摘要: A simple intrusion detection system (IDS) with respect to perception of human experts is proposed. Its computational framework designed based on concepts theory perceptions (CTP) and mass assignment (MAT). CTP provides a representing handling using linguistic terms corresponding fuzzy sets. MAT that bias consisting in between observed intrusions through the consistency management sets probability distributions. For knowledge construction this IDS, only descriptions extracted from organization policies expected. inference refinement knowledge, support logic, truth functional logic for manipulating intervals, used.