| Project/Area Number |
26540153
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Life / Health / Medical informatics
|
|---|
| Research Institution | The University of Electro-Communications |
|---|
Principal Investigator |
Kurihara Satoshi 電気通信大学, 大学院情報理工学研究科, 教授 (30397658)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
諏訪 博彦 奈良先端科学技術大学院大学, 情報科学研究科, 助教 (70447580)
篠田 孝祐 電気通信大学, 大学院情報理工学研究科, 助教 (90533191)
|
|---|
| Project Period (FY) |
2014-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2016: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2015: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2014: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | 多段創発 / ボトムアップ / 時系列データ / ＡＣＯ / 自律エージェント / 協調 / パタンマイニング / 大規模複雑システム / 人工生命 / Deep Learning / 中間層 / 仮想細胞 / 汎用性 / 転移学習 / トップダウン / ACO / 自己組織化 |
|---|
| Outline of Final Research Achievements |
"Multi-layered emergent hierarchical structure" is important when constructing smart grid, ambient information infrastructure, and next-generation information social infrastructure system for which urgent development and operation are necessary. Therefore, the main objective of this study is proposition of mechanism that the lower layer emergents upper layer by bottom-up approach.
We proposed a method based on ACO which is representative of collective intelligent method which enables autonomous hierarchical structure extraction from data including hierarchical time series pattern. Embedded hierarchical structure can be extracted through simple coordination of large number of autonomous agents.
|
