多元统计
计算机科学
系列(地层学)
时间序列
图形
人工神经网络
人工智能
模式识别(心理学)
机器学习
理论计算机科学
古生物学
生物
作者
Huaiyuan Liu,Donghua Yang,Xianzhang Liu,Xinglei Chen,Zhiyu Liang,Hongzhi Wang,Yong Cui,Jun Gu
标识
DOI:10.1016/j.ins.2024.120914
摘要
Multivariate time series classification (MTSC) is a crucial data mining task that can be effectively tackled using prevalent deep learning technology. However, current methods often overlook hidden dependencies across dimensions and struggle to capture dynamic time series features adequately, leading to poor accuracy. To tackle this challenge, we propose TodyNet, a novel dynamic temporal graph neural network. TodyNet extracts latent spatio-temporal dependencies without predefined graph structures, facilitating information flow among isolated but implicitly interdependent variables. It captures associations between time slots through dynamic graphs, boosting classification performance. Furthermore, to address the limitation that the hierarchical representations of graphs are challenging to learn with graph neural networks (GNNs), we introduce a temporal graph pooling layer for obtaining a global graph-level representation. The dynamic graph, graph information propagation, and temporal convolution are jointly learned within an end-to-end framework. Experimental results on 26 UEA benchmark datasets indicate that compared to current state-of-the-art deep learning methods in the MTSC task, the proposed Todynet achieved a performance improvement of 5.5%.
科研通智能强力驱动
Strongly Powered by AbleSci AI