Logo des Repositoriums
 

Dynamic Circular Network-Based Federated Dual-View Learning for Multivariate Time Series Anomaly Detection

Kurzanzeige
dc.contributor.authorZhang, Weishan
dc.contributor.authorWang, Yuqian
dc.contributor.authorChen, Leiming
dc.contributor.authorYuan, Yong
dc.contributor.authorZeng, Xingjie
dc.contributor.authorXu, Liang
dc.contributor.authorZhao, Hongwei
dc.date2024-02-01
dc.date.accessioned2024-01-29T10:13:40Z
dc.date.available2024-01-29T10:13:40Z
dc.date.issued2024
dc.description.abstractMultivariate time-series data exhibit intricate correlations in both temporal and spatial dimensions. However, existing network architectures often overlook dependencies in the spatial dimension and struggle to strike a balance between long-term and short-term patterns when extracting features from the data. Furthermore, industries within the business community are hesitant to share their raw data, which hinders anomaly prediction accuracy and detection performance. To address these challenges, the authors propose a dynamic circular network-based federated dual-view learning approach. Experimental results from four open-source datasets demonstrate that the method outperforms existing methods in terms of accuracy, recall, and F1_score for anomaly detection.de
dc.identifier.doi10.1007/s12599-023-00825-8
dc.identifier.issn1867-0202
dc.identifier.urihttp://dx.doi.org/10.1007/s12599-023-00825-8
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/43440
dc.publisherSpringer
dc.relation.ispartofBusiness & Information Systems Engineering: Vol. 66, No. 1
dc.relation.ispartofseriesBusiness & Information Systems Engineering
dc.subjectAnomaly detection||Deep learning||Federated learning||Graph neural network||Multivariate time series
dc.titleDynamic Circular Network-Based Federated Dual-View Learning for Multivariate Time Series Anomaly Detectionde
dc.typeText/Journal Article
mci.reference.pages19-42

Dateien

Sammlungen

BISE 66(1) - February 2024