INTRODUCTION TO ARTIFICIAL INTELLIGENCE

EXPERT
SYSTEM

Submitted by:

Jinny Sebestian
Submitted to:
Jyoti Rawal
Mr. Aman Nagpal
Nikita Daniel

Nishtha Verma
 EXPERT SYSTEM
An expert system is a computer program that is designed to solve complex
problems and to provide decision-making ability like a human expert. It
performs this by extracting knowledge from its knowledge base using the
reasoning and inference rules according to the user queries.
The performance of an expert system is based on the expert's knowledge
stored in its knowledge base. The more knowledge stored in the KB, the
more that system improves its performance. One of the common examples
of an ES is a suggestion of spelling errors while typing in the Google search
box.

Components of Expert System

An expert system mainly consists of three components:
User Interface
Inference Engine
Knowledge Base
 
Basic concept of an expert system
Basic concept of an expert system where the user supplies facts or other
information to the expert system and receives expert advice or expertise in
response. Internally the expert system consists of two main components.
The knowledge base contains the knowledge with which the inference
engine draws conclusions. These conclusions are the expert system’s
responses to the user’s queries for expertise.
 EXPERT SYSTEM

The expert system has all these capabilities:-

Strategic Goal Setting Explore impact of strategic goal

 Planning : Impact of plans n resources
Design: Integrate general design principles and manufacturing limitations
Decision making: Providing advise on decisions
Quality control and monitoring: Monitor quality and assist in finding
solutions.
Diagnosis: Look for causes and suggest solutions
 
The process of Building An Expert Systems

Determining the characteristics of the problem

Knowledge engineer and domain expert work in coherence to define the
problem
The knowledge engineer translates the knowledge into a computer-
understandable language. He designs an inference engine, a reasoning
structure, which can use knowledge when needed.
Knowledge Expert also determines how to integrate the use of uncertain
knowledge in the reasoning process and what type of explanation would
be useful.
 HUMAN SYSTEM EXPERT SYSTEM

Perishable Permanent

Difficult to transfer Transferable

Difficult to document Easy to document

Unpredictable Consitent

Expensive Cost effective system

Examples of some expert systems

MYCIN: One of the earliest expert systems based on backward

chaining. It can identify various bacteria that can cause severe infections
and can also recommend drugs based on the person’s weight
PXDES:  It could easily determine the type and the degree of lung cancer
in a patient based on the data.
CaDet: It is a clinical support system that could identify cancer in its early
stages in patients.
DXplain: It was also a clinical support system that could suggest a variety
of diseases based on the findings of the doctor

Advantages of the expert system

These systems are highly reproducible.

They can be used for risky places where the human presence is not safe.
Error possibilities are less if the KB contains correct knowledge.
The performance of these systems remains steady as it is not affected by
emotions, tension, or fatigue.
They provide a very high speed to respond to a particular query.
Limitations of the expert system

Unable to make a creative response in an extraordinary situation

Errors in the knowledge base can lead to wrong decision
The maintenance cost of an expert system is too expensive
Each problem is different therefore the solution from a human expert
can also be different and more creative

Some popular application where expert systems user:

Information management
Hospitals and medical facilities
Help desks management
Employee performance evaluation
Loan analysis
Virus detection
Useful for repair and maintenance projects
Warehouse optimization
Planning and scheduling
The configuration of manufactured objects
Financial decision making
Knowledge publishing
Process monitoring and control
Supervise the operation of the plant and controller
Stock market trading
Airline scheduling & cargo schedules
USER INTERFACE
It is the most crucial part of expert system. It takes queries as an input in a
readable format and passes it to the inference engine. After getting the
response from the inference engine, it displays the output to the user. In
other words, it is an interface that helps a non-expert user to communicate
with the expert system to find a solution. The goal of this interaction is to
allow effective operation and control of the machine from the human end,
whilst the machine simultaneously feeds back information that aids the
operators’ decision-making process.

It is generally Natural Language Processing to be used by the user who is

well-versed in the task domain.

Requirements of efficient user interface:     

It should help users accomplish their goals in the shortest way possible.
It should be designed to work for user’s existing or desired work
practices.
Its technology should be adaptable to user’s requirements, not the other
way round.
It should make efficient use of user input.
INTERFERENCE ENGINE

The inference engine is the brain of the expert system. Inference engine
contains rules to solve a specific problem. It refers the 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. This component is also helpful for formulating conclusions.

Knowledge based: If the Expert System is knowledge based, the Inference Engine acquires and
manipulates the knowledge from a knowledge base, i.e. knowledge engineer, to arrive at a particular
solution.

Rule Based: If the Expert System is rule based, then the Inference engine –

Applies rules repeatedly to the facts, which are obtained from earlier rule applications.

Adds new knowledge into the knowledge base if required.

