ABSTRACT
Small sample time series anomaly detection, as an important part of time series research, has attracted extensive attention and research in both academia and industry. The superior performance of deep learning for time series anomaly detection is largely due to the large number of training samples. However, the problem of difficult data collection leading to inaccurate modelling is common in practice. The solution to the problem of small-sample problem of anomaly detection on time series data, this paper proposes a small-sample time series data anomaly detection method ADGAN based on adversarial learning, which firstly uses the generative adversarial network as the basic framework with different network structures, in which the generative network integrates the TCN and the self-attention mechanism to achieve better data reconstruction results, and then the single-layer LSTM is used as the discriminative mechanism. The single-layer LSTM is used as the discriminative network, and the model can effectively detect anomalies in small-sample time series data through the improved GAN network structure. The experimental results on the NAB dataset show that this method has certain advantages in improving the detection accuracy and efficiency.
- DING X O, YU S J, WANG M X, Anomaly Detection on Industrial Time Series Based on Correlation Analysis[J]. Journal of Software, 2020, 31(3): 22. (in Chinese)Google Scholar
- ZHAO P, CHANG X, WANG M. A Novel Multi- variate Time-Series Anomaly Detection Approach Using an Unsupervised Deep Neural Network[J]. IEEE Access, 2021, 9: 109025-109041Google ScholarCross Ref
- CHOI Y, LIM H, CHOI H, GAN-based Anomaly Detection and Localization of Multivariate Time Series Data for Power Plant[C]//International Conference on Big Data and Smart Computing. 2020: 71-74.Google Scholar
- SHYAM P, GUPTA S, DUKKIPATI A. Attentive recurrent comparators[C]//Proceedings of the 34th International Conference on Machine Learning. Sydney, Australia: JMLR, 2017: 3173-3181.Google Scholar
- WANG Y, YAO Q, KWOK J T, Generalizing from a few examples: A survey on few-shot learning[J]. ACM Computing Surveys, 2020, 53(3): 1-34.Google Scholar
- FAWAZ H I, FORESTIER G, WEBER J, Data augmentation using synthetic data for time series classification with deep residual networks[EB/OL]. (2018-8-7) [2022-12-8]. https://doi.org/10.48550/arXiv.1808.02455.Google ScholarCross Ref
- SUN Y, LI S H, CUI C, Improved outlier detection method of power consumer data based on Gaussian kernel function[J]. Power System. Technology., 2018, 42(5):1595-1606. (in Chinese)Google Scholar
- MONEDERO I, BISCARRI F, LEÓN C, Detection of frauds and other non-technical losses in a power utility using Pearson coefficient, Bayesian networks and decision trees[J]. International Journal of Electrical Power &Energy Systems, 2012, 34(1): 90-98.Google ScholarCross Ref
- A. Lavin and S. Ahmad, “Evaluating Real-time Anomaly Detection Algorithms - the Numenta Anomaly Benchmark,” Proceedings - 2015 IEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015, pp. 38–44, 10 2015. [Online]. Available: http://arxiv.org/abs/1510.03336http: //dx.doi.org/10.1109/ICMLA.2015.141Google ScholarCross Ref
- A. Lavin, “The Numenta Anomaly Benchmark [White paper],” 2017. [Online]. Available: https://github.com/numenta/NAB/wikiGoogle Scholar
- Choi K, Yi J, Park C, Deep learning for anomaly detection in time-series data: review, analysis, and guidelines[J]. IEEE Access, 2021, 9: 120043-120065Google ScholarCross Ref
- LO Y L, HUANG S C, LU C N. Non-technical loss detection using smart distribution network measurement data[C]//IEEE PES Innovative Smart Grid Technologies.Tianjin: IEEE, 2012: 1-5.Google Scholar
- Yaacob A H, Tan I K T, Chien S F, Arima based network anomaly detection[C]//2010 Second International Conference on Communication Software and Networks. IEEE, 2010: 205-209.Google Scholar
- Nakamura T, Imamura M, Mercer R, Merlin: Parameter-free discovery of arbitrary length anomalies in massive time series archives[C]//2020 IEEE international conference on data mining (ICDM). IEEE, 2020: 1190-1195.Google Scholar
- IANLIANG M, HAIKUN S, LING B. The Application on Intrusion Detection Based on K-means Cluster Algorithm Meng[C]//International Forum on Information Technology and Applications. 2009: 150-152Google Scholar
