Association rule mining with a correlation-based interestingness measure for video semantic concept detection

Lin Lin, Mei-Ling Shyu, Shu Ching Chen

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Association rule mining (ARM) has been adopted in automatic semantic concept detection to discover the association patterns from the multimedia data and predict the target concept classes. As a rule-based method, ARM faces the challenges on rule pruning. Such challenges could be addressed by utilising proper interestingness measures. In this paper, a video semantic concept detection framework that uses ARM together with a novel correlation-based interestingness measure is proposed. The interestingness measure is obtained from applying multiple correspondence analysis (MCA) to capture the correlation between features and concept classes. This new correlation-based interestingness measure is first used in the rule generation stage, and then reused and combined with the inter-similarity and intra-similarity values to select the final rule set for classification. Experimented with 14 concepts from the benchmark TRECVID data, our proposed framework achieves higher accuracy than the other six classifiers that are commonly used in semantic concept detection.

Original languageEnglish (US)
Pages (from-to)199-216
Number of pages18
JournalInternational Journal of Information and Decision Sciences
Volume4
Issue number2-3
DOIs
StatePublished - 2012

Fingerprint

Association rules
Semantics
Classifiers
Association rule mining

Keywords

  • ARM
  • association rule mining
  • interestingness measure
  • MCA
  • multiple correspondence analysis
  • semantic concept detection

ASJC Scopus subject areas

  • Management of Technology and Innovation
  • Computer Science Applications
  • Information Systems and Management
  • Strategy and Management

Cite this

@article{ce91dc3745454be28570083a32b7875f,
title = "Association rule mining with a correlation-based interestingness measure for video semantic concept detection",
abstract = "Association rule mining (ARM) has been adopted in automatic semantic concept detection to discover the association patterns from the multimedia data and predict the target concept classes. As a rule-based method, ARM faces the challenges on rule pruning. Such challenges could be addressed by utilising proper interestingness measures. In this paper, a video semantic concept detection framework that uses ARM together with a novel correlation-based interestingness measure is proposed. The interestingness measure is obtained from applying multiple correspondence analysis (MCA) to capture the correlation between features and concept classes. This new correlation-based interestingness measure is first used in the rule generation stage, and then reused and combined with the inter-similarity and intra-similarity values to select the final rule set for classification. Experimented with 14 concepts from the benchmark TRECVID data, our proposed framework achieves higher accuracy than the other six classifiers that are commonly used in semantic concept detection.",
keywords = "ARM, association rule mining, interestingness measure, MCA, multiple correspondence analysis, semantic concept detection",
author = "Lin Lin and Mei-Ling Shyu and Chen, {Shu Ching}",
year = "2012",
doi = "10.1504/IJIDS.2012.047073",
language = "English (US)",
volume = "4",
pages = "199--216",
journal = "International Journal of Information and Decision Sciences",
issn = "1756-7017",
publisher = "Inderscience Publishers",
number = "2-3",

}

TY - JOUR

T1 - Association rule mining with a correlation-based interestingness measure for video semantic concept detection

AU - Lin, Lin

AU - Shyu, Mei-Ling

AU - Chen, Shu Ching

PY - 2012

Y1 - 2012

N2 - Association rule mining (ARM) has been adopted in automatic semantic concept detection to discover the association patterns from the multimedia data and predict the target concept classes. As a rule-based method, ARM faces the challenges on rule pruning. Such challenges could be addressed by utilising proper interestingness measures. In this paper, a video semantic concept detection framework that uses ARM together with a novel correlation-based interestingness measure is proposed. The interestingness measure is obtained from applying multiple correspondence analysis (MCA) to capture the correlation between features and concept classes. This new correlation-based interestingness measure is first used in the rule generation stage, and then reused and combined with the inter-similarity and intra-similarity values to select the final rule set for classification. Experimented with 14 concepts from the benchmark TRECVID data, our proposed framework achieves higher accuracy than the other six classifiers that are commonly used in semantic concept detection.

AB - Association rule mining (ARM) has been adopted in automatic semantic concept detection to discover the association patterns from the multimedia data and predict the target concept classes. As a rule-based method, ARM faces the challenges on rule pruning. Such challenges could be addressed by utilising proper interestingness measures. In this paper, a video semantic concept detection framework that uses ARM together with a novel correlation-based interestingness measure is proposed. The interestingness measure is obtained from applying multiple correspondence analysis (MCA) to capture the correlation between features and concept classes. This new correlation-based interestingness measure is first used in the rule generation stage, and then reused and combined with the inter-similarity and intra-similarity values to select the final rule set for classification. Experimented with 14 concepts from the benchmark TRECVID data, our proposed framework achieves higher accuracy than the other six classifiers that are commonly used in semantic concept detection.

KW - ARM

KW - association rule mining

KW - interestingness measure

KW - MCA

KW - multiple correspondence analysis

KW - semantic concept detection

UR - http://www.scopus.com/inward/record.url?scp=84882726384&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84882726384&partnerID=8YFLogxK

U2 - 10.1504/IJIDS.2012.047073

DO - 10.1504/IJIDS.2012.047073

M3 - Article

AN - SCOPUS:84882726384

VL - 4

SP - 199

EP - 216

JO - International Journal of Information and Decision Sciences

JF - International Journal of Information and Decision Sciences

SN - 1756-7017

IS - 2-3

ER -