Expert System

Group Members: Nabeel Hussain Syed Owais Ali

(SP07-BB-0006) (SP07-BB-0135)

Present to; Respected Sir Manoj Kumar

Presentation Topic

Agenda  Definitions  Expert System Concept  Expert System Components  Expert System Tasks  Expert System Domain  Expert System Characteristics  Advantages of Expert Systems  History and Examples  Summary

Knowledge-based Systems A knowledge-based system is a program whose performance depends more on the explicit presence of a large body of knowledge than on the possession of ingenious computational procedures. An Expert System is a KBS whose performance is intended to rival that of human experts. I.e., an expert system achieves expert level performance, while being highly domain specific.

How ES differ form other AI  Subject matter of realistic complexity that

normally requires a considerable amount of human expertise.  High performance in terms of speed and reliability is needed.  Must be capable of explaining and justifying solutions or recommendations.

Expert System Definition An expert system is a computer program that represents and reasons with knowledge of some specialist subject with a view to solving problems or giving advice. Possess knowledge Specific domain Solving problem or giving advice

Basic Expert System Concepts  Knowledge base  Inference engine  Facts  Expertise  Problem domain  Knowledge domain of the expert

Expert System components User interface Explanation facility- explains reasoning of the system to a user

Knowledge Base – production memory (rules) Working memory- global database of facts Inference engine Agenda- prioritized list of rules satisfied by facts Knowledge acquisition facility

Expert System Tasks  The interpretation of data  Diagnosis of malfunctions  Structural analysis of complex objects  Configuration of complex objects  Planning sequences of actions

Engineering Motivations Faster Reliable Cheaper Institutionalized memory E.g., HP micro-fabrication system

Less training

Expert Systems Domains  Medical and health applications  Agricultural, Livestock, and food issues

and needs  Energy Options  Natural Resource Exploitation  Space Technology

Expert System Characteristics  Simulates human reasoning about a

problem domain  Performs reasoning over representations of human knowledge.  Solves problems by heuristic or approximate methods.

Advantages of Expert systems Increased availability Reduced cost Reduced danger Permanence Multiple expertise Increased reliability Explanation Fast response; steady, unemotional complete response at all times; Intelligent tutor, Intelligent database

Early Expert System DENDRAL (’68, Feigenbaum,Buchanan, Letter berg)’ first expert system analyzed NMR mass spectrogram data to determine the geometric arrangement of atoms in a molecule. It is (was?) in routine use by chemists, and has contributed to refereed journal publications.

Different Expert Systems Agricultural Expert systems Rice-Crop Doctor National Institute of Agricultural Extension Management (MANAGE) has developed an expert system to diagnose pests and diseases for rice crop and suggest preventive/curative measures. The rice crop doctor illustrates the use of expert-systems.

Farm Advisory System Punjab Agricultural University, Ludhiana, has developed the Farm Advisory System to support agri-business management. The conversation between the system and the user is arranged in such a way that the system asks all the questions from user one by one which it needs to give recommendations on the topic of farm Management.

Different Expert Systems Medical Expert System HELP The HELP (Health Evaluation through Logical Processes) System is a complete knowledge based hospital information system. It supports not only the routine application of an HIS including ADT, order entry/charge capture, pharmacy, radiology, nursing documentation, ICU monitoring, but also supports a robust decision support function. The HELP system is an example of this type of knowledge-based hospital information system.

PEIRS

(Pathology Expert Interpretative Reporting System) appends interpretative comments to chemical pathology reports (Edwards et al., 1993). The knowledge acquisition strategy is the Ripple Down Rules method, which has allowed a pathologist to build over 2300 rules without knowledge engineering or programming support.. PEIRS commented on about 100 reports/day. Domains covered include thyroid function tests, arterial blood gases, glucose tolerance tests, hCG, catecholamine and a range of other hormones.

Summary Expert Systems solved practical problems with applications of logic based Techniques. However, handling certainty was generally given short shrift. There were successes in many areas. Expert System help to make the work easier than everbefore.