A framework to mine high-level emerging patterns by attribute-oriented induction

Authors:
Maybin K. Muyeba;Muhammad S. Khan;Spits Warnars;John Keane
Affiliations:
Sch. of Computing, Maths and Digital Techn., Manchester Metropolitan University, UK;Department of Computer Science, School of Electrical Engineering and Computer Science, University of Liverpool, UK;Sch. of Computing, Maths and Digital Techn., Manchester Metropolitan University, UK;Department of Computer Science, School of Electrical Engineering and Computer Science, University of Liverpool, UK
Venue:
IDEAL'11 Proceedings of the 12th international conference on Intelligent data engineering and automated learning
Year:
2011

Citing 9
Cited 0

Efficient mining of emerging patterns: discovering trends and differences

KDD '99 Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining
Knowledge Discovery and Measures of Interest

Knowledge Discovery and Measures of Interest
A Metric for Selection of the Most Promising Rules

PKDD '98 Proceedings of the Second European Symposium on Principles of Data Mining and Knowledge Discovery
Mining Generalized Association Rules

VLDB '95 Proceedings of the 21th International Conference on Very Large Data Bases
Mining border descriptions of emerging patterns from dataset pairs

Knowledge and Information Systems
Fast Discovery and the Generalization of Strong Jumping Emerging Patterns for Building Compact and Accurate Classifiers

IEEE Transactions on Knowledge and Data Engineering
Patterns Based Classifiers

World Wide Web
Emerging Pattern Based Classification in Relational Data Mining

DEXA '08 Proceedings of the 19th international conference on Database and Expert Systems Applications
Mining generalised emerging patterns

AI'06 Proceedings of the 19th Australian joint conference on Artificial Intelligence: advances in Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a framework to mine summary emerging patterns in contrast to the familiar low-level patterns. Generally, growth rate based on low-level data and simple supports are used to measure emerging patterns (EP) from one dataset to another. This consequently leads to numerous EPs because of the large numbers of items. We propose an approach that uses high-level data: high-level data captures the data semantics of a collection of attributes values by using taxonomies, and always has larger support than low-level data. We apply a well known algorithm, attribute-oriented induction (AOI), that generalises attributes using taxonomies and investigate properties of the rule sets obtained by generalisation algorithms.