Fair Use Notice
The material used in this presentation i.e., pictures/graphs/text, etc. is solely
intended for educational/teaching purpose, offered free of cost to the students for
use under special circumstances of Online Education due to COVID-19 Lockdown
situation and may include copyrighted material - the use of which may not have
been specifically authorised by Copyright Owners. Its application constitutes Fair
Use of any such copyrighted material as provided in globally accepted law of many
countries. The contents of presentations are intended only for the attendees of the
class being conducted by the presenter.
PART 5
Expert Systems
2
Example of an
Expert System
3
4
An expert system is a computer program that emulates the
decision-making ability of a human expert. They are designed
to solve complex problems by reasoning through bodies of
knowledge, represented mainly as if–then rules rather than
through conventional procedural code.
The first expert systems were created in the 1970s and then
proliferated in the 1980s. Expert systems were among the first
truly successful forms of artificial intelligence (AI) software.
5
An expert system tries to simulate the judgment and behavior
of a human that has expert knowledge and experience in a
particular field. It is an interactive computer-based decision-
making system which solves complex decision-making
problems. The Expert System can resolve many issues which
generally would require a human expert. It is capable of
reasoning about some domain of knowledge. Expert systems
were the predecessor of the current day artificial intelligence,
deep learning and machine learning systems.
6
Expert systems are designed for solution of following types of
problems
Diagnostic problems are better solved with backward chaining
Prognosis monitoring and control are better done by forward
chaining
7
Expert system for a hot rolling
8
9
10
Assignment 3:
Question 1 (Diagnosis): Consider yourself working in a hot rolling mill plant.
You are required to develop an expert system to ensure the production of rolls as
per requirement.
Tasks:
Write down three main requirements to ensure product quality.
What will be the possible causes if these requirements are not met.
Question 2 (Prognosis):
What changes you can make in the system that may improve quality? How will
you check what effect these changes made on product quality.
11
Characteristic of an Expert System
The Highest Level of Expertise:
It provides efficiency, accuracy and imaginative problem-solving.
Right on Time Reaction:
The total time is less than the time taken by an expert to get the most
accurate solution for the same problem.
Reliability:
They are reliable. It should not make any a mistake.
Flexible:
It is vital that it remains flexible.
12
13
Components of expert System
(1) User Interface
A user communicates with the expert system through this.
This takes the user's query and passes it to the inference engine.
It displays the results to the user.
14
(2) Inference Engine
It is the brain of the expert system.
It contains rules to solve a specific problem using knowledge
from the Knowledge Base.
It selects facts and rules to apply when trying to answer the
user's query.
It provides reasoning about the information in the knowledge
base.
It also helps in deducting the problem to find the solution.
15
(3) Knowledge Base
The knowledge base is a repository of facts.
It stores all the knowledge about the problem domain.
It is like a large container of knowledge which is obtained from
different experts of a specific field.
The success of the Expert System depends on the accurate
and precise knowledge.
16
Knowledge Acquisition
The term knowledge acquisition means getting required domain
knowledge by the expert system.
17
Participants of Expert Systems
18
Participants of Expert Systems
Participant Role
Domain Expert Person(s) whose expertise and
knowledge is taken to develop an
expert system.
E.g. Engineer, Doctor, Agriculturist
Knowledge Engineer Knowledge engineer is a technical
person who integrates knowledge
into computer systems.
End User Person(s) who are using the expert
system to get advice.
19
Human expert vs. expert system
Human Expert Artificial Expert
Perishable Permanent
Difficult to Transfer Portable
Difficult to Document Easy to Document
Unpredictable Consistent
Expensive Cost effective System
20
Benefits of expert systems
1. Improves the decision quality.
2. Cuts the expense of consulting experts for problem-solving
3. Provides fast and efficient solutions to problems in narrow area of
specialization.
4. Can gather scarce expertise and use it efficiently.
5. Offers consistent answer for the repetitive problem
6. Helps to get fast and accurate answers
7. Provides a proper explanation of decision making
8. Ability to solve complex and challenging issues
9. Expert Systems can work steadily without getting emotional,
tensed or fatigued. 21
Limitations of the expert system
• Unable to make a creative response in an extraordinary situation
Assignment:
Give examples of expert systems in (i) Medical domain , (ii)
Industrial domain where the expert system may not be able to make
creative response in extraordinary situations.
• Errors in the knowledge base can lead to wrong decision.
22
Limitations of the expert system
• Knowledge acquisition problem. Obtaining the time of domain
experts for any software application is always difficult, but for expert
systems it was especially difficult because the experts were by
definition highly valued and in constant demand by the organization.
