基于多尺度特征信息融合的时间序列异常检测

衡红军; 喻龙威

doi:10.19665/j.issn1001-2400.20230906

您当前的位置：

首页 >

文章列表页 >

基于多尺度特征信息融合的时间序列异常检测

网络空间安全 | 更新时间：2024-07-23

- 基于多尺度特征信息融合的时间序列异常检测
- Time series anomaly detection based on multi-scale feature information fusion
- 西安电子科技大学学报 2024年51卷第3期页码：203-214
- 作者机构：
  
  中国民航大学计算机科学与技术学院,天津 300300
- 作者简介：
  
  [ "衡红军(1968—),男,副教授,E-mail:[email protected]" ]
  喻龙威(1997—),男,中国民航大学硕士研究生,E-mail:[email protected]
- 基金信息：
  
  国家自然科学基金(U1333109)
- DOI：10.19665/j.issn1001-2400.20230906
  中图分类号： TP391
- 纸质出版日期：2024-06-20，
  
  网络出版日期：2023-09-27，
  
  收稿日期：2023-07-28，
- 稿件说明：
扫描看全文
衡红军, 喻龙威. 基于多尺度特征信息融合的时间序列异常检测[J]. 西安电子科技大学学报, 2024,51(3):203-214.

Hongjun HENG, Longwei YU. Time series anomaly detection based on multi-scale feature information fusion[J]. Journal of Xidian University, 2024,51(3):203-214.
衡红军, 喻龙威. 基于多尺度特征信息融合的时间序列异常检测[J]. 西安电子科技大学学报, 2024,51(3):203-214. DOI： 10.19665/j.issn1001-2400.20230906.

Hongjun HENG, Longwei YU. Time series anomaly detection based on multi-scale feature information fusion[J]. Journal of Xidian University, 2024,51(3):203-214. DOI： 10.19665/j.issn1001-2400.20230906.

摘要

目前大多数的时间序列都缺少相应的异常标签

且现有基于重构的异常检测算法不能很好地捕获到多维数据间复杂的潜在相关性和时间依赖性

为了构建特征丰富的时间序列

提出一种多尺度特征信息融合的异常检测模型。该模型首先通过卷积神经网络对滑动窗口内的不同序列进行特征卷积来获取不同尺度下的局部上下文信息。然后

利用Transformer中的位置编码对卷积后的时间序列窗口进行位置嵌入

增强滑动窗口中每一个时间序列和邻近序列之间的位置联系

并引入时间注意力获取数据在时间维度上的自相关性

并进一步通过多头自注意力自适应地为窗口内不同时间序列分配不同的权重。最后

对反卷积过程中上采样得到的窗口数据与不同尺度下得到的局部特征和时间上下文信息进行逐步融合

从而准确重构原始时间序列

并将重构误差作为最终的异常得分进行异常判定。实验结果表明

所构建模型在SWaT和SMD数据集上与基线模型相比F1分数均有所提升。在数据维度高且均衡性较差的WADI数据集上与GDN模型相比F1分数降低了1.66%。

Abstract

Currently

most time series lack corresponding anomaly labels and existing reconstruction-based anomaly detection algorithms fail to capture the complex underlying correlations and temporal dependencies among multidimensional data effectively.To construct feature-rich time series

a multi-scale feature information fusion anomaly detection model is proposed.First

the model employs convolutional neural networks to perform feature convolution on different sequences within sliding windows

capturing local contextual information at different scales.Then

position encoding from the Transformer is utilized to embed the convolved time series windows

enhancing the positional relationships between each time series and its neighboring sequences within the sliding window.Time attention is introduced to capture the temporal autocorrelation of the data

and multi-head self-attention adaptively assigns different weights to different time series within the window.Finally

the reconstructed window data obtained through the down-sampling process is progressively fused with the local features and temporal context information at different scales.This process accurately reconstructs the original time series

with the reconstruction error used as the final anomaly score for anomaly determination.Experimental results indicate that the constructed model achieves improved F1 scores compared to the baseline models on both the SWaT and SMD datasets.On the high-dimensional and imbalanced WADI dataset

the F1 score decreases by 1.66% compared to the GDN model.

关键词

异常检测多尺度信息融合卷积神经网络Transformer多维时间序列自编码器

Keywords

anomaly detectionmulti-scale information fusionconvolutional neural networktransformermultidimensional time seriesautoencoder

references

FENG C, TIAN P. Time Series Anomaly Detection for Cyber-physical Systems via Neural System Identification and Bayesian Filtering[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. New York: ACM, 2021:2858-2867.

