Jian Feng^*, Tian Liu, Cailing Du

CMC-Computers, Materials & Continua, Vol.81, No.2, pp. 2895-2909, 2024, DOI:10.32604/cmc.2024.056434 - 18 November 2024

Abstract Unsupervised learning methods such as graph contrastive learning have been used for dynamic graph representation learning to eliminate the dependence of labels. However, existing studies neglect positional information when learning discrete snapshots, resulting in insufficient network topology learning. At the same time, due to the lack of appropriate data augmentation methods, it is difficult to capture the evolving patterns of the network effectively. To address the above problems, a position-aware and subgraph enhanced dynamic graph contrastive learning method is proposed for discrete-time dynamic graphs. Firstly, the global snapshot is built based on the historical snapshots… More >

D. Ballhause¹, M. König¹, B. Kröplin¹

CMC-Computers, Materials & Continua, Vol.4, No.1, pp. 21-30, 2006, DOI:10.3970/cmc.2006.004.021

Abstract The mechanical behaviour of woven fabrics is dominated by the kinematics of the constituents on the microscopic scale. Their macroscopic response usually shows non-linearities which are due to the mobility of the interlaced yarns. The major deformation mechanisms of fabrics, i.e. the crimp interchange in case of biaxial tension and the trellising motion of the yarns in case of shear, reflect the dependency of the macroscopic material behaviour on the microstructural deformation mechanisms.
We present a novel modelling approach for woven fabrics which is capable to represent directly and locally the microstructure and its kinematics… More >