- PASSOS JÚNIOR L A, OBA RAMOS C C, RODRIGUES D, Unsupervised non-technical losses identification through optimum-path forest[J]. Electric Power Systems Research, 2016, 140(1): 413-423.Google Scholar
- PENG Y L, YANG Y N, XU Y J, Electricity theft detection in ami based on clustering and local outlier factor[J]. IEEE Access,2021, 9(1): 107250-107259.Google Scholar
- HABEEBA R A A, NASARUDDINA F, GANIB A, Real-time Big Data Processing for Anomaly Detection: A Survey[J]. International Journal of Information Management, 2019, 45: 289-307Google ScholarDigital Library
- HUNDMAN K, CONSTANTINOU V, LAPORTE C, Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding[C]//International Conference on Knowledge Discovery and Data Mining. 2018: 387- 395Google Scholar
- XU H, CHEN W, ZHAO N, Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications[C]//The World Wide Web Conference. 2018: 187-196Google Scholar
- CHEN N, TU H, DUAN X, Semisupervised Anomaly Detection of Multivariate Time Series Based on a Variational Autoencoder[J]. Applied Intelligence, 2022: 1-25Google Scholar
- GOODFELLOW I, POUGET-ABADIE J, MIRZA M, Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge MA, USA: MIT Press, 2014: 2672-2680Google Scholar
- Li D, Chen D, Jin B, MAD-GAN: Multivariate anomaly detection for time series data with generative adversarial networks[C]//Artificial Neural Networks and Machine Learning–ICANN 2019: Text and Time Series: 28th International Conference on Artificial Neural Networks, Munich, Germany, September 17–19, 2019, Proceedings, Part IV. Cham: Springer International Publishing, 2019: 703-716.Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NeurIPS, 2017.Google Scholar
- Tuli S, Casale G, Jennings N R. Tranad: Deep transformer networks for anomaly detection in multivariate time series data[J]. arXiv preprint arXiv:2201.07284, 2022.Google Scholar
- BAI S, KOLTER J Z, KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[EB/OL]. (2018-5-4) [2022-12-8]. https://doi.org/10.48550/arXiv.1803.01271.Google ScholarCross Ref
- LIU F T, TING K M, ZHOU Z H. Isolation Forest[C]//International Conference on Data Mining. 2008: 413-422.Google Scholar
- ZONG B, SONG Q, MIN M R, Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection[C]//International conference on learning representations. 2018: 1-19Google Scholar
- Hundman K, Constantinou V, Laporte C, Detecting spacecraft anomalies using lstms and nonparametric dynamic thresholding[C]//Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining. 2018: 387-395.Google Scholar
- Deng A, Hooi B. Graph neural network-based anomaly detection in multivariate time series[C]//Proceedings of the AAAI conference on artificial intelligence. 2021, 35(5): 4027-4035.Google Scholar
Index Terms
- Anomaly Detection of Small Time Series Data Based on Improved Generative Adversarial Networks
Recommendations
Anomaly Detection Method for Time Series Data Based on Transformer Reconstruction
IEEA '23: Proceedings of the 2023 12th International Conference on Informatics, Environment, Energy and ApplicationsMultiple temporal anomaly detection algorithms have important research significance in many application fields, such as system state estimation, fault prediction and diagnosis, network behavior anomaly detection and so on. Aiming at the problems of ...
STAD-GAN: Unsupervised Anomaly Detection on Multivariate Time Series with Self-training Generative Adversarial Networks
Anomaly detection on multivariate time series (MTS) is an important research topic in data mining, which has a wide range of applications in information technology, financial management, manufacturing system, and so on. However, the state-of-the-art ...
Adversarial Autoencoder for Unsupervised Time Series Anomaly Detection and Interpretation
WSDM '23: Proceedings of the Sixteenth ACM International Conference on Web Search and Data MiningIn many complex systems, devices are typically monitored and generating massive multivariate time series. However, due to the complex patterns and little useful labeled data, it is a great challenge to detect anomalies from these time series data. ...
Comments