Mis 009


Published on

Published in: Technology, Education
1 Like
  • Be the first to comment

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide

Mis 009

  1. 1. <ul><li>EXPERT SYSTEMS </li></ul><ul><li>or </li></ul><ul><li>KNOWLEDGE BASED SYSTEMS </li></ul>
  2. 2. <ul><li>When we wish to encode a rich source of knowledge within the program. </li></ul><ul><li>and ------ </li></ul><ul><li>The scope of systems knowledge is well defined. </li></ul><ul><li>An expert system could be defined as a program designed to model the problem solving ability of a human expert. It is a clone to the expert of real life. </li></ul>
  3. 3. An expert needs - How to reason with this knowledge. Knowledge processor also called INFERENCE ENGINE. You need to learn inferencing techniques. REASONING Specialized knowledge on problem areas. Facts, rules, concepts and relationships. To store this in a KNOWLEDGE BASE, you need to learn KNOWLEDGE REPRESENTATION. KNOWLEDGE
  4. 4. WHY EXPERT SYSTEMS & NOT EXPERTS <ul><li>Affordable cost </li></ul><ul><li>Work at a uniform speed </li></ul><ul><li>Consistent in performance </li></ul><ul><li>Non perishable </li></ul><ul><li>Replaceable </li></ul><ul><li>Available anywhere </li></ul><ul><li>Always available </li></ul>
  5. 5. These can be designed as replacement to an expert <ul><li>When a human being exists with that knowledge </li></ul><ul><li>There is a client who needs their expertise </li></ul><ul><li>This expertise is not available </li></ul><ul><li>A software specialist to program this expertise </li></ul>
  6. 6. These can be for assisting an expert <ul><li>Information recall </li></ul><ul><li>Improve productivity </li></ul><ul><li>Manage the complexities </li></ul>
  7. 7. USAGE-AREAS <ul><li>Information Management </li></ul><ul><li>Transportation </li></ul><ul><li>Image Processing </li></ul><ul><li>Space Technology* </li></ul><ul><li>Geology </li></ul><ul><li>Sciences </li></ul><ul><li>Environment* </li></ul><ul><li>Power Systems* </li></ul><ul><li>Engineering* </li></ul><ul><li>Mining </li></ul><ul><li>Electronics* </li></ul><ul><li>Military* </li></ul><ul><li>Education </li></ul><ul><li>Meteorology </li></ul><ul><li>Computer Systems* </li></ul><ul><li>Medicine** </li></ul><ul><li>Communications </li></ul><ul><li>Mathematics </li></ul><ul><li>Chemistry </li></ul><ul><li>Manufacturing** </li></ul><ul><li>Business </li></ul><ul><li>Law </li></ul><ul><li>Agriculture** </li></ul>As per a survey, the ES were found to be in :(**-Max, *-Next Max)
  8. 8. USAGE-PURPOSES NAVEX monitors radar data and estimates the velocity and position of the space shuttle MONITORING FXAA Provides auditing assistance in foreign exchange trading locating irregular transactions INTERPRETATION GUIDON instructs medical students on antimicrobial therapy for bacterial infections INSTRUCTION NEAT infers system malfunctioning of data processing and telecommunications network equipment DIAGNOSIS PEACE is an expert system developed to assist engineers in the design of an electronic circuit DESIGN VM monitors a patient in an intensive care unit and controls the treatment CONTROL
  9. 9. USAGE-PURPOSES STEAMER simulates and explains the operation of the Navy’s 1078-class frigate system propulsion plant to aspiring NAVAL engineers SIMULATION IREX assists in the selection of industrial robots in a work environment. It identifies the best choice from a list of possibilities SELECTION BLUE BOX recommends an appropriate therapy for patients suffering from depression PRESCRIPTION PLANT predicts the damage to corn caused by the invasion of black cutworms PREDICTION PLANPOWER provides a wide range of financial plans for households in the areas of cash management PLANNING
