An Unsupervised Long- and Short-Term Sparse Graph Neural Network for Multisensor Anomaly Detection

doi:10.1109/JSEN.2024.3383665

	An Unsupervised Long- and Short-Term Sparse Graph Neural Network for Multisensor Anomaly Detection
	Miao, Qiucheng 1; Wang, Dandan 2; Xu, Chuanfu 3,4; Zhan, Jun 3,4; Wu, Chengkun 3,4
	2024-07-15
发表期刊	IEEE SENSORS JOURNAL
ISSN	1530-437X
卷号	24 期号:14 页码:23088-23097
摘要	Anomaly detection of multivariate time series is critical in many applications. However, traditional statistical and machine learning models have limitations in modeling complex temporal dependencies and inter-sensor correlations. To address these limitations, graph neural networks (GNNs) have emerged as a powerful paradigm and have shown promising progress in anomaly detection. However, most existing GNN-based methods simplify sensor associations as fully connected graphs, contradicting real-world sparse connectivity. Moreover, while capturing intersensor dependencies, GNNs often overlook critical temporal dependencies in time series. To address these challenges, we propose an unsupervised long- and short-term sparse graph attention (LSGA) neural network. Specifically, we first use convolutional neural networks (CNNs) and skip-gate recurrent units (skip-GRUs) to extract local dependencies and long-term trends. Skip-GRU with time-skip connections effectively extends the span of information flow compared to traditional GRU. Due to the unknown graph structure between different sensors, we utilize node embedding to calculate the similarity between sensors and subsequently generate a dense similarity matrix. Then, we use the Gumbel-softmax sampling method to transform the similarity matrix into a sparse graph structure. To effectively fuse information from different sensors, we introduce a graph attention network (GAT), which can learn the relationships between sensors and dynamically fuse information based on the similarity of node embedding vectors. By means of sparse representation, we selectively focus on the information fusion of the sensors that have the greatest impact on themselves, thereby filtering out connections with low similarity between nodes and effectively removing redundant association information. Finally, we demonstrate with extensive experiments that our proposed method outperforms several state-of-the-art baseline methods in achieving better results on all four real datasets, improving average F1 by 0.97%, 7.7%, 1.92%, and 1.8%.
关键词	Sensors Anomaly detection Time series analysis Sensor systems Graph neural networks Correlation Sensor fusion Graph neural network (GNN) long-term short-term skip-gate recurrent unit (skip-GRU)
DOI	10.1109/JSEN.2024.3383665
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62006236] ; National Key Research and Development Program of China[2020YFA0709803] ; National Science Foundation of China[U1811462]
WOS研究方向	Engineering ; Instruments & Instrumentation ; Physics
WOS类目	Engineering, Electrical & Electronic ; Instruments & Instrumentation ; Physics, Applied
WOS记录号	WOS:001273156700138
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/39574
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wu, Chengkun
作者单位	1.Chinese Acad Sci, Shenzhen Inst Adv Technol, Ctr High Performance Comp, Shenzhen 423000, Peoples R China 2.Huawei Technol Co Ltd, Shenzhen 518000, Peoples R China 3.Natl Univ Def Technol NUDT, Inst Quantum Informat, Changsha 423000, Peoples R China 4.Natl Univ Def Technol NUDT, Coll Comp Sci & Technol, State Key Lab High Performance Comp, Changsha 423000, Peoples R China
推荐引用方式 GB/T 7714	Miao, Qiucheng,Wang, Dandan,Xu, Chuanfu,et al. An Unsupervised Long- and Short-Term Sparse Graph Neural Network for Multisensor Anomaly Detection[J]. IEEE SENSORS JOURNAL,2024,24(14):23088-23097.
APA	Miao, Qiucheng,Wang, Dandan,Xu, Chuanfu,Zhan, Jun,&Wu, Chengkun.(2024).An Unsupervised Long- and Short-Term Sparse Graph Neural Network for Multisensor Anomaly Detection.IEEE SENSORS JOURNAL,24(14),23088-23097.
MLA	Miao, Qiucheng,et al."An Unsupervised Long- and Short-Term Sparse Graph Neural Network for Multisensor Anomaly Detection".IEEE SENSORS JOURNAL 24.14(2024):23088-23097.