Irregularly Sampled Multivariate Time Series Classification: A Graph Learning Approach
Article
Wang, Zhen, Jiang, Ting, Xu, Zenghui, Zhang, Ji and Gao, Jianliang. 2023. "Irregularly Sampled Multivariate Time Series Classification: A Graph Learning Approach." IEEE Intelligent Systems. 38 (3), pp. 3-11. https://doi.org/10.1109/MIS.2023.3239797
Article Title | Irregularly Sampled Multivariate Time Series Classification: A Graph Learning Approach |
---|---|
ERA Journal ID | 4426 |
Article Category | Article |
Authors | Wang, Zhen, Jiang, Ting, Xu, Zenghui, Zhang, Ji and Gao, Jianliang |
Journal Title | IEEE Intelligent Systems |
Journal Citation | 38 (3), pp. 3-11 |
Number of Pages | 9 |
Year | 2023 |
Publisher | IEEE (Institute of Electrical and Electronics Engineers) |
Place of Publication | United States |
ISSN | 1541-1672 |
1941-1294 | |
Digital Object Identifier (DOI) | https://doi.org/10.1109/MIS.2023.3239797 |
Web Address (URL) | https://ieeexplore.ieee.org/abstract/document/10026346 |
Abstract | To date, graph-based learning methods are proven to be effective for modeling spatial and structural dependencies. However, when applied to IS-MTS, they encounter three major challenges due to the complex data characteristics of IS-MTS: 1) variable time intervals between observations; 2) asynchronous time points across dimensions; and 3) a lack of prior knowledge of connectivity structure for message propagation. To fill these gaps, we propose a multivariate temporal graph network to coherently capture structural interactions, learn temporal dependencies, and handle challenging characteristics of IS-MTS data. Specifically, we first build a multivariate interaction module to handle frequent missing values and extract the graph structure relation automatically. Second, we design a novel adjacent graph propagation mechanism to aggregate the neighbor information from multistep snapshots. Third, we construct a masked temporal-aware attention module to explicitly consider the timestamp context and interval irregularity. Based on an extensive experimental evaluation, we demonstrate the superior performance of the proposed method. |
ANZSRC Field of Research 2020 | 460999. Information systems not elsewhere classified |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | Aarhus University, Denmark |
Zhejiang University, China | |
University of Southern Queensland | |
Central South University, China |
Permalink -
https://research.usq.edu.au/item/z2719/irregularly-sampled-multivariate-time-series-classification-a-graph-learning-approach
36
total views0
total downloads3
views this month0
downloads this month