Existing generation models have difficulty in directly generating high-resolution images from complex semantic labels. Thus, a Generative Adversarial Network based on Semantic Labels and Noise Prior (SLNP-GAN) was proposed. Firstly, the semantic labels (including information of shape, position and category) were directly used as input, the global generator was used to encode them, the coarse-grained global attributes were learned by combining the noise prior, and the low-resolution images were generated. Then, with the attention mechanism, the local refined generator was used to query the high-resolution sub-labels corresponding to the sub-regions of the low-resolution images, and the fine-grained information was obtained, the complex images with clear textures were thus generated. Finally, the improved Adam with Momentum (AMM) algorithm was introduced to optimize the adversarial training. The experimental results show that, compared with the existing method text2img, the proposed method has the Pixel Accuracy (PA) increased by 23.73% and 11.09% respectively on COCO_Stuff and the ADE20K datasets; in comparison with the Adam algorithm, the AMM algorithm doubles the convergence speed with much smaller loss amplitude. It proves that SLNP-GAN can efficiently obtain global features as well as local textures and generate fine-grained high-quality images.

The researches on the emergency management capability evaluation mostly focus on the evaluation methods, models and etc., pay less attention on the influences varying from the emergency type, lack of dynamic and low participation of scholars and the public. A new method of emergency management capability evaluation was put forward by combining Formal Concept Analysis (FCA) and Analytic Hierarchy Process (AHP) to figure out those problems. FCA was used to assign the first level index weights because of its outstanding ability on processing the data and extracting the rules, while AHP was used to take into the various factors. Then, Fuzzy Comprehensive Evaluation (FCE) was used to draw the evaluation results. As a result, the index weights had been varied which are constant in the traditional one. And the dynamic characteristic of the evaluation was also achieved. Finally, experiments show its feasibility and effectiveness.

The information transmission ability of command information system was analyzed from the angle of uncertainty. The command information system network was divided into physical layer and logical layer, and relationships between information transmission and the layers were expounded. The effective working probability of nodes and links, time delay, logical links and physical links were taken into account. The information quantity was used to measure the uncertainty of information transmission, and then the information transmission ability of command information system was educed. The experiment was designed using combat command relationship, and influences of these factors above on information transmission ability were reflected. The experimental results show that the evaluation method take the demand of connectivity, timeliness and correctness in information transmission into consideration.