A new pedestrians' intuitionistic fuzzy risk exposure indicator and big data trajectories analytics on Spark-Hadoop ecosystem

Abstract Pedestrians are vulnerable users of the road system. The ability to meet pedestrian safety is an important component of efforts to prevent accidents in road traffic. The approach proposed in this paper aligns the theory of intuitionistic fuzzy numbers on pedestrian risk modeling goals. New indicators are proposed to model pedestrian exposure to hazards. The approach seems promising since it allows addressing behavioral psychology of pedestrians with intuitive methods based on fuzzy set theory. We develop a software system for this opportunity and we reuse simulation models of pedestrian developed in our previous work. Pedestrians’ trajectories are also stored in a Spark-Hadoop eco-system for analytical purposes and discovering patterns. Intuitionistic fuzzy set theory is very useful in providing a flexible model to elaborate uncertainty and vagueness involved in decision-making. The integration of behavioral factors related to the perception of space and the decision of the two antagonists are often missing or poorly considered. As such, the intuitionist approach allows connecting the two realities perceived by antagonists’ actors.