Rule mining with prior knowledge-a belief networks approach

Zonglin Zhou, Huan Liu, Stan Z. Li, Chin Seng Chua

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Some existing data mining methods, such as classification trees, neural networks and association rules, have the drawbacks that the user's prior knowledge cannot be easily specified and incorporated into the knowledge discovery process, and the rules mined from databases lack quantitative analyses. In this paper, we propose a belief networks method for rule mining, which takes the advantage of belief networks as the directed acyclic graph language and their function for numerical representation of probabilistic dependencies among the variables in the database, so that it can overcome the drawbacks. Since belief networks provide a natural representation for capturing causal relationship among a set of variables, our proposed method can mine more general correlation rules which can capture the relationship of more than two attribute variables. The potential application of the proposed method is demonstrated through the detailed case studies on benchmark databases.

Original languageEnglish (US)
Pages (from-to)95-110
Number of pages16
JournalIntelligent Data Analysis
Volume5
Issue number2
StatePublished - 2001
Externally publishedYes

Fingerprint

Belief Networks
Bayesian networks
Prior Knowledge
Mining
Data mining
Association rules
Classification Tree
Directed Acyclic Graph
Association Rules
Knowledge Discovery
Neural networks
Data Mining
Attribute
Neural Networks
Benchmark
Relationships

Keywords

  • belief networks
  • classification rule
  • correlation rule
  • machine learning
  • rule mining

ASJC Scopus subject areas

  • Artificial Intelligence
  • Theoretical Computer Science
  • Computer Vision and Pattern Recognition

Cite this

Rule mining with prior knowledge-a belief networks approach. / Zhou, Zonglin; Liu, Huan; Li, Stan Z.; Chua, Chin Seng.

In: Intelligent Data Analysis, Vol. 5, No. 2, 2001, p. 95-110.

Research output: Contribution to journalArticle

Zhou, Z, Liu, H, Li, SZ & Chua, CS 2001, 'Rule mining with prior knowledge-a belief networks approach', Intelligent Data Analysis, vol. 5, no. 2, pp. 95-110.
Zhou, Zonglin ; Liu, Huan ; Li, Stan Z. ; Chua, Chin Seng. / Rule mining with prior knowledge-a belief networks approach. In: Intelligent Data Analysis. 2001 ; Vol. 5, No. 2. pp. 95-110.
@article{56b2bf4fe47b43af920f78963bc02487,
title = "Rule mining with prior knowledge-a belief networks approach",
abstract = "Some existing data mining methods, such as classification trees, neural networks and association rules, have the drawbacks that the user's prior knowledge cannot be easily specified and incorporated into the knowledge discovery process, and the rules mined from databases lack quantitative analyses. In this paper, we propose a belief networks method for rule mining, which takes the advantage of belief networks as the directed acyclic graph language and their function for numerical representation of probabilistic dependencies among the variables in the database, so that it can overcome the drawbacks. Since belief networks provide a natural representation for capturing causal relationship among a set of variables, our proposed method can mine more general correlation rules which can capture the relationship of more than two attribute variables. The potential application of the proposed method is demonstrated through the detailed case studies on benchmark databases.",
keywords = "belief networks, classification rule, correlation rule, machine learning, rule mining",
author = "Zonglin Zhou and Huan Liu and Li, {Stan Z.} and Chua, {Chin Seng}",
year = "2001",
language = "English (US)",
volume = "5",
pages = "95--110",
journal = "Intelligent Data Analysis",
issn = "1088-467X",
publisher = "IOS Press",
number = "2",

}

TY - JOUR

T1 - Rule mining with prior knowledge-a belief networks approach

AU - Zhou, Zonglin

AU - Liu, Huan

AU - Li, Stan Z.

AU - Chua, Chin Seng

PY - 2001

Y1 - 2001

N2 - Some existing data mining methods, such as classification trees, neural networks and association rules, have the drawbacks that the user's prior knowledge cannot be easily specified and incorporated into the knowledge discovery process, and the rules mined from databases lack quantitative analyses. In this paper, we propose a belief networks method for rule mining, which takes the advantage of belief networks as the directed acyclic graph language and their function for numerical representation of probabilistic dependencies among the variables in the database, so that it can overcome the drawbacks. Since belief networks provide a natural representation for capturing causal relationship among a set of variables, our proposed method can mine more general correlation rules which can capture the relationship of more than two attribute variables. The potential application of the proposed method is demonstrated through the detailed case studies on benchmark databases.

AB - Some existing data mining methods, such as classification trees, neural networks and association rules, have the drawbacks that the user's prior knowledge cannot be easily specified and incorporated into the knowledge discovery process, and the rules mined from databases lack quantitative analyses. In this paper, we propose a belief networks method for rule mining, which takes the advantage of belief networks as the directed acyclic graph language and their function for numerical representation of probabilistic dependencies among the variables in the database, so that it can overcome the drawbacks. Since belief networks provide a natural representation for capturing causal relationship among a set of variables, our proposed method can mine more general correlation rules which can capture the relationship of more than two attribute variables. The potential application of the proposed method is demonstrated through the detailed case studies on benchmark databases.

KW - belief networks

KW - classification rule

KW - correlation rule

KW - machine learning

KW - rule mining

UR - http://www.scopus.com/inward/record.url?scp=0242440334&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0242440334&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0242440334

VL - 5

SP - 95

EP - 110

JO - Intelligent Data Analysis

JF - Intelligent Data Analysis

SN - 1088-467X

IS - 2

ER -