請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/80594完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 王勝德(Seng-De Wang) | |
| dc.contributor.author | Wei-Chin Chien | en |
| dc.contributor.author | 簡暐晉 | zh_TW |
| dc.date.accessioned | 2022-11-24T03:10:15Z | - |
| dc.date.available | 2022-02-16 | |
| dc.date.available | 2022-11-24T03:10:15Z | - |
| dc.date.copyright | 2022-02-16 | |
| dc.date.issued | 2022 | |
| dc.date.submitted | 2022-02-10 | |
| dc.identifier.citation | [1] P. Baldi. Autoencoders, unsupervised learning, and deep architectures. In I. Guyon, G. Dror, V. Lemaire, G. Taylor, and D. Silver, editors, Proceedings of ICML Workshop on Unsupervised and Transfer Learning, volume 27 of Proceedings of Machine Learning Research, pages 37–49, Bellevue, Washington, USA, 02 Jul 2012. PMLR. [2] D. Bank, N. Koenigstein, and R. Giryes. Autoencoders, 2021. [Online]. Available: https://arxiv.org/abs/2003.05991 [3] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding, 2019. [Online]. Available: https://arxiv.org/abs/1810.04805 [4] I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. Generative adversarial networks, 2014. [Online]. Available: https://arxiv.org/abs/1406.2661 [5] V. Hautamaki, I. Karkkainen, and P. Franti. Outlier detection using k-nearest neighbour graph. In Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004., volume 3, pages 430–433 Vol.3, 2004. [6] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition, 2015. [Online]. Available: https://arxiv.org/abs/1512.03385 [7] M.Hearst,S.Dumais,E.Osuna,J.Platt,andB.Scholkopf.Supportvectormachines. IEEE Intelligent Systems and their Applications, 13(4):18–28, 1998. [8] S. Hochreiter and J. Schmidhuber. Long short-term memory. Neural computation, 9(8):1735–1780, 1997. [9] T. Kieu, B. Yang, C. Guo, and C. S. Jensen. Outlier detection for time series with recurrent autoencoder ensembles. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, pages 2725–2732. International Joint Conferences on Artificial Intelligence Organization, 7 2019. [10] A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger, editors, Advances in Neural Information Processing Systems 25, pages 1097–1105. Curran Associates, Inc., 2012. [11] K. Lee, H. Lee, K. Lee, and J. Shin. Training confidence-calibrated classifiers for detecting out-of-distribution samples, 2018. [Online]. Available: https://arxiv.org/ abs/1711.09325 [12] F. Mao, X. Wu, H. Xue, and R. Zhang. Hierarchical video frame sequence repre- sentation with deep convolutional graph network. Computer Vision–ECCV 2018 Workshops, page 262–270, 2021. [13] A.P.MathurandN.O.Tippenhauer.Swat:awatertreatmenttestbedforresearchand training on ics security. In 2016 International Workshop on Cyber-physical Systems for Smart Water Networks (CySWater), pages 31–36, 2016. [14] M. Munir, S. A. Siddiqui, A. Dengel, and S. Ahmed. Deepant: A deep learning approach for unsupervised anomaly detection in time series. IEEE Access, 7:1991– 2005, 2019. [15] C. Ranjan, M. Reddy, M. Mustonen, K. Paynabar, and K. Pourak. Dataset: Rare event classification in multivariate time series, 2019. [Online]. Available: https:// arxiv.org/abs/1809.10717 [16] S. Russo, A. Disch, F. Blumensaat, and K. Villez. Anomaly detection using deep autoencoders for in-situ wastewater systems monitoring data, 2020. [Online]. Available: https://arxiv.org/abs/2002.03843 [17] T. Schlegl, P. Seeböck, S. M. Waldstein, U. Schmidt-Erfurth, and G. Langs. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery, 2017. [Online]. Available: https://arxiv.org/abs/1703.05921 [18] B. Schölkopf, R. C. Williamson, A. J. Smola, J. Shawe-Taylor, J. C. Platt, et al. Support vector method for novelty detection. In NIPS, volume 12, pages 582–588. Citeseer, 1999. [19] R. Taormina, S. Galelli, N. O. Tippenhauer, E. Salomons, A. Ostfeld, D. G. Eliades, M. Aghashahi, R. Sundararajan, M. Pourahmadi, M. K. Banks, et al. Battle of the attack detection algorithms: Disclosing cyber attacks on water distribution networks. Journal of Water Resources Planning and Management, 144(8):04018048, 2018. [20] H. Thanh-Tung and T. Tran. On catastrophic forgetting and mode collapse in generative adversarial networks, 2020. [Online]. Available: https:// arxiv.org/ abs/ 1807.04015 [21] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin. Attention is all you need, 2017. [Online]. Available: https:// arxiv.org/abs/1706.03762 [22] Y. Wang, J. Wong, and A. Miner. Anomaly intrusion detection using one class svm. In Proceedings from the Fifth Annual IEEE SMC Information Assurance Workshop, 2004., pages 358–364, 2004. [23] C. Zhang, D. Song, Y. Chen, X. Feng, C. Lumezanu, W. Cheng, J. Ni, B. Zong, H. Chen, and N. V. Chawla. A deep neural network for unsupervised anomaly de- tection and diagnosis in multivariate time series data, 2018. [Online]. Available: https://arxiv.org/abs/1811.08055 [24] Z. Zhang, Y. Song, and H. Qi. Decoupled learning for conditional adversarial net- works, 2018. [Online]. Available: https://arxiv.org/abs/1801.06790 | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/80594 | - |
