Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (10): 3300-3306.DOI: 10.11772/j.issn.1001-9081.2023101480
• The 40th CCF National Database Conference (NDBC 2023) • Previous Articles Next Articles
Received:
2023-10-30
Revised:
2023-12-26
Accepted:
2023-12-28
Online:
2024-10-15
Published:
2024-10-10
Contact:
Zhixue HE
About author:
YE Lishuo, born in 2001, M. S. candidate. His research interests include data mining, time series analysis.
Supported by:
通讯作者:
何志学
作者简介:
叶力硕(2001—),男,河南漯河人,硕士研究生,主要研究方向:数据挖掘、时间序列分析基金资助:
CLC Number:
Lishuo YE, Zhixue HE. Multiscale time series anomaly detection incorporating wavelet decomposition[J]. Journal of Computer Applications, 2024, 44(10): 3300-3306.
叶力硕, 何志学. 融合小波分解的多尺度时间序列异常检测[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 3300-3306.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2023101480
数据集 | 维度 | 训练集大小 | 测试集大小 | 信息 |
---|---|---|---|---|
PSM | 25 | 132 481 | 87 841 | 服务器 |
SMD | 38 | 708 405 | 708 420 | 服务器 |
SWaT | 51 | 495 000 | 449 919 | 传感器 |
MSL | 55 | 58 317 | 73 729 | 遥感 |
SMAP | 25 | 135 183 | 427 617 | 遥感 |
Tab. 1 Description of five datasets
数据集 | 维度 | 训练集大小 | 测试集大小 | 信息 |
---|---|---|---|---|
PSM | 25 | 132 481 | 87 841 | 服务器 |
SMD | 38 | 708 405 | 708 420 | 服务器 |
SWaT | 51 | 495 000 | 449 919 | 传感器 |
MSL | 55 | 58 317 | 73 729 | 遥感 |
SMAP | 25 | 135 183 | 427 617 | 遥感 |
数据集 | epoch | batchsize | c | k | 层数 |
---|---|---|---|---|---|
PSM | 5 | 128 | 64 | 3 | 6 |
SMD | 5 | 128 | 128 | 3 | 6 |
SWaT | 5 | 128 | 256 | 3 | 6 |
MSL | 6 | 128 | 256 | 3 | 6 |
SMAP | 6 | 128 | 64 | 3 | 6 |
Tab. 2 Partial parameter settings of WMAD method on five datasets
数据集 | epoch | batchsize | c | k | 层数 |
---|---|---|---|---|---|
PSM | 5 | 128 | 64 | 3 | 6 |
SMD | 5 | 128 | 128 | 3 | 6 |
SWaT | 5 | 128 | 256 | 3 | 6 |
MSL | 6 | 128 | 256 | 3 | 6 |
SMAP | 6 | 128 | 64 | 3 | 6 |
方法 | SWaT | SMD | MSL | SMAP | PSM | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
P | R | F1 | P | R | F1 | P | R | F1 | P | R | F1 | P | R | F1 | |
LSTM-ED | 87.68 | 94.13 | 90.79 | 75.72 | 83.39 | 79.37 | 89.66 | 73.80 | 80.96 | 89.22 | 53.80 | 67.12 | 99.61 | 81.60 | 89.71 |
TCN | 91.42 | 93.89 | 92.64 | 95.20 | 65.52 | 77.62 | 87.88 | 76.38 | 81.73 | 92.23 | 53.64 | 67.83 | 98.78 | 85.26 | 91.52 |
LSTM-VAE | 88.37 | 94.29 | 91.23 | 76.22 | 83.98 | 79.91 | 89.68 | 75.29 | 81.86 | 91.00 | 61.37 | 73.30 | 99.32 | 86.94 | 92.71 |
MSCRED | 99.66 | 71.54 | 83.29 | 68.12 | 85.34 | 75.76 | 89.72 | 75.66 | 82.09 | 89.56 | 54.97 | 70.06 | 98.71 | 83.66 | 90.56 |
Transformer | 99.96 | 66.45 | 79.83 | 69.20 | 79.23 | 73.87 | 90.21 | 75.15 | 81.99 | 90.12 | 63.45 | 74.46 | 99.99 | 78.43 | 87.90 |
TranAD | 99.56 | 69.32 | 81.73 | 68.44 | 79.96 | 73.75 | 90.62 | 74.91 | 82.02 | 89.72 | 56.54 | 69.36 | 99.42 | 84.12 | 91.13 |
WMAD | 92.20 | 93.26 | 92.73 | 87.68 | 79.19 | 83.22 | 86.77 | 85.02 | 85.88 | 89.78 | 62.49 | 73.68 | 98.65 | 92.95 | 95.72 |
Tab. 3 Performance comparison between WDAE method and other six methods
方法 | SWaT | SMD | MSL | SMAP | PSM | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
P | R | F1 | P | R | F1 | P | R | F1 | P | R | F1 | P | R | F1 | |
LSTM-ED | 87.68 | 94.13 | 90.79 | 75.72 | 83.39 | 79.37 | 89.66 | 73.80 | 80.96 | 89.22 | 53.80 | 67.12 | 99.61 | 81.60 | 89.71 |
TCN | 91.42 | 93.89 | 92.64 | 95.20 | 65.52 | 77.62 | 87.88 | 76.38 | 81.73 | 92.23 | 53.64 | 67.83 | 98.78 | 85.26 | 91.52 |
LSTM-VAE | 88.37 | 94.29 | 91.23 | 76.22 | 83.98 | 79.91 | 89.68 | 75.29 | 81.86 | 91.00 | 61.37 | 73.30 | 99.32 | 86.94 | 92.71 |
MSCRED | 99.66 | 71.54 | 83.29 | 68.12 | 85.34 | 75.76 | 89.72 | 75.66 | 82.09 | 89.56 | 54.97 | 70.06 | 98.71 | 83.66 | 90.56 |
