Artificial intelligent System & Expert system

As we observe in the computer it has a full of knowledge store on it and almost

the question can be answer and this is we call the artificial intelligence of a system.

a. An overview of Artificial Intelligence

Artificial intelligence
-- used to describe computers with ability to mimic or duplicate functions of
the human brain.
In which it’s all the combination all of the store knowledge in a human
brain of different individual.

Artificial Intelligence Systems

-Include the people, procedures, hardware, data and knowledge needed
to develop computer systems and machines that demonstrate characteristic of
intelligence.
This system is not made for the purpose of replacing the human decision
making completely but instead is to replicate it for certain types of well defined
problems. And the overall purpose of AI system is to help the organization to
achieve its goals.
The Nature of Intelligence

From the early AI pioneering stage, the research has been developing machines
with intelligent behavior. The following are the different specific characteristic of
intelligent behavior.

• Learn from experience & apply the knowledge acquired from experience
- Not only human has the ability to learn from experience even thought the
computers. For example in playing a cheese against the computer system it
can improve their game while they in a human competitor.
• Handle complex situation

1|Page
 - Some complex things happen in which we must handle even the computer
system that’s why it develop in order to handle the perplexing situations
requires careful planning and elaborate computers programming.
• Solve problems when important information is missing
- In the AI system today, it can make calculations, comparisons and decisions
even when it has missing information.

• Determine what is important

- We only know that a computers do not have a natural ability’ in which it must
develop [p the programs and approaches to allow the computer systems and
machines to identify the important information.
• React quickly & correctly to new situations
- The computers do not have this ability without the complex programming.
• Understand visual images
Perceptive system- a system that approximates’ the human see, hears, and
feels object.
- Having a perceptive system it allows a machine to approximate the way a
human sees, hears, and feels object.

• Process & manipulate symbol

- Computers have difficulty handling symbolic processing and reasoning. But in
the recent development in machine vision hardware and software, however
allow some computer to process and manipulate symbol on a limited basis.
• Be creative & imaginative
- Only few computers have the ability to be truly imaginative or creative in this
way, although software has been developed to enable a computer to write
short stories.
• Use heuristics
- Some computer system also has this ability. They can give the right
programs; obtain good solutions that can be use approximation instead trying
to search for an optimal solution, which would be technically difficult.

2|Page
 The difference between the natural and artificial Intelligence
In natural intelligence or the human, they have a high in using the
different senses, creative and imaginative and many more. But in terms of
calculating and transferring information is low, but in the artificial intelligence
is high in this situation and low in using senses and being creative &
imaginative.
The Major Branches of Artificial
Intelligence
Expert systems
- consist of hardware and software that stores knowledge and make
interferences, similar to a human expert.
It is a branch of AI a system has the skill the same to mankind .

Robotics
- Mechanical or computer devices that perform tasks requiring a high
degree of precision or that are tedious or hazardous for humans.
We know in a robot it has a program install to it in order to function. It is the
controlling software and one of the most important in AI system.
Vision system
- the hardware and software that permit computers to capture, store, and
manipulate visual images and picture.
This system can search through the huge database of fingerprints has
brought quick resolution to many long- standing mysteries. And these systems
are also effective at identifying people based on facial features.
Natural Language Processing
- processing that allows the computer to understand and react to
statements and commands made in “natural” language, such as English.
With this it is possible to speak into a microphone connected to computer
and have the computer convert the electrical impulses generated from the voice
into text files or program commands.
Learning system

3|Page
 - A combination of software and hardware that allows the computer to change
how it functions or reacts to situations based on feedback it receives.
Example of this is computerized games have learning abilities. When the
computer does not Win a particular game, it remembers not to make the same
action been done in the same condition. In a learning system it requires feedback
on the result of actions or decisions.