| dc.description.abstract | "在工業控制系統中，時常產生具有時間序列關係的數據。這些數據可能來自於橋樑震動，配水系統，或製造設備的監測數據。本文提出一個可預測多變數時間序列的異常偵測模型與訓練方法。該方法基於自編碼器，並且近一步使用生成式對抗網路，結合由生成模型產生殘差，以及判别模型輔助產生的異常分數，以增加預測精準度。所提出的演算法也降低了訓練生成式對抗網路的難度，並且該方法在SWaT, BATADAL, 以及Rare Event Classification 資料集上均比常見方法在F1 socre上取得了更好的表現。" | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-24T03:10:15Z (GMT). No. of bitstreams: 1 U0001-0802202214442000.pdf: 1134461 bytes, checksum: eafe2aafa05fa1b71ba8e7f1aa82d41e (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | Contents Acknowledgements i 摘要 iii Abstract v Contents vii List of Figures ix List of Tables xi Chapter 1 Introduction 1 Chapter 2 Related Work 5 2.1 Traditional Method........................... 5 2.2 DeepLearningMethod......................... 6 Chapter 3 Proposed Approach 11 3.1 Overview................................ 11 3.2 Problem formulation .......................... 11 3.3 Stage1:Autoencoder.......................... 12 3.4 Stage2:GAN.............................. 14 3.5 Anomaly Detection-Testing Stage ................... 16 Chapter 4 Experiments 19 4.1 Setup ................... 19 4.1.1 Dataset................................. 19 4.1.2 SWaT(SecureWaterTreatment) ................... 19 4.1.3 BATADAL (BATtle of the Attack Detection ALgorithms) . . . . . . 20 4.1.4 RareEventClassification....................... 20 4.2 Evaluation metrics ........................... 21 4.3 Baseline Models for Comparison .................... 22 4.4 Result .................................. 23 4.5 Analysis ................................ 24 Chapter 5 Conclusion 27 References 29 List of Figures 1.1 Example of a system with multivariate time series anomaly. . . . . . . . 2 2.1 An example of univariate anomaly detection. . . . . . . . . . . . . . . . 7 2.2 A simple illustration of autoencoder . . . . . . . . . . . . . . . . . . . . 8 2.3 A simple structure of GAN . . . . . . . . . . . . . . . . . . . . . . . . . 9 3.1 A module of LSTM cell . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 3.2 First stage with autoencoder . . . . . . . . . . . . . . . . . . . . . . . . 14 3.3 Second stage with autoencoder and GAN . . . . . . . . . . . . . . . . . 16 4.1 SWaT testbed process overview.[13] . . . . . . . . . . . . . . . . . . . . 20 4.2 Graphical representation of BATADAL C-Town water distribution system.[19] . . . . . . . . . . . . . 21 4.3 Visualization result on SWaT dataset of different methods . . . . . . . . . 25 4.4 Visualization result on BATADAL dataset of different methods . . . . . . 26 4.5 Visualization result on Rare Event dataset of different methods . . . . . . 26 List of Tables 4.1 Hyperparameters of different methods . . . . . . . . . . . . . . . . . . . 23 4.2 f1 score on SWaT and BATADAL dataset . . . . . . . . . . . . . . . . . 23 4.3 f1 score on Rare Event classification dataset . . . . . . . . . . . . . . . . 24 4.4 statistics for the datasets . . . . . . . . . . . . . . . . . . . . . . . . . . 24 | |
| dc.language.iso | en | |
| dc.subject | 生成對抗網路 | zh_TW |
| dc.subject | 異常偵測 | zh_TW |
| dc.subject | 時間序列 | zh_TW |
| dc.subject | 自編碼器 | zh_TW |
| dc.subject | Anomaly Detection | en |
| dc.subject | Generative Adversarial Network | en |
| dc.subject | Autoencoder | en |
| dc.subject | Time Series | en |
| dc.title | 基於解構式生成對抗網路於多變數工業傳感資料之異常檢測 | zh_TW |
| dc.title | Anomaly Detection for Multivariate Industrial Sensor Data via Decoupled Generative Adversarial Network | en |
| dc.date.schoolyear | 110-1 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 雷欽隆(Lily I-Wen Su),余承叡(Shu-chen Sherry Ou),(Yu-An Lu),(Chenhao Chiu) | |
| dc.subject.keyword | 異常偵測,時間序列,自編碼器,生成對抗網路, | zh_TW |
| dc.subject.keyword | Anomaly Detection,Time Series,Autoencoder,Generative Adversarial Network, | en |
| dc.relation.page | 32 | |
| dc.identifier.doi | 10.6342/NTU202200380 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2022-02-11 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電機工程學研究所 | zh_TW |
| 顯示於系所單位： | 電機工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-0802202214442000.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 1.11 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。