Development of fast calculation-type fuzzy inference models considering big data

2017 Fiscal Year Final Research Report

• Project/Area Number: 15K16065
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Soft computing
• Research Institution: Osaka University
• Principal Investigator: Seki Hirosato 大阪大学, 基礎工学研究科, 助教 (10583693)
• Project Period (FY): 2015-04-01 – 2018-03-31
• Keywords: ソフトコンピューティング / ファジィ推論 / 単一入力型ファジィ推論モデル / ビッグデータ解析 / 等価性 / 単調性 / 不精密ルール / 高速演算

Outline of Final Research Achievements

The single input type fuzzy inference models that unifies the inference outputs from fuzzy rule modules of one input type IF-THEN form can sharply reduce the number of fuzzy rules compared with conventional fuzzy inference models. However, since the number of rules of the single input type fuzzy inference models were limited as compared to the conventional fuzzy inference models, the inference results were simple in general. Therefore, several extended single input type fuzzy inference models are proposed in this study, and their properties are clarified from theoretical point of view. Moreover, their learning algorithms are proposed, and applied them to a medical diagnosis as a real system. Finally, the fuzzy inference models with imprecise rules and OR-type fuzzy rules are proposed. The inference results by these proposed models can be obtained by the fast calculation method. From the above results, it turns out that the proposed models are useful for big data.

Free Research Field

ソフトコンピューティング