Emergency evacuation risk assessment method for educational buildings based on improved extreme learning machine

Abstract

In educational facility interiors, the risk of congestion and trampling among occupants during the evacuation process presents a significant safety concern. Therefore, assessing the risk of the evacuation process is of great practical and academic importance. To meet the requirements of rapid and timely risk assessment, this article proposes an emergency evacuation risk assessment model based on the Improved Extreme Learning Machine (ELM). The ELM with fast learning speed and good generalization performance is improved to form the Deep Extreme Learning Machine (DELM) and Kernel Based Extreme Learning Machine (KELM) models, and the Improved Seagull Optimization Algorithm (ISOA) was used to constitute the ISOA-DELM and ISOA-KELM models for training. Taking a university library as an example, the evaluation process of model data acquisition, training, and testing is analyzed and compared. The prediction accuracy of the ISOA-DELM and ISOA-KELM models proposed in this paper reached more than 92%. The results show that improved extreme learning machine models can enable an efficient and fast risk assessment.