ALGAN: Time Series Anomaly Detection with Adjusted-LSTM GAN

TL;DR

ALGAN is a novel GAN model utilizing adjusted LSTM networks that significantly improves anomaly detection accuracy in both univariate and multivariate time series data across various real-world datasets.

Contribution

This paper introduces ALGAN, a new GAN architecture with adjusted LSTM, enhancing unsupervised anomaly detection in diverse time series datasets.

Findings

ALGAN outperforms existing methods in anomaly detection accuracy.

Effective in both univariate and multivariate time series.

Validated on 46 real-world datasets across multiple domains.

Abstract

Anomaly detection in time series data, to identify points that deviate from normal behaviour, is a common problem in various domains such as manufacturing, medical imaging, and cybersecurity. Recently, Generative Adversarial Networks (GANs) are shown to be effective in detecting anomalies in time series data. The neural network architecture of GANs (i.e. Generator and Discriminator) can significantly improve anomaly detection accuracy. In this paper, we propose a new GAN model, named Adjusted-LSTM GAN (ALGAN), which adjusts the output of an LSTM network for improved anomaly detection in both univariate and multivariate time series data in an unsupervised setting. We evaluate the performance of ALGAN on 46 real-world univariate time series datasets and a large multivariate dataset that spans multiple domains. Our experiments demonstrate that ALGAN outperforms traditional, neural network-based, and other GAN-based methods for anomaly detection in time series data.