Graph neural networks and fuzzy models offer effective and practical methods for solving various tasks at the large-scale graph level. Large-scale graph embedding based on deep methods and fuzzy models is categorized into fusion and integration. Feature extraction and graph structure at the local and global levels are based on augmented graph fusion. In fusion-based graph embedding, the fuzzy model is used as an activation function based on an aggregated process. In some cases, the fusion of graph neural network methods with fuzzy systems has been successful. However, no effective methods have been developed for integrating fuzzy models with deep methods. Two main issues are associated with this integration: (1) computational complexity due to the exponential increase in fuzzy rules with the number of features, and (2) the complexity of the solution space due to the combination of fuzzy regression rules between inputs and outputs. Additionally, modeling at the large-scale graph level using linear regression and graph neural networks is not sufficient. Therefore, this paper proposes a feature and structure combination method at the local and global levels using a combination of fuzzy modeling and graph transformers, an integrated deep learning technique called Fuzzy Graph Transformer (FuzzyGT). We conducted experiments on deep learning graph datasets to compare with the proposed model. Our method achieved the best results compared to other advanced models

Qeshm Channel is a shallow and narrow waterway located between Qeshm Island and the mainland in the vicinity of Hormuzgan Province, Islamic Republic of Iran. This channel is important because of its economic, industrial, fisheries and navigation role it plays as well as environmental issues it presents in the region. A prognostic study was performed to simulate currents in this channel, using COHERENS model. This model is a three-dimensional hydrodynamic model. Simulation of currents was carried out in 20 sigma levels from the seabed to the water surface during one month. It was assumed that the variations of seawater temperature and salinity, four main tidal constituents and the regional wind were the most effective factors in the numerical simulation. Finally, sensitivity analysis was carried out for each factor and the outputs of simulation were verified using the field data recorded by the experts from Iranian National Center for Oceanography. Very good agreements were found between the numerical results and the field data.

Upper bound limit analysis method is applied to determine the required reinforcement for three-dimensional stability of the slopes under seismic conditions. Horizontal blocks are used for determining the internal stability in three dimensional conditions. Seismic stability is studied by adopting a pseudo-static approach, considering only the horizontal acceleration. Reinforced soil has been considered to be a cohesionless material in the analysis. The failure mechanism is considered to be transitional and consists of several horizontal hexagonal blocks and a pentagonal one at the base. Velocity discontinuities between blocks are considered to be horizontal and each block consists of one reinforcement layer. Results are presented in graphical and tabular form to illustrate the effects of variation of different parameters such as seismic acceleration, three-dimensional geometry of the slope and soil friction angle on required reinforcement length and strength. By increasing of seismic acceleration, the stability of the reinforced soil slope decreases significantly, and thus greater strength and length of the reinforcement are required to maintain stability of the slope. On the other hand, three-dimensional modeling of reinforced slope results lower values of the required reinforcement. Comparisons of the present results with available pseudo-static results are shown, and discussed.