计算机科学 ›› 2023, Vol. 50 ›› Issue (5): 355-362.doi: 10.11896/jsjkx.220400221
张仁斌1,2, 左艺聪1, 周泽林1, 王龙1, 崔宇航1
ZHANG Renbin1,2, ZUO Yicong1, ZHOU Zelin1, WANG Long1, CUI Yuhang1
摘要： 针对传统多元时序数据异常检测模型未考虑时空数据的多模态分布问题,提出了一种多模态生成对抗网络多元时序数据异常检测模型。利用滑动窗口分割时间序列并构造特征矩阵来捕获数据的多模态特征,将其与原始数据分别作为模态信息输入多模态编码器及多模态生成器中,输出具有时空信息的多模态特征矩阵,并将真实数据编码成特征矩阵,将两类特征矩阵作为判别器输入,利用梯度惩罚方法并拟合真实分布与生成分布之间的Wasserstein距离,取代二分类交叉熵损失训练判别器,结合生成器重构误差及判别器评分实现异常检测。基于安全水处理(SWaT)及水量分布(WADI)等数据集的测试结果表明,所提模型相比基准模型在F1-分数性能指标上分别提升了0.11和0.19,能够较好地识别多元时序数据异常,具有较好的鲁棒性以及泛化能力。
中图分类号:
| [1]WANG L,LIN Y,WU Y,et al.Forecast-based Multi-aspectFramework for Multivariate Time-series Anomaly Detection[C]//2021 IEEE International Conference on Big Data(Big Data).Orlando,2021:938-947. [2]CHANDOLA V,BANERJEE A,KUMAR V.Anomaly detec-tion:A survey[J].ACM Computing Surveys(CSUR),2009,41(3):1-58. [3]BREUNIG M M,KRIEGEL H P,NG R T,et al.LOF:identi-fying density-based local outliers[C]//Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data.DallasS,2000:93-104. [4]LI C N,FENG G W,LIU R Y,et al.Traffic Trajectory Anomaly Detection Method Based on Reconstruction Error[J].Computer Science,2022,49(2):149-155. [5]JARQUE C M,BERA A K.Efficient tests for normality,homoscedasticity and serial independence of regression residuals[J].Economics Letters,1980,6(3):255-259. [6]LI J,PEDRYCZ W,JAMAL I.Multivariate time series anomaly detection:A framework of Hidden Markov Models[J].Applied Soft Computing,2017,60:229-240. [7]BURNAEV E,ISHIMTSEV V.Conformalized density-and distance-based anomaly detection in time-series data[J].arXiv:1608.04585,2016. [8]KARAAHMETOGLU O,ILHAN F,BALABAN I,et al.Unsupervised Online Anomaly Detection On Irregularly Sampled Or Missing Valued Time-Series Data Using LSTM Networks[J].arXiv:2005.12005,2020. [9]LIM B,ARIK S O,LOEFF N,et al.Temporal fusion transfor-mers for interpretable multi-horizon time series forecasting[J].arXiv:1912.09363,2019. [10]ANGIULLI F,PIZZUTI C.Fast outlier detection in high dimensional spaces[C]//European Conference on Principles of Data Mining and Knowledge Discovery.Berlin,2002:15-27. [11]RINGBERG H,SOULE A,REXFORD J,et al.Sensitivity of PCA for traffic anomaly detection[C]//Proceedings of the 2007 ACM SIGMETRICS International Conference on Measurement and Modeling of computer Systems.San Diego,2007:109-120. [12]WILINSKI A.Time series modeling and forecasting based on a Markov chain with changing transition matrices[J].Expert Systems with Applications,2019,133:163-172. [13]CHEN H,LIU H,CHU X,et al.Anomaly detection and critical SCADA parameters identification for wind turbines based on LSTM-AE neural network[J].Renewable Energy,2021,172:829-840. [14]ZHAO H,WANG Y,DUAN J,et al.Multivariate time-seriesanomaly detection via graph attention network[C]//2020 IEEE International Conference on Data Mining(ICDM).Sorrento,2020:841-850. [15]AN J,CHO S.Variational autoencoder based anomaly detection using reconstruction probability[J].Special Lecture on IE,2015,2(1):1-18. [16]LI L,YAN J,WANG H,et al.Anomaly detection of time series with