Deep Learning for Anomaly Detection in Time-Series Data: Review, Analysis, and Guidelines
Глубокое обучение для обнаружения аномалий во временных рядах данных: обзор, анализ и рекомендации
2021-01-01
SCID: 54.1/pu7fq42d
Discuss with AI
benchmark datasetsdeep learningmultivariate time seriestime-series anomaly detectionunsupervised representation learning
Figures from the paper
Abstract (AI)
As industries become automated and connectivity technologies advance, a wide range of systems continues to generate massive amounts of data. Many approaches have been proposed to extract principal indicators from the vast sea of data to represent the entire system state. Detecting anomalies using these indicators on time prevent potential accidents and economic losses. Anomaly detection in multivariate time series data poses a particular challenge because it requires simultaneous consideration of temporal dependencies and relationships between variables. Recent deep learning-based works have made impressive progress in this field. They are highly capable of learning representations of the large-scaled sequences in an unsupervised manner and identifying anomalies from the data. However, most of them are highly specific to the individual use case and thus require domain knowledge for appropriate deployment. This review provides a background on anomaly detection in time-series data and reviews the latest applications in the real world. Also, we comparatively analyze state-of-the-art deep-anomaly-detection models for time series with several benchmark datasets. Finally, we offer guidelines for appropriate model selection and training strategy for deep learning-based time series anomaly detection.
Key Findings
1
Deep learning methods can learn representations of large-scale sequences unsupervised and identify anomalies without requiring labeled data.
2
Existing deep anomaly-detection models are often highly use-case-specific and require domain knowledge for appropriate deployment.
3
Multivariate time-series anomaly detection must jointly model temporal dependencies and relationships among variables.
4
The paper provides guidelines for selecting and training deep-learning models for time-series anomaly detection.
5
The review comparatively analyzes state-of-the-art deep-learning models using several benchmark datasets.
Research Object
multivariate time-series data generated by automated and connected systems
Research Subject
deep learning-based anomaly detection, including the modeling of temporal dependencies and inter-variable relationships, and the comparative performance of detection models
Publication Details
Publication Date
2021-01-01
Journal
Publisher
ISSN
Cited by
667
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai17
ImageNet classification with deep convolutional neural networks2017
Exploiting Generative AI to Scale up Intelligent Tutoring Systems2023
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
Image-to-Image Translation with Conditional Adversarial Networks2017
Generative adversarial networks2020
Neural Machine Translation by Jointly Learning to Align and Translate2014
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks2015
Overcoming catastrophic forgetting in neural networks2017
Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network2019
A Review on Outlier/Anomaly Detection in Time Series Data2021
Graph Neural Network-Based Anomaly Detection in Multivariate Time Series2021
A Comparative Evaluation of Unsupervised Anomaly Detection Algorithms for Multivariate Data2016
Multivariate Time-Series Anomaly Detection via Graph Attention Network2020
DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series2018
Computer vision and deep learning–based data anomaly detection method for structural health monitoring2018
Learning Graph Structures With Transformer for Multivariate Time-Series Anomaly Detection in IoT2021
Qualitative Spatial Reasoning over Questions (Short Paper)2022