Expert System

Expert systems (ES) are one of the prominent research domains of AI. It is introduced by the researchers at Stanford University, Computer Science Department. These systems are the computer applications developed to solve complex problems in a particular domain, just like human experts.Expert systems are ideal when it is necessary for an individual to select the best alternative from a long list of choices. Based on the criteria supplied to it, the expert system can choose the best option. For example, there are expert systems that will help you to select one of the many places to invest your money based on your own financial conditions, goals, and personality traits.

Let's Look at the diffrence between conventional Database System and Expert System

Diffrence between DB and ES System

Conventional Database Systems	Expert Systems
DB system is composed of Database, DB repository and Database Management System (DBMS)	This system is comprised of knowledge base, inference engine and user interface.
Data is entered into DB via DBMS.	Data is fed into knowledge base through UI.
No component in DB to make decisions.	Inference Engine makes decisions on base of knowledge fed into the knowledge base
It accepts only textual Data.	It accepts all kind of data i.e. textual, pictorial or complex data patterns from nature.
It has no AI involvment.	The system involves some sort of AI functionality.

Features of Expert System

Each expert system has its own particular characteristics; there are several features common to many expert systems. These are:

• “The program should be useful.” An expert system should be developed to meet a specific need, one for which it is recognized that assistance is needed.
• “The program should be usable.” ” An expert system should be designed so that even a novice computer user finds it easy to use.
• “The program should be educational when appropriate.” An expert system may be used by non-experts, who should be able to increase their own expertise by using the system.
• “The program should be able to explain its advice.” ” An expert system should be able to explain the “reasoning” process that led it to its conclusions, to allow you to decide whether to accept the system’s recommendation.
• “The program should be able to respond to simple questions.” Because people with different levels of knowledge may use the system. An expert system should be able to answer questions about points that may not be clear to all users.
• The Program should be able to learn new knowledge. Not only should an expert system be able to respond to your questions, it also should be able to ask questions to gain additional information.
• The program’s knowledge should be easily modified. It is important that you be able to revise the knowledge base of an expert system easily to correct errors or add new information.

Applications of ExpertSystem

• Engineering and Manufacturing
ES in engineering and manufacturing process can provide greatest assistance for operational workers while performing and dealing the critical and important tasks. Furthermore, ES produces more accurate results than human expert and in short time.

• Medical
In many countries people have wait for longer periods before diesease has been diagnosed by specialist and when the treatment is stated, it may already late and patient could be suffered for the whole life. Computer technologies such as expert system can solve the above problem with the aim to conduct the earlier diagnosis diseases for patients, identify disease symptom and provide immediate accurate response to save patient life.

• Management
In large organization or companies, there are managers, accountant, financial analysis, consultant, strategic planners etc. These management people might have difficulties on budget, time constraint, planning and other management support and contributions. ES can provide assistance to the management of a company to investigate different aspects of organization’s problems.
• Military
ES can support in the command and control process ability by a military commander due to expensive and complexity real situation in the military program training. The potential of expert system can solve many problems for the military such as a device tool to find bombs and mines, and search different radar.
• Education and Training
Most of teaching courses provide today are inn conventional method where there is less or no interaction in the learning process between teachers and pupils. Teachers would teach by chalk-talk method and pupils were just listening and takes note. Therefore, an ES may very useful to facilitate teaching and learning process. Moreover, expert system can act as intelligent tutor and perhaps tutor and students are unnecessary anymore to meet in the same tutorial classroom.

Functionality of an Expert System

An ES includes following main components:

1. Knowledge Base:
It contains the knowledge related to specific domain.
What is Knowledge? The data is collection of facts. The information is organized as data and facts about the task domain. Data, information, and past experience combined together are termed as knowledge.
2. Inference Engine:
It acquires and manipulates the knowledge to reach to a solution from multiple solutions.
3. User Interface:
It provides interaction between user and ES.