Docstoc

Discovering Computers

Document Sample
Discovering Computers Powered By Docstoc
					           Topic 8
Intelligent Support Systems
Content

   Artificial Intelligence & Intelligent Behavior
   A.I: The Brief History of Time
   Knowledge & Artificial Intelligence
   The Commercial AI Field
   Expert System
   Natural Language Processing [NLP]
   Speech Recognition & Understanding
   Neural Computing
   Hybrid Systems
   Intelligent Agent
Artificial Intelligence & Intelligent Behavior

Artificial Intelligence (AI) is   AI is concerned with two basic
“behavior by a machine that, if   ideas.
performed by a human being,
                                   It involves studying the
would be called intelligent.”
                                     thought processes of
                                     humans;
AI’s ultimate goal is to build     It deals with representing
machines that will mimic human       those processes via
intelligence.                        machines
A.I: The Brief History of Time

 2002                                     •Hybrid technology, Intelligent Agent,
                                          Collaborative Intelligence, Humanoid,
                                                    Sociable Machines

                               •Deep Blue beats human Chess master
1990               •Data Mining, Face Recognition, Decision Support System
            •Tutoring System, Fuzzy System, Commercial AI system
1980                       •Machine Learning, Speech Recognition

1970          •Machine Vision, Natural Language Processing
                             •Expert Systems
1951          •Dartmouth Conference - The Birth of AI
                  •The Turing Test
1940
                                 •Neural Computation
         •1st Electronic Comp.
                •The Boolean Logic
1832    •The Birth of Analytical Engine
Knowledge & Artificial Intelligence
AI is frequently associated with the concept of knowledge.

   Such knowledge consists of facts, concepts, theories,
    heuristic methods, procedures, and relationships.

Knowledge Base = an organized & stored collection of
knowledge related to a specific problem (or an opportunity) to
be used in an intelligent system.

Organizational Knowledge Base = The collection of knowledge
related to the operation of an organization.
The Commercial AI Field


Expert Systems (ESs) are          Speech (Voice) Understanding is
computerized advisory             the recognition and
programs that attempt to          understanding by a computer of
imitate the reasoning processes   a spoken language.
of experts in solving difficult
problems.

Natural language processing       Robotics refers to a broad
(NLP) gives computer users the    category of systems that
ability to communicate with the   combines sensory systems such
computer in human languages.      as vision systems with AI.
The Commercial AI Field (cont.)

 Visual recognition has been        Machine learning refers to a set
 defined as the addition of         of methods that attempt to teach
 some form of computer              computers to solve problems or
 intelligence and decision          to support problem solving by
                                    analyzing (learning from)
 making to digitized visual         historical cases.
 information received from a
 machine sensor.                    Handwriting recognition is
                                    supported by technologies such
 Intelligent computer-aided         as expert systems and neural
 instruction (ICAI) refers to the   computing and is available in
 work of machines that can          some pen-based computers.
 tutor humans.
Expert Systems

Expert Systems (ES) are an attempt to
mimic human experts.
    Expert systems can either support
     decision makers or completely replace
     them.
    Expert systems are the most widely
     applied & commercially successful AI
     technology.
CASE: GE Models Human Troubleshooters
 Problem:
 GE wanted an effective & dependable way of disseminating
 expertise to its engineers & preventing valuable knowledge from
 “retiring” from the company.

 Solution:
 GE decided to build an expert system that modeled the way a
 human troubleshooter works.
 The system builders spend several months interviewing an
 employee & transfer their knowledge to a computer.
 The new diagnostic technology enables a novice engineer to
 uncover a fault by spending only a few minutes at the computer
 terminal.
 Results:
 The system is currently installed at every railroad repair shop
 served by GE.
Expertise & Knowledge


  Expertise is the extensive, task-specific knowledge acquired
  from training, reading, and experience.
  The transfer of expertise from an expert to a computer and
  then to the user involves four activities:

      knowledge acquisition from experts or other sources.
      knowledge representation in the computer.
      knowledge inferencing, resulting in a recommendation
       for novices.
      knowledge transfer to the user.
Components of Expert Systems

The knowledge base contains
knowledge necessary for
understanding, formulating, and
solving problems.

The blackboard is an area of      The “brain” of the ES is the
working memory set aside for      inference engine, a computer
the description of a current      program that provides a
problem, as specified by the      methodology for reasoning &
input data.                       formulating conclusions.
Components of Expert Systems (cont.)

