Search

Obtaining accurate road conditions is crucial for traffic management, dynamic route planning, and intelligent guidance services. The complex spatial correlation and nonlinear temporal dependence pose great challenges to obtaining accurate road conditions. Existing graph-based methods use a static adjacency matrix or a dynamic adjacency matrix to aggregate spatial information between nodes, which cannot fully represent the topological information. In this paper, we propose a Hybrid Graph Model (HGM) for accurate traffic prediction. The HGM constructs a static graph and a dynamic graph to represent the topological information of the traffic network, which is beneficial for mining potential and obvious spatial correlations. The proposed method combines a graph neural network, convolutional neural network, and attention mechanism to jointly extract complex spatial–temporal features. The HGM consists of two different sub-modules, called spatial–temporal attention module and dynamic graph convolutional network, to fuse complex spatial–temporal information. Furthermore, the proposed method designs a novel gated function to adaptively fuse the results from spatial–temporal attention and dynamic graph convolutional network to improve prediction performance. Extensive experiments on two real datasets show that the HGM outperforms comparable state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The study investigated the diversity of endophytic fungi in the roots, stems and leaves of the medicinal plant Anemarrhena asphodeloides and the antimicrobial activity of their secondary metabolites provide references for discovering new potent antimycotics against opportunistic pathogenic yeasts and dermatophytes. Samples of roots, stems and leaves of 5 healthy wild A. asphodeloides plants were collected from the Taihang Mountain in Hebei Province. The endophytic fungi of A. asphodeloides were isolated by tissue block isolation method, and were identified by morphological and molecular biological methods. The antimicrobial activity of opportunistic pathogenic yeasts and dermatophytes of endophytic fungi were studied by the agar diffusion and mycelial growth inhibition methods, respectively. A total of 438 isolates of endophytic fungi were isolated from A. asphodeloides tissues, these isolates belong to 23 genera. The colonization rate of the endophytic fungi in the roots, stems and leaves were 99. 33%, 74. 00% and 47. 33% respectively. Fusarium,60. 29% and Setophoma,33. 97%,were the dominant genera in the roots,Fusarium (91. 50%) and Clonostachys (7. 19%) were the dominant genera in the stems, and Fusarium (35. 53%) and Alternaria (14. 47%) were the dominant genera in the leaves. The Shannon diversity index shows that the species diversity in leaves is the highest, followed by roots and stems. The antibacterial results of 30 representative strains by performing fermentation broth showed that, 96. 77%, 100. 00%, 100. 00%, 3. 33% and 3. 33% of the isolated endophytic fungi had inhibitory activity against Microsporum canis, Trichophyton rubrum, Trichosporon mucoides, Malassezia furfur and Candida albicans, respectively. Among them, the strain ZMR35 has a strong inhibitory activity against four kinds of superficial fungi. The inhibition rates of the fermentation broth of strain ZML33 against Microsporum canis, Trichophyton rubrum, Trichosporon mucoides were all higher than 70%. The results indicated that the species diversity of A. asphodeloides endophytic fungi was rich and the colonization of these species showed tissue specificity. Two of the strains ZMR35 and ZML33 exhibited significant inhibitory effects on a variety of superficial pathogenic fungi in vitro. Our results indicate that the secondary metabolites produced by the endophytic fungi of A. asphodeloides can be used as natural drug candidates for the treatment of superficial mycosis. [ABSTRACT FROM AUTHOR]