| Project/Area Number |
15K01208
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Social systems engineering/Safety system
|
|---|
| Research Institution | Hosei University |
|---|
Principal Investigator |
|
|---|
| Research Collaborator |
ARAI Yuichiro
OTA Shuhei
OGIWARA Yumi
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2017: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2016: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2015: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
|
|---|
| Keywords | ソフトウェア品質 / 定性的データ / 多変量解析 / ソフトウェアプロジェクトデータ / 信頼性予測 / データの質 / ソフトウェアプロジェクト / 統計的特徴づけ / ソフトウェアプロセスデータ / ランダムフォレスト |
|---|
| Outline of Final Research Achievements |
We have studied on a new methodology which can precisely forecast the software quality by using software development characteristics data sets which were provided from the actual software development companies. The data sets consist of a mixture of both quality and quantity data. In particular, our approach is unique in the sense that our method utilizes the data sets which can be obtained in the early stage of software development process. This means that our new method can predict the software quality in the earlier stage, and can provide some chances to improve the software development process on-the-fly. As a result, a framework of neural networks generally yields good forecast performance, whereas we have newly faced the issues of data contamination including missing data.
|
