To classify the image material on the internet, the deep learning methodology, especially deep neural network, is the most optimal and costliest method of all computer vision methods. Convolutional neural networks (CNNs) learn a comprehensive feature representation by exploiting local information with a fixed receptive field, demonstrating distinguished capacities on image classification. Recent works concentrate on efficient feature exploration, which neglect the global information for holistic consideration. There is large effort to reduce the computational costs of deep neural networks. Here, we provide a hierarchical global attention mechanism that improve the network representation with restricted increase of computation complexity. Different from nonlocal-based methods, the hierarchical global attention mechanism requires no matrix multiplication and can be flexibly applied in various modern network designs. Experimental results demonstrate that proposed hierarchical global attention mechanism can conspicuously improve the image classification precision—a reduction of 7.94% and 16.63% percent in Top 1 and Top 5 errors separately—with little increase of computation complexity (6.23%) in comparison to competing approaches.

A chemical industry park (CIP) has a wide variety of hazardous chemicals, and once an accident occurs, the level of danger increases geometrically, while the domino effect may bring devastating consequences. To improve the emergency rescue capability of a chemical park and prevent the domino effect, a certain number of emergency centers are built at sites near the park for the purpose of rapid emergency rescue and deployment of emergency supplies. Based on this, in our study, a siting model of the emergency center of the chemical park, which aims to prevent the domino effect, was constructed by considering the timeliness and safety, while adopting the prevention of the domino effect as a constraint. The NSGA-II algorithm is used to solve the siting model, and the CPLEX method is used for the comparison. This study combines the prevention of the domino effect with multi-objective optimization theory, which has a good and simple applicability for solving the considered problem and can obtain solutions in line with science and reality. It also adds the risk radius of the demand point based on the traditional siting model and proposes a model that combines the risk and distance to reduce the risk of accidents across the whole region. Finally, the model is applied to a chemical park in China for an arithmetic analysis to provide decision makers with a targeted reference base for the siting of an emergency center. The experimental results show that the NSGA-II algorithm can effectively solve the model of the emergency center in the chemical park and outperforms the results obtained from the CPLEX solution in terms of its cost and safety.