Multi-attribute group decision-making plays an important role in modern politics, economy, culture, and life. The multi-attribute decision-making process is limited by policymakers’ experience, and knowledge of uncertainty factors, such as weight information, is difficult to directly provide. Moreover, many types of complex rescue information are difficult to accurately describe in numerical terms, which reduces the accuracy and objectivity of the decision results, although the fuzzy theory to solve these problems provides a suitable tool. In order to solve the above problems, a new VIKOR decision method based on trapezoidal fuzzy numbers (TFNs) is proposed. Firstly, the expert weight is calculated by the distance measurement method, the criterion weight is calculated by the deviation maximization method, and then the VIKOR method is used to solve the problem. In order to verify the effectiveness and feasibility of this method, it is applied to the emergency alternative selection problem. Finally, the symmetry analysis of the method is carried out by contrast experiment and sensitivity test.
When disasters occur, people use social media to post in real time, which includes rich text and visual images. Relevant authorities can use this information to make emergency decisions and public opinion analysis quickly. However, the high complexity of multimodal deep learning models cannot meet the high timeliness requirements of disaster analysis. In addition, social media multimodal datasets for disaster detection are often scarce, and simple features are not sufficient to adequately provide usable information for analysis models. To mitigate these concerns, this paper introduces a model for low-level fusion called the Multilayer Feature Low-Level Fusion Model (MLLMF). The model uses transfer learning pre-trained models to extract text features from different hidden layers instead of traditional single-layer text features, and introduces gate attention units (GAUs) to enhance each modal feature to fully extract the intrinsic information of each single modality so that the information of small sample data can be utilized to the maximum. Moreover, to tackle the challenge posed by the high complexity of multimodal models, this paper uses low-rank tensor for multimodal fusion of text and images. With low model complexity, not only the unique information of a single modality is retained, but also the correlation between different modal elements is exploited to achieve a balance between low model complexity and high accuracy. Experiments show that the method not only improves processing efficiency but also achieves higher accuracy compared to unimodal and strong multimodal baseline methods, making it more suitable for crisis-related tasks.
16 February 2026 in International Journal of Machine Learning and Cybernetics