 The user interface allows for    The explanation subsystem can
 user-computer dialogue,          trace responsibility and explain
                                  the ES’s behavior by
 which can be best carried out    interactively answering
 in a natural language, usually   questions.
 presented in a Q&As format
                                  A knowledge-refining system
 and sometimes supplemented
                                  enables the system to analyze
 by graphics.                     its performance, learn from it,
                                  and improve it for future
                                  consultations.
MYCIN

    Developed at Stanford University in the mid 1970's

    The first large expert system that perform at the level
     of human expert and use as benchmark by expert
     system developers.

    Provide consultative advise about bacteremia and
     meningitis.

    Bacteremia is an infections that involve bacteria in the
     blood.




                                                                13
MYCIN

   Meningitis is an infection which is an inflammation of the
    membranes that envelop the brain and spinal cord.

   Can be fatal, thus need quick response, but positive
    identification normally takes 24 - 48 hours.

   Normally doctors must begin treatment in the absence of
    lab results.

   Very complex and doctor need advice of an expert of
    bacteremia and meningitis.
How MYCIN works?


 MYCIN begin by initiating a dialogue.

 Physician response to the questions

 MYCIN provides:
      a. diagnosis
      b. Prescription

 MYCIN reason by the following ways:

    Laboratory results of body fluid analyses
    Symptoms that patient is displaying
    Characteristics of the patient such as age, sex etc.
MYCIN

 MYCIN consultative proceeds in 2 phases:

 a.   Diagnosis is made to identify the most likely infection
      organisms
 b.   Prescribe one or more drugs (antibiotics)
MYCIN: Example of a rule



   IF     the stain of the organism is gram-positive
   AND the morphology of the organism is coccus,
   AND the growth conformation of the organism is clumps,
   THEN
   there is suggestive evidence (0.7) that the identity of the
   organism is staphyloccus
 A consultation With MYCIN

1. Please enter information about the patient.
Name             Age                      Sex      Race
Sally            42 years                 Female Melayu
2. Are there any positive cultures obtained from SALLY?
No
3. Are there any pending cultures of SALLY?
Yes
4. Site: date collected: stain examined: method
CSF        3-Jun-75             Yes           N/A
5. Stain of smear:
(type NONE if no organism was seen on the smear)
None

(Unable to reach conclusion from lab test, like physician continue asking
questions.)
A consultation With MYCIN (cont..)

 6. Has Sally recently had symptoms of persistent headache or other
    abnormal neurologic symptoms(dizziness, lethargy etc.)
    Yes

 7. Has SALLY recently had objective evidence of abnormal neurologic
    signs documented by physician observation of examination?
     Yes

 Questions 6 and 7 traditional approach to diagnose by symptoms.

 Conclude from the questions by giving first conclusion.

 Conclusion: The CSF cultures will be considered to be associated
             with MENINGITIS.
A consultation With MYCIN (cont..)

 The following questions will identify particular organism that cause the
 infections.

 8. Is the meningitis a hospital-acquired infection?
     Yes
 9. Is SALLY clinical history consistent with EPIGLOTTITIS?
      No
 10. Is Sally clinical history consistent with OTITIS-MEDIA?
      No
 11. Has the patient ever been to an area that is endemic for
      coccidiomycoses?
      Unknown
 12. Is Sally a burn patient?
      Yes (Why)

 Conclusion: The type of infection may be bacterial .
A consultation With MYCIN (cont..)


  The final phase, prescription of antibiotics.

  13. Does SALLY have clinically significant allergic reaction to
       any antimicrobial agent?
      No
  14. Is Sally pregnant of breast feeding?
      No
  15. Do you have reason to suspect that SALLY may have
       impaired renal functions?
      No
  16. SALLY weight in kilograms?
      51.4
A consultation With MYCIN

My preferred therapy recommendation is as follows:

Give the following combination:

1. ETHAMBUTAL
   Dose: 1.28g (13.0 100mg tablets) q24h PO for 60 days
     then 770 mg (7.5 100 mg tablets) q24h PO.
   Comments: periodic vision screening tests are recommended
   for optic neuritis.

2. INH
   Dose: 513 mg (5.0 100mg-tablets) q24h PO

3. RIFAMPIN
   Dose: 600 mg PO q24h
   Comments: Administer dose on empty stomach.
 HOW GOOD AN EXPERT IS MYCIN?


In one complex evaluation, 8 independent evaluators evaluate
MYCIN with 9 others human diagnostician for 10 difficult cases of
meningitis.

