Development of heatstroke prevention methods recommendation system

Abstract

Many accidents due to heatstroke have been reported, and the countermeasures are required. Although methods for measuring the risk level of heatstroke have been reported, not many users are able to take appropriate measures, and developing methods to support countermeasure implementation is expected. The purpose of this study is to develop a method for recommending measures against heatstroke according to user's condition. Biological and environmental data of healthy workers were measured with wearable sensors during work. Three models were developed: a model for predicting the risk of heatstroke, a model for recommending countermeasures according to the prediction, and a recommendation model for suggesting countermeasures from these two models at the appropriate timing. The results showed an 8% improvement in the time available for work with low risk compared to conditions managed by experts of managing heatstroke countermeasures. It suggests that this method may lead to reduce heatstroke incidents.