A survey on graph neural networks for time series: Forecasting, classification, imputation, and anomaly detection

M Jin, HY Koh, Q Wen, D Zambon… - … on Pattern Analysis …, 2024 - ieeexplore.ieee.org
Time series are the primary data type used to record dynamic system measurements and
generated in great volume by both physical sensors and online processes (virtual sensors) …

[HTML][HTML] Graph spatiotemporal process for multivariate time series anomaly detection with missing values

Y Zheng, HY Koh, M Jin, L Chi, H Wang, KT Phan… - Information …, 2024 - Elsevier
The detection of anomalies in multivariate time series data is crucial for various practical
applications, including smart power grids, traffic flow forecasting, and industrial process …

Dyedgegat: Dynamic edge via graph attention for early fault detection in iiot systems

M Zhao, O Fink - IEEE Internet of Things Journal, 2024 - ieeexplore.ieee.org
In the Industrial Internet of Things (IIoT), condition monitoring sensor signals from complex
systems often exhibit nonlinear and stochastic spatial-temporal dynamics under varying …

Enhancing urban flow prediction via mutual reinforcement with multi-scale regional information

X Zhang, M Cao, Y Gong, X Wu, X Dong, Y Guo… - Neural Networks, 2025 - Elsevier
Abstract Intelligent Transportation Systems (ITS) are essential for modern urban
development, with urban flow prediction being a key component. Accurate flow prediction …

AD-NEv: A Scalable Multilevel Neuroevolution Framework for Multivariate Anomaly Detection

M Pietroń, D Żurek, K Faber… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Anomaly detection tools and methods present a key capability in modern cyberphysical and
failure prediction systems. Despite the fast-paced development in deep learning …

Vehicular Social Dynamic Anomaly Detection With Recurrent Mulit-Mask Aggregator Enabled VAE

Z Hu, Y He, Y Shen, M Jo, M Collotta… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Vehicle driving behavior analysis and detection tasks have become an indispensable part of
intelligent transportation systems. Accurate pattern recognition of potential anomalies during …

Rectifying inaccurate unsupervised learning for robust time series anomaly detection

Z Chen, Z Li, X Chen, X Chen, H Fan, R Hu - Information Sciences, 2024 - Elsevier
Unsupervised time series anomaly detection is a challenging task. Data contamination
brings more challenges for the existing methods that rely on completely clean training data …

Multivariate Time Series Anomaly Detection Based on Dynamic Graph Neural Networks and Self-Distillation in Industrial Internet of Things

M Zhao, H Peng, L Li - IEEE Internet of Things Journal, 2024 - ieeexplore.ieee.org
Time series anomaly detection is critical to securing the Industrial Internet of Things (IIoT).
Although numerous deep learning-based methods have been proposed, these methods fail …

A Multitask Dynamic Graph Attention Autoencoder for Imbalanced Multilabel Time Series Classification

L Sun, C Li, Y Ren, Y Zhang - IEEE Transactions on Neural …, 2024 - ieeexplore.ieee.org
Graph learning is widely applied to process various complex data structures (eg, time series)
in different domains. Due to multidimensional observations and the requirement for accurate …

HFTCRNet: Hierarchical Fusion Transformer for Interbank Credit Rating and Risk Assessment

J Li, Z Zhou, J Zhang, D Cheng… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
As a prominent application of deep neural networks in financial literature, bank credit ratings
play a pivotal role in safeguarding global economic stability and preventing crises. In the …