NVAE-GAN Based Approach for Unsupervised Time Series Anomaly Detection
This work provides an incremental improvement in anomaly detection accuracy for industries dealing with noisy and complex time series data, such as network monitoring and facility maintenance.
This paper addresses unsupervised time series anomaly detection by proposing T2IVAE, a model that transforms 1D time series into 2D images for a Nouveau VAE (NVAE) based architecture, enhanced with GAN-based techniques to mitigate overfitting. The model achieved F1 scores of 0.639 on Numenta Anomaly Benchmark, 0.651 on a NASA dataset, and 0.504 on a real-world dataset, outperforming comparison models.
In recent studies, Lots of work has been done to solve time series anomaly detection by applying Variational Auto-Encoders (VAEs). Time series anomaly detection is a very common but challenging task in many industries, which plays an important role in network monitoring, facility maintenance, information security, and so on. However, it is very difficult to detect anomalies in time series with high accuracy, due to noisy data collected from real world, and complicated abnormal patterns. From recent studies, we are inspired by Nouveau VAE (NVAE) and propose our anomaly detection model: Time series to Image VAE (T2IVAE), an unsupervised model based on NVAE for univariate series, transforming 1D time series to 2D image as input, and adopting the reconstruction error to detect anomalies. Besides, we also apply the Generative Adversarial Networks based techniques to T2IVAE training strategy, aiming to reduce the overfitting. We evaluate our model performance on three datasets, and compare it with other several popular models using F1 score. T2IVAE achieves 0.639 on Numenta Anomaly Benchmark, 0.651 on public dataset from NASA, and 0.504 on our dataset collected from real-world scenario, outperforms other comparison models.