Real-time Analytics Frameworks for Big Heterogeneous Data in Composite Parallel Computing Environments

2016 Fiscal Year Final Research Report

• Project/Area Number: 26280037
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Partial Multi-year Fund
• Section: 一般
• Research Field: Multimedia database
• Research Institution: University of Tsukuba
• Principal Investigator: KITAGAWA HIROYUKI 筑波大学, 計算科学研究センター, 教授 (00204876)
• Co-Investigator(Kenkyū-buntansha): 天笠 俊之 筑波大学, システム情報系, 准教授 (70314531) ; 早瀬 康裕 筑波大学, システム情報系, 助教 (40423090) ; 渡辺 知恵美 筑波大学, システム情報系, 助教 (20362832)
• Co-Investigator(Renkei-kenkyūsha): TAKAHASHI DAISUKE 筑波大学, 計算科学研究センター, 教授 (00292714) ; WATANABE YOUSUKE 名古屋大学, 未来社会創造機構, 准教授 (80532944)
• Project Period (FY): 2014-04-01 – 2017-03-31
• Keywords: 大規模不均質データ / データ分析 / 複合型並列計算環境

Outline of Final Research Achievements

The goal is to develop real-time analytics frameworks for big heterogeneous data in composite parallel computing environments. The main research outcomes cover the following topics: data modeling and data description for big heterogeneous data analytics, system architecture implementing the data model, massively parallel GPU-based data analytics, high performance data analytics using many core processors, efficient data analytics using incremental computation, semistructured stream filtering using intrinsic structures and keywords, real-time matching of multiple text streams, keyword query processing of multiple relational streams, and generation of optimal data analytics plans including fine grain and coarse grain data processing.

Free Research Field

データ工学