Presentation 2018-02-17
Graph-based Entropy for Detecting Precursors of Changes
Yukio Ohsawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Innovators Marketplace on Data Jackets is a platform for creating not only use scenario of data, but also basic models for computation in data analysis/visualization. Graph-based entropy is an index representing the structural diversity of items, one of the computational models recently created in IMDJ. This proposed index is computed on the co-occurrence graph of items in the data, where the distribution of items to subgraphs is reflected. The variation of this index corresponds to the separation and the combination of events, regarded as effects of latent dynamics or external forces of the target system. In this paper, we show the application of GBE to the analysis of earthquakes, analysis of online Q&A, and marketing with POS data.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # AI2017-33
Date of Issue 2018-02-10 (AI)

Conference Information
Committee AI
Conference Date 2018/2/17(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Tsunenori Mine(Kyushu Univ.)
Vice Chair Daisuke Katagami(Tokyo Polytechnic Univ.) / Naoki Fukuta(Shizuoka Univ.)
Secretary Daisuke Katagami(Ritsumeikan Univ.) / Naoki Fukuta(Univ. of Electro-Comm.)
Assistant Yuko Sakurai(AIST)

Paper Information
Registration To Technical Committee on Artificial Intelligence and Knowledge-Based Processing
Language ENG-JTITLE
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Graph-based Entropy for Detecting Precursors of Changes
Sub Title (in English) A Product of Innovators Marketplace on Data Jackets
Keyword(1)
1st Author's Name Yukio Ohsawa
1st Author's Affiliation The University of Tokyo(UT)
Date 2018-02-17
Paper # AI2017-33
Volume (vol) vol.117
Number (no) AI-440
Page pp.pp.87-92(AI),
#Pages 6
Date of Issue 2018-02-10 (AI)