Expert System

Both in management information system (MIS) and decision support system (DSS) one thing is common, both are dependent on decision rules and judgments, which are kept in mind by the decision maker.

On the other hand, Expert Systems (ES) also called knowledge-based systems are based on decision rules and judgment, which are made explicit by the decision makers. These rules and judgments, along with procedures processes, can be obtained by interview and dialogue with the decision makers who are usually the subject area specialists. When these rules, logics, and procedures are put on the computer, it becomes possible to use these procedures for being applied in the real line situation even by comparatively inexperienced people.

Software which is used to store data relevant to a particular subject and to provide solutions to problems requiring judgment based on that data. The concept stems from Artificial Intelligence (AI) research, the data being built up by experts in a particular field such that non-experts may subsequently use the system to guide them to a correct solution.

Artificial intelligence (AI):

Introduction:

· A computer Is an electronic device that processes the data by following the instructions given in the program at fast speed, by drawing a large memory.

· It can also be programmed to draw certain types of conclusion on the basis of input.

· It receives inputs and draw results or conclusions on the basis of computations It performs.

· For this reason, the abilities that can imparted to computers to enable them to display "human like intelligent" behavior Is commonly referred as "Artificial Intelligence".

Definition and Explanation:

It is a latest technology which is used in some electronic machines. These machines can think, decide themselves arid communicate like human beings.

Artificial Intelligence has been called the study of how to make computers do things at which, at the moment people are better and people are much better then computer at:

· Learning from experience

· Making sense out of information

· Responding in an appropriate way

· Reasoning the relative Importance of different aspects

· Understanding people's behavior

· Hence:

· Artificial intelligence is the study of making a computer:

· To learn from experience

· Making sense out of ambiguous information

· Responding in an appropriate way

· Recognizing the relative importance of matters

· Understanding human behavior

Or

Artificial intelligence is the capability of a computer system to provide a
level of performance that reflects human like intelligence.

Or

Artificial intelligence is knowledge based systems that mimic or reflects
the human decisions making process.

Or

Artificial intelligence is the concepts that computers can be; programmed to imitate certain features of human reasoning.

Evolution/history of Artificial Intelligence:

The term artificial intelligence was coined in the mid 1950's by John McCarthy at a conference at Dartmouth College.

One of the features of that conference was a software processor that manipulated symbols instead of numbers

Developer claimed that the processor which proved several mathematician theorems possessed a certain amount of "artificial intelligence".

As artificial intelligence evolved, it was put to work solving a number of tasks, like prove theorems, solve complex problems, in the filed or gaming as researchers developed "AI" programs to play and win at tic-tac-toe checkers and chess.

Since most types of tasks performed by the programs involved in these applications required human intelligence, most of the people assumed that such programs possessed artificial intelligence.

The assumptions was not always correct as some of the early chess programs relied more on the brute force of the computer than they did on methods of intelligence.

As chess programs incorporated, these heuristics, they truly embedded AI techniques. Better yet they improved dramatically challenging humans at the expert level class in chess.

Working of Artificial Intelligence:

Artificial intelligence software works by creating a knowledge bas that consists of facts, concepts and the relationships between them and then searches It using pattern making techniques to solve problems.

a. Rules of thumb or heuristics are important.

A simple example might be milk in first when making tea. This is a rule of thumb that how to make a cup of tea. Similarly a simple business example programmed into many accounting packages might be: don't allow credit to a customer who has exceeded their credit limit.

b. Pattern making finds similarities between objects events or processes that may not be clear if items are only understood in terms of their differences.

Computer systems are now recognized as a suitable device for use in the decision making process in a number of areas.

Information is necessary or essential to decision making and computerization has vastly changed the ways in which information can be handled.

However the rote of artificial intelligence is actually taking decisions is infect largely passive.

The computer will give you the information you want, provided it is requested in the right way.

It will give you the information which is accurate.

It processes it according to instructions given but it can't do the following:

Disadvantages/Limitation:

Artificial intelligence can't do the following:

Tell the users how to take decisions

Replace the feelings or rules of thumb based on past experience which may determine how decisions are taken in first place.

Weigh up the relative value of two different pieces of information.

Weigh up the qualitative factors in taking a particular decision.

Handle uncertainty very well

Access whether the results derived from execution" of its programmed instructions Is adequate to a problem.

Today, the main areas of Artificial Intelligence research are Expert Systems, problem solving, natural languages, and robotics.

Expert Systems:

These Artificial Intelligence systems present the computer as an expert on some particular topics.

