Multi-scale temporal features extraction based graph convolutional network with attention for multivariate time series prediction

• Published in: Expert systems with applications Vol. 200; p. 117011
• Main Authors: Chen, Yawen, Ding, Fengqian, Zhai, Linbo
• Format: Journal Article
• Language: English
• Published: New York Elsevier Ltd 15.08.2022; Elsevier BV
• Subjects: Artificial neural networks; Feature extraction; Features extraction; Forecasting; Graph neural network; Mathematical models; Multi-head attention; Multivariate analysis; Multivariate time series prediction; Neural networks; Nodes; Prediction models; Spatial dependencies; Time series; Multivariate time series prediction; Features extraction; Graph neural network; Multi-head attention
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2022.117011

•A novel GCN model is proposed for multivariate time series prediction.•EMD is used to extract multi-scale temporal features of original time series.•Multi-head attention mechanism is utilized to explore the spatial dependencies.•Real datasets from various fields confirms the superiority of the method. Modeling for multivariate time series have always been a meaningful subject. Multivariate time series forecasting is a fundamental problem attracting many researchers in various fields. However, most of the existing methods focused on univariate prediction and rarely take into account the potential spatial dependencies between multiple variables. Multivariate time series forecasting can be naturally viewed from graph perspective, where each variable from multivariate time series can be viewed as a node in the graph, and they are interlinked through hidden dependencies. Therefore, a novel graph neural network model based on multi-scale temporal feature extraction and attention mechanism is proposed for multivariate time series prediction. Specifically, empirical modal decomposition is used to extract the time-domain features of multivariate time series at different time scales to form the node features of the graph. Meanwhile, the multi-head attention mechanism is applied to construct potential associations between nodes and enhance the rationality of relationships in the graph. Furthermore, the graph convolutional neural network is used to generate node embeddings that contain rich spatial relationships. Finally, the temporal convolutional network establishes temporal relationships for the node embedding to achieve multivariate time series prediction. The real data from the financial, traffic and medical fields confirm the effectiveness of the proposed model.