Expert Systems

An Introduction to Some Of the Applications Of Expert system

Presenters

Raj Kumar Singh Vikas Kumar Madhwendra Gupta Kuwar Singh Mohd Asif Vaishnavesh Shukla Sourabh Panchall

10MCA061 10MCA060 10MCA056 10MCA057 10MCA055 10MCA064 10MCA059

Expert Systems
What is an Expert System

An intelligent computer program that uses knowledge and inference procedures to solve problems that are difficult enough to require human expertise for their solutions. - Professor Edward Feigenbaum, Stanford

Expert Systems
What is an Expert System

An experts knowledge is specific to one problem domain. A problem domain is medicine, science, engineering, etc. The experts knowledge about solving specific problems is called the knowledge domain. Knowledge is represented in an expert system as rules. In the knowledge domain that it knows about, the expert system reasons or makes inferences to produce the solution of a problem.

Expert Systems
Components of an Expert System

Knowledge base Inference Engine User Interface

Expert Systems
Why Use Expert System

Experts are not always available. An expert system can be used anywhere, any time. Human experts are not 100% reliable or consistent Experts may not be good at explaining decisions Cost effective

Expert Systems
Problems With Expert System

Limited domain Systems are not always up to date, and dont learn No common sense Experts needed to setup and maintain system

Expert Systems
Applications Of Expert System

Some Real Life Applications Of Expert Systems R1(XCON) MYCIN

DENDRAL
HEARSAY

Expert Systems
Applications Of Expert System

R1(XCON)(1980)
One of the first commercially successful expert system. Developed By John McDermott from Carnegie Mellon University (CMU).

Expert Systems
R1(XCON) Expert System

Main Task of R1(XCON )

Expert Systems
R1(XCON) Expert System

Main Task of R1(XCON ) Knowledge Representation Production Rules

Expert Systems
R1(XCON) Expert System

Main Task of R1(XCON ) Knowledge Representation Production Rules Inference Engine

Forward chaining

Expert Systems
R1(XCON) Expert System

Main Task of R1(XCON ) Knowledge Representation Production Rules Inference Engine

Forward chaining

Results Better quality of solutions Ten times faster estimated savings $25 million/year

Expert Systems
R1(XCON) Expert System

XCON has two types of knowledge:

The constraint knowledge The knowledge of components

Expert Systems
R1(XCON) Expert System

Working of the XCON System

In general, XCON works in an exception handling mode at every point. Typically a pair of rules would look like: If A and B and C then do Action1; If A and B and C and D then do Action2. If in a given state, A, B, C and D are all true, then the second rule is preferred to the first

Expert Systems
Applications Of Expert System

MYCIN (1984)
MYCIN is one of the most widely known of all expert system applications. Developed at Stanford University, By Bruce G Buchanan and Edward H Shortliffe.

Expert Systems
MYCIN Expert System

Domain of MYCIN
Diagnosing bacterial infections of blood.

Tracks down the organism causing the infection and prescribes a treatment.

Expert Systems
MYCIN Expert System

Domain of MYCIN
Diagnosing bacterial infections of blood.

Tracks down the organism causing the infection and prescribes a treatment.

Target of MYCIN
Physicians, Medical Students, Paramedics

Expert Systems
MYCIN Expert System

Working of MYCIN
The application is text-based and asks several questions requiring input. The first three questions request a patients background information Then several questions to identify the significance of the infecting organism

After about 50-60 questions, MYCIN prints the diagnostic hypotheses on which the therapy and antibiotics will be based off of.

Expert Systems
MYCIN Expert System

Working of MYCIN
MYCIN proceed through each rule, determining if the rule is false or true, and then will go onto the next rule. At the end of the consultation, all the answers will be compiled to discover which drugs should be selected.

Expert Systems
MYCIN Expert System

Despite the successful validation, MYCIN continues to be an academic system.

Reasons: Partly, in the medical domain one hesitates to entrust the task of diagnosis to a machine - the risks are too high. Secondly, the question of accountability arises. Who is to be blamed if the system makes a wrong diagnosis and the patient suffers because of that? MYCIN's domain includes only bacterial blood infections, which is a very small part of clinical medicine

Conclusion
Its Over! Expert Systems are a practical application of AI that has a deep past that draws from the work of many people. Early expert systems were expensive and difficult to build. With the advent of expert system tools like clips, expert systems can be built for much less cost and in less time. Procedural based programming languages like Java RULE!

References
Its Over! http://www.aiinc.ca/demos/whale.html

http://www.vanguardsw.com/decisionscript/examples.htm

http://www.exsys.com/demomain.html
http://www.expertise2go.com/webesie/car http://www.expertise2go.com/webesie/wine