KoopAGRU: A Koopman-based Anomaly Detection in Time-Series using Gated Recurrent Units

TL;DR

KoopAGRU is a novel deep learning model that combines Fourier analysis, Koopman theory, and GRUs to improve anomaly detection in complex, nonlinear time-series data, achieving high accuracy and efficiency.

Contribution

This paper introduces KoopAGRU, integrating FFT, DeepDMD, and GRUs for enhanced anomaly detection, a novel combination not previously explored in this context.

Findings

Achieved an average F1-score of 90.88% on benchmark datasets.

Outperformed existing methods in accuracy and inference speed.

Proved effective in real-world anomaly detection scenarios.

Abstract

Anomaly detection in real-world time-series data is a challenging task due to the complex and nonlinear temporal dynamics involved. This paper introduces KoopAGRU, a new deep learning model designed to tackle this problem by combining Fast Fourier Transform (FFT), Deep Dynamic Mode Decomposition (DeepDMD), and Koopman theory. FFT allows KoopAGRU to decompose temporal data into time-variant and time-invariant components providing precise modeling of complex patterns. To better control these two components, KoopAGRU utilizes Gate Recurrent Unit (GRU) encoders to learn Koopman observables, enhancing the detection capability across multiple temporal scales. KoopAGRU is trained in a single process and offers fast inference times. Extensive tests on various benchmark datasets show that KoopAGRU outperforms other leading methods, achieving a new average F1-score of 90.88\% on the well-known anomalies detection task of times series datasets, and proves to be efficient and reliable in detecting anomalies in real-world scenarios.