基于图神经网络的时序信号异常检测方法

王婕婷; 张泽珑; 李飞江; 钱宇华

doi:10.16152/j.cnki.xdxbzr.2025-02-011

您当前的位置：

首页 >

文章列表页 >

基于图神经网络的时序信号异常检测方法

不确定性与知识获取 | 更新时间：2025-04-21

- 基于图神经网络的时序信号异常检测方法
- A time series signal anomaly detection method based on graph neural network
- 西北大学学报（自然科学版） 2025年55卷第2期页码：343-354
- 作者机构：
  
  1.山西大学　大数据科学与产业研究院，山西　太原　 030006
  2.山西大学　计算智能与中文信息处理教育部重点实验室，山西　太原　 030006
- 作者简介：
  
  王婕婷，女，副教授，硕士生导师，从事统计机器学习和集成学习等研究，jtwang@sxu.edu.cn。
- 基金信息：
  
  国家自然科学基金(6230617062106132);山西省科技重大专项(202201020101006);山西省基础研究计划(202103021223026;20210302124271);山西省科技创新人才团队专项(202304051001001)
- DOI：10.16152/j.cnki.xdxbzr.2025-02-011
  中图分类号： TP391
- 收稿日期：2024-09-05，
  
  纸质出版日期：2025-04-25
- 稿件说明：
移动端阅览
王婕婷, 张泽珑, 李飞江, 等. 基于图神经网络的时序信号异常检测方法[J]. 西北大学学报（自然科学版）, 2025,55(2):343-354.

WANG Jieting, ZHANG Zelong, LI Feijiang, et al. A time series signal anomaly detection method based on graph neural network[J]. Journal of northwest university (natural science edition), 2025, 55(2): 343-354.
王婕婷, 张泽珑, 李飞江, 等. 基于图神经网络的时序信号异常检测方法[J]. 西北大学学报（自然科学版）, 2025,55(2):343-354. DOI： 10.16152/j.cnki.xdxbzr.2025-02-011.

WANG Jieting, ZHANG Zelong, LI Feijiang, et al. A time series signal anomaly detection method based on graph neural network[J]. Journal of northwest university (natural science edition), 2025, 55(2): 343-354. DOI： 10.16152/j.cnki.xdxbzr.2025-02-011.

摘要

高维时序数据异常检测是指从多元时间序列中识别出偏离整体模式或偏离预期行为的样本点的过程。在高维时序数据中，传感器间潜在的关联关系对于预测或检测任务的性能具有较大影响。图神经网络是一种基于节点的近邻关系学习节点表征的深度模型，能够有效建模传感器间的复杂关联。然而，现有基于图神经网络的异常检测方法大多依赖于单一的相似度度量来捕捉传感器间的关系，不能很好地学习传感器间的依赖关系。此外，在阈值选择时，现有方法使用正常数据中的最大异常得分作为切割阈值，限制了异常事件发生时的检测能力，从而造成较低的召回率。综上，提出了一种基于图神经网络的时序信号异常检测方法，根据传感器的特有特征使用多种相似度度量集成进行图结构学习；其次，将图结构学习方法与图神经网络相结合得到异常得分；最后，通过区间搜索法最优化

-measure指标寻找最优异常切割阈值。在两个真实传感器数据集上进行的实验表明，该方法比基准对比方法取得了较高的

值和召回率。

Abstract

Anomaly detection in high-dimensional time series data refers to the process of identifying sample points that deviate from the overall pattern or expected behavior from a multivariate time series. In high-dimensional time series data

the potential correlation between sensors has a significant impact on the performance of prediction or detection tasks. Graph neural networks are a deep model that learn node representations based on node proximity relationships

which can effectively model complex correlations between sensors. However

existing anomaly detection methods based on graph neural networks mostly rely on a single similarity measure to capture the relationships between variables and cannot learn the dependencies between variables well. In addition

when selecting thresholds

existing methods use the maximum anomaly score in normal data as the cutting threshold

which limits the detection ability when abnormal events occur

resulting in lower recall rates. In summary

this paper proposes a temporal signal anomaly detection method based on graph neural networks

whic

h integrates multiple similarity measures based on the unique features of sensors for graph structure learning. Then

the graph structure learning method is combined with the graph neural network to obtain anomaly scores. Finally

the interval search method was used to optimize the

-measure index and find the optimal anomaly cutting threshold. Experiments on two real sensor datasets showed that our method achieved higher

values and recall compared to the benchmark comparison method.

