Expert system Examples RBS Classic systems

Expert system : Examples

RBS “Classic” systems n n Pre-1980 s Systems showed how to n capture heuristic knowledge and store it; n make a software that could mimic advice dispensation like expert human do. Techniques that were implemented were used in many subsequent systems, Many expert system shells were developed. CS 331/531 Dr M M Awais 2

RBS Expert systems n MACSYMA n n DENDRAL n n advised the user on how to solve complex maths problems. advised the user on how to interpret the output from a mass spectrograph MYCIN PROSPECTOR R 1/XCON CS 331/531 Dr M M Awais 3

RBS Others n n n n CENTAUR INTERNIST All medical expert systems PUFF CASNET DELTA - locomotive engineering Drilling Advisor - oilfield prospecting Exper. Tax - tax minimisation advice XSEL - computer sales CS 331/531 Dr M M Awais 4

RBS Task Classification n n Various tasks could be performed A layout presented by Hayes-Roth & colleagues in 1983 is presented here CS 331/531 Dr M M Awais 5

RBS Diagnosis n finding faults in a system, or diseases in a living system MYCIN - diagnosed blood infection. Shortliffe, 1976. CS 331/531 Dr M M Awais 6

RBS Interpretation n The analysis of data, to determine their meaning PROSPECTOR - interpreted geological data as potential evidence for mineral deposits. Duda, Hart, et al 1976. CS 331/531 Dr M M Awais 7

RBS Monitoring n The continuous interpretation of signals from a system for avoiding dangerous situations NAVEX - monitored radar data and estimated the velocity and position of the space shuttle. Marsh, 1984 CS 331/531 Dr M M Awais 8

RBS CS 331/531 Dr M M Awais 9

RBS Design n To ensure production of specifications, satisfying particular requirements R 1/XCON - configured VAX computer systems on the basis of customers' needs. Mc. Dermott, 1980. CS 331/531 Dr M M Awais 10

RBS Planning n Production of a sequence of actions that will achieve a particular goal. MOLGEN - planned chemical processes whose purpose was to analyse and synthesise DNA. Stefik, 1981. CS 331/531 Dr M M Awais 11

RBS CS 331/531 Dr M M Awais 12

RBS Instruction: n Intelligent Tutoring Systems Teaching a student a body of knowledge, varying the teaching according to assessments SOPHIE - instructed the student on the repair of an electronic power-pack. Brown, Burton & de Kleer, 1982. CS 331/531 Dr M M Awais 13

RBS Prediction n Forecasting future events, using a model based on past events. PLANT - predicted the damage to be expected when a corn crop was invaded by black cutworm. Boulanger, 1983. CS 331/531 Dr M M Awais 14

RBS CS 331/531 Dr M M Awais 15

RBS Debugging & repair n Generating, administering remedies for system faults. COOKER ADVISER - provides repair advice with respect to canned soup sterilising machines. Texas Instruments, 1986. CS 331/531 Dr M M Awais 16

RBS CS 331/531 Dr M M Awais 17

RBS Controls n Governing the behaviour of a system by anticipating problems, planning solutions, and monitoring actions. VENTILATOR MANAGEMENT ASSISTANT scrutinised the data from hospital breathingsupport machines, and provided accounts of the patients' conditions. Fagan, 1978. CS 331/531 Dr M M Awais 18

RBS MYCIN: Diagnosis System n n Domain: diagnose blood infections of the sort that might be contracted in hospital Developed by: Edward Shortliffe and colleagues, 1972 to late 1970 s. CS 331/531 Dr M M Awais 19

RBS MYCIN n Purpose: to assist a physician, who was not an expert in the field of antibiotics, with the diagnosis & treatment of blood disorders (and in particular to establish whether the patient was suffering from a serious infection like meningitis). n n Input: symptoms & test results Output: a diagnosis, accompanied by a degree of certainty, & recommended therapy CS 331/531 Dr M M Awais 20

RBS MYCIN n n n Knowledge representation: production rules Inference engine: Mixed chaining, but principally backward chaining from a top goal Dealing with uncertainty: calculating By certainty factors. CS 331/531 Dr M M Awais 21

RBS MYCIN · A Complete system that did complex task. Performed better than medical students and nonspecialist doctors. · Performed equally good to blood infection specialist doctors · MYCIN was a laboratory demonstration only · Was never commercialised, was never marketed, or installed in a hospital and used for routine work. · CS 331/531 Dr M M Awais 22

RBS MYCIN · Description of the system. · Written in LISP. · MYCIN was a mixed-chaining production system. CS 331/531 Dr M M Awais 23

RBS MYCIN 1. The sequence of operations was that the system asked: 1. Questions to get general details about the patient (name, age, sex, race, clinical test results already known). 2. Questions designed to find a possible, general diagnosis (e. g. the patient has probably got some form of meningitis), by forward chaining. CS 331/531 Dr M M Awais 24

