Time Series Anomaly Detection Using Convolutional Neural Networks and Transfer Learning
arXiv:1905.13628
Abstract
Time series anomaly detection plays a critical role in automated monitoring systems. Most previous deep learning efforts related to time series anomaly detection were based on recurrent neural networks (RNN). In this paper, we propose a time series segmentation approach based on convolutional neural networks (CNN) for anomaly detection. Moreover, we propose a transfer learning framework that pretrains a model on a large-scale synthetic univariate time series data set and then fine-tunes its weights on small-scale, univariate or multivariate data sets with previously unseen classes of anomalies. For the multivariate case, we introduce a novel network architecture. The approach was tested on multiple synthetic and real data sets successfully.
8 pages, 8 figures, AI for Internet of Things Workshop in IJCAI 2019
References in corpus (4)
- Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks
- Multi-Scale Convolutional Neural Networks for Time Series Classification
- Multivariate Industrial Time Series with Cyber-Attack Simulation: Fault Detection Using an LSTM-based Predictive Data Model
- Automatic salt deposits segmentation: A deep learning approach
Cited by in corpus (10)
- Deep Learning for Time Series Anomaly Detection: A Survey
- A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions
- Deep transfer learning for intrusion detection in industrial control networks: A comprehensive review
- RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks
- Unsupervised Deep Learning for IoT Time Series
- Intra-domain and cross-domain transfer learning for time series data -- How transferable are the features?
- Transfer Learning for Future Wireless Networks: A Comprehensive Survey
- Deep learning models for predictive maintenance: a survey, comparison, challenges and prospect
- Sequence-to-Sequence Modeling for Action Identification at High Temporal Resolution
- Anomaly Detection and Sampling Cost Control via Hierarchical GANs