smoothness-inducing sequential variational auto-encoder[J].IEEE Transactionson Neural Networks and Learning Systems,2020,32(3):1177-1191. [17]MALHOTRA P,TV V,RAMAKRISHNAN A,et al.Multi-sensor prognostics using an unsupervised health index based on LSTM encoder-decoder[J].arXiv:1608.06154,2016. [18]GOODFELLOW I J,POUGET A J,MIRZA M,et al.Genera-tive Adversarial Networks[J].Advances in Neural Information Processing Systems,2014,3:2672-2680. [19]ESTEBAN C,HYLAND S L,RÄTSCH G.Real-valued(medical) time series generation with recurrent conditional gans[J].arXiv:1706.02633,2017. [20]LI D,CHEN D,JIN B,et al.MAD-GAN:Multivariate anomaly detection for time series data with generative adversarial networks[C]//International Conference on Artificial Neural Networks.Cham,2019:703-716. [21]GEIGER A,LIU D,ALNEGHEIMISH S,et al.TadGAN:Time series anomaly detection using generative adversarial networks[C]//2020 IEEE International Conference on Big Data(Big Data).Atlanta,2020:33-43. [22]NHO Y H,RYU S,KWON D S.UI-GAN:Generative adversa-rial network-based anomaly detection using user initial information for wearable devices[J].IEEE Sensors Journal,2021,21(8):9949-9958. [23]BASHAR M A,NAYAK R.TAnoGAN:time series anomaly detection with generative adversarial networks[C]//2020 IEEE Symposium Series on Computational Intelligence(SSCI).Canberra,2020:1778-1785. [24]WANG S,LI C,LIM A.A model for non-stationary time series and its applications in filtering and anomaly detection[J].IEEE Transactions on Instrumentation and Measurement,2021,70:1-11. [25]HALLAC D,VARE S,BOYD S,et al.Toeplitz inverse cova-riance-based clustering of multivariate time series data[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.Halifax,2017:215-223. [26]ZHANG C,SONG D,CHEN Y,et al.A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time series data[J].arXiv:1811.08055,2018. [27]ARJOVSKY M,BOTTOU L.Towards principled methods for training generative adversarial networks[J].arXiv:1701.04862,2017. [28]ARJOVSKY M,CHINTALA S,BOTTOU L.Wasserstein ge-nerative adversarial networks[C]//International Conference on Machine Learning.Sydney,2017:214-223. [29]PETZKA H,FISCHER A,LUKOVNICOV D.On the regularization of wasserstein gans[J].arXiv:1709.08894,2017. [30]GULRAJANI I,AHMED F,ARJOVSKY M,et al.Improvedtraining of wasserstein gans[C]//Advances in Neural Information Processing Systems.Long Beach,2017:5767-5777. [31]GOH J,ADEPU S,JUNEJO K N,et al.A dataset to support research in the design of secure water treatment systems[C]//International Conference on Critical Information Infrastructures Security.Cham,2016:88-99. [32]MATHUR A P,TIPPENHAUER N O.SWaT:A water treatment testbed for research and training on ICS security[C]//2016 International Workshop on Cyber-Physical Systems for Smart Water Networks(CySWater).Vienna,2016:31-36. [33]XU H,CHEN W,ZHAO N,et al.Unsupervised Anomaly De-tection via Variational Auto-Encoder for Seasonal KPIs in Web Applications[C]//Proceedings of the 2018 World Wide Web Conference.Lyon,2018:187-196. [34]CHOI K,YI J,PARK C,et al.Deep Learning for Anomaly Detection in Time-Series Data:Review,Analysis,and Guidelines[J].IEEE Access,2021,9:120043-120065. |
