Assessment of firefighter-training effectiveness in China based on human-factor parameters and machine learning.

Abstract

The emergency rescue ability of firefighters is particularly important in the event of major disasters or accidents. Therefore, an assessment of the firefighter-training effectiveness is necessary. This paper aims to achieve a scientific and effective assessment of the firefighter-training effectiveness in China. An assessment method based on human factor parameters and machine learning was proposed. The model is constructed by collecting the corresponding human factor parameters such as electrocardiographic signals, electroencephalographic signals, surface electromyographic signals, and photoplethysmographic signals through wireless sensors and using them as constraint indicators. For the problems of weak human factor parameters and high noise proportion, an improved flexible analytic wavelet transform algorithm is used to denoise and extract the corresponding feature values. To overcome the limitations of traditional assessment methods, improved machine learning algorithms are used to comprehensively assess the training effectiveness of firefighters and provide targeted training suggestions. The effectiveness of this study's evaluation method is verified by comparing it with the expert scoring method and considering firefighters from a special fire station in Xhongmen, Daxing District, Beijing, as an example. This study can effectively guide the scientific training of firefighters and the method is more objective and accurate than the traditional method.