Construction of emergency management model for university emergencies based on fuzzy set theory

Abstract

Universities are dynamic places where students, faculty and staff come together for a variety of activities every day. Previous studies highlight the need for strong emergency management systems to help deal with any natural disaster, health crisis or security threat that may take place on campus and cause disruption. Even with the complexity and unpredictability of emergencies, models are still not effectively able to respond to changing campus threats and emergency scenarios. With the help of Fuzzy Set Theory, the study offers the Fuzzy Adaptive Emergency Response Model (FAERM), which aims to tackle such issues. The FAERM uses fuzzy logic principles to analyze ambiguous and imprecise information such as risk levels, resources and priorities that change over time. Emergencies are classified and decision making is accomplished in real-time through a fuzzy logic system that mimics the cognitive process of human experts in assessing the level of urgency, allocating limited resources and prioritizing actions in the face of uncertainty. The fuzzy inference output classifies emergencies as Very Low, Low, Moderate, High and Critical Priority. These linguistic categories categorize and determine allocation of resources and the strategies of response to each scenario depending on the degree of severity and urgency. The effectiveness of the model has been tested against simulated scenarios, such as fire, extreme weather conditions and medical emergencies. The proposed framework of FAERM is well suited for the emergency management activities. Experimental tests demonstrate that the model can achieve a classification accuracy of 93%, reduce response time by 20%, and obtain a closeness coefficient of 0.90 for the prioritization of emergencies. The findings show that FAERM is successful in enhancing the accuracy of the decisions made and the efficiency of the allocation of resources in emergency situations where the conditions are dynamic and uncertain, relative to baseline methods. The results confirmed the robustness and usefulness of the proposed framework for university emergency situations.