Resolves rule conflicts when multiple rules are applicable to a particular case.
INTERFERENCE ENGINE

Strategies used by Inference Engine

Forward Chaining
Backward Chaining
Note:
the strategy used by the Inference Engine can be Forward chaining or
backward chaining.

Forward Chaining       

It works on the strategy of ‘What will happen next?’  
Here, the Inference Engine follows the chain of conditions and derivations
and finally deduces the outcome. It considers all the facts and rules. And
sorts them before concluding to a solution.
The strategy is followed for working on conclusions, result or effect.
INTERFERENCE ENGINE

Backward Chaining
With this strategy, an expert finds out the answer to the question, ‘Why this
happens?’ on the basis of what has already happened, the Inference Engine
tries to find out which condition would have happened in the past for this
result. This strategy is followed for finding out causes or reason. For e.g.
diagnosis of blood cancer in humans.
KNOWLEDGE BASED

Knowledge-based systems can be constructed by obtaining this knowledge

from a human expert and transforming it into a form that a computer may
use to solve similar problems. The ‘expert’ programme does not know what
it knows through the raw volume of facts in the computer's memory, but by
virtue of a reasoning-like process of applying a set of rules to the
knowledge. It chooses among alternatives, not through brute-force
calculation, but by using some of the same rules-of-thumb that human
experts use.

Components of Knowledge Base

The knowledge base of an ES is a store of both, factual and heuristic
knowledge.
Factual Knowledge  − It is the information widely accepted by the
Knowledge Engineers and scholars in the task domain.
Heuristic Knowledge  − It is about practice, accurate judgement, one’s
ability of evaluation, and guessing.

EXAMPLE : Healthcare has remained an important market for knowledge-

based systems, which are now referred to as  clinical decision-support
systems in the health sciences context.
 CASE STUDY
Mary Kay Cosmetics

Death of expert system:A case study of success and

failure

A decision team composed  of managers and staff experts at Mary Kay

Cosmetics develops for new and revised products as well as set their prices.
The results in the process has results that cost the company a lot. If the
packaging and the product are not compatible it can cause product to lose
it's colour. So the team at Mary Kay decided to develop an Expert System to
design better packaging and prevent losses.
Identifying the problem:
Selection of the packaging was the biggest problem because it is based on
chemical composition and marketing requirements. Normally too much
thought wasn't put into the packaging as there were no formal procedures.
They relied on heuristic knowledge based on past experiences to develop
the packaging which took a lot of time and effort. Moreover, this resulted in
the redesigning of the package due to conflict of opinion between the
design team and the marketing team.

Knowledge and Information Sources used

Marketing requirements contained within the product specification

Knowledge of thech emical formulation used in the product
Knowledge of the performance of previous container types for similar
product formulations·      
Results of compatibility tests on similar container types and similar
product formulations
Vendor information  
Cosmetic industry and packaging industry publications  
Manufacturing process information
Shipping requirements (e.g., government regulations on hazardous
material)    
The company then worked with University of North Texas  they
developed an ES. Development costs of the ES were quite reasonable.
The Inference Engine operates on a knowledge base system, rather than a
rule based system. The employees provided the Neuron Data, which had
over 40 rules and consisted of mathematics tool plus two ES components.
They also used forward chaining , i.e. it followed a chain of derivations to
deduct the outcome.
The two ES were Package Material Selector(PMS), which recommended
suitable package materials and Product Cost Estimator(PCE),used the
output of the PMS to help with the design and product cost.
After the development Mary Kay trained on its operation. Marketing
requested their product to the formulator and the chemical data helped
identify the recommendations from the ES.It was The ES automated the
product/package compatibility, as well as some technical cost feasibility
issues. The ES later on could do most of the decision work on its own. This
in turn greatly speeded the entire process and reduced the amount of
effort.
The ES gave the recommendation more reasoning and educated the group
about the designs costs and other issues.
The ES resulted to be consistent and gradually  made the
results more reliable. Thus the initial package proposals became more
credible that resulted in saving a lot of time, money and reducing the
workload of the team members.
Reasons for success
Match between the abilities of the expert system solution and the nature of
the problem. Problem -solving process was suitable for incorporation as
network of rules. Cost benefits by using ES approach. Development costs of
the ES was done by graduate students so it was less expensive. The director of
package designed believed and was personally involved project and
supported throughout.

Failure of the Expert System

The problem was insufficient training regarding the ES. They maintained no
contact with the ES developers and no one knew how use Neuron Data's
software to maintain or enhance the ES. The IT unit of the firm was not
involved when the package design team needed help there was no one to turn
to. The ES got discontinued as it did not evolve. No one of authority wanted to
sustain the project and as a result no one was willing to contribute.

Conclusion
Although ES performed so well that the group ceased to meet for purposes of
making the decisions but instead assembled only to confirm and approve the
expert system's solution.
Despite the clear benefits associated with using this ES approach, the
application fell into disuse and the behavior of the group returned to the pre-
ES

THANK YOU