Minimum Enclosing and Maximum Excluding Machine for Pattern Description and Discrimination

Authors:
Yi Liu;Yuan F. Zheng
Affiliations:
Ohio State University, Columbus, Ohio;Ohio State University, Columbus, Ohio
Venue:
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Year:
2006

Citing 0
Cited 5

Active and Semi-supervised Data Domain Description

ECML PKDD '09 Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: Part I
Active learning for network intrusion detection

Proceedings of the 2nd ACM workshop on Security and artificial intelligence
Margin and domain integrated classification

ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Enhancing one-class support vector machines for unsupervised anomaly detection

Proceedings of the ACM SIGKDD Workshop on Outlier Detection and Description
Toward supervised anomaly detection

Journal of Artificial Intelligence Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

This work addresses the description problem of a target class in the presence of negative samples or outliers. Traditional Support Vector Machines (SVM) has strong discrimination capability to distinguish the target class but does not reject the uncharacteristic patterns well. The one-class SVM, on the other hand, provides good representation for the class of interest but overlooks the discrimination issue between the class and outliers. This paper presents a new one-class classifier named minimum enclosing and maximum excluding machine (MEMEM), which offers capabilities for both pattern description and discrimination. The properties of MEMEM are analyzed and the performance comparisons using synthetic and real data are presented.