Neutral Network
- A computer system that can stimulate the functioning of a human brain.
This system is use massively parallel processors in an architecture that is based
on the human brains own meshlike structure. The neutral network software can
used to stimulate a neutral network using standard computers.
.
b. An Overview of Expert System
The computerized expert systems are been develop to diagnose
problems, predict future events, and solve energy problems. It uses heuristic or
rules of the thumb like a human expert to arrive at conclusion or make
suggestions.
Characteristics of an Expert System
• Can explain their reasoning or suggested decisions
It is the ability to explain its reasoning processes the most valuable
featured of a computer expert system.
• Can display “intelligent” behavior
Some applications of expert system are imaginative medical diagnosis
based on a patient condition, a suggestion to explore for natural gas at a
particular location, and job counseling.
• Can draw conclusions from complex relationships
For example, when one proposed expert system will work with a flexible
manufacturing system to determine the best use of tools. And another expert
system can suggest ways to improve quality control procedure.
• Can provide portable knowledge

4|Page
 It can be used to capture the human expertise that might otherwise be
lost.
• Can deal with uncertainty
It is the abilty to deal with knowledge that is incomplete or not completely
accurate. The system deals with this problem through the use of probability
statistic and heuristic.
• Not widely used or tested
It has not been widely tested in corporate settings.
• Limited to relatively narrow problems
It can perform complex data analysis others are limited to simple
problems.
• Possibility of error
If the knowledge of a human expert is incorrect or incomplete, it will affect the
system negatively.
• Cannot refine its own knowledge
It is not capable of acquiring knowledge directly.
• May have high development cost
The expert system can be expensive to develop while using traditional
programming languages and approaches.
Expert system shell
–a collection of software packages and tools used to develop expert system.
• Raise legal and ethical concerns
The people who make decisions and take action are legally and ethically
responsible for their behavior.
Capabilities of An Expert Systems
Expert system can’t avoid having problems the following are different
solutions of the said system.
 Strategic goal setting
- is one of the most important functions of top level decision makers.

5|Page
 This provides a framework for all other activities throughout the organization.
Without having these said system is running not knowing how to accomplish
goal.
 Planning
-the ability to reach overall corporate objectives, the impact of plans on
organizational resources, and the ways specific plans will help an organization
compete in the market place can be investigated via expert system.
With this it can assist to reach in the final decision based on fact supplied by
management.
 Design
–these types of expert system use general design principles, an
understanding of manufacturing procedures, and a collection of design rules.
The different varieties of products to be design are the micro chips and system.
 Decision-making
-expert systems have provided this type of support for many individuals
and organization.
With these it can suggest possible alternatives, ways of looking at the problem
and logical approaches in the decision making process.
 Quality control and monitoring
-determining whether an existing computer is operating intended and used
to monitor product quality.
It can assist in monitoring various systems and proposing solutions to system
problems.
 Diagnosis
- looks at the causes and proposes solutions.
With these it can provide a doctor with the probable cause of medical problem
and propose treatment or interventions.
When to Use Expert Systems
It is important to make sure that the potential benefits are
worth the effort and that various expert system characteristic are balanced in
terms of cost, control and complexity.

6|Page
 These are the circumstances using the expert system:
 High payoff
 Preserve scarce expertise
 Distribute expertise
 Provide more consistency than humans
 Faster solutions than humans
 Training expertise
Components of an Expert System
These components must work together in providing expertise.
A. Knowledge Base

– stores all relevant information, data, rules, cases and relationship

used by the expert system.
It must developed for each unique application and included
to it the generic knowledge from theories that been established over time and
specific knowledge that comes from more recent experiences and rule of the
thumb.
Challenges in developing a Knowledge Base
 Assembling human experts
- Its objective in building knowledge base is to integrate the
knowledge of individuals with similar expertise.
Example of this is many doctors may contribute to a
medical diagnosis knowledge base.
 The use of fuzzy logic
- a special research area in computer science that allows
shades of gray and does not require conditions to be black/ white, yes/no or
true /false.

This is the ability to estimate whether a condition fits a

situation more closely resembles the judgment a person makes when evaluating
a situation.
 The use of rules

7|Page
 – A conditional statement that links given conditions to
actions or outcomes
When a certain condition exists, then specific actions are
taken or certain conclusions are reached.
 The use of cases
– In developing solution to a current problem. It involves
finding cases stored in the knowledge base that are similar to the problems and
modifying the solution to the cases fit or accommodate the current problem or
situation.
B. Inference Engine
-parts of the expert system that seeks information and
relationships from the knowledge base and provides answers, predictions , and
suggestions the way a human expert would.
It is a component in which delivers the expert advice. It is a
process of retrieving relevant information and a relationship from the knowledge
base is not simple.
References: Principles of Information Systems – fifth and sixth edition, written by

Ralph M. Stair and George W. Reynolds.

8|Page