Anomaly Detection in Imbalance Secure Water Treatment Dataset Using LSTM-DC-Wasserstein Generative Adversarial Network with Gradient Penalty

Jonathan Marshell Kevin; Naufan Raharya

doi:10.62146/ijecbe.v2i3.56

Authors

Jonathan Marshell Kevin Universitas Indonesia
Naufan Raharya Universitas Indonesia

DOI:

https://doi.org/10.62146/ijecbe.v2i3.56

Keywords:

wasserstein gan, deep convolutional neural network, long-short term memory, anomaly detection, multivariate time series

Abstract

In modern industrial systems, particularly with the advancement of the Internet of Things (IoT), industry players can record machine and system data for comprehensive analysis. This capability is crucial for detecting anomalies and taking necessary corrective actions.
However, it is common for manufacturers to lack recorded anomaly datasets, especially for newly operational systems. In this paper, we develop a model to detect anomalies in an imbalanced dataset from the Secure Water Treatment (SWaT) system. The performance of the proposed model is compared with previous works, demonstrating significant improvements in anomaly detection capabilities where it achieves accuracy of 0.9546, precision of 0.9086, recall of 0.6654, and F1 score of 0.7681

Author Biographies

Jonathan Marshell Kevin, Universitas Indonesia

Department of Electrical Engineering, Faculty of Engineering, Universitas Indonesia, Depok, Indonesia

Naufan Raharya, Universitas Indonesia

Department of Electrical Engineering, Faculty of Engineering, Universitas Indonesia, Depok, Indonesia

References

Shunfeng Cheng et al. “A Wireless Sensor System for Prognostics and Health Management”. In: IEEE Sensors Journal 10.4 (2010), pp. 856–862. DOI: 10.1109/JSEN.2009.2035817.

Daoqu Geng et al. “Big Data-Based Improved Data Acquisition and Storage System for Designing Industrial Data Platform”. In: IEEE Access 7 (2019), pp. 44574–44582. DOI: 10.1109/ACCESS.2019. 2909060.

Weiting Zhang, Dong Yang, and Hongchao Wang. “Data-Driven Methods for Predictive Maintenance of Industrial Equipment: A Survey”. In: IEEE Systems Journal 13.3 (2019), pp. 2213–2227. DOI: 10.1109/JSYST.2019.2905565.

Andrea Bonci, Massimiliano Pirani, and Sauro Longhi. “Tiny Cyber-Physical Systems for Performance Improvement in the Factory of the Future”. In: IEEE Transactions on Industrial Informatics 15.3 (2019), pp. 1598–1608. DOI: 10.1109/TII.2018.2855747.

Dmitry Shalyga, Pavel Filonov, and Andrey Lavrentyev. Anomaly Detection for Water Treatment System based on Neural Network with Automatic Architecture Optimization. 2018. arXiv: 1807.07282 [cs.LG].

Pavel Filonov, Andrey Lavrentyev, and Artem Vorontsov. Multivariate Industrial Time Series with Cyber-Attack Simulation: Fault Detection Using an LSTM-based Predictive Data Model. 2016. arXiv: 1612.06676 [cs.LG].

Pavel Filonov, Fedor Kitashov, and Andrey Lavrentyev. RNN-based Early Cyber-Attack Detection for the Tennessee Eastman Process. 2017. arXiv: 1709.02232 [cs.CR].

David S. Matteson and Nicholas A. James. A Nonparametric Approach for Multiple Change Point Analysis of Multivariate Data. 2013. arXiv: 1306.4933 [stat.ME].

Ian J. Goodfellow et al. Generative Adversarial Networks. 2014. arXiv: 1406.2661 [stat.ML].

Yong jun Hong et al. “How Generative Adversarial Networks and Their Variants Work: An Overview”. In: ACM Computing Surveys 52.1 (Feb. 2019), pp. 1–43. ISSN: 1557-7341. DOI: 10.1145/3301282. URL: http://dx.doi.org/10.1145/3301282.

Martin Arjovsky, Soumith Chintala, and Léon Bottou. Wasserstein GAN. 2017. arXiv: 1701.07875 [stat.ML].

