This study proposes three-second rule intelligence that simulates the human behavior selection. This method first calculates the appearance probability of an action candidate, and it selects an action that has appearance probability exceeds the preset threshold. As a previous study, there is a study that evaluates the environment using deep learning and makes an action selection, but it is essentially different from this selection method. there is no study that calculates the appearance probability of each action candidate and selects actions that exceed the preset threshold. And as far as I have investigated, this method is unique and innovative. By sequentially calculating and evaluating the time-series appearance probabilities of action candidates, it may be possible to give an empirical explanation for the "fluctuations" hidden in human behavior selection. This study applied this method to patient wait-and-see behavior of medical staff in radiation therapy, and by subdividing the factors to be observed and evaluating the appearance probability of action candidates by three-second rule intelligence, it clinically showed this method was effective. And this study succeeded in showing the feasibility of automating patient wait-and-see behavior of medical staff in radiation therapy.
View full abstract