2. B. I NFORMATION T ECHNOLOGY (IS) CISB434: D ECISION S UPPORT S YSTEMS Chapter 7: Artificial Intelligence & Expert Systems

3. L EARNING O BJECTIVES Explore the concept and evolution of artificial intelligence Describe the concept and evolution of rule-based expert systems (ES) Examine the structure of rule-based ES Explain the development process of ES Describe the benefits and limitations of rule- based systems 2

4. A RTIFICAL I NTELLIGENCE & E XPERT S YSTEMS Concept & Evolution of Artificial Intelligence

5. A RTIFICIAL I NTELLIGENCE C ONCEPTS Knowledge-based systems (KBS) Technologies that use qualitative knowledge rather than mathematical models to provide the needed supports Artificial intelligence (AI) The sub-field of computer science con-cerned with symbolic reasoning and pro-blem solving Turing test A test designed to measure the intelli-gence of a computer 4

6. A RTIFICIAL I NTELLIGENCE C ONCEPTS Characteristics of artificial intelligence Symbolic processing Numeric versus symbolic Algorithmic versus heuristic Heuristics Informal, judgmental knowledge of an applica-tion area that constitutes the rules of good judg-ment in the field 5

7. A RTIFICIAL I NTELLIGENCE C ONCEPTS Characteristics of artificial intelligence Heuristics also encompasses the knowledge of how to solve problems efficiently and effectively how to plan steps in solving a complex problem how to improve performance 6

8. A RTIFICIAL I NTELLIGENCE C ONCEPTS Characteristics of artificial intelligence Inferencing Reasoning capabilities that can build higher-level knowledge from existing heuristics Machine learning Learning capabilities that allow systems to adjust their behavior and react to changes in the outside environment 7

9. A RTIFICIAL I NTELLIGENCE E VOLUTION Naïve solutions stage General methods stage Domain knowledge stage Expert ystem or Knowledge-based system Multiple integration stage Embedded applications stage 8

10. A RTIFICIAL I NTELLIGENCE E VOLUTION 9

11. A RTIFICIAL I NTELLIGENCE A REAS 10

12. A RTIFICIAL I NTELLIGENCE A PPLICATIONS Expert System (ES) A computer system that applies reasoning methodologies to knowledge in a specific domain to render advice or recommenda-tions, much like a human expert A computer system that achieves a high level of performance in task areas that, for human beings, require years of special education and training 11

13. A RTIFICIAL I NTELLIGENCE A PPLICATIONS Natural Language Processing (NLP) Using a natural language processor to interface with a computer-based system Two sub-fields of NLP Natural language understanding Natural language generation 12

14. A RTIFICIAL I NTELLIGENCE A PPLICATIONS Natural Language Processing (NLP) Speech (voice) understanding Translation of the human voice into individual words and sentences understandable by a computer 13

15. A RTIFICIAL I NTELLIGENCE A PPLICATIONS Robotics and Sensory systems Robots Machines that have the capability of performing manual functions without human intervention An intelligent robot has some kind of sensory apparatus, such as a camera, that collects information about the robot’s operation and its environment 14

16. A RTIFICIAL I NTELLIGENCE A PPLICATIONS Computer vision and scene recognition Visual recognition The addition of some form of computer intelligence and decision-making to digitized visual information, received from a machine sensor such as a camera The basic objective of computer vision is to interpret scenarios rather than generate pictures 15

17. A RTIFICIAL I NTELLIGENCE A PPLICATIONS Intelligent Computer-aided Instruction (ICAI) The use of AI techniques for training or teaching with a computer Intelligent Tutoring System (ITS) Self-tutoring systems that can guide learners in how best to proceed with the learning process 16

18. A RTIFICIAL I NTELLIGENCE A PPLICATIONS Automatic programming Allows computer programs to be automatically generated when AI techniques are embedded in compilers Neural computing Neural (computing) networks An experimental computer design aimed at building intelligent computers that operate in a manner modeled on the func-tioning of the human brain 17

