Extension of Incremental Linear Discriminant Analysis to Online Feature Extraction under Nonstationary Environments

Annie, Joseph and Young Min, Jang and Seiichi, Ozawa and Minho, Lee (2012) Extension of Incremental Linear Discriminant Analysis to Online Feature Extraction under Nonstationary Environments. In: Neural Information Processing 19th International Conference, ICONIP 2012 Doha, Qatar, November 12-15, 2012 Proceedings, Part II. Lecture Notes in Computer Science ; 7664 . Springer, pp. 640-647.

[img] PDF
Neural Information Processing - Copy.pdf

Download (950kB)

Abstract

In this paper, a new approach to an online feature extrac�tion under nonstationary environments is proposed by extending Incre�mental Linear Discriminant Analysis (ILDA). The extended ILDA not only detect so-called “concept drifts” but also transfer the knowledge on discriminant feature spaces of the past concepts to construct good feature spaces. The performance of the extended ILDA is evaluated for the benchmark datasets including sudden changes and reoccurrence in concepts.

Item Type: Book Chapter
Uncontrolled Keywords: incremental learning, concept drift, online feature extrac�tion, linear discriminant analysis, knowledge transfer.
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
T Technology > TN Mining engineering. Metallurgy
Divisions: Academic Faculties, Institutes and Centres > Faculty of Engineering
Depositing User: Joseph
Date Deposited: 19 Sep 2022 09:08
Last Modified: 19 Sep 2022 09:08
URI: http://ir.unimas.my/id/eprint/39677

Actions (For repository members only: login required)

View Item View Item