{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T14:29:50Z","timestamp":1773239390424,"version":"3.50.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,1,6]],"date-time":"2024-01-06T00:00:00Z","timestamp":1704499200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,1,6]],"date-time":"2024-01-06T00:00:00Z","timestamp":1704499200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61937001"],"award-info":[{"award-number":["61937001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2024,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The detection of anomalies in high-dimensional time-series has always played a crucial role in the domain of system security. Recently, with rapid advancements in transformer model and graph neural network (GNN) technologies, spatiotemporal modeling approaches for anomaly detection tasks have been greatly improved. However, most methods focus on optimizing upstream time-series prediction tasks by leveraging joint spatiotemporal features. Through experiments, we found that this modeling approach not only risks the loss of some original anomaly information during data preprocessing, but also focuses on optimizing the performance of the upstream prediction task and does not directly enhance the performance of the downstream detection task. We propose a spatiotemporal anomaly detection model that incorporates an improved attention mechanism in the process of temporal modeling. We adopt a heterogeneous graph contrastive learning approach in spatio modeling to compensate for the representation of anomalous behavioral information, thereby guiding the model through thorough training. Through validation on two widely used real-world datasets, we demonstrate that our model outperforms baseline methods. We also explore the impact of multivariate time-series prediction tasks on the detection task, and visualize the reasons behind the benefits gained by our model.<\/jats:p>","DOI":"10.1007\/s40747-023-01306-x","type":"journal-article","created":{"date-parts":[[2024,1,6]],"date-time":"2024-01-06T08:02:25Z","timestamp":1704528145000},"page":"2937-2950","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["An enhanced abnormal information expression spatiotemporal model for anomaly detection in multivariate time-series"],"prefix":"10.1007","volume":"10","author":[{"given":"Di","family":"Ge","sequence":"first","affiliation":[]},{"given":"Yuhang","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Shuangshuang","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Yanmei","family":"Ma","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5721-8715","authenticated-orcid":false,"given":"Yanwen","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,6]]},"reference":[{"key":"1306_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-9229-1_5","author":"Z Chen","year":"2022","unstructured":"Chen Z, Peng Z, Zou X, Sun H (2022) Deep learning based anomaly detection for muti-dimensional time series: a survey. Commun Comput Inf Sci. https:\/\/doi.org\/10.1007\/978-981-16-9229-1_5","journal-title":"Commun Comput Inf Sci"},{"key":"1306_CR2","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1109\/jas.2021.1004261","volume":"9","author":"J Zhang","year":"2022","unstructured":"Zhang J, Pan L, Han Q-L, Chen C, Wen S, Xiang Y (2022) Deep learning based attack detection for cyber-physical system cybersecurity: a survey. IEEE\/CAA J Autom Sin 9:377\u2013391. https:\/\/doi.org\/10.1109\/jas.2021.1004261","journal-title":"IEEE\/CAA J Autom Sin"},{"key":"1306_CR3","doi-asserted-by":"crossref","unstructured":"Song X, Wu N, Song S, et al.\nSwitching-Like Event-Triggered State Estimation for Reaction\u2013Diffusion Neural\nNetworks Against DoS Attacks[J]. Neural Processing Letters 2023:1\u201322","DOI":"10.1007\/s11063-023-11189-1"},{"key":"1306_CR4","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2019.1316","author":"X Dong","year":"2020","unstructured":"Dong X, He S, Stojanovic V (2020) Robust fault detection filter design for a class of discrete-time conic-type non-linear markov jump systems with jump fault signals. IET Control Theory Appl. https:\/\/doi.org\/10.1049\/iet-cta.2019.1316","journal-title":"IET Control Theory Appl"},{"key":"1306_CR5","doi-asserted-by":"publisher","first-page":"10924","DOI":"10.1002\/int.23027","volume":"37","author":"X Xie","year":"2022","unstructured":"Xie X, Ning W, Huang Y, Li Z, Yu S, Yang H (2022) Graph-based Bayesian network conditional normalizing flows for multiple time series anomaly detection. Int J Intell Syst 