Class-Driven Graph Attention Network for Multi-Label Time Series Classification in Mobile Health Digital Twins
Le Sun, Chenyang Li, Bo Liu, Yanchun Zhang
Abstract
Digital Twins for Mobile Networks (DTMN) can enhance mobile health (mHealth) by increasing diagnostic and monitoring capabilities. Classifying multi-label time series mHealth data in DTMN is challenging due to complex class relevance and feature extraction difficulties. This paper proposes a Class-Driven Graph Attention network learning framework (C-DGAM) for Multi-label classification of mHealth data in DTMN. C-DGAM captures the complex class relationships by constructing a unique class relevance graph for each time series. It uses a temporal context attention module to generates class representation vectors by fusing multi-dimensional features of time and class. Then, it dynamically models different relevance among the class representation vectors through a dynamic graph attention module which improves the performance of multi-label time series classification while maintaining a smaller parameter size and lower computational complexity. The mean Average Precision achieved by C-DGAM on two different multi-label time series datasets are 0.955 and 0.776, respectively, with corresponding F1 scores of 0.867 and 0.80. It demonstrates leading performance compared to existing state-of-art works. It provides more accurate and generalized algorithmic support for DMTN systems.