Incremental One-Class Models for Data Classification

TL;DR

This paper proposes a new incremental one-class classification framework capable of adapting to non-stationary data environments, especially effective with small initial datasets and large-scale data variability.

Contribution

It introduces an incremental Covariance-guided One-Class SVM that emphasizes low variance directions and maintains support vectors through KKT conditions, improving classification performance.

Findings

Significantly better classification accuracy than existing methods.

Effective handling of non-stationary data environments.

Robust performance on artificial and real datasets.

Abstract

In this paper we outline a PhD research plan. This research contributes to the field of one-class incremental learning and classification in case of non-stationary environments. The goal of this PhD is to define a new classification framework able to deal with very small learning dataset at the beginning of the process and with abilities to adjust itself according to the variability of the incoming data which create large scale datasets. As a preliminary work, incremental Covariance-guided One-Class Support Vector Machine is proposed to deal with sequentially obtained data. It is inspired from COSVM which put more emphasis on the low variance directions while keeping the basic formulation of incremental One-Class Support Vector Machine untouched. The incremental procedure is introduced by controlling the possible changes of support vectors after the addition of new data points, thanks to the Karush-Kuhn-Tucker conditions, that have to be maintained on all previously acquired data. Comparative experimental results with contemporary incremental and non-incremental one-class classifiers on numerous artificial and real data sets show that our method results in significantly better classification performance.