37:10924\u201310939. https:\/\/doi.org\/10.1002\/int.23027","journal-title":"Int J Intell Syst"},{"key":"1306_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126498","author":"X Song","year":"2023","unstructured":"Song X, Wu N, Song S, Zhang Y, Stojanovic V (2023) Bipartite Synchronization for Cooperative-Competitive Neural Networks with Reaction-Diffusion Terms via Dual Event-Triggered Mechanism. Neurocomputing. https:\/\/doi.org\/10.1016\/j.neucom.2023.126498","journal-title":"Neurocomputing"},{"key":"1306_CR7","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/978-3-030-59194-6_4","volume-title":"Systems and Information Sciences","author":"JL Charco","year":"2021","unstructured":"Charco JL, Roque-Colt T, Egas-Arizala K, P\u00e9rez-Espinoza CM (2021) Cruz-Ch\u00f3ez A (2021) Using multivariate time series data via long-short term memory network for temperature forecasting. In: Botto-Tobar M, Zamora W, Larrea Pl\u00faa J, Bazurto Roldan J, Santamar\u00eda Philco A (eds) Systems and Information Sciences. Springer International Publishing, Cham, pp 38\u201347"},{"key":"1306_CR8","first-page":"199","volume":"10","author":"S Maini","year":"2018","unstructured":"Maini S, Aggarwal AK (2018) Camera position estimation using 2D image dataset. Int J Innov Eng Technol 10:199\u2013203","journal-title":"Int J Innov Eng Technol"},{"key":"1306_CR9","volume-title":"Attention is all you need","author":"A Vaswani","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN et al (2017) Attention is all you need. Curran Associates Inc"},{"key":"1306_CR10","doi-asserted-by":"publisher","first-page":"1201","DOI":"10.14778\/3514061.3514067","volume":"15","author":"S Tuli","year":"2022","unstructured":"Tuli S, Casale G, Jennings NR (2022) Tranad: deep transformer networks for anomaly detection in multivariate time series data. Proc VLDB Endow 15:1201\u20131214. https:\/\/doi.org\/10.14778\/3514061.3514067","journal-title":"Proc VLDB Endow"},{"key":"1306_CR11","doi-asserted-by":"crossref","unstructured":"Maru C, Brandherm B, Kobayashi I (2022) Combining transformer with a discriminator for anomaly detection in multivariate time series. In: 2022 Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems (SCIS&ISIS). p. 1\u20137","DOI":"10.1109\/SCISISIS55246.2022.10002131"},{"key":"1306_CR12","doi-asserted-by":"crossref","unstructured":"Wiederer J, Bouazizi A, Troina M, Kressel U, Belagiannis V (2021) Anomaly detection in multi-agent trajectories for automated driving. arXiv preprint   arXiv:211007922","DOI":"10.1109\/ITSC55140.2022.9922440"},{"key":"1306_CR13","doi-asserted-by":"crossref","unstructured":"Su Y, Zhao Y, Niu C, Liu R, Sun W, Pei D (2019) Robust anomaly detection for multivariate time series through stochastic recurrent neural network. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining. p. 2828\u20132837","DOI":"10.1145\/3292500.3330672"},{"key":"1306_CR14","unstructured":"Xu J, Wu H, Wang J, Long M (2021) Anomaly transformer: Time series anomaly detection with association discrepancy. arXiv preprint arXiv:211002642"},{"key":"1306_CR15","doi-asserted-by":"publisher","first-page":"4027","DOI":"10.1609\/aaai.v35i5.16523","volume":"35","author":"A Deng","year":"2021","unstructured":"Deng A, Hooi B (2021) Graph neural network-based anomaly detection in multivariate time series. Proc Innov Appl Artif Intell 35:4027\u20134035. https:\/\/doi.org\/10.1609\/aaai.v35i5.16523","journal-title":"Proc Innov Appl Artif Intell"},{"key":"1306_CR16","doi-asserted-by":"publisher","first-page":"9179","DOI":"10.1109\/jiot.2021.3100509","volume":"9","author":"Z Chen","year":"2022","unstructured":"Chen Z, Chen D, Zhang X, Yuan Z, Cheng X (2022) Learning graph structures with transformer for multivariate time-series anomaly detection in IoT. IEEE Internet Things J 9:9179\u20139189. https:\/\/doi.org\/10.1109\/jiot.2021.3100509","journal-title":"IEEE Internet Things J"},{"key":"1306_CR17","doi-asserted-by":"publisher","unstructured":"Han S, Woo SS (2022) \u201cLearning Sparse Latent Graph Representations for Anomaly Detection in Multivariate Time Series.