Time Series Anomaly Detection Leveraging MSE Feedback with AutoEncoder and RNN
Anomaly Transformer: обнаружение аномалий во временных рядах с использованием расхождения ассоциаций
2024-01-01
SCID: 54.1/da2qpb8v
Discuss with AI
Anomaly Transformerassociation discrepancyautoencoder-RNNreconstruction error feedbacktime series anomaly detection
Figures from the paper
Abstract (AI)
Anomaly detection in time series data is a critical task in various domains, including finance, healthcare, cybersecurity and industry. Traditional methods, such as time series decomposition, clustering, and density estimation, have provided robust solutions for identifying anomalies that exhibit distinct patterns or significant deviations from normal data distributions. Recent advancements in machine learning and deep learning have further enhanced these capabilities. This paper introduces a novel method for anomaly detection that combines the strengths of autoencoders and recurrent neural networks (RNNs) with an reconstruction error feedback mechanism based on Mean Squared Error. We compare our method against classical techniques and recent approaches like OmniAnomaly, which leverages stochastic recurrent neural networks, and the Anomaly Transformer, which introduces association discrepancy to capture long-range dependencies and DCDetector using contrastive representation learning with multi-scale dual attention. Experimental results demonstrate that our method achieves superior overall performance in terms of precision, recall, and F1 score. The source code is available at http://github.com/mribrahim/AE-FAR
Key Findings
1
Experiments report superior overall precision, recall, and F1 score compared with the evaluated methods.
2
Source code is publicly available at http://github.com/mribrahim/AE-FAR.
3
The approach is designed to detect time-series anomalies by leveraging reconstruction errors and learned temporal patterns.
4
The method is evaluated against classical techniques, OmniAnomaly, Anomaly Transformer, and DCDetector.
5
The paper introduces an anomaly detection method combining autoencoders, recurrent neural networks, and Mean Squared Error reconstruction-error feedback.
Research Object
time series data
Research Subject
anomaly detection performance, including precision, recall, and F1 score, using an autoencoder–RNN method with reconstruction-error feedback
Publication Details
Publication Date
2024-01-01
Journal
Publisher
ISSN
Cited by
7
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai10
PyTorch: An Imperative Style, High-Performance Deep Learning Library2019
Isolation Forest2008
Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network2019
Graph Neural Network-Based Anomaly Detection in Multivariate Time Series2021
Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications2018
Multivariate Time-Series Anomaly Detection via Graph Attention Network2020
Practical Approach to Asynchronous Multivariate Time Series Anomaly Detection and Localization2021
Multivariate Time Series Anomaly Detection and Interpretation using Hierarchical Inter-Metric and Temporal Embedding2021
Learning Graph Structures With Transformer for Multivariate Time-Series Anomaly Detection in IoT2021
DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection2023
Cited by5
Transformers in Time Series: A Survey2023
Deep Learning for Time Series Anomaly Detection: A Survey2024
A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection2024
DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection2023
A Survey of Deep Anomaly Detection in Multivariate Time Series: Taxonomy, Applications, and Directions2025