Expert System


What is Expert System (ES) ?


Meaning of Expert System


An expert system is software consisting of a 'knowledge base' of facts and relationships and is able to draw conclusions based on such knowledge base. In other words, an expert system is a computer based information system, where knowledge is represented in data. The processing of such knowledge is controlled by computer programs.

It can also be said that an expert system is a computer application, which even a non-expert can use and come up with results. This means that an expert system is equivalent to the expert of that problem domain. The expert system acts as an excellent guide towards performance of ill-structured tasks. Hence, expert system can be considered as a Decision Support System (DSS), having unique features of knowledge base, data and decision rules. which help ES to act as an expert.

Due to its wide applicability in business decisions. the expert system is also referred to as Business Expert System (BES). It is a knowledge-based information system and to work as an expert, it relies on its knowledge about a specific and complex application area.

Definition of Expert System


According to Professor E. Feigenbaum :
“An Expert System is an intelligent computer program that uses knowledge and inference procedures to solve problems those are difficult enough to significant human expertise for their solution. Knowledge necessary to perform at such a level, plus require the inference procedures used, can be thought of as a model of the expertise of the best practitioners of the field."

According to Gaschnig, Reboh and Reiter :
"Expert systems are interactive computer programs incorporating judgment, rules of thumb, intuition and other expertise to provide knowledgeable advice about a variety of tasks."

Features of Expert System 


The important features of expert systems / Characteristics of expert system are as follows :

1) High-Level Expertise : 
The most helpful feature of the expert system is the high-level expertise which it gives while solving any problem. It offers best thinking, just like top experts and end up with imaginative, accurate and efficient solutions to the problems.

2) Predictive Modelling Power : 
Predictive modelling power is another significant feature of an expert system as it helps the user to evaluate the possible effects of changes in facts or data. It also helps to understand the relationship of changes to the outcome. This is possible because the system acts as a model of problem-solving, which provides answers to given problems and also illustrates changes occurring due to new situations.

3) Institutional Memory : 
An expert system is a corpus of knowledge (providing expertise to the system) and thus acts as institutional memory. This implies that even when important people leave the organisation, their expertise remains intact. This feature is essential in business and mainly in military and government that has rapid turnovers and frequent personnel transfers.

4) Ability to Provide a Training Facility : 
Expert system has the ability to train important personnel and staff members. It can provide such training because of its vast knowledge base and ability to explain.

Structure of Expert System 


Figure shows that expert system in MIS have two environments :

1) Development Environment : 
An ES builder uses the development environment to build components and place the knowledge inside the knowledge base.

2) Consultation (runtime) Environment : 
This is used by a novice to attain expert knowledge and advice.
As the system gets completed, these environments may be separated.

Components of Expert System 


The following are the part of an expert system components :

1) Knowledge Acquisition Subsystem : 
Knowledge acquisition refers to the gathering, transmission and conversion of problem-solving capability from experts or documented sources to a computer program. This helps in construction or expansion of the knowledge base. Sources of knowledge can be human experts, textbooks, multimedia documents, databases, special research reports.

2) Knowledge Base : 
The main raw material of expert systems is knowledge. The knowledge which is essential for the understanding and solving a problem is included in the knowledge base. This contains two elements:

i) Facts : 
It encompasses details about problem situation or area.

ii) Special Heuristics or Rules : 
They control the use of knowledge to solve particular problems in a specific domain. The informal judgmental knowledge in an application area is generally expressed by rules or heuristics.

3) Inference Engine : 
The inference engine is the brain of the expert system. It is also known as the control structure or the rule interpreter. This is a computer program that offers a procedure for reasoning about information present in the knowledge base. It can also be used for formulating inferences. It provides guidelines on how to use the knowledge base and organises and controls the steps taken to solve the problems.

4) User Interface : 
A language processor is one of the key components of ES as it provides easy communication between user and computer for solving problem. The communication takes place best in the natural language, but most of the existing systems use the question-answer method to interact with the user because of technological constraints. This is supported by the use of menus, electronic forms and graphics.

5) Blackboard (Workplace) : 
The blackboard is a temporary database which interprets the current problem as per the input data. This is that part of working memory which records transitional (intermediary) hypothesis and decisions. Three types of decisions, recorded in the blackboard, are as follows :
  • A plan on how to tackle the problem, 
  • An agenda on actions to be executed, and
  • Finding a solution by taking into consideration different hypothetical situations and the corresponding actions the system has generated.

6) Explanation Subsystem (Justifier) : 
The explanation sub-system or justifier has the capability to trace responsibility about the conclusions obtained from the sources. This function is extremely important for transfer of expertise as well as problem solving. The justifier explains ES behavior by answering the following questions:
  • Why did the expert system ask a specific question? 
  • How did an ES come to the conclusion?
  • What was the reason of rejecting other alternatives?
  • What is the procedure adopted to reach a solution? For example, what is yet to be established or analysed before reaching to a final diagnosis?
In a simple ES, the explanation tells about the rules which can be used to obtain the particular suggestions or solutions.

