Open access
Jul 2026
A multilevel interactive framework based Siamese graph networks for multisource track association
A multilevel interactive Siamese graph neural network, termed MIS-GNN, which achieves an average F1-score of 0.9264, outperforming state-of-the-art comparison methods and verifying the robustness and deployment feasibility of the proposed method.
Yu-Chen Zhao, Li Yuan, Kai Liu et al.
· Measurement science and tech... · 1 citation