\u201d In: Zhang A, Rangwala H (eds), KDD \u201922: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 2977\u20132986). Washington, DC, USA: ACM. DOI: https:\/\/doi.org\/10.1145\/3534678.3539117","DOI":"10.1145\/3534678.3539117"},{"issue":"6","key":"1306_CR18","doi-asserted-by":"publisher","first-page":"1201","DOI":"10.14778\/3514061.3514067","volume":"15","author":"S Tuli","year":"2022","unstructured":"Tuli S, Casale G, Jennings NR (2022) Tranad: deep transformer networks for anomaly detection in multivariate time series data. Proc VLDB Endowment 15(6):1201\u20131214","journal-title":"Proc VLDB Endowment"},{"key":"1306_CR19","unstructured":"Liu Y, Wu H, Wang J, Long M (2022) Non-stationary transformers: exploring the stationarity in time series forecasting. arXiv preprint arXiv:220514415"},{"key":"1306_CR20","doi-asserted-by":"crossref","unstructured":"Yokkampon U, Chumkamon S, Mowshowitz A, Hayashi E (2020) Anomaly detection using variational autoencoder with spectrum analysis for time series data. In: 2020 Joint 9th International Conference on Informatics, Electronics & Vision (ICIEV) and 2020 4th International Conference on Imaging, Vision & Pattern Recognition (icIVPR). IEEE","DOI":"10.1109\/ICIEVicIVPR48672.2020.9306570"},{"key":"1306_CR21","doi-asserted-by":"crossref","unstructured":"Fu Y, Xue F (2022) MAD: Self-supervised masked anomaly detection task for multivariate time series. In: 2022 International Joint Conference on Neural Networks (IJCNN). IEEE","DOI":"10.1109\/IJCNN55064.2022.9892218"},{"key":"1306_CR22","unstructured":"Malhotra P, Vig L, Shroff GM, Agarwal P (2015) Long short term memory networks for anomaly detection in time series. In: The European Symposium on Artificial Neural Networks"},{"key":"1306_CR23","doi-asserted-by":"publisher","first-page":"19038","DOI":"10.1038\/s41598-019-55320-6","volume":"9","author":"A Sagheer","year":"2019","unstructured":"Sagheer A, Kotb M (2019) Unsupervised pre-training of a deep LSTM-based stacked autoencoder for multivariate time series forecasting problems. Sci Rep 9:19038. https:\/\/doi.org\/10.1038\/s41598-019-55320-6","journal-title":"Sci Rep"},{"key":"1306_CR24","doi-asserted-by":"crossref","unstructured":"Han S, Woo SS (2022) Learning sparse latent graph representations for anomaly detection in multivariate time series. Association for Computing Machinery, New York, NY, USA, p. 2977\u20132986","DOI":"10.1145\/3534678.3539117"},{"key":"1306_CR25","doi-asserted-by":"crossref","unstructured":"Ahmad S, Purdy S (2016) Real-time anomaly detection for streaming analytics. arXiv preprint arXiv:160702480","DOI":"10.1016\/j.neucom.2017.04.070"},{"key":"1306_CR26","doi-asserted-by":"publisher","first-page":"2404","DOI":"10.3724\/SP.J.1146.2009.01342","volume":"32","author":"Q Ye-Kui","year":"2010","unstructured":"Ye-Kui Q, Ming C (2010) A multivariate online anomaly detection algorithm based on SVD updating. J Electron Inform Technol 32:2404\u20132409. https:\/\/doi.org\/10.3724\/SP.J.1146.2009.01342","journal-title":"J Electron Inform Technol"},{"key":"1306_CR27","unstructured":"Malhotra P, Ramakrishnan A, Anand G, Vig L, Agarwal P, Shroff G (2016) LSTM-based encoder-decoder for multi-sensor anomaly detection. arXiv preprint arXiv:160700148"},{"key":"1306_CR28","unstructured":"Aggarwal AK (2020) \u201cAtmospheric Delay Correction of RINEX GPS Data\u201d"},{"key":"1306_CR29","unstructured":"Aggarwal AK (2023) \u201cA hybrid approach to GPS improvement in urban canyons\u201d"},{"key":"1306_CR30","doi-asserted-by":"publisher","first-page":"6074","DOI":"10.1007\/s10489-022-03829-1","volume":"53","author":"N Chen","year":"2023","unstructured":"Chen N, Tu H, Duan X, Hu L, Guo C (2023) Semisupervised anomaly detection of multivariate time series based on a variational autoencoder. Appl Intell 53:6074\u20136098. https:\/\/doi.org\/10.1007\/s10489-022-03829-1","journal-title":"Appl Intell"},{"key":"1306_CR31","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1109\/TII.2021.3078192","volume":"19","author":"F Kong","year":"2023","unstructured":"Kong F, Li J, Jiang B, Wang H, Song H (2023) Integrated generative model for industrial anomaly detection via bidirectional LSTM and attention mechanism. IEEE Trans Ind Inform 19:541\u2013550. https:\/\/doi.org\/10.1109\/TII.2021.3078192","journal-title":"IEEE Trans Ind Inform"},{"key":"1306_CR32","unstructured":"Jeong Y, Yang E, Ryu J, Park I, Kang M (2023) AnomalyBERT: self-supervised transformer for time series anomaly detection using data degradation scheme"},{"key":"1306_CR33","unstructured":"Aggarwal AK, Sato T, Oishi T, Ono S, Ikeuchi K (2014) \u201cImproving GPS Position Accuracy by Identification of Reflected GPS Signals Using Range Data for Modeling of Urban Structures.