| [1] | 赵松, 傅豪, 王洪星. 伪异常选择驱动学习的视频异常检测 Pseudo-abnormal Sample Selection for Video Anomaly Detection 计算机科学, 2023, 50(5): 146-154. https://doi.org/10.11896/jsjkx.220400227 |
| [2] | 叶瀚, 李欣, 孙海春. 结合门控机制的卷积网络实体缺失检测方法 Convolutional Network Entity Missing Detection Method Combined with Gated Mechanism 计算机科学, 2023, 50(5): 262-269. https://doi.org/10.11896/jsjkx.220400126 |
| [3] | 饶丹, 时宏伟. 基于深度聚类的航空交通流识别与异常检测研究 Study on Air Traffic Flow Recognition and Anomaly Detection Based on Deep Clustering 计算机科学, 2023, 50(3): 121-128. https://doi.org/10.11896/jsjkx.220100086 |
| [4] | 陈真, 普园媛, 赵征鹏, 徐丹, 钱文华. 基于自适应门控信息融合的多模态情感分析 Multimodal Sentiment Analysis Based on Adaptive Gated Information Fusion 计算机科学, 2023, 50(3): 298-306. https://doi.org/10.11896/jsjkx.220100156 |
| [5] | 崔竞松, 张童桐, 郭迟, 郭文飞. 基于时延特征的网络设备异常检测 Network Equipment Anomaly Detection Based on Time Delay Feature 计算机科学, 2023, 50(3): 371-379. https://doi.org/10.11896/jsjkx.211200280 |
| [6] | 李海涛, 王瑞敏, 董卫宇, 蒋烈辉. 一种基于GRU的半监督网络流量异常检测方法 Semi-supervised Network Traffic Anomaly Detection Method Based on GRU 计算机科学, 2023, 50(3): 380-390. https://doi.org/10.11896/jsjkx.220100032 |
| [7] | 王祥炜, 韩锐, 刘驰. 基于层级化数据记忆池的边缘侧半监督持续学习方法 Hierarchical Memory Pool Based Edge Semi-supervised Continual Learning Method 计算机科学, 2023, 50(2): 23-31. https://doi.org/10.11896/jsjkx.221100133 |
| [8] | 邹芸竹, 杜圣东, 滕飞, 李天瑞. 一种基于多模态深度特征融合的视觉问答模型 Visual Question Answering Model Based on Multi-modal Deep Feature Fusion 计算机科学, 2023, 50(2): 123-129. https://doi.org/10.11896/jsjkx.211200303 |
| [9] | 黄泽南, 刘晓捷, 赵晨晖, 邓亚彬, 郭东辉. 类脑计算脉冲神经网络模型及其学习算法研究进展 Spiking Neural Network Model for Brain-like Computing and Progress of Its Learning Algorithm 计算机科学, 2023, 50(1): 229-242. https://doi.org/10.11896/jsjkx.220100058 |
| [10] | 徐天慧, 郭强, 张彩明. 基于全变分比分隔距离的时序数据异常检测 Time Series Data Anomaly Detection Based on Total Variation Ratio Separation Distance 计算机科学, 2022, 49(9): 101-110. https://doi.org/10.11896/jsjkx.210600174 |
| [11] | 聂秀山, 潘嘉男, 谭智方, 刘新放, 郭杰, 尹义龙. 基于自然语言的视频片段定位综述 Overview of Natural Language Video Localization 计算机科学, 2022, 49(9): 111-122. https://doi.org/10.11896/jsjkx.220500130 |
| [12] | 曹晓雯, 梁美玉, 鲁康康. 基于细粒度语义推理的跨媒体双路对抗哈希学习模型 Fine-grained Semantic Reasoning Based Cross-media Dual-way Adversarial Hashing Learning Model 计算机科学, 2022, 49(9): 123-131. https://doi.org/10.11896/jsjkx.220600011 |
| [13] | 周旭, 钱胜胜, 李章明, 方全, 徐常胜. 基于对偶变分多模态注意力网络的不完备社会事件分类方法 Dual Variational Multi-modal Attention Network for Incomplete Social Event Classification 计算机科学, 2022, 49(9): 132-138. https://doi.org/10.11896/jsjkx.220600022 |
| [14] | 武红鑫, 韩萌, 陈志强, 张喜龙, 李慕航. 监督和半监督学习下的多标签分类综述 Survey of Multi-label Classification Based on Supervised and Semi-supervised Learning 计算机科学, 2022, 49(8): 12-25. https://doi.org/10.11896/jsjkx.210700111 |
| [15] | 李其烨, 邢红杰. 基于最大相关熵的KPCA异常检测方法 KPCA Based Novelty Detection Method Using Maximum Correntropy Criterion 计算机科学, 2022, 49(8): 267-272. https://doi.org/10.11896/jsjkx.210700175 |
|
||
首页