Group Members: Nabeel Hussain Syed Owais Ali Present to; Respected Sir Manoj Kumar (SP07-BB-000

6) (SP07-BB-0135)

Presentation Topic

Agenda Definitions Expert System Concept Expert System Components Expert System Tasks xpert System Domain Expert System Characteristics Advantages of Expert Systems H istory and Examples Summary

E

Knowledge-based Systems A knowledge-based system is a program whose performance depends more on the expl icit presence of a large body of knowledge than on the possession of ingenious c omputational procedures. An Expert System is a KBS whose performance is intended to rival that of human e xperts. I.e., an expert system achieves expert level performance, while being hi ghly 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 just ifying solutions or recommendations.

Expert System Definition An expert system is a computer program that represents and reasons with knowledg e 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 of the expert

Facts

Expertise

Problem domain

Knowledge domain

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 fact s Inference engine Agenda- prioritized list of rules satisfied by facts Knowledg e acquisition facility

Expert System Tasks The interpretation of data Diagnosis of malfunctions Structural analysis of comp lex 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 and needs Energy Options

Agricultural, Livestock, and food issues Space Technology

Natural Resource Exploitation

Expert System Characteristics Simulates human reasoning about a problem domain Performs reasoning over representations of human knowledge. s problems by heuristic or approximate methods. Solve

Advantages of Expert systems Increased availability Reduced cost Reduced danger Permanence Multiple expertise Increased reliability Explanation Fast response; steady, unemotional complete r esponse 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 geometri c arrangement of atoms in a molecule. It is (was?) in routine use by chemists, a nd has contributed to refereed journal publications.

Different Expert Systems Agricultural Expert systems Rice-Crop Doctor National Institute of Agricultural Extension Management (MANAGE) has developed a n expert system to diagnose pests and diseases for rice crop and suggest prevent ive/curative measures. The rice crop doctor illustrates the use of expert-system s. Farm Advisory System Punjab Agricultural University, Ludhiana, has developed the Farm Advisory System to support agri-business management. The conversation between the system and th e user is arranged in such a way that the system asks all the questions from use r one by one which it needs to give recommendations on the topic of farm Managem ent.

Different Expert Systems Medical Expert System HELP The HELP (Health Evaluation through Logical Processes) System is a complete know ledge based hospital information system. It supports not only the routine applic ation of an HIS including ADT, order entry/charge capture, pharmacy, radiology, nursing documentation, ICU monitoring, but also supports a robust decision suppo rt function. The HELP system is an example of this type of knowledge-based hospi tal information system. PEIRS (Pathology Expert Interpretative Reporting System) appends interpretative commen ts to chemical pathology reports (Edwards et al., 1993). The knowledge acquisiti on strategy is the Ripple Down Rules method, which has allowed a pathologist to build over 2300 rules without knowledge engineering or programming support.. PEI RS commented on about 100 reports/day. Domains covered include thyroid function tests, arterial blood gases, glucose tolerance tests, hCG, catecholamine and a r ange of other hormones.

Summary Expert Systems solved practical problems with applications of logic based Techni ques. However, handling certainty was generally given short shrift. There were s uccesses in many areas. Expert System help to make the work easier than everbefo re.

Sign up to vote on this title
UsefulNot useful