\u201d SEISAN KENKYU"},{"key":"1306_CR34","unstructured":"Xiao J, Aggarwal AK, Kiran U, Katiyar V, Avtar R (Year) \u201cDeep Learning-based spatiotemporal fusion of unmanned aerial vehicle and satellite reflectance images for crop monitoring\u201d"},{"key":"1306_CR35","unstructured":"Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv preprint   arXiv:160902907"},{"key":"1306_CR36","unstructured":"Veli\u010dkovi\u0107 P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2017) Graph attention networks. arXiv preprint arXiv:171010903"},{"key":"1306_CR37","doi-asserted-by":"publisher","first-page":"5953","DOI":"10.3233\/jifs-222554","volume":"44","author":"Q He","year":"2023","unstructured":"He Q, Wang G, Wang H, Chen L (2023) Multivariate time-series anomaly detection via temporal convolutional and graph attention networks. J Intell Fuzzy Syst 44:5953\u20135962. https:\/\/doi.org\/10.3233\/jifs-222554","journal-title":"J Intell Fuzzy Syst"},{"key":"1306_CR38","doi-asserted-by":"crossref","unstructured":"Zhao H, Wang Y, Duan J, Huang C, Cao D, Tong Y, et al. (2020) Multivariate time-series anomaly detection via graph attention network. In: 2020 IEEE International Conference on Data Mining (ICDM). IEEE","DOI":"10.1109\/ICDM50108.2020.00093"},{"key":"1306_CR39","unstructured":"Zhu Y, Xu Y, Yu F, Liu Q, Wu S, Wang L (2020) Deep graph contrastive representation learning. arXiv preprint arXiv:200604131"},{"key":"1306_CR40","unstructured":"Aggarwal AK, Banno A, Ono S, Oishi T, Ikeuchi K (2013) \u201cGlobal Coordinate Adjustment of the 3D Survey Models under Unstable GPS Condition.\u201d SEISAN KENKYU"},{"key":"1306_CR41","unstructured":"Shyu M-L, Chen S-C, Sarinnapakorn K, Chang L (2003) A novel anomaly detection scheme based on principal component classifier. In: IEEE Foundations and New Directions of Data Mining Workshop, in conjunction with the Third IEEE International Conference on Data Mining (ICDM\u201903)"},{"key":"1306_CR42","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/3-540-45681-3_2","volume-title":"Principles of data mining and knowledge discovery","author":"F Angiulli","year":"2002","unstructured":"Angiulli F, Pizzuti C (2002) Fast outlier detection in high dimensional spaces. Principles of data mining and knowledge discovery. Springer, pp 15\u201327"},{"key":"1306_CR43","volume-title":"Deep autoencoding Gaussian mixture model for unsupervised anomaly detection","author":"B Zong","year":"2018","unstructured":"Zong B, Song Q, Min MR, Cheng W, Lumezanu C, Cho D et al (2018) Deep autoencoding Gaussian mixture model for unsupervised anomaly detection. Springer"},{"key":"1306_CR44","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-6396-2","volume-title":"Outlier analysis","author":"C Aggarwal","year":"2013","unstructured":"Aggarwal C (2013) Outlier analysis. Springer"},{"key":"1306_CR45","doi-asserted-by":"publisher","first-page":"1544","DOI":"10.1109\/lra.2018.2801475","volume":"3","author":"D Park","year":"2018","unstructured":"Park D, Hoshi Y, Kemp CC (2018) A Multimodal anomaly detector for robot-assisted feeding using an LSTM-based variational autoencoder. IEEE Robot Autom Lett 3:1544\u20131551. https:\/\/doi.org\/10.1109\/lra.2018.2801475","journal-title":"IEEE Robot Autom Lett"},{"key":"1306_CR46","doi-asserted-by":"publisher","first-page":"11106","DOI":"10.1609\/aaai.v35i12.17325","volume":"35","author":"H Zhou","year":"2021","unstructured":"Zhou H, Zhang S, Peng J, Zhang S, Li J, Xiong H et al (2021) Informer: beyond efficient transformer for long sequence time-series forecasting. Proc Innov Appl Artif Intell 35:11106\u201311115. https:\/\/doi.org\/10.1609\/aaai.v35i12.17325","journal-title":"Proc Innov Appl Artif Intell"},{"key":"1306_CR47","first-page":"22419","volume-title":"Autoformer: decomposition transformers with auto-correlation for long-term series forecasting","author":"H Wu","year":"2021","unstructured":"Wu H, Xu J, Wang J, Long M (2021) Autoformer: decomposition transformers with auto-correlation for long-term series forecasting. Curran Associates Inc, pp 22419\u201322430"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-023-01306-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-023-01306-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-023-01306-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,30]],"date-time":"2024-03-30T15:36:17Z","timestamp":1711812977000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-023-01306-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,6]]},"references-count":47,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["1306"],"URL":"https:\/\/doi.org\/10.1007\/s40747-023-01306-x","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,6]]},"assertion":[{"value":"14 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 November 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}