Making use of the most expressive jumping emerging patterns for classification

DOI10.1007/PL00011662MaRDI QIDQ1606553zbMATH OpenOpenAlexFDO

Authors Guozhu Dong, Kotagiri Ramamohanarao, Jinyan (Leo) Li

Publication date 25 July 2002

Published in Knowledge and Information Systems (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/pl00011662

zbMATH Keywords

Border representationBorder-based algorithmsClassificationCollective impactMost expressive jumping emerging patterns

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10) Computing methodologies for information systems (hypertext navigation, interfaces, decision support, etc.) (68U35) Computing methodologies and applications (68U99)

Review text

Classification aims to discover a model from training data that can be used to predict the class of test instances. In this paper, we propose the use of jumping emerging patterns (JEPs) as the basis for a new classifier called the JEP-Classifier. Each JEP can capture some crucial difference between a pair of datasets. Then, aggregating all JEPs of large supports can produce a more potent classification power. Procedurally, the JEP-Classifier learns the pair-wise features (sets of JEPs) contained in the training data, and uses the collective impacts contributed by the most expressive pair-wise features to determine the class labels of the test data. Using only the most expressive JEPs in the JEP-Classifier strengthens its resistance to noise in the training data, and reduces its complexity (as there are usually a very large number of JEPs). We use two algorithms for constructing the JEP-Classifier which are both scalable and efficient. These algorithms make use of the border representation to efficiently store and manipulate JEPs. We also present experimental results which show that the JEP-Classifier achieves much higher testing accuracies than the association-based classifier of (Liu et al, 1998), which was reported to outperform C4.5 in general.

Recommendations

• Efficient Mining of Jumping Emerging Patterns with Occurrence Counts for Classification
• scientific article; zbMATH DE number 2088115
• On the relation between jumping emerging patterns and rough set theory with application to data classification

Cited in

(10)

• DeEPs: A new instance-based lazy discovery and classification system
• Jumping emerging patterns with negation in transaction databases -- classification and discovery
• scientific article; zbMATH DE number 1696426 (Why is no real title available?)
• scientific article; zbMATH DE number 1700014 (Why is no real title available?)
• Efficient Mining of Jumping Emerging Patterns with Occurrence Counts for Classification
• Efficient Discovery of Top-K Minimal Jumping Emerging Patterns
• On the relation between jumping emerging patterns and rough set theory with application to data classification
• scientific article; zbMATH DE number 2088115 (Why is no real title available?)
• A visual word weighting scheme based on emerging itemsets for video annotation
• On the relation between rough set reducts and jumping emerging patterns

Describes a project that uses

Uses Software

• MLC++
• UCI
• C4.5

This page was built for publication: Making use of the most expressive jumping emerging patterns for classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1606553)