Transformer | 99.96 | 66.45 | 79.83 | 69.20 | 79.23 | 73.87 | 90.21 | 75.15 | 81.99 | 90.12 | 63.45 | 74.46 | 99.99 | 78.43 | 87.90 |
TranAD | 99.56 | 69.32 | 81.73 | 68.44 | 79.96 | 73.75 | 90.62 | 74.91 | 82.02 | 89.72 | 56.54 | 69.36 | 99.42 | 84.12 | 91.13 |
WMAD | 92.20 | 93.26 | 92.73 | 87.68 | 79.19 | 83.22 | 86.77 | 85.02 | 85.88 | 89.78 | 62.49 | 73.68 | 98.65 | 92.95 | 95.72 |
方法 | 参数量/MB | 平均每次迭代时间/s |
---|---|---|
WMAD | 0.76 | 0.043 |
LSTM-ED | 0.84 | 0.046 |
TCN | 0.67 | 0.032 |
LSTM-VAE | 0.79 | 0.045 |
MCRED | 1.65 | 0.054 |
Transformer | 3.65 | 0.059 |
TranAD | 3.61 | 0.061 |
Tab. 4 Comparison of model efficiency on PSM dataset
方法 | 参数量/MB | 平均每次迭代时间/s |
---|---|---|
WMAD | 0.76 | 0.043 |
LSTM-ED | 0.84 | 0.046 |
TCN | 0.67 | 0.032 |
LSTM-VAE | 0.79 | 0.045 |
MCRED | 1.65 | 0.054 |
Transformer | 3.65 | 0.059 |
TranAD | 3.61 | 0.061 |
方法 | F1值 | ||||
---|---|---|---|---|---|
SWaT | SMD | MSL | SMAP | PSM | |
WMAD | 92.73 | 83.22 | 85.88 | 73.68 | 95.72 |
WMAD-A | 87.48 | 81.79 | 79.71 | 68.17 | 89.91 |
WMAD-B | 92.67 | 82.58 | 81.35 | 68.78 | 93.01 |
WMAD-C | 92.58 | 80.96 | 80.37 | 68.77 | 92.97 |
Tab. 5 Results of ablation experiments on five different datasets
方法 | F1值 | ||||
---|---|---|---|---|---|
SWaT | SMD | MSL | SMAP | PSM | |
WMAD | 92.73 | 83.22 | 85.88 | 73.68 | 95.72 |
WMAD-A | 87.48 | 81.79 | 79.71 | 68.17 | 89.91 |
WMAD-B | 92.67 | 82.58 | 81.35 | 68.78 | 93.01 |
WMAD-C | 92.58 | 80.96 | 80.37 | 68.77 | 92.97 |
1 | 胡珉,白雪,徐伟,等.多维时间序列异常检测算法综述[J].计算机应用,2020,40(6):1553-1564. |
HU M, BAI X, XU W, et al. Review of anomaly detection algorithms for multidimensional time series[J]. Journal of Computer Applications,2020,40(6):1553-1564. | |
2 | ELMAN J L. Finding structure in time[J]. Cognitive Science, 1990, 14(2):179-211. |
3 | LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324. |
4 | VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates, 2017: 6000-6010. |
5 | J-S CHOU, TELAGA A S. Real-time detection of anomalous power consumption[J]. Renewable and Sustainable Energy Reviews, 2014, 33: 400-411. |
6 | REDDY A, ORDWAY-WEST M, LEE M, et al. Using Gaussian mixture models to detect outliers in seasonal univariate network traffic[C]// Proceedings of the 2017 IEEE Security and Privacy Workshops. Piscataway: IEEE, 2017: 229-234. |
7 | MÜNZ G, LI S, CARLE G. Traffic anomaly detection using k-means clustering[EB/OL]. [2023-10-01]. . |
8 | BREUNIG M M, H-P KRIEGEL, NG R T, et al. LOF: identifying density-based local outliers[C]// Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data. New York: ACM, 2000: 93-104. |
9 | ZHANG A, ZHAO X, WANG L. CNN and LSTM based encoder-decoder for anomaly detection in multivariate time series[C]// Proceedings of the 2021 IEEE 5th Information Technology, Networking, Electronic and Automation Control Conference. Piscataway: IEEE, 2021: 571-575. |
10 | HE Y, ZHAO J. Temporal convolutional networks for anomaly detection in time series[J]. Proceedings of the 2019 Journal of Physics: Conference Series, 2019: 1213(4): 042050. |
11 | 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: AAAI Press, 2019: 1409-1416. |
12 | 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. |
13 | 梁宏涛,刘硕,杜军威,等.深度学习应用于时序预测研究综述[J].计算机科学与探索,2023,17(6):1285-1300. |
LIANG H T, LIU S, DU J W, et al. Review of deep learning applied to time series prediction[J]. Journal of Frontiers of Computer Science and Technology,2023,17(6):1285-1300. | |
14 | WU H, HU T, LIU Y, et al. TimesNet: temporal 2D-variation modeling for general time series analysis [EB/OL]. [2023-04-12]. . |
