出版社:Academy & Industry Research Collaboration Center (AIRCC)
摘要:The classification by inductive learning finds its originality in the fact that humans often use itto resolve and to handle very complex situations in their daily lives. However, the induction inhumans is often approximate rather than exact. Indeed, the human brain is able to handleimprecise, vague, uncertain and incomplete information. Also, the human brain is able to learnand to operate in a context where uncertainty management is indispensable. In this paper, wepropose a Boolean model of fuzzy reasoning for indexing the monitoring sub-plans, based oncharacteristics of the classification by inductive learning. Several competing motivations haveled us to define a Boolean model for CBR knowledge base systems. Indeed, we have not onlydesired experiment with a new approach to indexing of cases by fuzzy decision tree, but we alsowanted to improve modelling of the vague and uncertain of the natural language concepts,optimize response time and the storage complexity.