Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (11): 3419-3426.DOI: 10.11772/j.issn.1001-9081.2023111636
• Data science and technology • Previous Articles Next Articles
Pei ZHAO, Yan QIAO(), Rongyao HU, Xinyu YUAN, Minyue LI, Benchu ZHANG
Received:
2023-11-27
Revised:
2024-03-04
Accepted:
2024-03-18
Online:
2024-03-22
Published:
2024-11-10
Contact:
Yan QIAO
About author:
ZHAO Pei, born in 1999, M. S. candidate. His research interests include anomaly detection, information security.Supported by:
通讯作者:
乔焰
作者简介:
赵培(1999—),男,安徽滁州人,硕士研究生,主要研究方向:异常检测、信息安全基金资助:
CLC Number:
Pei ZHAO, Yan QIAO, Rongyao HU, Xinyu YUAN, Minyue LI, Benchu ZHANG. Multivariate time series anomaly detection based on multi-domain feature extraction[J]. Journal of Computer Applications, 2024, 44(11): 3419-3426.
赵培, 乔焰, 胡荣耀, 袁新宇, 李敏悦, 张本初. 基于多域特征提取的多变量时间序列异常检测[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3419-3426.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2023111636
数据集 | 数据维度 | 训练长度 | 测试长度 | 异常比例/% |
---|---|---|---|---|
SMAP | 25 | 135 183 | 427 617 | 13.13 |
MSL | 55 | 58 317 | 73 729 | 10.72 |
SMD | 38 | 708 405 | 708 420 | 4.16 |
WADI | 123 | 1 048 571 | 172 810 | 5.99 |
SWAT | 51 | 496 800 | 449 919 | 11.98 |
Tab. 1 Information of datasets
数据集 | 数据维度 | 训练长度 | 测试长度 | 异常比例/% |
---|---|---|---|---|
SMAP | 25 | 135 183 | 427 617 | 13.13 |
MSL | 55 | 58 317 | 73 729 | 10.72 |
SMD | 38 | 708 405 | 708 420 | 4.16 |
WADI | 123 | 1 048 571 | 172 810 | 5.99 |
SWAT | 51 | 496 800 | 449 919 | 11.98 |
数据集 | DAGMM | Omni | LSTM-VAE | TS2Vec | CRT | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
F1 | P | R | F1 | P | R | F1 | P | R | F1 | P | R | F1 | P | R | |
SMAP | 87.74 | 81.37 | 95.21 | 86.93 | 82.93 | 91.35 | 78.10 | 92.20 | 67.75 | 53.26 | 55.43 | 51.26 | 83.33 | 93.06 | 77.95 |
MSL | 81.43 | 69.32 | 98.67 | 89.28 | 84.51 | 94.63 | 82.62 | 85.49 | 79.94 | 50.75 | 50.54 | 50.96 | 87.81 | 95.01 | 83.12 |
SMD | 85.32 | 89.84 | 81.65 | 88.64 | 85.91 | 91.65 | 82.30 | 75.76 | 90.08 | 47.51 | 45.27 | 50.02 | 95.16 | 93.34 | 97.05 |
WADI | 43.09 | 27.56 | 98.69 | 50.84 | 41.58 | 65.41 | 49.51 | 35.29 | 82.96 | 53.07 | 50.88 | 55.47 | 70.28 | 68.47 | 72.11 |
SWAT | 75.54 | 93.63 | 63.31 | 81.31 | 97.82 | 69.57 | 82.20 | 76.00 | 89.50 | 49.41 | 48.25 | 50.63 | 87.21 | 84.33 | 90.98 |
数据集 | AnomalyTran | INRAD | FGANomaly | TranAD | MFE-TS | ||||||||||
F1 | P | R | F1 | P | R | F1 | P | R | F1 | P | R | F1 | P | R | |
SMAP | 96.44 | 93.57 | 99.49 | 92.13 | 85.82 | 99.55 | 85.04 | 93.14 | 78.98 | 89.12 | 80.43 | 99.92 | 96.49 | 94.67 | 98.39 |
MSL | 93.59 | 92.09 | 95.15 | 96.09 | 93.32 | 99.04 | 92.03 | 90.24 | 93.89 | 94.60 | 90.65 | 98.91 | 95.27 | 93.33 | 97.30 |
SMD | 92.33 | 89.40 | 95.45 | 97.46 | 98.21 | 96.73 | 87.51 | 86.14 | 88.92 | 96.05 | 92.62 | 99.74 | 98.13 | 97.75 | 98.51 |
WADI | 70.93 | 71.64 | 70.23 | 53.07 | 39.26 | 81.87 | 51.80 | 37.18 | 85.36 | 53.07 | 39.26 | 81.87 | 77.62 | 78.27 | 76.99 |
SWAT | 94.07 | 91.55 | 96.73 | 97.22 | 95.67 | 98.83 | 86.38 | 87.06 | 85.72 | 90.02 | 97.60 | 83.54 | 95.96 | 97.95 | 94.04 |
