Establishment of Linguistic clustering - Conversion from Model-based Clustering

2016 Fiscal Year Final Research Report

• Project/Area Number: 26330271
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Soft computing
• Research Institution: University of Tsukuba
• Principal Investigator: ENDO Yasunori 筑波大学, システム情報系, 教授 (10267396)
• Project Period (FY): 2014-04-01 – 2017-03-31
• Keywords: クラスタリング / 言語ベース / モデルベース / データマイニング / ビッグデータ / ファジィ推論

Outline of Final Research Achievements

In this research project, we aim to establish a language-based clustering (linguistic clustering) technique by converting from conventional model-based clustering. First, we extract the mathematical models which are the basis of the conventional clustering algorithms, and discuss the description by the language of the extracted mathematical models. Next, considering the discussion, we consider language-based inference in clustering. Then, based on the language-based inference, some new clustering algorithms based on language-based inference are constructed. After comparing and examining the constructed algorithm with the conventional model-based clustering algorithm through numerical examples, we consider the possibility of mathematical development based on linguistic clustering and the applicable real data.

Free Research Field

クラスタリング