The theory of filter based feature selection and high-performance algorithms

2017 Fiscal Year Final Research Report

• Project/Area Number: 26280090
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Partial Multi-year Fund
• Section: 一般
• Research Field: Intelligent informatics
• Research Institution: Gakushuin University
• Principal Investigator: Kuboyama Tetsuji 学習院大学, 計算機センター, 教授 (80302660)
• Co-Investigator(Kenkyū-buntansha): 申 吉浩 兵庫県立大学, 応用情報科学研究科, 教授 (60523587) ; チャクラボルティ バサビ 岩手県立大学, ソフトウェア情報学部, 教授 (90305293) ; 橋本 隆子 千葉商科大学, 商経学部, 教授 (80551697) ; 川前 徳章 東京電機大学, 公私立大学の部局等, 研究員 (30447031)
• Project Period (FY): 2014-04-01 – 2018-03-31
• Keywords: 特徴選択 / カテゴリカルデータ / 一貫性指標

Outline of Final Research Achievements

We focus on feature selection algorithms that extract minimal subsets of features relevant to class labels from categorical data with high dimensional feature space. Filter-based feature selection consists of two important components; consistency measures between feature sets and class labels, and search strategies for minimal feature sets . Through theoretical and empirical analysis on these two components, we designed and implemented a very fast feature selection algorithm with high accuracy and scalability. We applied this algorithm to two applications; topic extraction from tweets, and pattern acquisition from graph-structured data.

Free Research Field

情報科学