Tab. 2 Performance comparison of MFE-TS and multiple baseline methods
数据集 | DAGMM | Omni | LSTM-VAE | TS2Vec | CRT | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
F1 | P | R | F1 | P | R | F1 | P | R | F1 | P | R | F1 | P | R | |
SMAP | 87.74 | 81.37 | 95.21 | 86.93 | 82.93 | 91.35 | 78.10 | 92.20 | 67.75 | 53.26 | 55.43 | 51.26 | 83.33 | 93.06 | 77.95 |
MSL | 81.43 | 69.32 | 98.67 | 89.28 | 84.51 | 94.63 | 82.62 | 85.49 | 79.94 | 50.75 | 50.54 | 50.96 | 87.81 | 95.01 | 83.12 |
SMD | 85.32 | 89.84 | 81.65 | 88.64 | 85.91 | 91.65 | 82.30 | 75.76 | 90.08 | 47.51 | 45.27 | 50.02 | 95.16 | 93.34 | 97.05 |
WADI | 43.09 | 27.56 | 98.69 | 50.84 | 41.58 | 65.41 | 49.51 | 35.29 | 82.96 | 53.07 | 50.88 | 55.47 | 70.28 | 68.47 | 72.11 |
SWAT | 75.54 | 93.63 | 63.31 | 81.31 | 97.82 | 69.57 | 82.20 | 76.00 | 89.50 | 49.41 | 48.25 | 50.63 | 87.21 | 84.33 | 90.98 |
数据集 | AnomalyTran | INRAD | FGANomaly | TranAD | MFE-TS | ||||||||||
F1 | P | R | F1 | P | R | F1 | P | R | F1 | P | R | F1 | P | R | |
SMAP | 96.44 | 93.57 | 99.49 | 92.13 | 85.82 | 99.55 | 85.04 | 93.14 | 78.98 | 89.12 | 80.43 | 99.92 | 96.49 | 94.67 | 98.39 |
MSL | 93.59 | 92.09 | 95.15 | 96.09 | 93.32 | 99.04 | 92.03 | 90.24 | 93.89 | 94.60 | 90.65 | 98.91 | 95.27 | 93.33 | 97.30 |
SMD | 92.33 | 89.40 | 95.45 | 97.46 | 98.21 | 96.73 | 87.51 | 86.14 | 88.92 | 96.05 | 92.62 | 99.74 | 98.13 | 97.75 | 98.51 |
WADI | 70.93 | 71.64 | 70.23 | 53.07 | 39.26 | 81.87 | 51.80 | 37.18 | 85.36 | 53.07 | 39.26 | 81.87 | 77.62 | 78.27 | 76.99 |
SWAT | 94.07 | 91.55 | 96.73 | 97.22 | 95.67 | 98.83 | 86.38 | 87.06 | 85.72 | 90.02 | 97.60 | 83.54 | 95.96 | 97.95 | 94.04 |
噪声 比例 | SMD | WADI | SWAT | ||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MFE-TS | Omni | INRAD | FGANomaly | TranAD | MFE-TS | Omni | INRAD | FGANomaly | TranAD | MFE-TS | Omni | INRAD | FGANomaly | TranAD | |
3.09 | 8.31 | 7.53 | 6.57 | 11.26 | 4.80 | 9.69 | 10.22 | 5.58 | 10.11 | 3.66 | 14.12 | 8.48 | 5.13 | 9.06 | |
0 | 98.13 | 88.64 | 97.46 | 87.51 | 96.05 | 77.62 | 50.84 | 71.48 | 51.80 | 53.07 | 95.96 | 81.31 | 97.22 | 86.38 | 90.02 |
5 | 97.65 | 87.53 | 95.33 | 86.22 | 94.31 | 75.04 | 49.03 | 69.79 | 52.56 | 51.28 | 95.39 | 78.43 | 96.34 | 84.21 | 88.23 |
10 | 97.08 | 85.02 | 94.54 | 85.91 | 93.09 | 73.84 | 47.89 | 66.44 | 49.77 | 51.66 | 95.35 | 73.58 | 93.31 | 83.06 | 86.54 |
15 | 95.87 | 84.61 | 91.27 | 85.94 | 93.24 | 73.92 | 45.06 | 65.87 | 49.61 | 47.81 | 94.21 | 82.74 | 91.99 | 83.61 | 85.47 |
20 | 95.80 | 84.89 | 91.01 | 84.13 | 91.55 | 73.33 | 41.29 | 64.93 | 49.03 | 46.55 | 94.74 | 70.66 | 91.85 | 82.97 | 85.03 |
25 | 95.23 | 82.27 | 90.45 | 84.36 | 87.61 | 72.93 | 41.35 | 64.50 | 48.52 | 46.07 | 93.43 | 69.29 | 91.03 | 81.48 | 83.11 |
30 | 95.04 | 80.33 | 89.93 | 80.94 | 84.79 | 72.82 | 41.15 | 61.26 | 46.22 | 42.96 | 92.30 | 67.19 | 88.74 | 81.25 | 80.96 |
Tab.3 F1-score under different proportions of noise
