Λεπτομέρειες βιβλιογραφικής εγγραφής
| Τίτλος: |
A situation-aware emergency evacuation (SAEE) model using multi-agent-based simulation for crisis management after earthquake warning. |
| Συγγραφείς: |
Keykhaei, Mahdi, Samany, Najmeh Neysani, Jelokhani-Niaraki, Mohammadreza, Zlatanova, Sisi |
| Πηγή: |
Geo-Spatial Information Science; Dec2024, Vol. 27 Issue 6, p1800-1823, 24p |
| Θεματικοί όροι: |
Long short-term memory, Situational awareness, Travel time (Traffic engineering), Rescue work, Fuzzy logic, Civilian evacuation, Crisis management |
| Περίληψη: |
Earthquake is a disastrous natural hazard that threatens numerous cities worldwide. The interval between the foreshock and the main event can sometimes last several minutes. Meanwhile, crowd emergency evacuation and finding shelter are vital for search and rescue managers. At the same time, many unpredicted challenges, such as the sudden increase in travel demand, shifts in public behavior, and the change in the regular transport supply, may arise due to evacuation conditions, which lead to different situations. This paper aims to introduce an approach for quick decision-making and timely evacuation response required by establishing a situation-aware system to minimize these risks and ensure the success of the evacuation plans, to support and predict current and future actions within the dynamic space of the crisis. The main contribution is innovating a Situation-Aware Emergency Evacuation (SAEE) model to enable crisis managers and evacuees to make the right decisions by providing timely and reliable information about the situation. This method is utilized in two situations: designing the emergency evacuation plan and finding the shortest/safest routes to reduce travel time for evacuees. Therefore, a hybrid approach is introduced, which involves a Fuzzy Inference System (FIS) and Deep Long Short-Term Memory (DLSTM) algorithm to identify, infer, and extract the existing situation at different levels (e.g. people, vehicles, and surroundings) after a foreshock using multi-agent-based simulation. The method proposed was simulated in the traffic network of District 6 of Tehran, the capital of Iran. The model results show that the evacuees' spatial knowledge and perception, as well as awareness of the situation of other agents and their surroundings, led to a significant (40%) reduction in the complete evacuation time. This time is considered the most pivotal factor in saving human lives and their arrival in safer areas. The role of situation awareness systems and increasing human cognition and perception can significantly help in this matter. [ABSTRACT FROM AUTHOR] |
|
Copyright of Geo-Spatial Information Science is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Βάση Δεδομένων: |
Complementary Index |