RBS MYCIN Questions designed to test this theory, and establish specific details, by backward chaining. This was where most of the reasoning was done. · Questions designed to produce a recommended treatment, again by forward chaining. · CS 331/531 Dr M M Awais 25

RBS MYCIN n MYCIN could explain its reasoning in a rather simple way: n when asked "Why do you think that is the diagnosis? ”, MYCIN listed the rules it had applied, in reverse order, with CFs. n When asked "Why do you want to know that? ", MYCIN described the rule it was trying to execute, and what value it was trying to find. CS 331/531 Dr M M Awais 26

RBS MYCIN A Consultation with MYCIN @ mycin MYCIN 26 -March Instructions? (Y or N) n N 26 -March 10: 42 -----PATIENT-1 ----Patient's name: n Yousaf CS 331/531 Dr M M Awais 27

RBS Consultation with MYCIN Age? n 34 Sex? n Why n [i. e. Why is it important to determine the sex of PATIENT-1? ] The sex of the patient is one of the four standard parameters that identify a patient. This may be useful later. CS 331/531 Dr M M Awais 28

RBS Consultation with MYCIN Sex? n Male Race? n Sindhi Are there any cultures for. Yousaf that may be related to the present illness, and from which organisms have been grown successfully in the lab? n No CS 331/531 Dr M M Awais 29

RBS Consultation with MYCIN Are there any pending cultures for Yousaf? n Yes -----CULTURE-1 ----From what site was the specimen for CULTURE-1 taken? n Cerebro Spinal Fluid Please give the date and time when the pending CSF culture was obtained. CS 331/531 Dr M M Awais 30

RBS Consultation with MYCIN 26 -March-7: 00 Was a smear examined at the time the specimen was obtained? n Yes Were there any cultures seen on the smear of the specimen? n No Are there any other pending cultures? n CS 331/531 Dr M M Awais 31

RBS Consultation with MYCIN No Has Yousaf recently had symptoms of persistent headache or other abnormal neurological symptoms (dizziness, lethargy, etc)? n Yes Has Yousaf recently had objective evidence of abnormal neurological signs (nuchal rigidity, coma, seizures, etc) documented by a physician? n CS 331/531 Dr M M Awais 32

RBS A Consultation with MYCIN Yes The CSF cultures will be considered to be associated with MENINGITIS. Please give the date on which clinical evidence (symptoms, signs, or laboratory tests) of the meningitis first appeared. n 25 March 10: 00 Has Yousaf had neurosurgery ? n CS 331/531 Dr M M Awais 33

RBS A Consultation with MYCIN Why n [i. e. WHY is it important to determine whether PATIENT-1 has had neurosurgery ? ] This will aid in determining the organisms (other than those seen on cultures or smears) that might be causing the infection. n CS 331/531 Dr M M Awais 34

RBS A Consultation with MYCIN It has already been established that [1] the culture that requires therapy is meningitis, and n [2] organisms were not seen on the stain of the pending csf culture (CULTURE-1), and n [3] the type of infection is bacterial n CS 331/531 Dr M M Awais 35

RBS A Consultation with MYCIN Therefore, if n n n [4] Yousaf has had neurosurgery and , [5] the time since the neurosurgical operation is less than two months, and [6] the type of neurosurgeryis not ventricularurethal shunt then n n there is evidence that the organisms that might be causing the infection are staphylococcus-coag-pos (0. 75), staphylococcus- coag -neg (. 5), e. coli (. 4), klebsiella (0. 3) Author: Yu [RULE 511] CS 331/531 Dr M M Awais 36

RBS A Consultation with MYCIN Has Yousaf had neurosurgery ? n How [3] n [i. e. HOW was it established that the type of infection is bacterial? ] CS 331/531 Dr M M Awais 37

RBS A Consultation with MYCIN The following rules concluded about the likelihood that the type of infection is bacterial: Rule Yes No 500 (. 4) 501 (. 17) 502 (. 1) 524 (. 42) 504 (. 28) Thus it has been established that the type of infection might be bacterial. CS 331/531 Dr M M Awais 38

RBS A Consultation with MYCIN Has Yousaf had neurosurgery ? n No Is Yousaf a burn patient? n Yes CS 331/531 Dr M M Awais 39

RBS A Consultation with MYCIN I have found evidence (RULE 507) that treatment should cover for Diplococcus pneumoniae causing meningitis. I have found evidence (RULE 545) that treatment should cover for e. coli causing meningitis. I have found evidence (RULE 545 RULE 578) that treatment should cover for Pseudomonas aeruginosa causing meningitis. CS 331/531 Dr M M Awais 40

