Presentation 2010-06-28
Knowledge Discovery over Continuous Time-series Data Streams
Wei Fan, Toyohide Watanabe, Koichi Asakura,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, a new generation of mining algorithms is necessary for real-time analysis and query response in data stream applications: for example, outlier detection from sensor network data, prediction of stock price data, web access analysis from click stream data and so on. In this paper, we propose methods for automatic trend detection over time-series data streams to discover useful knowledge. We validate the accuracy and affectivity of our methods by analyzing stock price data and news articles. According to the resultant classifiers which disclose the correlation between stock data and news articles, we can predict rise/drop trend of stock price when given a newly released news article.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Data stream mining / Trend detection / Text classification
Paper # DE2010-2
Date of Issue

Conference Information
Committee DE
Conference Date 2010/6/21(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 Data Engineering (DE)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Knowledge Discovery over Continuous Time-series Data Streams
Sub Title (in English)
Keyword(1) Data stream mining
Keyword(2) Trend detection
Keyword(3) Text classification
1st Author's Name Wei Fan
1st Author's Affiliation Department of Systems and Social Informatics, Graduate School of Information Science, Nagoya University()
2nd Author's Name Toyohide Watanabe
2nd Author's Affiliation Department of Systems and Social Informatics, Graduate School of Information Science, Nagoya University
3rd Author's Name Koichi Asakura
3rd Author's Affiliation School of Informatics, Daido University
Date 2010-06-28
Paper # DE2010-2
Volume (vol) vol.110
Number (no) 107
Page pp.pp.-
#Pages 6
Date of Issue