Summary:
Summary Expert systems are software that uses human expertise for problem solving as a knowledge base, to clarify uncertainties where normally one or more human experts would be consulted. Expert Systems are found in specific problem domain and are generally related to AI (Artificial Intelligence). There are various methods that can be used to simulate the performance of the expert: however all Expert systems have a common structure which is
Common structure:
Common structure The creation of a knowledge base which uses some form of knowledge representation structure to capture the knowledge of the SME (Subject Matter Expert). A process of gathering and codifying the knowledge from the SME according to the structure , which is called knowledge engineering. Once the system is developed, it is placed alongside real world problem solving situations as the human SME, mostly as an aid to the heuman worker or as an supplement to some information system. They may or may not have learning components.
Advantages and Disadvantages:
Advantages and Disadvantages Advantages: Compared to traditional programming techniques, expert system approaches to data provides flexibility/modifiability, with the ability to model rules as data rather than codes. It allows organizations to adapt more readily to changing needs. In practice, modern expert system technology is employed alongside traditional programming techniques to get the best out of both of them . Disadvantages: The GIGO (Garbage In, Garbage Out) phenomenon: A system that uses expert system technology provides no guarantee about the quality of the rules on which it operates. One challenge in expert system design is to get the system to recognize its own limits in knowledge. An expert system or rule based approach will not work for all problems and considerable knowledge is needed so it will not misapply the systems. Ease of rule creation and modification can be double edged. A system can be sabotaged by inexperienced users who will add worthless rules, or rules that oppose with existing rules within the system. Failure in the system usually include the absence of faculties for system audit, detection of possible conflict and rule lifecycle management