Junrong Du
ABSTRACT
In the field of aerospace, the abnormal detection of data is of great significance. The rapid and effective detection of abnormal parameters is key to find potential failures of spacecraft. Traditional methods of anomaly detection need much manual labour and material resources but cannot satisfy the requirements of real-time accuracy. At the same time, there are far more normal samples than abnormal samples, and the original classification methods cannot be applied. In this paper, we propose a GANomaly-based framework for anomaly detection of aerospace data. GANomaly is a framework that analyzes the underlying relationships of data using potential space, which is more in line with the characteristics of the payload data and the actual scenarios for anomaly detection. This article compares GANomaly with other anomaly detection methods on the public aerospace dataset and payload dataset respectively. The results show that the GANomaly-based anomaly detection framework has good capabilities for detecting abnormality of aerospace datasets.
- Smolensky P. Information processing in dynamical systems: Foundations of harmony theory. Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Cambridge, MA, USA: MIT Press, 1986.Google Scholar
- Hinton G E, Zemel R S. Autoencoders, minimum description length and Helmholtz free energy. In: Proceedings of the 6th International Conference on Neural Information Processing Systems. Denver, Colorado, USA: Morgan Kaufmann Publishers Inc., 1994. 3--10Google Scholar
- Bengio Y, Lamblin P, Popovici D, Larochelle H. Greedy layer-wise training of deep networks. In: Proceedings of the 21st Annual Conference on Neural Information Processing Systems. Vancouver, BC, Canada: MIT Press, 2007. 153--160Google Scholar
- Schlegl T, Seeböck P, Waldstein S M, et al. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery[C]//International Conference on Information Processing in Medical Imaging. Springer, Cham, 2017: 146--157.Google Scholar
- Zenati H, Foo C S, Lecouat B, et al. Efficient gan-based anomaly detection[J]. arXiv preprint arXiv:1802.06222, 2018.Google Scholar
- Akcay S, Atapour-Abarghouei A, Breckon T P. Ganomaly: Semi-supervised anomaly detection via adversarial training[C]//Asian Conference on Computer Vision. Springer, Cham, 2018: 622--637.Google Scholar
- Donahue, J., Krhenbhl, P., and Darrell, T. Adversarial Feature Learning. abs/1605.09782, 2016. URL http://arxiv.org/abs/1605.09782.Google Scholar
- Dumoulin, V., Belghazi, M. I. D., Poole, B., Lamb, A., Arjovsky, M., Mastropietro, O., and Courville, A. Adversarially learned inference. 2017. URL http://arXiv.org/abs/1606.00704.Google Scholar
- I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, "Generative adversarial nets," in Advances in Neural Information Processing Systems 27, 2014, pp. 2672---2680.Google Scholar
- Isola P, Zhu J Y, Zhou T, et al. Image-to-image translation with conditional adversarial networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 1125--1134.Google Scholar
- Di Mattia F, Galeone P, De Simoni M, et al. A survey on gans for anomaly detection[J]. arXiv preprint arXiv:1906.11632, 2019.Google Scholar
- Wang Z, She Q, Ward T E. Generative adversarial networks: A survey and taxonomy[J]. arXiv preprint arXiv:1906.01529, 2019.Google Scholar
- Silva E, Lochter J. A study on Anomaly Detection GAN-based methods on image data[C]//Anais do XVI Encontro Nacional de Inteligência Artificial e Computacional. SBC, 2020: 823--831.Google Scholar
- Kliger M, Fleishman S. Novelty detection with gan[J]. arXiv preprint arXiv:1802.10560, 2018.Google Scholar
- Lee W, Xiang D. Information-theoretic measures for anomaly detection[C]//Proceedings 2001 IEEE Symposium on Security and Privacy. S&P 2001. IEEE, 2000: 130--143.Google Scholar
Index Terms
- Anomaly Detection of Aerospace Facilities Using Ganomaly
Recommendations
Anomaly detection for sensor data of semiconductor manufacturing equipment using a GAN
AbstractIn semiconductor manufacturing, it is required to detect anomalies which cause expensive defects. In recent years, Generative Adversarial Networks (GANs) have played a big role in anomaly detection. This study aims to detect anomalies by analyzing ...
Deep learning for anomaly detection in multivariate time series: Approaches, applications, and challenges
AbstractAnomaly detection has recently been applied to various areas, and several techniques based on deep learning have been proposed for the analysis of multivariate time series. In this study, we classify the anomalies into three types, ...
Highlights- The methods for anomaly detection on multivariate time series are reviewed.
- The ...
Explainable contextual anomaly detection using quantile regression forests
AbstractTraditional anomaly detection methods aim to identify objects that deviate from most other objects by treating all features equally. In contrast, contextual anomaly detection methods aim to detect objects that deviate from other objects within a ...
Comments