19. A RTIFICIAL I NTELLIGENCE A PPLICATIONS Game playing One of the first areas that AI researchers studied It is a perfect area for investigating new strategies and heuristics because the results are easy to measure Language translation Automated translation uses computer pro-grams to translate words and sentences from one language to another without much interpretation by humans 18

20. A RTIFICIAL I NTELLIGENCE A PPLICATIONS Fuzzy logic Logically consistent ways of reasoning that can cope with uncertain or partial informa-tion characteristic of human thinking and many expert systems Genetic algorithms Intelligent methods that use computers to simulate the process of natural evolution to find patterns from a set of data Intelligent Agent (IA) An expert or knowledge-based system embedded in computer-based information systems (or their components) to make them smarter 19

21. A RTIFICAL I NTELLIGENCE & E XPERT S YSTEMS Concepts & Evolution of Rule-based Expert Systems

22. E XPERT S YSTEMS R ULE - BASED S YSTEM Expert systems “are computer-based information systems that use expert knowledge to attain high-level decision performance in a narrow problem domain” Most ES are rule-based A system in which knowledge is represen-ted completely in terms of rules e.g. a system based on production rules 21

23. E XPERT S YSTEMS R ULE - BASED S YSTEM : E XAMPLE 22

24. E XPERT S YSTEMS B ASIC C ONCEPTS The basic concepts of ES include How to determine who experts are How expertise can be transferred from a person to a computer How the system works 23

25. E XPERT S YSTEMS B ASIC C ONCEPTS Expert A human being who has developed a high level of proficiency in making judgments in a specific, usually narrow, domain 24

26. E XPERT S YSTEMS B ASIC C ONCEPTS Expertise The set of capabilities that underlines the performance of human experts including extensive domain knowledge heuristic rules that simplify and improve app-roaches to problem solving meta-knowledge and meta-cognition and compiled forms of behavior that afford great economy in a skilled performance 25

27. E XPERT S YSTEMS B ASIC C ONCEPTS Features of ES Expertise Symbolic reasoning Deep knowledge Self-knowledge 26

28. E XPERT S YSTEMS B ASIC C ONCEPTS Why we need ES ES are an excellent tool for preserving professional knowledge crucial to a company's competitiveness ES is an excellent tool for documenting professional knowledge for examination or improvement ES is a good tool for training new employees and disseminating knowledge in an organization ES allow knowledge to be transferred more easily at a lower cost 27

29. E XPERT S YSTEMS A PPLICATIONS 28 Expert SystemsOrganizationApplication Domain MYCINStanford UnivMedical Diagnosis XCONDECSystem Configuration Expert TaxCoopers & LybrandTax Planning Fish-ExpertNorth ChinaFish disease diagnosis HelpDeskIQBMC RemedyHelp Desk Management eCareCIGNAInsurance Claim

30. E XPERT S YSTEMS C LASSICAL S UCCESSFUL ES DENDRAL project deduces likely molecular structure of com-pounds MYCIN diagnoses bacterial infections XCON determine optimal systems configuration 29

31. E XPERT S YSTEMS N EWER A PPLICATIONS FOR ES Credit analysis systems Pension fund advisors Automated help desks Homeland security systems Market surveillance systems Business process reengineering 30

32. E XPERT S YSTEMS A REAS FOR ES A PPLICATIONS Finance Data processing Marketing Human resources Manufacturing Homeland security Business process automation Health care management 31

33. A RTIFICAL I NTELLIGENCE & E XPERT S YSTEMS Structure of Rule-based Expert System

34. S TRUCTURE OF ES D EVELOPMENT E NVIRONMENTS Parts of expert systems used by builders knowledge base inference engine knowledge acquisition reasoning capability The knowledge engineer and the expert are considered part of these environments 33