"An application software system which is used to store data relevant to a particular subject area and to provide solutions to problems requiring discriminatory judgments based on that data. The concepts stem from "Artificial Intelligence" research the data being built up by the experts in a particular field such that non experts may subsequently use the systems to guide them to a correct solution"

Problem Solving:

This area of Artificial Intelligence includes a spectrum of activities from playing games to planning military strategies.

Natural Languages:

It involves the study of person/computer interface In simple English language.

Robotics:

It is the field of Artificial Intelligence concerned with the design, manufacturing, and implementation of computer, controlled machines with electronic capabilities for vision, speech, and touch.

Components of An Expert System (ES):

Main Components of an Expert system are explained below:

a. Knowledge Base:

At the center of any Expert System their is knowledge base, which contains specific facts about the expert area and rules that the Expert System will use to make decisions based on those facts.

The most popular knowledge representation technique is the use of rule. A rule specifies what to do in a given situation and consists of two parts:

A condition that may or may not be true

Actions to be taken when the condition is true or false An example of a rule is:

All of the rules contained in an Expert System are called the rule set, which can vary from dozen to 10,000 and so on for a complex one.

Most Expert Systems are capable of dealing with binary logic, yes or no, true or false, 0 or 1. IF Expert Systems are to truly incorporate human thinking patterns, they must handle such imprecise terms as "most", "many", or "some" which are called "Fuzzy logic".

b. Inference Engine:

The engine inference is the portion of the Expert System that performs reasoning by using the contents of the knowledge base in a particular sequence. During the consultation, the inference engine examines the rules of the knowledge base one at a time, and when rule condition is true the specified action is taken. In Expert Systems terminology, the rule is fixed when the action is taken.

Two main methods have been devised for the inference engine to use in examining the rules: forward reasoning and reverse reasoning.

Eliza

In the 1960s a computer scientist named Joseph Weizenbaum wrote a little program as an experiment in natural language. He named the program after Eliza Doolittie, the character in My Fair Lady who wanted to learn to speak proper English. The software allows the: computer to act as a gentle therapist who does not talk much but, \ instead, encourages the patient - the computer user - to talk. The Eliza software has a storehouse of key phrases to be dragged out when triggered by the patient. For example, if a patient types; "My mother never liked me," The software cued by the word mother - can respond; "Tell me more about your family." If there are no key words from the patient, the computer responds neutrally, with a phrase such as; "I see" or "That's very interesting" or "Why do you think that?" If a patient gives yes or no answers, the computer may respond; "I prefer complete sentences." With party tricks like these, the program is able to move along quite swiftly from line to line. Weizenbaum was astonished to discover that people were taking his little program seriously, pouring out their hearts to the computer.'

Forward Reasoning:

Forward reasoning is also called forward chaining; the rules are examined one after another in a certain order. The order might be the sequence in which the rules were entered into the rule set, or it might be some other sequence specified by the user. As each rule is examined, the Expert Systems attempt to evaluate whether the condition is true or false. For example, a medical expert system may be used to examine a patient's symptoms and provide a diagnosis. Based on these symptoms, the expert system might locate several diseases that the patient may have.

Reverse Reasoning:

Reverse reasoning is also called backward chaining; the inference engine selects a rule and regards it as a problem to be solved. Such procedures are often called goal driven inferential processes. For example, the expert system might be given the goal to "find the symptoms of this disease" and would work back from there, asking questions as necessary to confirm.

c. User Interface:

Users often interact with the Expert Systems through a user interface. In most cases, the Expert Systems prompt (asks) the user to supply information about the problem and the user types in the requested data. The data entered are examined by the inference engine and compared to the facts, rules, and the relationships in the knowledge base. This examination and comparison process results in the system continuing to prompt the user for more information until the system has enough data about the current problem so that it can reach a conclusion. Thus the user interface for' an Expert System is highly interactive.

Ideally, the user interface should enable to communicate with the Expert Systems in his natural language, without needing to learn rigid, programming language syntax.

d. Explanation Facilities:

After users supply information about the current problem-solving situation, the Expert System reaches a conclusion and/or makes a recommendation (which can be output to a screen, printer, or storage device) about what should be done. In many cases, users are interested in knowing the line of reasoning followed by the Expert System in drawing conclusions.

The explanation facility communicates to user the logic followed in reaching a decision and, in some cases, may also attempt to explain the importance of certain information inputs. Also, if the Expert Systems cannot draw a conclusion, it should display what it has uncovered and let human experts use these facts to their advantage.

Дата добавления: 2014-01-11