EXPERT SYSTEM


Kontributor : Annisa Roudlotul Jannah

What is Expert System?

An expert system is a system that seeks to adopt human knowledge to computers, so that computers can solve problems as is usually done by experts, and a good expert system is designed to solve a particular problem by imitating the work of experts (Kusumadewi, 2003: 109). Experts referred to here are people who have special skills that can solve problems that cannot be solved by ordinary people. For example doctors, mechanics, psychologists, and others.

What is the history of Expert System?

The expert system was first developed by the AI community in the mid 1960s. The expert system that first emerged was the General Purpose Problem Solver (GPS) developed by Newel & Simon (Turban, 1995).

Expert system itself is a software package or computer program package that is intended as a provider of advice and help tools in solving problems in certain areas of specialization such as science, engineering, mathematics, medicine, education and so on. Expert systems are a subset of Artificial Intelligence (Arhami, 2005).


The transfer of expertise from experts to electronic media such as computers is then transferred again to people who are not experts, is the main goal of the expert system. This process requires 4 activities, namely:
  1. Additional knowledge (from experts or other sources),
  2. Knowledge representation (to computers),
  3. Knowledge inference, and
  4. Transfer of knowledge to the user.

Knowledge stored on a computer is called a knowledge base, namely: facts and procedures (usually rules). One feature that must be possessed by expert systems is the ability to reason. If the skills have been stored as a knowledge base and there are programs that are able to access the database, then the computer must be programmed to make inferences. This inference process is packaged in the form of an inference engine. And each sub-system has the nature of the system to run a certain system function and affect the overall system process.

The Advantages of Expert System:

  1. Allows ordinary people to do the work of experts
  2. Simplify work and increase work efficiency
  3. Can do the process repeatedly automatically
  4. Save the knowledge and expertise of experts
  5. Increase output and productivity
  6. Improve quality
  7. Able to take and preserve the expertise of experts
  8. Able to operate in hazardous environments
  9. Having the ability to access knowledge
  10. Having reliability
  11. Increase the capabilities of the computer system
  12. Having the ability to work with information that is incomplete and contains uncertainty
  13. As a complementary medium in training
  14. Increase capability in solving problems
  15. Save time in decision making

The Weaknesses of Expert System :

  1. The costs required to make and maintain it are very expensive.
  2. Difficult to develop. This is closely related to the availability of experts in their fields. Expert systems can only handle consistent knowledge. Expert systems are designed with rules whose results are certain and consistent according to the grooves in the tree diagram. For knowledge that changes rapidly from time to time, the knowledge base in the expert system must always be changed, which is certainly quite troublesome.
  3. The expert system is not 100% true. Expert systems cannot handle things that are judgment (Consideration or intuition). The expert system gives definite results, so that the final decision making decision if it involves policy and institution is still in the hands of management.

Applied of Expert System

Basically an expert system is applied to support problem solving activities. Some of the problem solving activities referred to are (Lestari, 2012):

  • Interpretation

Make conclusions or descriptions of a set of raw data. Decision making from the results of observations, including speech recognition, image analysis, signal interpretation, etc.

  • Prediction

Projecting possible consequences of certain situations. Examples: demographic predictions, economic predictions, etc.

  • Diagnosis

Determine the cause of malfunction in complex situations based on symptoms observed by medical, electronic, mechanical, etc.

  • Design

Determine the configuration of system components that match certain performance goals that meet certain constraints. Example: designing circuit layout, buildings.

  • Planning

Plan a series of actions that will achieve a number of objectives with certain initial conditions. Examples: financial, military, etc. planning

  • Monitoring

Comparing observations with expected conditions. Example: computer aided monitoring system.

  • Debugging

Determine and interpret ways to overcome malfunction. Example: prescribe medication for failure.

  • Instructions

Detect and correct deficiencies in understanding the subject domain. Example: do instructions for diagnosis and debugging.

  • Control

Set the behavior of a complex environment. Example: control the interpretation, prediction, improvement and monitoring of system behavior.

Popular posts

Sistem informasi global dan penerapannya oleh perusahaan multinasional

Intelligent agent

Apa itu budaya global?