LSTM-Based VAE-GAN for Time-Series Anomaly Detection
www.mdpi.com › 1424/8220/20-13 › 3738May 19, 2020 · In this paper, we propose a long short-term memory-based variational autoencoder generation adversarial networks (LSTM-based VAE-GAN) method for time series anomaly detection, which effectively solves the above problems. Our method jointly trains the encoder, the generator and the discriminator to take advantage of the mapping ability of the ...
Anomaly Detection for Time Series Using VAE-LSTM Hybrid Model
https://www.oxford-man.ox.ac.uk/wp-content/uploads/2020/06/ANOM…ANOMALY DETECTION FOR TIME SERIES USING VAE-LSTM HYBRID MODEL Shuyu Lin 1, Ronald Clark 2, Robert Birke 3, Sandro Sch onborn¨ 3, Niki Trigoni 1, Stephen Roberts 1 1 University of Oxford, Oxford OX1 2JD, UK 2 Imperial College London, South Kensington, London SW7 2AZ, UK 3 ABB Future Labs, Segelhofstrasse 1K, 5404 Baden-D attwil, Switzerland¨ ABSTRACT In this …