Periodic Unitary Encoding for Quantum Anomaly Detection of Temporal Series

Daniele Lizzio Bosco, Daniele Lizzio Bosco, Riccardo Romanello, Giuseppe Serra

2025

Abstract

Anomaly detection in temporal series is a compelling area of research with applications in fields such as finance, healthcare, and predictive maintenance. Recently, Quantum Machine Learning (QML) has emerged as a promising approach to tackle such problems, leveraging the unique properties of quantum systems. Among QML techniques, kernel-based methods have gained significant attention due to their ability to effectively handle both supervised and unsupervised tasks. In the context of anomaly detection, unsupervised approaches are particularly valuable as labeled data is often scarce. Nevertheless, temporal series data frequently exhibit known seasonality, even in unsupervised settings. We propose a novel quantum kernel designed to incorporate seasonality information into anomaly detection tasks. Our approach constructs a Hamiltonian matrix that induces a unitary operator which period corresponds to the seasonality of the task under consideration. This unitary operator is then used to encode the data into the quantum kernel, ensuring that values sampled at instants equivalent under the period are treated consistently by the kernel. We evaluate the proposed method on an anomaly detection task for temporal series, demonstrating that embedding seasonality directly into the quantum kernel generation improves the overall performance of quantum kernel-based support vector machines.

Paper Citation

in Harvard Style

Lizzio Bosco D., Romanello R. and Serra G. (2025). Periodic Unitary Encoding for Quantum Anomaly Detection of Temporal Series. In Proceedings of the 1st International Conference on Quantum Software - Volume 1: IQSOFT; ISBN 978-989-758-761-0, SciTePress, pages 27-36. DOI: 10.5220/0013537800004525

in Bibtex Style

@conference{iqsoft25,
author={Daniele Lizzio Bosco and Riccardo Romanello and Giuseppe Serra},
title={Periodic Unitary Encoding for Quantum Anomaly Detection of Temporal Series},
booktitle={Proceedings of the 1st International Conference on Quantum Software - Volume 1: IQSOFT},
year={2025},
pages={27-36},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013537800004525},
isbn={978-989-758-761-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Quantum Software - Volume 1: IQSOFT
TI - Periodic Unitary Encoding for Quantum Anomaly Detection of Temporal Series
SN - 978-989-758-761-0
AU - Lizzio Bosco D.
AU - Romanello R.
AU - Serra G.
PY - 2025
SP - 27
EP - 36
DO - 10.5220/0013537800004525
PB - SciTePress