Deterministic annealing multi-sphere support vector data description

Authors:
Trung Le;Dat Tran;Wanli Ma;Dharmendra Sharma
Affiliations:
University of Canberra, ACT, Australia;University of Canberra, ACT, Australia;University of Canberra, ACT, Australia;University of Canberra, ACT, Australia
Venue:
ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part III
Year:
2012

Citing 6
Cited 0

Simulated annealing & boltzmann Machines: a stochastic approach to combinatorialoptimization & neural computing

Simulated annealing & boltzmann Machines: a stochastic approach to combinatorialoptimization & neural computing
Support Vector Data Description

Machine Learning
Learning Minimum Volume Sets

The Journal of Machine Learning Research
Multi-sphere Support Vector Data Description for Outliers Detection on Multi-distribution Data

ICDMW '09 Proceedings of the 2009 IEEE International Conference on Data Mining Workshops
A theoretical framework for multi-sphere support vector data description

ICONIP'10 Proceedings of the 17th international conference on Neural information processing: models and applications - Volume Part II
A new kernel-based fuzzy clustering approach: support vector clustering with cell growing

IEEE Transactions on Fuzzy Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Current well-known data description method such as Support Vector Data Description is conducted with assumption that data samples of a class in feature space are drawn from a single distribution. Based on this assumption, a single hypersphere is constructed to provide a good data description for the data. However, real-world data samples may be drawn from some distinctive distributions and hence it does not guarantee that a single hypersphere can offer the best data description. In this paper, we introduce a Deterministic Annealing Multi-sphere Support Vector Data Description (DAMS-SVDD) approach to address this issue. We propose to use a set of hyperspheres to provide a better data description for a given data set. Calculations for determining optimal hyperspheres and experimental results for applying this proposed approach to classification problems are presented.