Adapting Open-Set Recognition Method to Various Time-Series Data

András Halász, Lóránt Daubner, Nawar Al-Hemeary, János Juhász, Tamás Zsedrovits, Kálmán Tornai

2023

Abstract

In real-world scenarios, conventional classifier methods often stumble when faced with the unexpected emergence of unknown samples or classes previously unseen during training. Open-Set Recognition (OSR) models have emerged as a solution to this ubiquitous challenge. Our previous work introduced a robust OSR method leveraging synthesized – or “fake” – features to delineate the uncharted territory of unknowns, focusing on image datasets. Recognizing the imperative to extend this capability to diverse data types, we have successfully transposed this model to time-series datasets. A pivotal feature of the original model was its modular archi-tecture, allowing for focused modification in feature extraction. Consequently, the core components remained intact, including feature extraction, sample generation, and feature transformation. This paper illuminates our initial strides, employing a one-dimensional convolutional network for feature extraction and showcasing promising preliminary OSR results using that network. Additionally, our adapted model maintains its advantageous edge in terms of time complexity, achieved through the discreet generation of fake features in a simplified hidden layer. Future investigations will further delve into alternative feature extraction methodologies, promising to broaden the scope of applications for this adaptable OSR model.

Paper Citation

in Harvard Style

Halász A., Daubner L., Al-Hemeary N., Juhász J., Zsedrovits T. and Tornai K. (2023). Adapting Open-Set Recognition Method to Various Time-Series Data. In Proceedings of the 19th International Conference on Web Information Systems and Technologies - Volume 1: DMMLACS; ISBN 978-989-758-672-9, SciTePress, pages 595-601. DOI: 10.5220/0012265700003584

in Bibtex Style

@conference{dmmlacs23,
author={András Halász and Lóránt Daubner and Nawar Al-Hemeary and János Juhász and Tamás Zsedrovits and Kálmán Tornai},
title={Adapting Open-Set Recognition Method to Various Time-Series Data},
booktitle={Proceedings of the 19th International Conference on Web Information Systems and Technologies - Volume 1: DMMLACS},
year={2023},
pages={595-601},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012265700003584},
isbn={978-989-758-672-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Conference on Web Information Systems and Technologies - Volume 1: DMMLACS
TI - Adapting Open-Set Recognition Method to Various Time-Series Data
SN - 978-989-758-672-9
AU - Halász A.
AU - Daubner L.
AU - Al-Hemeary N.
AU - Juhász J.
AU - Zsedrovits T.
AU - Tornai K.
PY - 2023
SP - 595
EP - 601
DO - 10.5220/0012265700003584
PB - SciTePress