Ishaan Gulrajani et al. Improved Training of Wasserstein GANs. 2017. arXiv: 1704.00028 [cs.LG].

Peng Xu, Rui Du, and Zhongbao Zhang. “Predicting pipeline leakage in petrochemical system through GAN and LSTM”. In: Knowledge-Based Systems 175 (2019), pp. 50–61. ISSN: 0950-7051. DOI: 10 . 1016 / j . knosys . 2019 . 03 . 013. URL: https://www.sciencedirect.com/science/article/pii/S0950705119301340.

Wenqian Jiang et al. “A GAN-Based Anomaly Detection Approach for Imbalanced Industrial Time Series”. In: IEEE Access 7 (2019), pp. 143608–143619. DOI: 10.1109/ACCESS.2019.2944689.

Ugo Fiore et al. “Using generative adversarial networks for improving classification effectiveness in credit card fraud detection”. In: Information Sciences 479 (2019), pp. 448–455. ISSN: 0020-0255. DOI: 10 . 1016 / j . ins . 2017 . 12 . 030. URL: https://www.sciencedirect.com/science/article/pii/S0020025517311519.

Thomas Schlegl et al. Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery. 2017. arXiv: 1703.05921 [cs.CV].

Mikel Galar et al. “A Review on Ensembles for the Class Imbalance Problem: Bagging-, Boosting, and Hybrid-Based Approaches”. In: IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) 42.4 (2012), pp. 463–484. DOI: 10.1109/TSMCC.2011.2161285.

Cheuk Ki Man et al. “Wasserstein Generative Adversarial Network to Address the Imbalanced Data Problem in Real-Time Crash Risk Prediction”. In: IEEE Transactions on Intelligent Transportation Systems 23.12 (2022), pp. 23002–23013. DOI: 10.1109/TITS.2022.3207798.

Octavio Loyola-González et al. “Study of the impact of resampling methods for contrast pattern based classifiers in imbalanced databases”. In: Neurocomputing 175 (2016), pp. 935–947. ISSN: 0925-2312. DOI: 10.1016/j.neucom.2015.04.120. URL: https://www.sciencedirect.com/science/article/pii/S0925231215015908.

Yong Oh Lee, Jun Jo, and Jongwoon Hwang. “Application of deep neural network and generative adversarial network to industrial maintenance: A case study of induction motor fault detection”. In: 2017 IEEE International Conference on Big Data (Big Data). 2017, pp. 3248–3253. DOI: 10.1109/BigData.2017.8258307.

Zhenyu Wu, Wenfang Lin, and Yang Ji. “An Integrated Ensemble Learning Model for Imbalanced Fault Diagnostics and Prognostics”. In: IEEE Access 6 (2018), pp. 8394–8402. DOI: 10.1109/ACCESS.2018.2807121.

Jonathan Goh et al. “A Dataset to Support Research in the Design of Secure Water Treatment Systems”. In: Critical Information Infrastructures Security. Springer International Publishing, 2017, pp. 88–99. ISBN: 978-3-319-71368-7.

Varun Chandola, Arindam Banerjee, and Vipin Kumar. “Anomaly detection: A survey”. In: ACM Comput. Surv. 41.3 (July 2009). ISSN: 0360-0300. DOI: 10.1145/1541880.1541882. URL: https://doi.org/10.1145/1541880.1541882.

Wafa Shafqat and Yung-Cheol Byun. “A Hybrid GAN-Based Approach to Solve Imbalanced Data Problem in Recommendation Systems”. In: IEEE Access 10 (2022), pp. 11036–11047. DOI: 10.1109/ACCESS.2022.3141776.

Kanika and Jimmy Singla. “Class Balancing Methods for Fraud Detection using Deep Learning”. In: 2022 Second International Conference on Artificial Intelligence and Smart Energy (ICAIS). 2022, pp. 395–400. DOI: 10.1109/ICAIS53314.2022.9742836.

Dan Li et al. MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks. 2019. arXiv: 1901.04997 [cs.LG].

Carl Vondrick, Hamed Pirsiavash, and Antonio Torralba. Generating Videos with Scene Dynamics. 2016. arXiv: 1609.02612 [cs.CV].

Tim Salimans et al. Improved Techniques for Training GANs. 2016. arXiv: 1606.03498 [cs.LG].

