An Intelligent Method for Knowledge Derived from Limited Data
Fengming M. Chang · 2006
Decisions are often made under limited information in the real world. Although many approaches have been researched in the field of artificial intelligence, most of them rely on large amounts of data to make a knowledge base. This study presents an intelligent method to improve accuracy of knowledge derived from limited data in the early stages of a system. This method first proposes a concept of transforming crisp data into continuous to gain new virtual examples. Fuzzy theory and fuzzy neural network technology are applied. A data domain external expansion approach is introduced in the proposed method. Furthermore, three cases applying the proposed method are presented. The results indicate that the proposed method can indeed improve the accuracy of the system knowledge.