|
Title:
|
SIMILARITY BASED TIME-SERIES DATA EXPLORATION |
|
Author(s):
|
Hiroshi Sugimura, Kazunori Matsumoto |
|
ISBN:
|
978-972-8939-47-2 |
|
Editors:
|
Miguel Baptista Nunes, Pedro Isaías and Philip Powell |
|
Year:
|
2011 |
|
Edition:
|
Single |
|
Keywords:
|
Time series data, exploratory search, user interface, query language, datamining |
|
Type:
|
Poster/Demonstration |
|
First Page:
|
359 |
|
Last Page:
|
361 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Time-series data has a huge number of applications. We typically start with partially specified ambiguous information, and search for explicit and useful knowledge of fragment patterns. The search task requires an exploratory search a whole database with a long period of trial and error. We then develop an intelligent exploration tool that supports this task. The main contribution of this paper is threefold; first we propose a time-series query language that has an affinity to the standard database query language SQL; second we develop a similarity handling method that effectively realizes a matching of sub-patterns with certain ambiguity; finally we show a combinatory use of the exploration tool and a datamining technique increases the capability of the knowledge discovery. |
|
|
|
|
|
|