  10. 10. EXPERT SYSTEM DEVELOPMENT MEDIUM <ul><li>1970s : LISP, PROLOG and OPS </li></ul><ul><li>1980s : Expert System Shells (PC Based) </li></ul><ul><li>A shell is a programming environment that contains all of the necessary utilities for both developing and running an expert system. </li></ul><ul><li>Other programming languages can also be used. </li></ul><ul><li>All these can be on : </li></ul><ul><li>PCs/Workstations/Minis/Mains </li></ul><ul><li>Largest number of shells is available on PCs today. </li></ul>
  11. 11. BASIC CONCEPTS OF EXPERT SYSTEMS <ul><li>EXPERTISE : Expertise includes: </li></ul><ul><ul><li>Facts about the problem area </li></ul></ul><ul><ul><li>Theories about the problem area </li></ul></ul><ul><ul><li>Hard-n-fast rules & procedures </li></ul></ul><ul><ul><li>Rules of what to do in a problem situation </li></ul></ul><ul><li>EXPERTS : </li></ul><ul><li>To mimic a human expert, it is necessary to build a system that exhibits a capability to: </li></ul><ul><ul><li>Recognize and formulate the problem </li></ul></ul><ul><ul><li>Solve the problem quickly </li></ul></ul><ul><ul><li>Explain the solution </li></ul></ul><ul><ul><li>Learn from experience </li></ul></ul><ul><ul><li>Restructure knowledge </li></ul></ul><ul><ul><li>Break rules </li></ul></ul><ul><ul><li>Determine relevance </li></ul></ul>
  12. 12. BASIC CONCEPTS OF EXPERT SYSTEMS <ul><li>TRANSFERING EXPERTISE : </li></ul><ul><li>The objective of an ES is to transfer expertise from the expert to the computer and then on to other humans. This includes: </li></ul><ul><ul><li>Knowledge acquisition (from experts) </li></ul></ul><ul><ul><li>Knowledge representation (in the computer) </li></ul></ul><ul><li>In the knowledge base, you may have : </li></ul><ul><ul><li>Facts </li></ul></ul><ul><ul><li>Procedures </li></ul></ul>
  13. 13. BASIC CONCEPTS OF EXPERT SYSTEMS <ul><li>REASONING : </li></ul><ul><li>From knowledge base, the ES is programmed to make INFERENCES. The reasoning is performed in a component called INFERENCE ENGINE which includes procedures regarding problem solving by an approach called SYMBOLIC REASONING. </li></ul><ul><li>EXPLANATION CAPABILITY : </li></ul><ul><li>ES has the ability to explain its advice or recommendations and even to justify why a certain action was not recommended. </li></ul>
  14. 14. HUMAN ELEMENT IN EXPERT SYSTEMS <ul><li>THE EXPERT </li></ul><ul><li>Also called DOMAIN EXPERT, a person possesses some special knowledge, judgement, experience and methods. </li></ul><ul><li>THE KNOWLEDGE ENGINEER: </li></ul><ul><li>The person who helps the human experts structure the problem area by : </li></ul><ul><ul><li>Interpreting </li></ul></ul><ul><ul><li>Integrating human answers to questions </li></ul></ul><ul><ul><li>Drawing analogies </li></ul></ul><ul><ul><li>Posing counter examples </li></ul></ul><ul><ul><li>Highlighting conceptual difficulties </li></ul></ul>
  15. 15. HUMAN ELEMENT IN EXPERT SYSTEMS <ul><li>THE USER </li></ul><ul><li>Person may be using an ES as a : </li></ul><ul><ul><li>Consultant – one who seeks advice </li></ul></ul><ul><ul><li>Instructor - one who wants to learn </li></ul></ul><ul><ul><li>Partner - one who wants to improve KB </li></ul></ul><ul><ul><li>Colleague - one who is an expert </li></ul></ul>
  17. 17. User Interface Recommended Action Explanation Inference Engine, Draws Conclusions KNOWLEDGE BASE FACTS: What is known about the problem area Rules: Logical Reference (Relation between Symptoms and Causes) Knowledge Engineer Expert Blackboard (Workplace) Plan: Agenda Solution: Problem Description Reasoning Capability Improvement KA Facts about the specific incident USER