Prediction and interpretation of physical properties from simulation data by induction approach
Project/Area Number |
26800203
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Multi-year Fund |
Research Field |
Mathematical physics/Fundamental condensed matter physics
|
Research Institution | Yamanashi Eiwa College |
Principal Investigator |
Sugiyama Ayumu 山梨英和大学, 人間文化学部, 准教授 (20586606)
|
Research Collaborator |
Dam Hieu Chi 北陸先端科学技術大学院大学, 知識マネジメント領域, 准教授 (70397230)
|
Project Period (FY) |
2014-04-01 – 2017-03-31
|
Project Status |
Completed (Fiscal Year 2016)
|
Budget Amount *help |
¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2016: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2015: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2014: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
|
Keywords | データマイニング / 第一原理計算 / マテリアルズインフォマティクス / 金属合金 / BNO / マテリアルズ・インフォマティクス / 物性予測 |
Outline of Final Research Achievements |
The purpose of this research isI establishing a methodology for obtaining new physical knowledge from prediction of physical properties of metal alloys and interpretation of results by Materials Informatics using machine learning and data mining techniques. At first, physical property database is constructed from the first principle calculation of metal complex and binary metal alloy and known experimental data and classified by unsupervised learning by machine learning and data mining for each data group. We also interpreted the physical meaning from the classified data group and examined the semantics of each classified data group. In the data group classified as data group on the metal complex and the data group on the binary metal alloy covered in this research, classification by machine learning is the same as classification by known physical properties, and semantics of the conventional physical property knowledge are also indicated.
|
Report
(4 results)
Research Products
(1 results)