INTRODUCTION TO EXPERT SYSTEM

INTRODUCTION

Artificial Intelligence has many application areas. One of the famous areas is an expert system. It is a type of artificial intelligence (AI) program that uses knowledge and reasoning techniques to solve complex problems that would normally require human expertise. An expert is a person who possesses specialized skills and knowledge and has the ability to apply that knowledge to solve a problem efficiently. Similarly, the expert system is software based on specific concepts of AI that act as an expert in a particular field.

Expert systems are designed to replicate the decision-making process of a human expert in a particular domain. The system is built by capturing the knowledge of an expert in a specific field and organizing it in a way that a computer program can use to reason about specific problems.

HISTORY OF EXPERT SYSTEM

The concept of expert systems originated in the 1960s and 1970s, when researchers began exploring the idea of creating computer programs that could replicate the problem-solving abilities of human experts.

The first expert system was developed in 1965 by Edward Feigenbaum and Joshua Lederberg along with his students at Stanford University. The system, called DENDRAL, was designed to solve problems in the field of organic chemistry by analyzing mass spectrometry data.

In the 1970s and 1980s, the concept become popular and were used in a variety of applications. One of the most famous examples was MYCIN, an expert system developed in the early 1970s at Stanford University to diagnose bacterial infections and recommend treatment.

In 1980, an expert system called as XCON was developed at CMU for Digital Equipment Corporation. This expert system proved to be very useful as it was saving the company 40 million dollars annually by 1986. Many companies like Symbolic and LISP machines and Software Companies such as IntelliCorp and AION supported the expert system concept.

During this time, there was a great deal of interest in expert systems, and many companies and organizations began developing their own systems for various applications. However, the limitations of the technology at the time, such as the difficulty of acquiring and organizing large amounts of knowledge and the lack of computing power, limited the widespread adoption of expert systems.

With the advent of more powerful computers and the development of new knowledge representation and reasoning techniques, expert systems continued to evolve in the 1990s and beyond. While they are no longer as popular as they were in the past, expert systems are still used in some applications today, such as in medical diagnosis and financial analysis.

Components of Expert System

An expert system typically consists of the following components:

  1. Knowledge Base: The first part of human expertise is a long term memory of facts, structure and rules that represent expert knowledge about the domain of expertise. This similar structure in an expert system is called as knowledge base.This is the repository of knowledge, information, and data that the expert system uses to draw conclusions and make decisions. The knowledge base is typically composed of rules, facts, and heuristics that are relevant to the specific domain of the expert system. Rules are in the form IF condition and THEN action.The knowledge base differs from a traditional database. A database is a collection of related or unrelated facts while  the knowledge base not only includes the facts about a particular subject but also the instruction about how the facts are related.

  2. Knowledge Engineer : To create knowledge base special designers called knowledge engineers are required with the human expert to extract and structure the facts rules and knowledge.

  3. Knowledge Editor: The editor is used by the developer to create new rules or modify old rules to knowledge base. These editors have ability to perform the consistency tests for the newly created rules or to add missing conditions etc.

  4. Knowledge Acquisition/Representation Module: This is the component of the expert system that is used to acquire new knowledge and update the knowledge base. It may include tools for extracting knowledge from human experts, analyzing data, and discovering new patterns and relationships in the data. This system checks for the consistency of data, redundant information, or conflicting information when the knowledge is updated or entered.

  5. Inference Engine: This is the most important part of the expert system that carries out the reasoning function. This component of the expert system is responsible for drawing conclusions and making decisions based on the knowledge base. The inference engine is a reusable program that allows the computer to apply the facts and rules to solve a problem. The process of combining the facts and rules to deduce new facts is called inference. The purpose of the expert system is to develop the solution for the problem and for this the inference engine performs the search in an effective manner using various search strategies.It uses a variety of reasoning methods, such as forward chaining and backward chaining, to infer new knowledge from existing knowledge. The forward and backward chaining can be shown as:

     

  6. User Interface: This is the interface through which the user interacts with the expert system. The user interface may include text-based or graphical interfaces, as well as natural language interfaces that allow the user to ask questions and receive answers in natural language.

  7. Explanation Module: This component of the expert system is responsible for explaining the reasoning and decision-making process used by the system. It may provide the user with a detailed explanation of how the system arrived at a particular decision or recommendation.

 

Application Areas of Expert System

Expert systems have been used in a variety of fields, including medicine, finance, and engineering, to provide assistance with tasks such as diagnosis, decision-making, and troubleshooting. They can be used to reduce errors, increase efficiency, and improve the accuracy of decision-making.