7) Knowledge Refining System : 
Human beings (experts) contain a knowledge refining system. They use this system so that they can review their own knowledge base, learn from it and enhance it for better results. Such kind of assessment is also essential in computerized systems so that the program can learn and analyse the causes for its success or failure, thereby developing a more accurate knowledge base. However, at present, this component is not available in the commercial expert systems, but research institutions and universities are working on the development of such experimental ESS.

Advantages of Expert System


The importance of expert system (ES) are as follows :

1) Increased Output and Productivity :
Expert System works faster than human beings.

2) Decreased Decision-Making Time : 
A human beings can make decisions much faster with the help of provided by an ES. This is very helpful for front-line decision-makers when they interact with customers.

3) Increased Process and Product Quality : 
ES provides consistent advice and reduces the size and rate of errors. This helps in increasing product quality.

4) Reduced Downtime : 
Machine downtime can be reduced significantly as ES diagnoses malfunction and recommends repairs whenever required.

5) Capture of Scarce Expertise : 
ES provides support when expertise becomes scarce. This may happen when sufficient experts are not available for the tasks, the expert is about to retire or leave the job, or the expertise is needed at more than one location.

6) Flexibility : 
Expert system offers flexibility in both manufacturing and service industries.

7) Easier Equipment Operation : 
Complex equipment's, become easier to operate with the help of ES.

8) Elimination of the Need for Expensive Equipment : 
Expert system performs monitoring and controlling, using low cost instruments. This is possible because the ES examines the information provided by instruments quickly and in detailed manner.

9) Operation in Hazardous Environment : 
ES permits the human beings to avoid working in hazardous environment ES helps to avoid hot, moist or toxic environments, c.g.. a malfunctioned nuclear power plant. It is also helpful at the time of military conflicts.

10) Accessibility to Knowledge and Help Desks : 
ES enables accessibility of knowledge thereby relieving the experts from the daily tasks. People can ask questions to systems and get the appropriate advice, e.g., help desks.

11) Ability to Work with Incomplete or Uncertain Information : 
ES, similar to human experts, cant work with incomplete, inaccurate, uncertain data, information or knowledge. Most of the time, "do not know" or "not sure" are the answers by the user to several questions during discussion, whereas ES produces an answer, although it may not be complete or correct.

12) Provision of Training : 
ES can provide training to beginners who become experienced with work. Notes and explanations (inserted into the system's knowledge base) also act as teaching devices.

13) Enhancement of Problem-Solving and Decision-Making : 
ES improves the problem solving ability by incorporating the opinion of experts into analysis. 
For example, Statistical Navigator is an ES, which helps the learners to use complex statistical computer packages.

14) Improved Decision-Making Processes : 
ES supports for a better understanding of the decision-making conditions as it provides instant feedback on decision concerns, facilitates communication among decision makers in a team and allows quick response to unexpected changes in the environment.

15) Improved Decision Quality : 
ES are reliable because they pay attention to details and do not manage important information and potential solutions. Thus, they make very few errors and provide similar solutions to repeated problems.

16) Ability to Solve Complex Problems : 
ES handles complex problems and provides solutions, which are beyond the scope of knowledge of any individual. This helps the decision-makers to control complicated conditions and improve operations of comple systems.

17) Knowledge Transfer to Remote Locations : 
One of the most beneficial features of ES is that it transfers knowledge easily across global boundaries.

18) Enhancement of Other Information Systems : 
ES offers intelligent capabilities to other information systems and enhances the organisation's reputation. It helps in improving decision-making, improved products and services and sustainable strategic advantage.

Disadvantages of Expert System


The limitations of expert system are as follows :

1) Hard : 
It is very difficult, even for the most skilled expert to get good situational assessment in case of restricted time limit.

2) Specific Tasks : 
ES works well only with certain types of operational and analytical tasks.

3) Need of Expert Engineers : 
Expert engineers are required for construction and design of an ES. An ES turns out to be very costly because expert engineers are rare and expensive.

4) Limited Domain : 
ES works well in solving only limited problems. pertaining to some specific domains only.

5) Limited Vocabulary : 
Experts normally uses very limited vocabulary for expressing facts and relations.

6) Dependent : 
Experts do not have any independent way of checking whether the conclusions provided is rational or not.

7) Different Thought : 
The approach of each expert towards assessment may be different, yet all are correct. 

8) Costly : 
The development and maintenance of ES is very costly.

Difference between Conventional System and Expert System


Attribute

Conventional System

Expert System

Objectives

 

In conventional applications, in both program and data structures, problem expertise is preset

In the expert system, problem related expertise is preset in data structures only.

Who Makes the Recommendations (Decisions)?

The human and/or the system.

The system.

 

Major Orientation

 

Decision making.

 

Transfer of expertise (human machine-human) and provide advice.

Major Query Direction

 

Human questions the machine.

Machine questions the human.

Nature of Support

 

Personal, groups and institutional.

Personal and groups.

 

Data Manipulation Method

Numerical

Symbolic

Characteristics of Problem Area

Complex, broad

Narrow domain

Type of Problems Treated

Ad hoc, unique

Repetitive

Content of Database

Factual knowledge.

Procedural and factual knowledge.

Reasoning Capability

No

Yes, limited

Explanation Capability

Limited

Yes