Application of AI

Application of AI
There are various application areas of artificial intelligence. Some of the applications of AI include
expert systems, natural language processing, speech recognition, machine vision and robotics.

Expert System
 An Expert system is a set of program that manipulates encoded knowledge to solve
problem in a specialized domain that normally requires human expertise.
 A computer system that simulates the decision- making process of a human expert in a
specific domain.
 An expert system‘s knowledge is obtained from expert sources and coded in a form suitable
for the system to use in its inference or reasoning processes. The expert knowledge must
be obtained from specialists or other sources of expertise, such as texts, journals, articles
and data bases.
 An expert system is “intelligent” program that solves problems in a narrow problem area
by using high-quality, specific knowledge rather than an algorithm.
 The expert systems are the computer applications developed to solve complex problems in
a particular domain, at the level of human intelligence and expertise.
 An expert system is a computer system that emulates the decision-making ability of a
human expert.
 The expert system can resolve many issues which generally would require a human expert.
It is based on knowledge acquired from an expert. It is also capable of expressing and
reasoning about some domain of knowledge. Expert systems were the predecessor of the
current day artificial intelligence, deep learning and machine learning systems.
 Following are examples of Expert Systems
 MYCIN: It was based on backward chaining and could identify various
bacteria that could cause acute infections. It could also recommend drugs
based on the patient's weight.
 DENDRAL: Expert system used for chemical analysis to predict molecular
structure.
 PXDES: Expert system used to predict the degree and type of lung cancer

1
Collected by Bipin Timalsina
 Application of AI

 CaDet: Expert system that could identify cancer at early stages

Major Components of ES

 There is currently no such thing as “standard” expert system. Because a variety of

techniques are used to create expert systems, they differ as widely as the programmers who
develop them and the problems they are designed to solve. However, the principal
components of most expert systems are knowledge base, an inference engine, and user
interface, as illustrated in the figure and also working memory.

Figure: Block Diagram of Expert System

Knowledge Base
The component of an expert system that contains the system‘s knowledge is called its knowledge
base. This element of the system is so critical to the way most expert systems are constructed that
they are also popularly known as knowledge-based systems

A knowledge base contains both declarative knowledge (facts about objects, events and situations)
and procedural knowledge (information about courses of action). Depending on the form of
knowledge representation chosen, the two types of knowledge may be separate or integrated.

2
Collected by Bipin Timalsina
 Application of AI

Although many knowledge representation techniques have been used in expert systems, the most
prevalent form of knowledge representation currently used in expert systems is the rule-based
production system approach.

To improve the performance of an expert system, we should supply the system with some
knowledge about the knowledge it possess, or in other words, meta-knowledge.

Inference Engine
Simply having access to a great deal of knowledge does not make you an expert; you also must
know how and when to apply the appropriate knowledge. Similarly, just having a knowledge base
does not make an expert system intelligent. The system must have another component that directs
the implementation of the knowledge. That element of the system is known variously as the control
structure, the rule interpreter, or the inference engine.

The inference engine decides which heuristic search techniques are used to determine how the
rules in the knowledge base are to be applied to the problem. In effect, an inference engine “runs”
an expert system, determining which rules are to be invoked, accessing the appropriate rules in the
knowledge base, executing the rules , and determining when an acceptable solution has been found.

User Interface
The component of an expert system that communicates with the user is known as the user interface.
The communication performed by a user interface is bidirectional. At the simplest level, we must
be able to describe our problem to the expert system, and the system must be able to respond with
its recommendations. We may want to ask the system to explain its “reasoning”, or the system
may request additional information about the problem from us.

Working Memory
Beside these three components, there is a Working Memory - a data structure which stores
information about a specific run. It holds current facts and knowledge.

3
Collected by Bipin Timalsina
 Application of AI

Stages of Expert System Development

Although great strides have been made in expediting the process of developing an expert system,
it often remains an extremely time consuming task. It may be possible for one or two people to
develop a small expert system in a few months; however the development of a sophisticated system
may require a team of several people working together for more than a year.

An expert system typically is developed and refined over a period of several years. We can divide
the process of expert system development into five distinct stages. In practice, it may not be
possible to break down the expert system development cycle precisely. However, an examination
of these five stages may serve to provide us with some insight into the ways in which expert
systems are developed.

Figure: Phases of expert system development

Identification:

Beside we can begin to develop an expert system, it is important that we describe, with as much
precision as possible, the problem that the system is intended to solve. It is not enough simply to
feel that the system would be helpful in certain situation; we must determine the exact nature of
the problem and state the precise goals that indicate exactly how we expect the expert system to
contribute to the solution.

Conceptualization:

Once we have formally identified the problem that an expert system is to solve, the next stage
involves analyzing the problem further to ensure that its specifics, as well as it generalities, are
understood. In the conceptualization stage the knowledge engineer frequently creates a diagram of
the problem to depict graphically the relationships between the objects and processes in the

4
Collected by Bipin Timalsina
 Application of AI

problem domain. It is often helpful at this stage to divide the problem into a series of sub-problems
and to diagram both the relationships among the pieces of each sub-problem and the relationships
among the various sub-problems.

Formalization:

In the preceding stages, no effort has been made to relate the domain problem to the artificial
intelligence technology that may solve it. During the identification and the conceptualization
stages, the focus is entirely on understanding the problem. Now, during the formalization stage,
the problem is connected to its proposed solution, an expert system, by analyzing the relationships
depicted in the conceptualization stage.

During formalization, it is important that the knowledge engineer be familiar with the following:

 The various techniques of knowledge representation and heuristic search used in expert
systems.
 The expert system “tools” that can greatly expedite the development process. And
 Other expert systems that may solve similar problems and thus may be adequate to the
problem at hand.

Implementation:

During the implementation stage, the formalized concepts are programmed onto the computer that
has been chosen for system development, using the predetermined techniques and tools to
implement a “first pass” prototype of the expert system.

Theoretically, if the methods of the previous stage have been followed with diligence and care, the
implementation of the prototype should be as much an art as it is a science, because following all
rules does not guarantee that the system will work the first time it is implemented. Many scientists
actually consider the first prototype to be a “throw-away” system, useful for evaluating progress
but hardly a usable expert system.

Testing:

Testing provides opportunities to identify the weakness in the structure and implementation of the
system and to make the appropriate corrections. Depending on the types of problems encountered,
the testing procedure may indicate that the system was

5
Collected by Bipin Timalsina
 Application of AI

Features of an expert system

What are the features of a good expert system? Although each expert system has its own particular
characteristics, there are several features common to many systems. The following list from Rule-
Based Expert Systems suggests seven criteria that are important prerequisites for the acceptance
of an expert system.

1. “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.
2. “The program should be usable.” An expert system should be designed so that even a
novice computer user finds it easy to use.
3. “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.
4. “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 us to decide whether
to accept the system‘s recommendations.
5. “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.
6. “The program should be able to learn new knowledge.” Not only should an expert system
be able to respond to our questions, it also should be able to ask questions to gain additional
information.

7. “The program‘s knowledge should be easily modified.” It is important that we should be

able to revise the knowledge base of an expert system easily to correct errors or add new
information

6
Collected by Bipin Timalsina