Abstract
First generation expert systems used shallow knowledge based on heuristic information to solve a diagnostic problem. This approach has many disadvantages, which can be avoided with the use of deep knowledge. Diagnostic reasoning based on deep knowledge is called model based diagnoses. Recently the use of qualitative modeling in relation to deep knowledge in expert systems has become increasingly important. Model based reasoning in our diagnostic system is performed with a simulation process of a qualitative system model. The qualitative system model need not to be specially adapted for use in a diagnostic domain. It only needs to simulate system behavior expressed by normal or abnormal functioning of its components. The proposed architecture is not complex, is very efficient and simply takes into account a previous diagnostic result to obtain a new one from additional observation measurement (medical tests or examinations) of the system.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have