Evidence theory based knowledge representation
R. Mohamed, Junzo Watada · 2011
Knowledge is presented in various ways such as semantic network. Hierarchical representation is widely used as one of the well-known methods in knowledge representation. Knowledge representation plays a pivotal role in dealing with knowledge, facts, procedures and meanings for solving problems. The knowledge representation is a crucial task in handling problems, and it tends to fail if we do not understand well the problem or situation to model. The aim of this paper is to propose a logical hierarchical structure for knowledge representation in semantic network. We place stress on modeling knowledge from semantic network perspective during analysis phase. This method is known as evidence-based semantic network or ESN. "Scene labeling" is used as an example for the proposed method. The results show the proposed method is easier to understand than original semantic network.