关键词

Keywords

references

SHYU M , CHEN S , SARINNAPAKORN K , et al . A novel anomaly detection scheme based on principal component classifier [C ] // Proc Icdm Foundation & New Direction of Data Mining Workshop . Melbourne, FL, USA : IEEE , 2003 : 353 - 365 .

ANGIULLI F , PIZZUTI C . Fast outlier detection in high dimensional spaces [C ] // Principles of Data Mining and Knowledge Discovery . Berlin, Heidelberg : Springer Berlin Heidelberg , 2002 : 15 - 27 .

BREUNIG M M , KRIEGEL H P , NG R T , et al . LOF: Identifying density-based local outliers [J ] . ACM SIGMOD Record , 2000 , 29 ( 2 ): 93 - 104 .

SCHÖLKOPF B , PLATT J C , SHAWE-TAYLOR J , et al . Estimating the support of a high-dimensional distribution [J ] . Neural Computation , 2001 , 13 ( 7 ): 1443 - 1471 .

HU M , FENG X W , JI Z W , et al . A novel computational approach for discord search with local recurrence rates in multivariate time series [J ] . Information Sciences , 2019 , 477 : 220 - 233 .

KHOSHNEVISAN F , FAN Z W , CARVALHO V R . Improving robustness on seasonality-heavy multivariate time series anomaly detection [EB/OL ] . ( 2020-07-25 ) [ 2024-05-10 ] . https://arxiv.org/abs/2007.14254v1 https://arxiv.org/abs/2007.14254v1 .

SU Y , ZHAO Y J , NIU C H , 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 . Anchorage AK USA : ACM , 2019 : 2828 - 2837 .

ZHANG Z J , LI W Z , DING W X , et al . STAD-GAN: Unsupervised anomaly detection on multivariate time series with self-training generative adversarial networks [J ] . ACM Transactions on Knowledge Discovery from Data , 2023 , 17 ( 5 ): 1 - 18 .

YAN K , LI W , JI Z W , et al . A hybrid LSTM neural network for energy consumption forecasting of individual households [J ] . IEEE Access , 2019 , 7 : 157633 - 157642 .

CHEN Z K , CHEN D S , ZHANG X , et al . Learning graph structures with transformer for multivariate time-series anomaly detection in IoT [J ] . IEEE Internet of Things Journal , 2022 , 9 ( 12 ): 9179 - 9189 .

DENG A L , HOOI B . Graph neural network-based anomaly detection in multivariate time series [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2021 , 35 ( 5 ): 4027 - 4035 .

SHEN L , LI Z , KWOK J . Timeseries anomaly detection using temporal hierarchical one-class network [J ] . Neural Information Processing Systems , 2020 , 33 : 13016 - 13026 .

HE Y D , ZHAO J B . Temporal convolutional networks for anomaly detection in time series [J ] . Journal of Physics: Conference Series , 2019 , 1213 ( 4 ): 042050 .

DING N , GAO H B , BU H Y , et al . RADM: Real-time anomaly detection in multivariate time series based on Bayesian network [C ] // 2018 IEEE International Conference on Smart Internet of Things . Xi'an, China : IEEE , 2018 : 129 - 134 .

SHANG C , CHEN J , BI J B . Discrete graph structure learning for forecasting multiple time series [EB/OL ] . ( 2021-04-21 ) [ 2024-05-10 ] . https://arxiv.org/abs/2101.06861v3 https://arxiv.org/abs/2101.06861v3 .

ROSSI E , CHAMBERLAIN B , FRASCA F , et al . Temporal graph networks for deep learning on dynamic graph [EB/OL ] . ( 2020-10-09 ) [ 2024-05-10 ] https://arxiv.org/abs/2006.10637v3 https://arxiv.org/abs/2006.10637v3 .

