In this paper we propose an approach to build a decision support system that can help emergency planners and responders to detect and manage emergency situations. The internal mechanism of the system is independent from the treated application. Therefore, we think the system may be used or adapted easily to different case studies. We focus here on a first step in the decision-support process which concerns the modeling of information issued from the perceived environment and their representation dynamically using a multiagent system. This modeling was applied on the RoboCupRescue Simulation System. An implementation and some results are presented here.
Multi-Agent Systems in Emergency Departments: Validation Study on a ED Digital Twin
Constructor University（Constructor大学）；Fraunhofer Institute for Digital Medicine MEVIS（弗劳恩霍夫数字医学研究所MEVIS）；Asklepios Kliniken Hamburg GmbH（阿斯克列庇斯汉堡医院有限公司）
School of Computer and Artificial Intelligence, Zhengzhou University（郑州大学计算机与人工智能学院）；Engineering Research Center of Intelligent Swarm Systems, Ministry of Education（教育部智能集群系统工程研究中心）；National Supercomputing Center in Zhengzhou（国家超级计算郑州中心）；Henan Research Center for Large Model Technology and New Quality Software Engineering（河南省大模型技术与新质软件工程研究中心）
本文提出MAFIG框架，通过多智能体生成局部正式指令以应对调度系统紧急情况，采用span-focused loss-driven local distillation机制提升决策效率，实验结果显示在港口、仓储和甲板调度数据集上成功率高且处理速度快。
Emergency Caching: Coded Caching-based Reliable Map Transmission in Emergency Networks
School of Computer Science, Beijing University of Posts and Telecommunications（北京邮电大学计算机学院）；School of Electronic Engineering, Beijing University of Posts and Telecommunications（北京邮电大学电子工程学院）；Frontier Research Center, Peng Cheng Laboratory（鹏城实验室前沿研究中心）
