An appropriate and safe behavior for exiting a facility is key to reducing injuries and increasing survival when facing an emergency evacuation in a building. Knowledge on the best evacuation practice is commonly delivered by traditional training approaches such as videos, posters, or evacuation drills, but they may become ineffective in terms of knowledge acquisition and retention. Serious games (SGs) are an innovative approach devoted to training and educating people in a gaming environment. Recently, increasing attention has been paid to immersive virtual reality (IVR)-based SGs for evacuation knowledge delivery and behavior assessment because they are highly engaging and promote greater cognitive learning.This paper aims to understand the development and implementation of IVR SGs in the context of building evacuation training and research, applied to various indoor emergencies such as fire and earthquake. Thus, a conceptual framework for effective design and implementation through the systematic literature review method was developed. As a result, this framework integrates critical aspects and provides connections between them, including pedagogical and behavioral impacts, gaming environment development, and outcome and participation experience measures.

No abstract

No abstract

Discriminative feature extraction and rolling element bearing failure diagnostics are very important to ensure the reliability of rotating machines. Therefore, in this paper, we propose multi-scale wavelet Shannon entropy as a discriminative fault feature to improve the diagnosis accuracy of bearing fault under variable work conditions. To compute the multi-scale wavelet entropy, we consider integrating stationary wavelet packet transform with both dispersion (SWPDE) and permutation (SWPPE) entropies. The multi-scale entropy features extracted by our proposed methods are then passed on to the kernel extreme learning machine (KELM) classifier to diagnose bearing failure types with different severities. In the end, both the SWPDE–KELM and the SWPPE–KELM methods are evaluated on two bearing vibration signal databases. We compare these two feature extraction methods to a recently proposed method called stationary wavelet packet singular value entropy (SWPSVE). Based on our results, we can say that the diagnosis accuracy obtained by the SWPDE–KELM method is slightly better than the SWPPE–KELM method and they both significantly outperform the SWPSVE–KELM method.

Children are vulnerable in earthquakes, but they are also essential to foster earthquake‐resilient communities. It is critical to enhance the preparedness of children against earthquakes through effective education and training. Immersive virtual reality (IVR) and serious games (SGs) are innovative digital technologies that enable realistic and engaging training environments. However, little research has been made on the applications of IVR SGs for earthquake training targeting children. In order to fill this gap, this paper presents an IVR SG training system based on a problem‐based gaming framework. Three instructional mechanisms within the training system, namely prior instruction, immediate feedback, and post‐game assessment, were investigated to promote learning through effective reflection. A controlled experiment involving 125 secondary school students aged from 11 to 15 years old was undertaken, using leaflets as a traditional training approach for the control group and the IVR SG training system as the main intervention. Results revealed that the IVR SG training system with post‐game assessment was the most effective way to train children, with greater knowledge acquisition and self‐efficacy improvement observed. Possible improvements, such as increasing the time for reflection and differentiating the stimulation between positive and negative feedback, are suggested for further research.