Discovering and matching elastic rules from sequence databases

Park Sang Hyun, W. Chu Wesley

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

This paper presents techniques for discovering and matching rules with elastic patterns. Elastic patterns are ordered lists of elements that can be stretched along the time axis. Elastic patterns are useful for discovering rules from data sequences with different sampling rates. For fast discovery of rules whose heads (left-hand sides) and bodies (right-hand sides) are elastic patterns, we construct a trimmed suffix tree from succinct forms of data sequences and keep the tree as a compact representation of rules. The trimmed suffix tree is also used as an index structure for finding rules matched to a target head sequence. When matched rules cannot be found, the concept of rule relaxation is introduced. Using a cluster hierarchy and relaxation error as a new distance function, we find the least relaxed rules that provide the most specific information on a target head sequence. Experiments on synthetic data sequences reveal the effectiveness of our proposed approach.

Original languageEnglish
Pages (from-to)75-90
Number of pages16
JournalFundamenta Informaticae
Volume47
Issue number1-2
Publication statusPublished - 2001 Jul 1

Fingerprint

Sampling
Experiments
Suffix Tree
Target
Synthetic Data
Distance Function
Experiment

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Algebra and Number Theory
  • Information Systems
  • Computational Theory and Mathematics

Cite this

@article{5ad84c93dd2c457c94517ab1d2c6ad15,
title = "Discovering and matching elastic rules from sequence databases",
abstract = "This paper presents techniques for discovering and matching rules with elastic patterns. Elastic patterns are ordered lists of elements that can be stretched along the time axis. Elastic patterns are useful for discovering rules from data sequences with different sampling rates. For fast discovery of rules whose heads (left-hand sides) and bodies (right-hand sides) are elastic patterns, we construct a trimmed suffix tree from succinct forms of data sequences and keep the tree as a compact representation of rules. The trimmed suffix tree is also used as an index structure for finding rules matched to a target head sequence. When matched rules cannot be found, the concept of rule relaxation is introduced. Using a cluster hierarchy and relaxation error as a new distance function, we find the least relaxed rules that provide the most specific information on a target head sequence. Experiments on synthetic data sequences reveal the effectiveness of our proposed approach.",
author = "Hyun, {Park Sang} and {Chu Wesley}, W.",
year = "2001",
month = "7",
day = "1",
language = "English",
volume = "47",
pages = "75--90",
journal = "Fundamenta Informaticae",
issn = "0169-2968",
publisher = "IOS Press",
number = "1-2",

}

Discovering and matching elastic rules from sequence databases. / Hyun, Park Sang; Chu Wesley, W.

In: Fundamenta Informaticae, Vol. 47, No. 1-2, 01.07.2001, p. 75-90.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Discovering and matching elastic rules from sequence databases

AU - Hyun, Park Sang

AU - Chu Wesley, W.

PY - 2001/7/1

Y1 - 2001/7/1

N2 - This paper presents techniques for discovering and matching rules with elastic patterns. Elastic patterns are ordered lists of elements that can be stretched along the time axis. Elastic patterns are useful for discovering rules from data sequences with different sampling rates. For fast discovery of rules whose heads (left-hand sides) and bodies (right-hand sides) are elastic patterns, we construct a trimmed suffix tree from succinct forms of data sequences and keep the tree as a compact representation of rules. The trimmed suffix tree is also used as an index structure for finding rules matched to a target head sequence. When matched rules cannot be found, the concept of rule relaxation is introduced. Using a cluster hierarchy and relaxation error as a new distance function, we find the least relaxed rules that provide the most specific information on a target head sequence. Experiments on synthetic data sequences reveal the effectiveness of our proposed approach.

AB - This paper presents techniques for discovering and matching rules with elastic patterns. Elastic patterns are ordered lists of elements that can be stretched along the time axis. Elastic patterns are useful for discovering rules from data sequences with different sampling rates. For fast discovery of rules whose heads (left-hand sides) and bodies (right-hand sides) are elastic patterns, we construct a trimmed suffix tree from succinct forms of data sequences and keep the tree as a compact representation of rules. The trimmed suffix tree is also used as an index structure for finding rules matched to a target head sequence. When matched rules cannot be found, the concept of rule relaxation is introduced. Using a cluster hierarchy and relaxation error as a new distance function, we find the least relaxed rules that provide the most specific information on a target head sequence. Experiments on synthetic data sequences reveal the effectiveness of our proposed approach.

UR - http://www.scopus.com/inward/record.url?scp=0035401768&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035401768&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0035401768

VL - 47

SP - 75

EP - 90

JO - Fundamenta Informaticae

JF - Fundamenta Informaticae

SN - 0169-2968

IS - 1-2

ER -