Expert Systems: Dr.P.Mohan Dcms

You might also like

Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 23

EXPERT SYSTEMS

Dr.P.Mohan
DCMS
Artificial
intelligence

Vision Learning
systems systems

Robotics
Expert systems

Neural networks
Natural language
processing
EXPERT SYSTEMS
 Expert systems are designed to solve real
problems in a particular domain that normally
would require a human expert. It can solve many
types of problems
 Developing an expert system involves extracting
relevant knowledge from human experts in the
area of problem, called domain experts.
Components of Expert System
 Knowledge acquisition facility
 Knowledge base
 Knowledge-based management system
 Inference engine,
 Work space
 Explanation facility
 Reasoning capability and ,
 User interface.
Characteristics of ES
 Expert system is capable of handling
challenging decision problems and delivering
solutions.
 Expert system uses knowledge rather than
data for solution. Much of the knowledge is
heuristic- based rather than algorithmic.
 Expert system has the capability to explain h
o
wthe
decision was made.
Characteristics contd…
 Can…
Explain their reasoning or suggested decisions
Display intelligent behavior
 Draw conclusions from complex relationships
 Provide portable knowledge
 Expert systemshell
 A collection of software packages and tools used to develop
expert systems
Limitations of Expert Systems
 N o t widely used ortested
 Limited to relatively narrow problems
 Cannot readily deal with “mixed” knowledge
Possibility of error
 Cannot refine own knowledge base
Difficult to maintain
 May have high development costs
 Raise legal and ethical concerns
Capabilities of Expert Systems
Strategic goal setting Explore impact of strategic goals

Planning Impact of plans on resources

Design Integrate general design principles and


manufacturing limitations

Decision making Provide advise on decisions

Quality control and monitoring Monitor quality and assist in finding solutions

Diagnosis Look for causes and suggest solutions


Components of Expert System
 Fuzzy logic
 A specialty research area in computer science that allows shades
of gray and does not require everything to be simply yes/no, or
true/false
Backward chaining
 A method of reasoning that starts with conclusions and works
backward to the supporting facts
 Forward chaining
 A method of reasoning that starts with the facts andworks
forward to the conclusions
Explanation Inference
facility engine

Knowledge
Knowledge base User
base acquisition interface
facility

Experts User
Rules for a Credit Application
Mortgage application for a loan for Rs.100,000 to Rs.200,000

If there are no previous credits problems, and


If month net income is greater than 4x monthly loan payment, and
If down payment is 15% of total value of property, and

If net income of borrower is > Rs.25,000, and


If employment is > 3 years at same company

Then accept the applications

Else check other credit rules


Explanation Facility
 A part of the expert system that allows a user or decision
maker to understand how the expert system arrived at certain
conclusions or results
Knowledge Acquisition Facility
Knowledge acquisition facility
Provides a convenient and efficient means of capturing and storing al
components of the knowledge base

Knowledge
Knowledge acquisition
base facility

Expert
Expert Systems Development

Determining requirements

Identifying experts
Domain
Construct expert system components • The area of knowledge
addressed by the
expert system.
Implementing results

Maintaining and reviewing system


Participants in Expert Systems
Development and Use
 Domain expert
 The individual or group whose expertise and knowledge is
captured for use in an expert system
Knowledge user
 The individual or group who uses and benefits from the expert
system
Knowledge engineer
Someone trained or experienced in the design, development,
implementation, and maintenance of an expert system
Expert
system

Knowledge
Domain expert engineer Knowledge user
Evolution of Expert Systems
Software
 Expert systemshell
Collection of software packages &tools to design, develop,
implement, and maintain expert systems

high Expert system


shells
Ease of use

Special and 4th


generation
Traditional
languages
programming
languages
low
Before 1980 1980s 1990s
Limitations of Expert Systems
 N o t widely used ortested
 Limited to relatively narrow problems
 Cannot readily deal with “mixed” knowledge
Possibility of error
 Cannot refine own knowledge base
Difficult to maintain
 May have high development costs
 Raise legal and ethical concerns
When to Develop an ES?
 The problem cannot be specified in terms of a
well-defined algorithm.
 T h e problem requires consistency a n
d
standardization.
 T h e domain or problem area is narrow o r
limited.
 When the task is hazardous.
 There is scarcity of experts in the area.
 The problem involves complex logic or a large
number of rules.
 Human experts have successfully solved
similar problems
Advantages of ES
 I t enhances decisionquality.
 I t reduces the cost of consulting experts
for problem solving.
 I t provides quick and efficient solutions to
problems in narrow area of specialization.
 I t offers high reliability of expert suggestions o
r
decisions.
 I t gathers scarce expertise and uses it
efficiently.
Advant ages of ES cont d…
 I t can tackle very complex problems that a
re
difficult for human experts to solve.
 I t can work on standard computerhardware.
 I t can not only give solutions, but also the
decision logic and how the solution was arrived
at.
Limitations of ES
 T h e knowledge base may not be complete
 Each problem is different. Hence the solution from a h
um
an
expert too may be different
Expensive to build and maintain
 Takes long time to develop and fine tune ES
 Large ESis difficult to build and maintain
THANKS
 Share your ideas!

You might also like