As a result of this problem, a great deal of research in the later years of
expert systems was focused on tools for knowledge acquisition, to help
automate the process of designing, debugging, and maintaining rules
defined by experts.
23
• Another major challenge is the size of the knowledge base.
For instance, an expert system with 1 million rules would be too
complex and it would face too many computational problems. An
inference engine would have to be able to process huge numbers of
rules to reach a decision.
24
Applications of expert systems
(Think about example for each of the following application areas, one example
has been given in blue color below)
• Hospitals and medical facilities
To recommend the suitable doctor to a patient.
TRIAGE
• Help desks management (Application area)
To guide visitors to appropriate halls in a big conference (Application)
A visitor wants to know the location of poster exhibition (Use case)
• Employee performance evaluation (Application area)
Evaluating performance on the basis of the punctuality of an employee
It will record the time of arrival of employee
25
Applications of expert systems
• Loan analysis
A system to recommended whether the loan application may be approved or
not.
• Repair and maintenance projects
To estimate the cost of repair
• Process monitoring and control
Bottling plant. If bottles are not filled fully:
1.You increased the liquid outflow to see if bottles are filled completely.
2. You increase the time of filling.
26
Applications of expert systems
• Supervise the operation of the plant and controller
• Stock market trading
Diagnostic: Losses (causes: inappropriate timing of selling and buying)
Prognostic: change the timings of buying/selling, change the type shares you
buy)
• Airline scheduling & cargo schedules
Home work. Give examples for both diagnostic and prognostic expert
systems.
27
Applications of Expert System (More examples)
Design Domain
Camera lens design, automobile design
Medical Domain
Diagnosis Systems to deduce cause of disease from observed data, conduction of medical
operations on humans.
Monitoring Systems
Comparing data continuously with observed system or with prescribed behavior such as
leakage monitoring in long petroleum pipeline.
Process Control Systems
Controlling a physical process based on monitoring.
Finance/Commerce
Detection of possible fraud, suspicious transactions, stock market trading, Airline scheduling,
cargo scheduling.
28
ASSIGNMENT 3:
Question 3:
Using Google Scholar, search, download and read a research paper reporting an expert
system in the domain of your choice.
Submit your assignment containing following:
1. Aim of reported research
2. What motivated authors to develop reported expert system (Need, application domain)
3. What tools and technologies were used
4. What were performance metrics and their values
Submit your assignment in MS word along with the paper referred to.
29
ASSIGNMENT 4:
Develop an expert system using Python.
The system may be of diagnosis or prognosis type.
Select application area and application yourself.
This is an individual task.
30
Inference Engine
Use of right rules by the Inference Engine is essential in deducting a correct, flawless
solution.
To recommend a solution, the Inference Engine uses the following strategies −
• Forward Chaining
• Backward Chaining
31
Forward Chaining
It is a strategy of an expert system to answer the
question, “What can happen next?”
Here, the Inference Engine follows the chain of conditions and
finally deduces the outcome. It considers all the facts and rules,
and sorts them before concluding to a solution.
It is data driven. Used for designing.
This strategy is followed for working on conclusion, result, or
effect. For example ?
32
Forward Chaining
33
Backward Chaining
With this strategy, an expert system finds out the answer to the
question, “Why this happened?”
It is goal-driven. Used for diagnosis.
On the basis of what has already happened, the Inference
Engine tries to find out which conditions could have happened
in the past for this result. This strategy is followed for finding
out cause or reason. For example ?
34
Backward Chaining
35
Examples of Expert 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.
CaDet: Expert system that could identify cancer at early stages.
36
ROSS:
(Legal expert system)
It applies AI technologies to replicate and improve upon the
abilities of a human legal research assistant.
ROSS Intelligence is an AI lawyer that began life as a
research program at the University of Toronto. ROSS is built
on IBM’s Watson cognitive computing platform.
37
Tools Available to Produce Expert Systems (ES)
• Programming languages
• Expert system shells
• Expert system development environments
Programming languages include conventional computer languages, such as C++
and Java, as well as languages specifically designed for AI applications, these
include LISP and PROLOG.
Expert system shells (e.g. Intermodellar) provide a framework to produce an ES, so
the knowledge base and rules are simply added to this framework.
Expert system development environments provide a more powerful and flexible
framework within which an ES can be written. They generally allow multiple
knowledge representation schemes to be used and allow knowledge bases to be
segmented. E.g. CLIPS (C Language Integrated Production System).
38
THE END.
39