35. S TRUCTURE OF ES C ONSULTATION E NVIRONMENT The part of an expert system that is used by a non-expert to obtain expert knowledge and advice workplace inference engine explanation facility recommended action user interface 34

36. S TRUCTURE OF ES 35

37. S TRUCTURE OF ES Three major components in ES are Knowledge base Inference engine User interface 36 41

38. S TRUCTURE OF ES ES may also contain Knowledge acquisition subsystem Blackboard (workplace) Explanation subsystem (justifier) Knowledge refining system 37 41

39. S TRUCTURE OF ES Knowledge acquisition (KA) The process of extraction and formulation of knowledge derived from various sources especially from experts 38 41

40. S TRUCTURE OF ES Knowledge base A collection of facts, rules, and procedures organized into schemas The assembly of all the information and knowledge about a specific field of interest 39 41

41. S TRUCTURE OF ES Inference engine The part of an expert system that actually performs the reasoning function 40 41

42. S TRUCTURE OF ES User interfaces The parts of computer systems that inter-act with users accepting commands from the computer keyboard and displaying the results gene-rated by other parts of the systems 41

43. S TRUCTURE OF ES Blackboard (workplace) An area of working memory set aside for the description of a current problem and for recording intermediate results in an expert system 42 41

44. S TRUCTURE OF ES Explanation subsystem (justifier) The component of an expert system that can explain the system’s reasoning and justify its conclusions 43 41

45. S TRUCTURE OF ES Knowledge-refining system A system that has the ability to analyze its own performance, learn, and improve itself for future consultations 44 41

46. H OW ES W ORK R EPRESENTING K NOWLEDGE Knowledge representation and organi-zation Expert knowledge must be represented in a computer-understandable format and organized properly in the knowledge base 45

47. H OW ES W ORK R EPRESENTING K NOWLEDGE Knowledge representation and organi-zation Different ways of representing human knowledge include Production rules Semantic networks Logic statements 46

48. H OW ES W ORK I NFERENCE M ECHANISMS The inference process Inference is the process of chaining multi-ple rules together based on available data 47

49. H OW ES W ORK I NFERENCE M ECHANISMS Forward chaining A data-driven search in a rule-based system 48

50. H OW ES W ORK I NFERENCE M ECHANISMS Backward chaining A search technique using if-then rules used in production systems that begins with the action clause of a rule and works backward through a chain of rules in an attempt to find a verifiable set of condition clauses 49

51. P ROBLEM A REAS S UITABLE FOR ES G ENERIC C ATEGORIES OF ES 50 Interpretation Prediction Diagnosis Design Planning Monitoring Debugging Repair Instruction Control

52. A RTIFICAL I NTELLIGENCE & E XPERT S YSTEMS Expert System Development Process

53. D EVELOPMENT OF ES A typical process for developing ES knowledge acquisition knowledge representation selection of development tools system prototyping evaluation improvement 52

54. D EVELOPMENT OF ES Defining the nature and scope of the problem Rule-based ES are appropriate when the nature of the problem is qualitative knowledge is explicit and experts are available to solve the problem effectively and provide their knowledge 53

55. D EVELOPMENT OF ES Identifying proper experts A proper expert should have a thorough understanding of Problem-solving knowledge The role of ES and decision support technology Good communication skills 54

56. D EVELOPMENT OF ES Acquiring knowledge Knowledge engineer An AI specialist responsible for the technical side of developing an expert system The knowledge engineer works closely with the domain expert to capture the expert’s know-ledge in a knowledge base The engineering discipline in which knowledge is integrated into computer systems to solve complex problems normally requiring a high level of human expertise 55

57. D EVELOPMENT OF ES Selecting the building tools General-purpose development environ-ment Expert system shell A computer program that facilitates relatively easy implementation of a specific expert sys-tem Analogous to a DSS generator 56

