Expert systems frame-based

In these frames all specific columns that are relevant for the reasoning process of the expert system can be described in a structured and comprehensive way. The frame-based and rule-based knowledge representation are both required to represent expertise in a natural way. Therefore, in most expert systems a combination of rule-based and frame-based knowledge representation is used. The rule base together with the factual and descriptive knowledge by means, of e.g., frames constitute the knowledge base of the expert system. 

The advantage of these systems over the procedural, relational approach is that the experts often do not have all the rules of thumb for each and every situation. A rule-based or frame-based approach will enable the developer to build a system to replicate the state of knowledge as it exists, with an inherent ease of enhancement by addition or modification of the rules. However, the number of rules needed to enable the system to perform these tasks in a generic manner for any number of site conditions will be inordinately large. Further, once such a system is designed, it is not always easy to resolve subsequent conflicts among rules that are added to the system. 

To summarize, a rule-based or frame-based system could provide a reasonably flexible tool to the Superfund Program, which may at times need to specify and utilize small modifications of a standard, such as the CLP QC criteria. Such a system could select a CLP method and its associated QC criteria based on the inputs (Section 3.1), modify the QC limits for certain analytes and/or samples, and specify modifications in the rules of thumb used for validation. However, the potential for an inordinately large number of rules, this apparently simple solution has the practical drawback of embedding conflicts among the rules which will be difficult to debug and modify. This is contrary to the way in which experts think and consequently, this scheme is deemed to be unsuitable. 

The symbolic process consists of production rules, semantic networks, frames, and objects. Systems built on this principle are called expert systems and are useful for reasoning about process state (temperature, pressure, etc.) and process structures. The subsymbolic process is based on a model of biological neural system. Systems modeled on this principle are called artificial neural networks (ANNs) and are useful for reasoning about process trends and the complex causal interaction of process variables and states. 

Object-oriented systems store information in frames and slots which contain facts, pointers to other objects, or rules. This combination allows the objects to be interrelated to each other in different ways. In objected-oriented systems, slots may inherit information from other objects rather than creating duplicative objects. The structure of object-oriented expert systems more resembles that of hypertext (discussed above) than rule-based systems. Object-oriented systems contain more declarative knowledge than rule-based systems. 

Expert system tools are now available that can deEne and depict the knowledge of an expert. These are known as frame-based systems, which deEne frames or schemas and instantiate those with information that enable them to inherit information from other frames. These systems are practical replications of schema theory. They enable you define the knowledge of the expert as well as converting that knowledge into a production system of if-then rules. Rather than instantiating the frames with information, instantiate the frames with the addresses of the nodes in the hypeitext. That would, in effect, m the expert s knowledge directly onto the hypertext. It would also be important to assess learner s cognitive stractures to assess the extent to which they reflected the expert s. 

---