SPICE

A new framework for data mining based on probability logic and formal concept analysis

Liying Jiang, Jitender S Deogun

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Formal concept analysis and probability logic are two useful tools for data analysis. Data is usually represented as a two-dimensional context of objects and features. FCA discovers dependencies within the data based on the relation among objects and features. On the other hand, the probability logic represents and reasons with both statistical and propositional probability among data. We propose SPICE - Symbolic integration of Probability Inference and Concept Extraction, which provides a more flexible and robust framework for data mining tasks. Within SPICE, we formalize the important notions of data mining, such as concepts and patterns, and develop new notions such as maximal potentially useful patterns. In this paper, we formalize the association rule mining in SPICE and propose an enhanced rule mining approach, called SPICE association rule mining, to solve the problem of time inefficiency and rule redundancy in general association rule mining. We show an application of the SPICE approach in the Geo-spatial Decision Support System (GDSS). The experimental results show that SPICE can efficiently and effectively discover a succinct set of interesting association rules.

Original languageEnglish (US)
Pages (from-to)467-485
Number of pages19
JournalFundamenta Informaticae
Volume78
Issue number4
StatePublished - Sep 18 2007

Fingerprint

Probability Logic
Formal concept analysis
Formal Concept Analysis
Association Rule Mining
SPICE
Data mining
Data Mining
Association rules
Association Rules
Decision Support Systems
Redundancy
Mining
Data analysis
Experimental Results
Decision support systems
Framework
Concepts
Object

Keywords

  • Association rules
  • Data mining
  • FCA
  • Important items
  • Probability logic
  • Redundant rules

ASJC Scopus subject areas

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

Cite this

SPICE : A new framework for data mining based on probability logic and formal concept analysis. / Jiang, Liying; Deogun, Jitender S.

In: Fundamenta Informaticae, Vol. 78, No. 4, 18.09.2007, p. 467-485.

Research output: Contribution to journalArticle

@article{50c8b6be0c0e42629e006f0ae424a06f,
title = "SPICE: A new framework for data mining based on probability logic and formal concept analysis",
abstract = "Formal concept analysis and probability logic are two useful tools for data analysis. Data is usually represented as a two-dimensional context of objects and features. FCA discovers dependencies within the data based on the relation among objects and features. On the other hand, the probability logic represents and reasons with both statistical and propositional probability among data. We propose SPICE - Symbolic integration of Probability Inference and Concept Extraction, which provides a more flexible and robust framework for data mining tasks. Within SPICE, we formalize the important notions of data mining, such as concepts and patterns, and develop new notions such as maximal potentially useful patterns. In this paper, we formalize the association rule mining in SPICE and propose an enhanced rule mining approach, called SPICE association rule mining, to solve the problem of time inefficiency and rule redundancy in general association rule mining. We show an application of the SPICE approach in the Geo-spatial Decision Support System (GDSS). The experimental results show that SPICE can efficiently and effectively discover a succinct set of interesting association rules.",
keywords = "Association rules, Data mining, FCA, Important items, Probability logic, Redundant rules",
author = "Liying Jiang and Deogun, {Jitender S}",
year = "2007",
month = "9",
day = "18",
language = "English (US)",
volume = "78",
pages = "467--485",
journal = "Fundamenta Informaticae",
issn = "0169-2968",
publisher = "IOS Press",
number = "4",

}

TY - JOUR

T1 - SPICE

T2 - A new framework for data mining based on probability logic and formal concept analysis

AU - Jiang, Liying

AU - Deogun, Jitender S

PY - 2007/9/18

Y1 - 2007/9/18

N2 - Formal concept analysis and probability logic are two useful tools for data analysis. Data is usually represented as a two-dimensional context of objects and features. FCA discovers dependencies within the data based on the relation among objects and features. On the other hand, the probability logic represents and reasons with both statistical and propositional probability among data. We propose SPICE - Symbolic integration of Probability Inference and Concept Extraction, which provides a more flexible and robust framework for data mining tasks. Within SPICE, we formalize the important notions of data mining, such as concepts and patterns, and develop new notions such as maximal potentially useful patterns. In this paper, we formalize the association rule mining in SPICE and propose an enhanced rule mining approach, called SPICE association rule mining, to solve the problem of time inefficiency and rule redundancy in general association rule mining. We show an application of the SPICE approach in the Geo-spatial Decision Support System (GDSS). The experimental results show that SPICE can efficiently and effectively discover a succinct set of interesting association rules.

AB - Formal concept analysis and probability logic are two useful tools for data analysis. Data is usually represented as a two-dimensional context of objects and features. FCA discovers dependencies within the data based on the relation among objects and features. On the other hand, the probability logic represents and reasons with both statistical and propositional probability among data. We propose SPICE - Symbolic integration of Probability Inference and Concept Extraction, which provides a more flexible and robust framework for data mining tasks. Within SPICE, we formalize the important notions of data mining, such as concepts and patterns, and develop new notions such as maximal potentially useful patterns. In this paper, we formalize the association rule mining in SPICE and propose an enhanced rule mining approach, called SPICE association rule mining, to solve the problem of time inefficiency and rule redundancy in general association rule mining. We show an application of the SPICE approach in the Geo-spatial Decision Support System (GDSS). The experimental results show that SPICE can efficiently and effectively discover a succinct set of interesting association rules.

KW - Association rules

KW - Data mining

KW - FCA

KW - Important items

KW - Probability logic

KW - Redundant rules

UR - http://www.scopus.com/inward/record.url?scp=34548570766&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548570766&partnerID=8YFLogxK

M3 - Article

VL - 78

SP - 467

EP - 485

JO - Fundamenta Informaticae

JF - Fundamenta Informaticae

SN - 0169-2968

IS - 4

ER -