TAnoGAN: Time Series Anomaly Detection with Generative Adversarial Networks
Authors:
- 1 December 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1778-1785
Abstract
Anomaly detection in time series data is a significant problem faced in many application areas such as manufacturing, medical imaging and cyber-security. Recently, Generative Adversarial Networks (GAN) have gained attention for generation and anomaly detection in image domain. In this paper, we propose a novel GAN-based unsupervised method called TAnoGan for detecting anomalies in time series when a small number of data points are available. We evaluate TAnoGan with 46 real-world time series datasets that cover a variety of domains. Extensive experimental results show that TAnoGan performs better than traditional and neural network models.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- A survey of deep learning-based network anomaly detectionCluster Computing, 2017
- Anomaly Detection with Robust Deep Autoencoders2017
- Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery2017
- Evaluating Real-Time Anomaly Detection Algorithms -- The Numenta Anomaly Benchmark2015
- A model-based fault detection and diagnostic methodology based on PCA method and wavelet transformEnergy and Buildings, 2014
- From Model, Signal to Knowledge: A Data-Driven Perspective of Fault Detection and DiagnosisIEEE Transactions on Industrial Informatics, 2013
- Comparative Evaluation of Anomaly Detection Techniques for Sequence Data2008
- Angle-based outlier detection in high-dimensional data2008
- Feature bagging for outlier detection2005
- Long Short-Term MemoryNeural Computation, 1997