RBS A Consultation with MYCIN Does Yousaf have focal neurological signs? n No [Determining which dosages are desirable for use against the e. coli. . . ] [Determining which drugs are desirable for use. . . ] CS 331/531 Dr M M Awais 41

RBS A Consultation with MYCIN INFECTION-1 is MENINGITIS + <ITEM-1> DIPLOCOCCUS-PNEUMONIAE (from clinical evidence only) + <ITEM-2> E. COLI (from clinical evidence only) + <ITEM-3> PSEUDOMONAS AERUGINOSA (from clinical evidence only) CS 331/531 Dr M M Awais 42

RBS A Consultation with MYCIN [REC-1] My preferred therapy recommendation is as follows: In order to cover for items <1 2 3>: Give the following in combination: 1) AMPICILLIN Dose: 3. 85 g(30. 8 ml) q 4 h IV 2) GENTAMICIN Dose: 131 mg(3. 2 ml) q 8 h IV CS 331/531 Dr M M Awais 43

RBS A Consultation with MYCIN Comments: monitor serum concentrations. Since high concentrations of penicillins can inactivate aminoglycosides, do not mix these antibiotics in the same IV bottle. Do you wish to see the next choice therapy? n No CS 331/531 Dr M M Awais 44

RBS CROP ADVISOR n n n Developed by ICI (in 1989) to advise cereal grain farmers on appropriate fertilisers and pesticides for their farms. The choice of chemical, amount, and time of application depends on such factors as crop to be grown, previous cropping, soil condition, acidity of soil, and weather. Farmers can access the system via the internet. CS 331/531 Dr M M Awais 45

RBS CROP ADVISOR n n n Given relevant data, the system produces various financial return projections for different application rates of different chemicals. The system uses statistical reasoning to come to these conclusions. If the question asked is outside the system's expertise, it refers the caller to a human expert. CS 331/531 Dr M M Awais 46

RBS CROP ADVISOR n The chief advantages of this system have been n that employees at ICI have been relieved of the need to provide lengthy telephone advice sessions, n and the quality of the advice has become much more uniform, which has increased confidence in the company's products. CS 331/531 Dr M M Awais 47

RBS R 1/XCON n n Knowledge domain: Configuring VAX computers, to customers' specifications. Written by: John Mc. Dermott and colleagues, 1978 - 1981 Input: Required characteristics of the computer system. Output: Specification for the computer system. CS 331/531 Dr M M Awais 48

RBS R 1/XCON n n n Knowledge representation: Production rules. Inference engine: Forward chaining: the output specification was assembled in working memory. Dealing with uncertainty: mechanism for No this: the system simply assembled one answer, assumed to be good enough to do the job. CS 331/531 Dr M M Awais 49

RBS R 1/XCON n Significance: A rather simple forward-chaining rulebased expert system, which performed well, solved a difficult manufacturing problem, and proved to be enormously profitable. CS 331/531 Dr M M Awais 50

RBS n n R 1/XCON Digital Equipment Corporation's problem was that they were marketing the best-selling Vax-11 series of computers, and the department responsible for configuration was failing to keep up with customer demand. Each computer was the result of a consultation between a sales executive and the customer, designed to discover the customer's requirements, after which a configuration was drawn up, from which the system was built. Each configuration was taking 25 minutes, and orders were arriving at a rate of 10, 000 a year. High error rate in the configurations was recorded. CS 331/531 Dr M M Awais 51

RBS n n R 1/XCON DEC tried a conventional program to solve this problem, with no success, then asked Mc. Dermott to write an AI system. Mc. Dermott wrote R 1/XCON. By 1986, it had processed 80, 000 orders, and achieved 95 -98% accuracy. It was reckoned to be saving DEC $25 M a year. CS 331/531 Dr M M Awais 52

RBS n R 1/XCON However, R 1/XCON suffered from the shortcomings of simple production-rulebased systems. n When the nature of the task changed, fresh rules were simply added at the end of the rulebase. n Soon, the rulebase was very large, unreliable and incomprehensible. n Expensive rewriting was needed to restore the operation of the system. CS 331/531 Dr M M Awais 53

RBS OPTIMUM-AIV n n OPTIMUM-AIV is a planner used by the European Space Agency (1994) to help in the assembly, integration, and verification of spacecraft. It generates plans, and monitors their execution. CS 331/531 Dr M M Awais 54

RBS OPTIMUM-AIV n n it has a knowledgebase that describes the causal links that describe that in what particular order the assembly must be undertaken. Also, if a plan fails and has to be repaired, the system can make intelligent decisions about the alternative plans that will work and will not. CS 331/531 Dr M M Awais 55

RBS OPTIMUM-AIV n n It can engage in hierarchical planning this involves producing a top-level plan with very little detail, and then turning this into increasingly more detailed lower-level plans. It can reason about complex conditions, time, and resources (such as budget constraints). CS 331/531 Dr M M Awais 56