An Attribute Reduction Algorithms of Expert System Knowledge Acquisition
Knowledge acquisition is the bottleneck of construction expert system, to provide an accurate inference of knowledge is the key decision-making plan. This article use the rough sets theory, through the rough sets reduction eliminate redundant condition attribute, to achieve the streamlining of the knowledge library. First study the knowledge acquisition, in exposition knowledge hierarchical structure foundation, has given the conceptualization, formal, the knowledge library refinement and so on three knowledge acquisition; and then study attributes reduction algorithms, in the research sets difference and the attribute importance, the reduction algorithms inferential reasoning process's foundation, has given the attribute reduction algorithms six steps. Finally, according to the attributes reduction algorithms and the steps, to estimate the expert system to the function analytic method construction software cost, the composition technology complexity factor of 14 factors reduction. The results showed that the use of rough sets theory to reduce the attributes, can simplify the structure of complex systems, and can effectively maintain the knowledge library structure and performance.
Y. C. Ren et al., "An Attribute Reduction Algorithms of Expert System Knowledge Acquisition", Applied Mechanics and Materials, Vols. 48-49, pp. 187-191, 2011