58. D EVELOPMENT OF ES 57

59. D EVELOPMENT OF ES Selecting the building tools Tailored turn-key solutions Contain specific features often required for developing applications in a particular domain 58

60. D EVELOPMENT OF ES Choosing an ES development tool Consider the cost benefits Consider the technical functionality and flexibility of the tool Consider the tool's compatibility with the existing information infrastructure Consider the reliability of and support from the vendor 59

61. D EVELOPMENT OF ES Coding the system The major concern at this stage is whether the coding process is efficient and properly managed to avoid errors Evaluating the system Two kinds of evaluation Verification Validation 60

62. A RTIFICAL I NTELLIGENCE & E XPERT S YSTEMS Benefits & Limitations of Expert Systems

63. E XPERT S YSTEMS B ENEFITS Increased output and productivity Decreased decision-making time Increased process and product quality Reduced downtime Capture of scarce expertise Flexibility Easier equipment operation 62

64. E XPERT S YSTEMS B ENEFITS Elimination of the need for expensive equipment Operation in hazardous environments Accessibility to knowledge and help desks Ability to work with incomplete or un-certain information Provision of training 63

65. E XPERT S YSTEMS B ENEFITS Enhancement of problem solving and decision making Improved decision-making processes Improved decision quality Ability to solve complex problems Knowledge transfer to remote locations Enhancement of information systems 64

66. E XPERT S YSTEMS P ROBLEMS & L IMITATIONS Knowledge is not always readily avail-able It can be difficult to extract expertise from humans The approach of each expert to a situ-ation assessment may be different yet correct 65

67. E XPERT S YSTEMS P ROBLEMS & L IMITATIONS Difficult to abstract good situational assessments when under time pressure Users of ES have natural cognitive limits ES work well only within a narrow domain of knowledge 66

68. E XPERT S YSTEMS P ROBLEMS & L IMITATIONS Most experts have no independent means of checking whether their con-clusions are reasonable The vocabulary that experts use to express facts and relations is often limited and not understood by others ES construction can be costly because of the expense of knowledge engineers 67

69. E XPERT S YSTEMS P ROBLEMS & L IMITATIONS Lack of trust on the part of end users may be a barrier to ES use Knowledge transfer is subject to a host of perceptual and judgmental biases ES may not be able to arrive at conclu-sions in some cases ES sometimes produce incorrect re- commendations 68

70. E XPERT S YSTEMS F ACTORS IN D ISUSE OF ES Lack of system acceptance by users Inability to retain developers Problems in transitioning from develop-ment to maintenance Shifts in organizational priorities 69

71. E XPERT S YSTEMS S UCCESS F ACTORS Management support must be cultivated Level of managerial and user involve-ment Sufficiently high level of knowledge Expertise available from at least one cooperative expert 70

72. E XPERT S YSTEMS S UCCESS F ACTORS The problem to be solved must be mostly qualitative The problem must be sufficiently narrow in scope The problem must be important and difficult enough to warrant development of an ES The ES shell must be of high quality and naturally store and manipulate the knowledge The user interface must be friendly for novice users 71

73. E XPERT S YSTEMS S UCCESS F ACTORS Knowledgeable system developers with good people skills are needed End-user attitudes and expectations must be considered End-user training is necessary The organizational environment should favor adoption of new technology The application must be well defined, structured, and it should be justified by strategic impact 72

74. ES ON THE W EB The relationship between ES and the Internet and intranets can be divided into two categories The Web supports of ES (and other AI) applications The support ES (and other AI methods) give to the Web 73

75. L INKS http://www.atwebo.com/dss_examples.htm#ARTI FICIAL%20INTELLIGENCE/EXPERT%20SYST ES%20EXAMPLES http://easydiagnosis.com/modules.html http://www.uky.edu/BusinessEconomics/dssakba/ instmat.htm#Videos 74

76. THE END T HANK Y OU FOR LISTENING

77. U SEFUL URLS http://www.trusoft.com/principles.html 76