Introduction to Expert Systems

Introduction to Expert Systems

This section is not a comprehensive consideration of Expert Systems but an introduction. We would take the basics of the following topics. I recommend you watch the video which includes a complete presentation on expert systems.

 

1. Formal Definition of Expert System

“An expert system has been defined as an intelligent computer program that makes use of knowledge and inference to solve problems that are difficult enough to require significant human expertise for their solution” – Prof. E. O. Nwachukwu (University of Port Harcourt, Nigeria).

Some notable expert system include: MYCIN which was by physicians to diagnose certain bacterial diseases. PROSPECTOR, used to predict where certain mineral deposits may be found. DENDRAL, used to hypothesize on the possible molecular structure of chemical compounds.

Another definition goes this way: “An expert system is a computer program that represents and reasons with knowledge of some specialist of particular fields with a view to solving problems or giving needed advice” – Jackson(1999)

To summarize, we can say that an expert system is a system the tries to behave like a human expert in some particular area.

 


 

2. Advantages of Expert System

I outline the following benefits of expert systems:

  • They are indefinitely reproducible
  • They normally operate at optimal or peak performance
  • They are based on availability, i.e. they are always available
  • They are based on convenience
  • They do not discriminate
  • They lack personality
  • They generate the best opinion possible

3. Characteristics of an Efficient Expert System

4. Process of Developing an Expert System

5. Building Blocks of an Expert System: They include

  • The Knowledge-base
  • Inference Engine
  • User Interface

6. Reasoning

7 Expert System Performance

8. Language Processing

9. Knowledge Engineering

What is an Expert System: Can be defined as a computer program that exhibits intelligence by applying knowledge, logic and inference procedure to solve problems. An expert system tends to mimic a real human expert. They rely on information that have been provided to arrive at a conclusion.