2021 Fiscal Year Final Research Report
Representations and calculations of uncertainty for decision aid considering human factors and utilization of ambiguity
| Project/Area Number |
18H01658
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 25010:Social systems engineering-related
|
|---|
| Research Institution | Osaka University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2018-04-01 – 2022-03-31
|
| Keywords | ファジィ線形計画法 / 必然性測度 / ロバスト最適性 / 階層分析法 / 2重集合 / 整合化法 / ルール抽出 / k-匿名性 |
|---|
| Outline of Final Research Achievements |
Recently, studies using complex models representing uncertainties of the uncertainty degrees are popular. However, such a model requests a lot of effort from human experts to provide various information in modelling. In this study, we demonstrate that simple uncertainty models requesting much less information can work well and effectively for representing human preferences in the settings of optimization and decision-making problems. Moreover, we show that models retaining the uncertainty existing in the given data and information are advantageous for the specification of tolerance and privacy protection in decision analysis and rule induction、respectively.
|
| Free Research Field |
システム計画数理
|
| Academic Significance and Societal Importance of the Research Achievements |
少ない情報でも不確かさと選好を十分に反映でき，モデルの簡便性により問題が扱いやすくなること，および，データに含まれる不確かさをモデルに反映する方法とその有用性を明らかにしている．特に，選好を反映した必然性測度の定め方，非退化基底解の必然的最適性の容易な解析法，最小と最大の範囲で表される不明確な範囲に関する矛盾した情報の整合化法，相対重要度が不明確な範囲で与えられる場合の多基準決定問題の解析法，不精密ルールのプライバシー保護への応用など，まったく新しい考え方に基づいた新規な手法を提案している．
|
