A4 Article in conference proceedings
Linear-Time One-Class Classification with Repeated Element-Wise Folding (2024)


Raitoharju, J. (2024). Linear-Time One-Class Classification with Repeated Element-Wise Folding. In 32nd European Signal Processing Conference (EUSIPCO 2024) : Proceedings (pp. 1952-1956). IEEE. European Signal Processing Conference. https://doi.org/10.23919/eusipco63174.2024.10715412


JYU authors or editors


Publication details

All authors or editorsRaitoharju, Jenni

Parent publication32nd European Signal Processing Conference (EUSIPCO 2024) : Proceedings

Place and date of conferenceLyon, France26.-30.8.2024

ISBN979-8-3315-1977-3

eISBN978-9-4645-9361-7

Journal or seriesEuropean Signal Processing Conference

ISSN2219-5491

eISSN2076-1465

Publication year2024

Publication date26/08/2024

Pages range1952-1956

Number of pages in the book2761

PublisherIEEE

Publication countryUnited States

Publication languageEnglish

DOIhttps://doi.org/10.23919/eusipco63174.2024.10715412

Publication open accessNot open

Publication channel open access

Publication is parallel published (JYX)https://jyx.jyu.fi/handle/123456789/99074

Web address of parallel published publication (pre-print)https://arxiv.org/abs/2408.11412


Abstract

This paper proposes an easy-to-use method for one-class classification: Repeated Element-wise Folding (REF). The algorithm consists of repeatedly standardizing and applying an element-wise folding operation on the one-class training data. Equivalent mappings are performed on unknown test items and the classification prediction is based on the item's distance to the origin of the final distribution. As all the included operations have linear time complexity, the proposed algorithm provides a linear-time alternative for the commonly used computationally much more demanding approaches. Furthermore, REF can avoid the challenges of hyperparameter setting in one-class classification by providing robust default settings. The experiments show that the proposed method can produce similar classification performance or even outperform the more complex algorithms on various benchmark datasets. Matlab codes for REF are publicly available at https://github.com/JenniRaitoharju/REF.


Keywordsclassificationalgorithmsmachine learning

Free keywordsOne-class Classification; Linear-time; Repeated Element-wise Folding


Contributing organizations


Ministry reportingYes

VIRTA submission year2024

Preliminary JUFO rating1


Last updated on 2025-16-01 at 20:05