2014 Fiscal Year Final Research Report
Application of Pareto learning SOM to multi-modal big data analysis
| Project/Area Number |
24500279
|
|---|
| 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 | Saga University |
|---|
Principal Investigator |
HIRTOSHI Dozono 佐賀大学, 工学(系)研究科(研究院), 准教授 (00217613)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
NAKAKUNI Masanori 福岡大学, 総合情報処理センター研究開発室, 准教授 (10347049)
|
|---|
| Research Collaborator |
新名 玄 佐賀大学, 工学系研究科
岡田 望邦 佐賀大学, 工学系研究科先端融合工学専攻
|
|---|
| Project Period (FY) |
2012-04-01 – 2015-03-31
|
| Keywords | マルチモーダルデータ解析 / ビッグデータ解析 / 自己組織化マップ / メタゲノム解析 / IPパケット解析 |
|---|
| Outline of Final Research Achievements |
In this research,we applied the Pareto type Self organizing Maps, which are developed for the analyses of multi-modal data to genome analysis, IP-Packet analysis, the analysis of students in the lecture class and time series such as stock price.Mainly, the genome analysis was conducted, and form big data of genome data, the context and correlation coefficients among the nucleotides are calculated with the frequencies of nucleotides, and they are analyzed as multi-modal features by pareto type learning SOM. As for IP-packet analysis, we applied CGH-SOM which is effective for big data analysis.
|
| Free Research Field |
ソフトコンピューティング
|
