Time-series Anomaly Detection Study Based on Deep Learning

Wenjuan Wu

doi:10.54097/stbmz463

Authors

Wenjuan Wu

DOI:

https://doi.org/10.54097/stbmz463

Keywords:

Anomaly detection; Deep learning; Time series.

Abstract

With the rapid development of deep learning technology, anomaly detection based on deep learning has become an important research direction. This paper classifies and summarizes anomaly detection methods, covering traditional methods, machine learning-based methods, and deep learning-based methods. It particularly introduces typical deep learning models, analyzing their respective advantages and disadvantages. Experiments were conducted on two public datasets, and the performance of each model in anomaly detection was compared in detail.

Downloads

Download data is not yet available.

References

[1] Imani M. Collaborative representation based unsupervised CNN for hyperspectral anomaly detection[J]. Infrared Physics & Technology, 2024, 141: 105498.

[2] Cai Y, Tu Y X, Teng Y T, et al. Anomaly detection of earthquake precursor data using long short-term memory networks [J]. Applied Geophysics, 2019, 16(03): 257-266.

[3] Xue J, Yan S, Qu JH, et al. Deep Membrane Systems for Multitask Segmentation in Diabetic Retinopathy[J]. Knowledge-Based System, 2019, 183(1): 1-10.

[4] Wang Q, Qi F, Sun M, et al. Identification of Tomato Disease Types and Detection of Infected Areas Based on Deep Convolutional Neural Networks and Object Detection Techniques[J]. Computational Intelligence and Neuroscience, 2019, 2019(2): 1-15.

[5] Pittino F, Puggl M, Moldaschl T, et al. Automatic anomaly detection on in-production manufacturing machines using statistical learning methods[J]. Sensors, 2020, 20(8): 2344.

[6] Wu S, Fang L, Zhang J, et al. Unsupervised Anomaly Detection and Diagnosis in Power Electronic Networks: Informative Leverage and Multivariate Functional Clustering Approaches[J]. IEEE Transactions on Smart Grid, 2023.

[7] Wang C, Zhou H, Hao Z, et al. Network traffic analysis over clustering-based collective anomaly detection[J]. Computer Networks, 2022, 205: 108760.

[8] Enayati E, Mortazavi R, Basiri A, et al. Time series anomaly detection via clustering-based representation[J]. Evolving Systems, 2024, 15(4): 1115-1136.

[9] Li, M., Xu, D., Zhang, D. et al. The seeding algorithms for spherical k-means clustering[J]. Glob Optim,2020: 695–708.

[10] Chen J, Pi D, Wu Z, et al. Imbalanced satellite telemetry data anomaly detection model based on Bayesian LSTM[J]. Acta Astronautica, 2021, 180: 232-242.

[11] Hosseinzadeh M, Rahmani A M, Vo B, et al. Improving security using SVM-based anomaly detection: issues and challenges[J]. Soft Computing, 2021, 25(4): 3195-3223.

[12] Li Y, Lei M, Liu P, et al. A novel framework for anomaly detection for satellite momentum wheel based on optimized SVM and Huffman-Multi-Scale entropy[J]. Entropy, 2021, 23(8): 1062.

[13] Djenouri Y, Belhadi A, Lin J C W, et al. Adapted k-nearest neighbors for detecting anomalies on spatio–temporal traffic flow[J]. Ieee Access, 2019, 7: 10015-10027.

[14] Ruff L, Kauffmann J R, Vandermeulen R A, et al. A unifying review of deep and shallow anomaly detection[J]. the IEEE, 2021, 109(5): 756-795.

[15] Zhao H, Liu M, Qiu S, et al. Satellite unsupervised anomaly detection based on deconvolution-reconstructed temporal convolutional autoencoder[J]. IEEE Transactions on Consumer Electronics, 2023.

[16] Kong F, Li J, Jiang B, et al. Integrated generative model for industrial anomaly detection via bidirectional LSTM and attention mechanism[J]. IEEE Transactions on Industrial Informatics, 2021, 19(1): 541-550.

[17] Su Y, Zhao Y, Niu C,et al. Robust anomaly detection for multivariatetime series through stochastic recurrent neural network[C]//Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery &data mining.2019:2828-2837.

[18] Zhao P, Chang X, Wang M. A novel multivariate time-series anomaly detection approach using an unsupervised deep neural network[J]. IEEE Access, 2021, 9: 109025-109041.

[19] Yao X, Zhu J, Jiang Q, et al. RUL prediction method for rolling bearing using convolutional denoising autoencoder and bidirectional LSTM[J]. Measurement Science and Technology, 2023, 35(3): 035111.

[20] Zou L, Zhuang K J, Zhou A, et al. Bayesian optimization and channel-fusion-based convolutional autoencoder network for fault diagnosis of rotating machinery[J]. Engineering Structures, 2023, 280: 115708.

[21] Moon J, Noh Y, Jung S, et al. Anomaly detection using a model-agnostic meta-learning-based variational auto-encoder for facility management[J]. Journal of Building Engineering, 2023, 68: 106099.

[22] de Albuquerque Filho J E, Brandão L C P, Fernandes B J T, et al. A review of neural networks for anomaly detection[J]. IEEE Access, 2022, 10: 112342-112367.

[23] Zhang X, Mu J, Zhang X, et al. Deep anomaly detection with self-supervised learning and adversarial training[J]. Pattern Recognition, 2022, 121: 108234.

[24] Chen Z, Duan J, Kang L, et al. Supervised anomaly detection via conditional generative adversarial network and ensemble active learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 45(6): 7781-7798.

[25] Schlegl T, Seeböck P, Waldstein S M, et al. f-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks[J]. Medical image analysis, 2019, 54: 30-44.

[26] Li Z, Zhao N, Zhang S, et al. Constructing large-scale real-world benchmark datasets for Aiops[J]. arXiv preprint arXiv:2208.03938, 2022.