ZHANG H, XIA Y, YAN T, et al. Unsupervised Anomaly Detection in Multivariate Time Series through Transformer-Based Variational Autoencoder[C]//2021 33rd Chinese Control and Decision Conference(CCDC).Kunming:CCDC, 2021:281-286.

XIE L, PI D, ZHANG X, et al. Graph Neural Network Approach for Anomaly Detection[J]. Measurement, 2021, 180(1):109546.

RUIZ L, GAMA F, RIBEIRO A. Gated Graph Recurrent Neural Networks[J]. IEEE Transaction Signal Process, 2020, 68:6303-6318.

DENG A, HOOI B. Graph Neural Network-Based Anomaly Detection in Multivariate Time Series[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2021:4027-4035.

ZHAO H, WANG Y, DUAN J, et al. Multivariate Time-Series Anomaly Detection via Graph Attention Network[C]//Proceedings of the 2020 IEEE International Conference on Data Mining(ICDM). Piscataway:IEEE, 2020:841-850.

NANDURI A, SHERRY L. Anomaly Detection in Aircraft Data Using Recurrent Neural Networks(RNN)[C]//Integrated Communications Navigation & Surveillance. Piscataway:IEEE, 2016:1-8.

BONETTO R, SOLDAN M, LANARO A, et al. Seq2Seq RNN Based Gait Anomaly Detection from Smartphone Acquired Multimodal Motion Data(2019)[J/OL].[2019-11-19]. https://arxiv.org/pdf/1911.08608.https://arxiv.org/pdf/1911.08608https://arxiv.org/pdf/1911.08608

MALHOTRA P, RAMAKRISHNAN A, ANAND G, et al. LSTM-Based Encoder-Decoder for Multi-Sensor Anomaly Detection(2016)[J/OL].[2016-07-11]. https://arxiv.org/pdf/1607.00148v1.https://arxiv.org/pdf/1607.00148v1https://arxiv.org/pdf/1607.00148v1

LIN S, CLARK R, BIRKE R, et al. Anomaly Detection for Time Series Using VAE-LSTM Hybrid Model[C]//ICASSP 2020-2020 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP).Piscataway:IEEE, 2020:4322-4326.

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 AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2019:1409-1416.

LI D, CHEN D, SHI L, et al. MAD-GAN:Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks[C]//Artificial Neural Networks and Machine Learning. Heidelberg:Springer, 2019:703-716.

AUDIBERT J, MICHIARDI P, GUYARD F, et al. USAD:UnSupervised Anomaly Detection on Multivariate Time Series[C]//Proceedings of the 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York: ACM, 2020:3395-3404.

杨静雅, 齐彦丽, 周一青, 等. CNN-Transformer轻量级智能调制识别算法[J]. 西安电子科技大学学报, 2023, 50(3):40-49.

YANG Jingya, QI Yanli, ZHOU Yiqing, et al. Algorithm for Recognition of Lightweight Intelligent Modulation Based on the CNN-Transformer Networks[J]. Journal of Xidian University, 2023, 50(3):40-49.

TULI S, CASALE G, JENNINGS N R. TranAD:Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data(2022)[J/OL].[2022-05-14]. https://arxiv.org/pdf/2201.07284v6.https://arxiv.org/pdf/2201.07284v6https://arxiv.org/pdf/2201.07284v6

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. New York: ACM, 2017:6000-6010.

WANG X, PI D, ZHANG X, et al. Variational Transformer-Based Anomaly Detection Approach for Multivariate Time Series[J]. Measurement, 2022:191.

YA S, ZHAO C, NIU R, et al. Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network[C]//Conference on Knowledge Discovery and Data Mining(KDD’19). New York: ACM, 2019:2828-2837.

SONG Q. Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection[C]//International Conference on Learning Representations. La Jolla: ICLR, 2018:1-19.

DENG A, HOOI B. Graph Neural Network-Based Anomaly Detection in Multivariate Time Series[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2021:4027-4035.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向带宽受限场景的高效语义通信方法

面向多维时间序列异常检测的时空图卷积网络

基于多边形特征池化与融合的复杂文本检测

基于多注意力机制的纹理感知视频修复方法

多尺度卷积结合Transformer的抑郁脑电分类研究