噪声 比例 | SMD | WADI | SWAT | ||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MFE-TS | Omni | INRAD | FGANomaly | TranAD | MFE-TS | Omni | INRAD | FGANomaly | TranAD | MFE-TS | Omni | INRAD | FGANomaly | TranAD | |
3.09 | 8.31 | 7.53 | 6.57 | 11.26 | 4.80 | 9.69 | 10.22 | 5.58 | 10.11 | 3.66 | 14.12 | 8.48 | 5.13 | 9.06 | |
0 | 98.13 | 88.64 | 97.46 | 87.51 | 96.05 | 77.62 | 50.84 | 71.48 | 51.80 | 53.07 | 95.96 | 81.31 | 97.22 | 86.38 | 90.02 |
5 | 97.65 | 87.53 | 95.33 | 86.22 | 94.31 | 75.04 | 49.03 | 69.79 | 52.56 | 51.28 | 95.39 | 78.43 | 96.34 | 84.21 | 88.23 |
10 | 97.08 | 85.02 | 94.54 | 85.91 | 93.09 | 73.84 | 47.89 | 66.44 | 49.77 | 51.66 | 95.35 | 73.58 | 93.31 | 83.06 | 86.54 |
15 | 95.87 | 84.61 | 91.27 | 85.94 | 93.24 | 73.92 | 45.06 | 65.87 | 49.61 | 47.81 | 94.21 | 82.74 | 91.99 | 83.61 | 85.47 |
20 | 95.80 | 84.89 | 91.01 | 84.13 | 91.55 | 73.33 | 41.29 | 64.93 | 49.03 | 46.55 | 94.74 | 70.66 | 91.85 | 82.97 | 85.03 |
25 | 95.23 | 82.27 | 90.45 | 84.36 | 87.61 | 72.93 | 41.35 | 64.50 | 48.52 | 46.07 | 93.43 | 69.29 | 91.03 | 81.48 | 83.11 |
30 | 95.04 | 80.33 | 89.93 | 80.94 | 84.79 | 72.82 | 41.15 | 61.26 | 46.22 | 42.96 | 92.30 | 67.19 | 88.74 | 81.25 | 80.96 |
1 | ZONG B, SONG Q, MIN M R, et al. Deep autoencoding gaussian mixture model for unsupervised anomaly detection[EB/OL]. [2023-09-21]. . |
2 | XU H, CHEN W, ZHAO N, et al. Unsupervised anomaly detection via variational auto-encoder for seasonal KPIs in Web applications[C]// Proceedings of the 2018 World Wide Web Conference. Republic and Canton of Geneva: International World Wide Web Conferences Steering Committee, 2018:187-196. |
3 | LI D, CHEN D, JIN B, et al. MAD-GAN: multivariate anomaly detection for time series data with Generative adversarial networks[C]// Proceedings of the 2019 International Conference on Artificial Neural Networks, LNCS 11730. Cham: Springer, 2019:703-716. |
4 | GEIGER A, LIU D, ALNEGHEIMISH S, et al. TadGAN: time series anomaly detection using generative adversarial networks[C]// Proceedings of the 2020 IEEE International Conference on Big Data. Piscataway: IEEE, 2020: 33-43. |
5 | PARK D, HOSHI Y, KEMP C C. A multimodal anomaly detector for robot-assisted feeding using an LSTM-based variational autoencoder[J]. IEEE Robotics and Automation Letters, 2018, 3(3): 1544-1551. |
6 | LIN S, CLARK R, BIRKE R, et al. Anomaly detection for time series using VAE-LSTM hybrid model[C]// Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2020:4322-4326. |
7 | TULI S, CASALE G, JENNINGS N R. TranAD: deep Transformer networks for anomaly detection in multivariate time series data[J]. Proceedings of the VLDB Endowment, 2022, 15(6): 1201-1214. |
8 | XU J, WU H, WANG J, et al. Anomaly Transformer: time series anomaly detection with association discrepancy[EB/OL]. (2022-06-29) [2023-09-21].. |
9 | SHEN L, LI Z, KWOK J T. Timeseries anomaly detection using temporal hierarchical one-class network[C]// Proceedings of the 34th International Conference on Neural Information Processing System. Red Hook, NY: Curran Associates Inc., 2020: 13016-13026. |
