Anomaly Detection for Time Series Using VAE-LSTM Hybrid Model
Shu‐Yu Lin, Ronald Clark, Robert Birke, Sandro Schönborn, Niki Trigoni, Stephen Roberts
Abstract
In this work, we propose a VAE-LSTM hybrid model as an unsupervised approach for anomaly detection in time series. Our model utilizes both a VAE module for forming robust local features over short windows and a LSTM module for estimating the long term correlation in the series on top of the features inferred from the VAE module. As a result, our detection algorithm is capable of identifying anomalies that span over multiple time scales. We demonstrate the effectiveness of our detection algorithm on five real world problems and find our method outperforms three other commonly used detection methods.
Topics & Concepts
Anomaly detectionComputer scienceSeries (stratigraphy)Artificial intelligenceTime seriesPattern recognition (psychology)Anomaly (physics)Data miningMachine learningPaleontologyCondensed matter physicsBiologyPhysicsAnomaly Detection Techniques and ApplicationsTime Series Analysis and ForecastingNetwork Security and Intrusion Detection