15 | ABDULAAL A, LIU Z, LANCEWICKI T. Practical approach to asynchronous multivariate time series anomaly detection and localization[C]// Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. New York: ACM, 2021: 2485-2494. |
16 | 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 & Data Mining. New York: ACM, 2019: 2828-2837. |
17 | 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 28th International Conference on Artificial Neural Networks. Berlin: Springer-Verlag, 2019: 703-716. |
18 | HUNDMAN K, CONSTANTINOU V, LAPORTE C, et al. Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding[C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: ACM, 2018: 387-395. |
19 | KINGMA D P, BA J. Adam: a method for stochastic optimization [EB/OL]. [2023-04-30]. . |
20 | 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. |
[1] | Tingwei CHEN, Jiacheng ZHANG, Junlu WANG. Random validation blockchain construction for federated learning [J]. Journal of Computer Applications, 2024, 44(9): 2770-2776. |
[2] | Jing QIN, Zhiguang QIN, Fali LI, Yueheng PENG. Diagnosis of major depressive disorder based on probabilistic sparse self-attention neural network [J]. Journal of Computer Applications, 2024, 44(9): 2970-2974. |
[3] | Lilin FAN, Fukang CAO, Wanting WANG, Kai YANG, Zhaoyu SONG. Intermittent demand forecasting method based on adaptive matching of demand patterns [J]. Journal of Computer Applications, 2024, 44(9): 2747-2755. |
[4] | Liting LI, Bei HUA, Ruozhou HE, Kuang XU. Multivariate time series prediction model based on decoupled attention mechanism [J]. Journal of Computer Applications, 2024, 44(9): 2732-2738. |
[5] | Zhiqiang ZHAO, Peihong MA, Xinhong HEI. Crowd counting method based on dual attention mechanism [J]. Journal of Computer Applications, 2024, 44(9): 2886-2892. |
[6] | Qinzhuang ZHAO, Hongye TAN. Time series causal inference method based on adaptive threshold learning [J]. Journal of Computer Applications, 2024, 44(9): 2660-2666. |
[7] | Kaipeng XUE, Tao XU, Chunjie LIAO. Multimodal sentiment analysis network with self-supervision and multi-layer cross attention [J]. Journal of Computer Applications, 2024, 44(8): 2387-2392. |
[8] | Pengqi GAO, Heming HUANG, Yonghong FAN. Fusion of coordinate and multi-head attention mechanisms for interactive speech emotion recognition [J]. Journal of Computer Applications, 2024, 44(8): 2400-2406. |
[9] | 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. |
[10] | Zhonghua LI, Yunqi BAI, Xuejin WANG, Leilei HUANG, Chujun LIN, Shiyu LIAO. Low illumination face detection based on image enhancement [J]. Journal of Computer Applications, 2024, 44(8): 2588-2594. |
[11] | Shangbin MO, Wenjun WANG, Ling DONG, Shengxiang GAO, Zhengtao YU. Single-channel speech enhancement based on multi-channel information aggregation and collaborative decoding [J]. Journal of Computer Applications, 2024, 44(8): 2611-2617. |
[12] | 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. |
[13] | Wu XIONG, Congjun CAO, Xuefang SONG, Yunlong SHAO, Xusheng WANG. Handwriting identification method based on multi-scale mixed domain attention mechanism [J]. Journal of Computer Applications, 2024, 44(7): 2225-2232. |
[14] | Huanhuan LI, Tianqiang HUANG, Xuemei DING, Haifeng LUO, Liqing HUANG. Public traffic demand prediction based on multi-scale spatial-temporal graph convolutional network [J]. Journal of Computer Applications, 2024, 44(7): 2065-2072. |
[15] | Dianhui MAO, Xuebo LI, Junling LIU, Denghui ZHANG, Wenjing YAN. Chinese entity and relation extraction model based on parallel heterogeneous graph and sequential attention mechanism [J]. Journal of Computer Applications, 2024, 44(7): 2018-2025. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||