VELICKOVIC P , CUCURULL G , CASANOVA A , et al . Graph attention networks [EB/OL ] . ( 2018-02-04 ) [ 2024-05-10 ] . https://arxiv.org/abs/1710.10903v3 https://arxiv.org/abs/1710.10903v3 .

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 . Abnormal detection of industrial time-series data based on correlation analysis [J ] . Journal of Software , 2020 , 31 ( 3 ): 726 - 747 .

卢光曦 . 基于图神经网络的目标检测与识别算法研究 [D ] . 西安 : 西安电子科技大学 , 2022 .

WANG J T , QIAN Y H , LI F J . Learning with mitigating random consistency from the accuracy measure [J ] . Machine Learning , 2020 , 109 ( 12 ): 2247 - 2281 .

KOTŁOWSKI W , DEMBCZYИSKI K . Surrogate regret bounds for generalized classification performance metrics [J ] . Machine Learning , 2017 , 106 ( 4 ): 549 - 572 .

ELKAN C . The foundations of cost-sensitive learning [J ] . Proceedings of the International Joint Conference on Artifcial Intelligence , 2001 , 17 : 973 - 978 .

NAEASIMHAN H , VAISH R , AGARWAL S . On the statistical consistency of plug-in classifiers for non-decomposable performance measures [J ] . In Proceedings of the 27th International Conference on Neural Information Processing Systems , 2014 , 1 : 1493 - 1501 .

CHONG E K P , ZAK S H . An introduction to optimization . 3rd ed [M ] . New York : Wiley , 2011 .

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 . Vienna, Austria . IEEE , 2016 : 31 - 36 .

AHMED C M , PALLETI V R , MATHUR A P . WADI: A water distribution testbed for research in the design of secure cyber physical systems [C ] // Proceedings of the 3rd International Workshop on Cyber-Physical Systems for Smart Water Networks . Pittsburgh Pennsylvania : ACM , 2017 : 25 - 28 .

AUDIBERT J , MICHIARDI P , GUYARD F , et al . USAD: Unsupervised anomaly detection on multivariate time series [C ] // Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining . Virtual Event CA USA : ACM , 2020 : 3395 - 3404 .

DAS S , WONG W K , DIETTERICH T , et al . Incorporating expert feedback into active anomaly discovery [C ] // 2016 IEEE 16th International Conference on Data Mining . Barcelona, Spain : IEEE , 2016 : 853 - 858 .

FERNANDO B . Outlier analysis [J ] . Computing reviews , 2014 : 55 - 10 .

ZONG B , SONG Q , MIN M R , et al . Deep autoencoding gaussian mixture model for unsupervised anomaly detection [C ] // International Conference on Learning Representations , 2018 : 1 - 19 .

LIU F T , TING K M , ZHOU Z H . Isolation forest [C ] // 2008 Eighth IEEE International Conference on Data Mining . Pisa, Italy : IEEE , 2008 : 413 - 422 .

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 .

LI D , CHEN D C , JIN B H , et al . MAD-GAN: Multivariate anomaly detection for time series data with generative adversarial networks [C ] // Artificial Neural Networks and Machine Learning, ICANN 2019: Text and Time Series . Cham : Springer International Publishing , 2019 : 703 - 716 .

ZHANG W Q , ZHANG C , TSUNG F . GRELEN: Multivariate time series anomaly detection from the perspective of graph relational learning [C ] // Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence . Vienna, Austria : International Joint Conferences on Artificial Intelligence Organization , 2022 : 2390 - 2397 .

LI F J , QIAN Y H , WANG J T , et al . Clustering ensemble based on sample's stability [J ] . Artificial Intelligence , 2019 , 273 : 37 - 55 .

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

注意力机制的秦腔视频去噪算法

面向非遗美术图像分类的提示学习方法

嵌入混合注意力机制的Swin Transformer人脸表情识别

多源描述符融合的药物－靶标相互作用预测框架

基于生成对抗网络的乳腺MRI图像生成