Understanding Expert System. Expert systems are one of the fields of artificial intelligence engineering that is quite in demand because of their application in various fields, both science and business, which have proven to be very helpful in making decisions and are very broad in their application. An expert system is a computer system design to be able to reason like an expert in a particular area of expertise
Expert system characteristics
The characteristics of an expert system are as follows:
Limited to certain skill domains.
Can provide reasoning for data that is uncertain.
Can articulate the set of reasons it gives in an understandable way.
Based on certain rules / regulations.
Designed to develop incrementally.
His family is recommended.
Expert system components divided into four parts, namely:
Knowledge Base (Knowledge Base) Knowledge Base is the core of an expert system program because the knowledge base is a technology presentation of knowledge or knowledge representation. The knowledge base is a knowledge database consisting of a collection of objects and their rules and attributes (characteristics or characteristics). represent wings and lay eggs then animal species of birds.
Working Memory (Database or Working Memory) Working memory is a part that contains all the facts, both the initial facts when the system was operating and the facts at the time when the conclusion made while the expert system operating, the database was in working memory.
Also Read: Remembering Steve Jobs
Inference Engine is a part that provides a function mechanism for thinking and system reasoning patterns used by an expert.
· This mechanism will analyze a specific problem and will then look for the best answer or conclusion.
· This engine will start tracking by matching the rules in the knowledge base with the facts in the database.
Two Inference techniques, namely:
Backward Chaining (backward tracking)
Through his reasoning, from a set of hypotheses to supporting facts, the tracking process goes backwards, starting with determining the conclusions to be sought and then the facts that build the conclusion or a Goal Orientation.
Forward Chaining (Forward tracking)
Lastly Forward Chaining is the opposite of Backward Chaining, which is starting from the data set to the conclusion. A case conclusion is build on known facts or data driven.