10 | 丁小欧,于晟健,王沐贤,等.基于相关性分析的工业时序数据异常检测[J].软件学报,2020,31(3):726-747. |
DING X O, YU S J, WANG M X, et al. Anomaly detection on industrial time series based on correlation analysis[J]. Journal of Software, 2020, 31(3): 726-747. | |
11 | 曾惟如,吴佳,闫飞.基于层级实时记忆算法的时间序列异常检测算法[J].电子学报,2018,46(2):325-332. |
ZENG W R, WU J, YAN F. Time series anomaly detection model based on hierarchical temporal memory[J]. Acta Electronica Sinica, 2018, 46(2): 325-332. | |
12 | ZHANG C, SONG D, CHEN Y, et al. A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time series data[C]// Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Palo Alto, CA: AAAI Press, 2019:1409-1416. |
13 | LI Z, ZHAO Y, HAN J, et al. Multivariate time series anomaly detection and interpretation using hierarchical inter-metric and temporal embedding[C]// Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York: ACM, 2021: 3220-3230. |
14 | DING C, SUN S, ZHAO J. MST-GAT: a multimodal spatial-temporal graph attention network for time series anomaly detection[J]. Information Fusion, 2023, 89: 527-536. |
15 | 张本初,乔焰,胡荣耀.结合对抗互信息的多变量时间序列抗噪异常检测[J/OL].计算机应用研究,2024 [2024-04-12].. |
ZHANG B C, QIAO Y, HU R Y. Robust anomaly detection for multivariate time series based on adversarial mutual information[J/OL]. Application Research of Computers, 2024 [2024-04-12].. | |
16 | YANG L, HONG S. Unsupervised time-series representation learning with iterative bilinear temporal-spectral fusion[C]// Proceedings of the 39th International Conference on Machine Learning. New York: JMLR.org, 2022: 25038-25054. |
17 | ZHANG W, YANG L, GENG S, et al. Self-supervised time series representation learning via cross reconstruction Transformer[J]. IEEE Transactions on Neural Networks and Learning Systems, 2023 (Early Access): 1-10. |
18 | ZEILER M D, TAYLOR G W, FERGUS R. Adaptive deconvolutional networks for mid and high level feature learning[C]// Proceedings of the 2011 International Conference on Computer Vision. Piscataway: IEEE, 2011: 2018-2025. |
19 | ZEILER M D, KRISHNAN D, TAYLOR G W, et al. Deconvolutional networks[C]// Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2010: 2528-2535. |
20 | WANG X, PI D, ZHANG X, et al. Variational Transformer-based anomaly detection approach for multivariate time series[J]. Measurement, 2022, 191: No.110791. |
21 | SU Y, ZHAO Y, NIU C, et al. Robust anomaly detection for multivariate time series through stochastic recurrent neural network[C]// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2019: 2828-2837. |
22 | DU B, SUN X, YE J, et al. GAN-based anomaly detection for multivariate time series using polluted training set[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(12): 12208-12219. |
23 | YUE Z, WANG Y, DUAN J, et al. TS2Vec: towards universal representation of time series[C]// Proceedings of the 36th AAAI Conference on Artificial Intelligence. Palo Alto, CA: AAAI Press, 2022: 8980-8987. |
24 | JEONG K J, SHIN Y M. Time-series anomaly detection with implicit neural representation[EB/OL]. [2023-10-17].. |
