08-03 – 2014-08-07
Related Report
-
-
-
-
-
-
-
-
-
-