This paper describes the integration of two Artificial intelligence technologies, Radial Basis Function networks with expert systems to construct a robust hybrid system. Constructing this proposed hybrid system software is to diagnose the error messages and give recommendations to repair the operating system (Windows 7) problems and troubleshoot the problems that can be repaired. The neural network has unique characteristics which it can complete the uncompleted data, the expert system can't deal with data that is incomplete, but using the neural network individually has some disadvantages which it can't gives explanations and recommendations to the problems. The expert system has the opposite characteristics of Neural Network which is the ability to explain and give recommendations by using the rules and the human expert in some conditions. Therefore, we have combined the two technologies. Software engineering process models is used for constructing the proposed software. The paper will explain the integration methods between the two technologies and which method is suitable to be used in the proposed hybrid system.
تاريخ النشر
01/03/2015
الناشر
International Journal of Engineering Research & Management Technology
ثابت حسان ثابت | Thabit Hassan Thabit | 17714