article · Procedia Computer Science
Evacuating people from a burning building is often complicated by human behaviour, panic, crowd size, and architectural layouts. In an emergency, fear and hazardous conditions frequently cause severe disorganisation, yet existing evacuation models often fail to establish clear parameters for practical evaluation, frequently relying solely on the final count of survivors. To address this limitation, an intelligent agent-based model simulates the movement and egress of crowds during a fire. The system incorporates four specific parameters to enable practical performance assessment. Evaluated through a simulation case study reflecting the structural layout of supermarkets in Kinshasa, the framework demonstrates broad adaptability. Its generalised design allows implementation across diverse types of commercial buildings without requiring major alterations to the underlying architecture.
Understanding how crowds behave during structural fires helps safety planners design safer spaces and robust emergency protocols. Because panic and high crowd density can trigger severe chaos, relying merely on final survival counts is inadequate. Providing a practical simulation tool based on defined evaluation metrics enables better planning and risk management for emergency egress in crowded public and commercial venues.
The model could support building safety managers, architectural consultants, and emergency planners seeking to test evacuation strategies for commercial facilities. Currently at an early, simulated stage of applied research, it has been demonstrated on supermarket layouts. Moving towards commercialisation would require developing the model into user-ready design software or safety audit tools for regulatory compliance and venue risk assessments.
AI-generated from the published abstract. Always read the original work before citing.
The evacuation of people from a building on fire is a task which can prove to be very difficult, in particular because of the influence of human behavior, but also of the type of people or the evacuation place configuration. Thus, it is crucial to think on how to organize the evacuation upstream for a situation of emergency can give rise disorganization, on one hand because of panic which grips evacuees, and on the other end because of the large quantity of evacuees in dangerous conditions. These recent years, several fire evacuation models have been proposed. Unfortunately, most of these models do not clearly define the parameters to be considered for their effective evaluations. These models consider, more generally, the number of survivors as a key parameter of evaluation. The purpose of this paper is to propose an intelligent Agent-Based Model enabling the modelling and simulation of evacuation of people from a building on fire. Our proposed model is based on four parameters that allow her practical evaluation. A case study of simulation is carried out in a building having the general configuration of Kinshasa supermarkets. This model is general enough for it to be implemented in several types of commercial buildings without major changes.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.procs.2018.04.006
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