Md Abul Bashar and Richi Nayak. ALGAN: Time Series Anomaly Detection with Adjusted-LSTM GAN. 2023. arXiv: 2308.06663 [cs.LG].

Sidi Lu et al. CoT: Cooperative Training for Generative Modeling of Discrete Data. 2019. arXiv: 1804. 03782 [cs.LG].

Sepp Hochreiter and Jürgen Schmidhuber. “Long Short-Term Memory”. In: Neural Computation 9.8 (1997), pp. 1735–1780. DOI: 10.1162/neco.1997.9.8.1735.

Alex Sherstinsky. “Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network”. In: Physica D: Nonlinear Phenomena 404 (2020), p. 132306. ISSN: 0167-2789. DOI: 10.1016/j.physd.2019.132306. URL: http://dx.doi.org/10.1016/j.physd.2019.132306.

Zhou Jing et al. “Lifetime Prediction of Ultraviolet Light-Emitting Diodes Using a Long Short-Term Memory Recurrent Neural Network”. In: IEEE Electron Device Letters 41.12 (2020), pp. 1817–1820. DOI: 10.1109/LED.2020.3034567.

Yuguang Chen et al. “Improved Long Short-Term Memory-Based Periodic Traffic Volume Prediction Method”. In: IEEE Access 11 (2023), pp. 103502–103510. DOI: 10 . 1109 / ACCESS . 2023 . 3305398.

Xujuan Zhou et al. “A New Deep Convolutional Neural Network Model for Automated Breast Cancer Detection”. In: 2020 7th International Conference on Behavioural and Social Computing (BESC). 2020, pp. 1–4. DOI: 10.1109/BESC51023.2020.9348322.

F.A. Gers, J. Schmidhuber, and F. Cummins. “Learning to forget: continual prediction with LSTM”. In: 1999 Ninth International Conference on Artificial Neural Networks ICANN 99. (Conf. Publ. No. 470). Vol. 2. 1999, 850–855 vol.2. DOI: 10.1049/cp:19991218.

Takeru Miyato et al. Spectral Normalization for Generative Adversarial Networks. 2018. arXiv: 1802.

[cs.LG].

Donald J. Berndt and James Clifford. “Using Dynamic Time Warping to Find Patterns in Time Series”. In: KDD Workshop. 1994. URL: https://api.semanticscholar.org/CorpusID:929893.

Hardik Prabhu, Jayaraman Valadi, and Pandarasamy Arjunan. Generative Adversarial Network with Soft-Dynamic Time Warping and Parallel Reconstruction for Energy Time Series Anomaly Detection. 2024. arXiv: 2402.14384 [cs.LG].

Thokozani Shongwe, Theo G. Swart, and Hendrik C. Ferreira. “Distance-Preserving Mapping with Euclidean Distance for 4-ary PAM”. In: 2018 11th International Symposium on Communication Systems, Networks Digital Signal Processing (CSNDSP). 2018, pp. 1–6. DOI: 10.1109/CSNDSP.2018. 8471854.

Marco Cuturi and Mathieu Blondel. Soft-DTW: a Differentiable Loss Function for Time-Series. 2018. arXiv: 1703.01541 [stat.ML].

Alexander Geiger et al. TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks. 2020. arXiv: 2009.07769 [cs.LG].

Jason Brownlee. How to Calculate Precision, Recall, and F-Measure for Imbalanced Classification. MachineLearningMastery.com. Accessed: 09-07-2024. URL: https://machinelearningmastery.com/precision-recall-and-f-measure-for-imbalanced-classification/.

Tom Fawcett. “An introduction to ROC analysis”. In: Pattern Recognition Letters 27.8 (2006), pp. 861–874. DOI: 10.1016/j.patrec.2005.10.010. URL: https://www.sciencedirect.com/science/article/pii/S016786550500303X.

Dan Li et al. Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series. 2019. arXiv: 1809.04758 [cs.LG].

G. Parthasarathy and B.N. Chatterji. “A class of new KNN methods for low sample problems”. In: IEEE Transactions on Systems, Man, and Cybernetics 20.3 (1990), pp. 715–718. DOI: 10.1109/21.57285.