Presentation 2010-06-14
Relational Data Mining on Causal Relations Between Variables
Takashi WASHIO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Under development of sensing techniques to ease simultaneous measurements of many variables and features on objects, the need increases to systematically understand an objective system underlying data generation process where the data is generated under influences from some variables/relations to the other variables/relations. While graphical modeling techniques and time series analyses have been used for this need in the long past period, novel techniques are emerging in recent years. Members in our laboratory currently work on development of novel relational data mining methods focusing on data generation process based on the causality between many variables/elements by using graph mining, statistical causal inference and optimization algorithm. In this talk, we introduce these studies and their application examples and further prospect the future possibility of relational data mining for understanding the data generation process.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) data generation process / statistical causal inference / graph mining / relational data mining
Paper # IBISML2010-3
Date of Issue

Conference Information
Committee IBISML
Conference Date 2010/6/7(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Information-Based Induction Sciences and Machine Learning (IBISML)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Relational Data Mining on Causal Relations Between Variables
Sub Title (in English)
Keyword(1) data generation process
Keyword(2) statistical causal inference
Keyword(3) graph mining
Keyword(4) relational data mining
1st Author's Name Takashi WASHIO
1st Author's Affiliation The Institute of Scientific and Industrial Research, Osaka University()
Date 2010-06-14
Paper # IBISML2010-3
Volume (vol) vol.110
Number (no) 76
Page pp.pp.-
#Pages 1
Date of Issue