[1] | Jieru JIA, Jianchao YANG, Shuorui ZHANG, Tao YAN, Bin CHEN. Unsupervised person re-identification based on self-distilled vision Transformer [J]. Journal of Computer Applications, 2024, 44(9): 2893-2902. |
[2] | Tingwei CHEN, Jiacheng ZHANG, Junlu WANG. Random validation blockchain construction for federated learning [J]. Journal of Computer Applications, 2024, 44(9): 2770-2776. |
[3] | Yuhan LIU, Genlin JI, Hongping ZHANG. Video pedestrian anomaly detection method based on skeleton graph and mixed attention [J]. Journal of Computer Applications, 2024, 44(8): 2551-2557. |
[4] | Hong CHEN, Bing QI, Haibo JIN, Cong WU, Li’ang ZHANG. Class-imbalanced traffic abnormal detection based on 1D-CNN and BiGRU [J]. Journal of Computer Applications, 2024, 44(8): 2493-2499. |
[5] | Xinrui LIN, Xiaofei WANG, Yan ZHU. Academic anomaly citation group detection based on local extended community detection [J]. Journal of Computer Applications, 2024, 44(6): 1855-1861. |
[6] | Zixuan YUAN, Xiaoqing WENG, Ningzhen GE. Early classification model of multivariate time series based on orthogonal locality preserving projection and cost optimization [J]. Journal of Computer Applications, 2024, 44(6): 1832-1841. |
[7] | Fan MENG, Qunli YANG, Jing HUO, Xinkuan WANG. EraseMTS: iterative active multivariable time series anomaly detection algorithm based on margin anomaly candidate set [J]. Journal of Computer Applications, 2024, 44(5): 1458-1463. |
[8] | Zimeng ZHU, Zhixin LI, Zhan HUAN, Ying CHEN, Jiuzhen LIANG. Weakly supervised video anomaly detection based on triplet-centered guidance [J]. Journal of Computer Applications, 2024, 44(5): 1452-1457. |
[9] | Xiawuji, Heming HUANG, Gengzangcuomao, Yutao FAN. Survey of extractive text summarization based on unsupervised learning and supervised learning [J]. Journal of Computer Applications, 2024, 44(4): 1035-1048. |
[10] | Rui JIANG, Wei LIU, Cheng CHEN, Tao LU. Asymmetric unsupervised end-to-end image deraining network [J]. Journal of Computer Applications, 2024, 44(3): 922-930. |
[11] | Yongjiang LIU, Bin CHEN. Pixel-level unsupervised industrial anomaly detection based on multi-scale memory bank [J]. Journal of Computer Applications, 2024, 44(11): 3587-3594. |
[12] | Nengbing HU, Biao CAI, Xu LI, Danhua CAO. Graph classification method based on graph pooling contrast learning [J]. Journal of Computer Applications, 2024, 44(11): 3327-3334. |
[13] | Yuhao TANG, Dezhong PENG, Zhong YUAN. Fuzzy multi-granularity anomaly detection for incomplete mixed data [J]. Journal of Computer Applications, 2024, 44(10): 3097-3104. |
[14] | Hui JIANG, Qiuyan YAN, Zhujun JIANG. Symmetric positive definite autoencoder method for multivariate time series anomaly detection [J]. Journal of Computer Applications, 2024, 44(10): 3294-3299. |
[15] | Lishuo YE, Zhixue HE. Multiscale time series anomaly detection incorporating wavelet decomposition [J]. Journal of Computer Applications, 2024, 44(10): 3300-3306. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||