The task used was the selection of drugs for cases of meningitis
before causative agents had been identified.

Two phases of the evaluation:
      a. MCYIN and 9 human experts evaluate 10 cases
      b. Each of them prescribe medications
HOW GOOD AN EXPERT IS MYCIN?

Two evaluative criteria was used to see
whether the prescriptions:

   a.   Would be effective against the actual bacteria after it was
        finally identified.

   b.   Adequately covered for other possible bacteria while
        avoiding over-prescribing.
HOW GOOD AN EXPERT IS MYCIN?

 Result:

 Criteria 1:   MYCIN and 3 other humans expert consistently
               prescribe therapy that would have been effective
               for all 10 cases.

 Criteria 2:   MYCIN received higher ratings. 65% correct in all
               the cases whereas human expert 42.5% to 62.5%.
HOW GOOD AN EXPERT IS MYCIN?

MYCIN strengths is based on 4 factors:

    a.   MYCIN's knowledge base is extremely detail because acquired
         from the best human practitioners.

    b.   MYCIN do not overlook anything or forget any details. It
         considers every possibility.

    c.   MYCIN never jumps to conclusions of fails to ask for key
         pieces of information.

    d.   MYCIN is maintained at a major medical center and
         consequently, completely current.

MYCIN represents 50 man-years of effort.
Using Expert Systems on the Net


The widespread availability and use of the Internet and intranets now
provide the opportunity to disseminate expertise and knowledge to mass
audiences.

ESs can be transferred over the Net not only to human users, but also to
other computerized systems, including DSS, robotics, and databases.

The Web also can support the spread of multimedia-based expert
systems.

    Such systems, referred to as Intellimedia Systems, support the
     integration of extensive multimedia applications and ES.
Natural Language Processing [NLP]


   Natural Language             Natural Language
   Understanding                Generation
   Investigates methods of      Strives to allow computers
   allowing a computer to       to produce ordinary English
   comprehend instructions      language, on the screen or
   given in ordinary English,   by voice (known as voice
   via the keyboard or by       synthesis), so people can
   voice, so that computers     understand computers
   are able to understand       more easily.
   people.
Applications of NLP

 Natural language processing programs have been applied in
 several areas.
 The most important are:
    Human–computer interfaces (mainly to databases)
    Abstracting and summarizing text
    Grammar analysis
    Translation of a natural language to another natural
     language
    Translation of a computer language to another computer
     language
    Speech understanding
    Composing letters by machine.
ELIZA

 One of the first AI programs employing NLP

 Written to be a therapist
 ELIZA – A computer program for the study of natural
      language communication between man and machine.
ELIZA (cont..)


Person :   Men are all alike.
ELIZA :    In what way?
Person :   They’re always bugging us about something or other.
ELIZA :    Can you think of a specific example?
Person :   Well, my boyfriend made me come here.
ELIZA :    Your boyfriend made you come here?
Person :   He says I’m depressed much of the time.
ELIZA :    I am sorry to hear that you are depressed.
Person :   It’s true. I am unhappy.
ELIZA :    Do you think coming here will help you not to be unhappy?
Person :   I need some help, that much seems certain.
ELIZA :    What would it mean to you if you got some help?
Person :   Perhaps I could learn to get along with my mother.
ELIZA :    Tell me more about your family
ELIZA (cont..)


  (X me Y)    (X you Y)

  (I remember X)  (Why do you remember X just now?)

  (My {family-member} is Y)  (Who else in your family is Y?)

  (X {family-member} Y)  (Tell me more about your family)
Speech Recognition & Understanding

 SPEECH RECOGNITION               SPEECH UNDERSTANDING
 is a process that allows us to   refers to the second part of
 communicate with a               the communication
 computer by speaking to it.      process, where the
 The computer recognizes          meaning of the speech is
 words that have been spoken      ascertained.
 without necessarily
 interpreting their meanings.
Neural Computing


  Neural Computing or Artificial Neural Networks (ANN), a field in
  AI that mimics certain processing capabilities of the brain.
  The results are:
       knowledge representations and processing based on
          massive parallel processing,
       fast retrieval of large amounts of information, and
       the ability to recognize patterns based on experiences.
Benefits of Neural Systems

 Pattern recognition. Neural       Generalization. When a neural
 networks can analyze large        network is presented with an
 quantities of data to establish   incomplete or previously
 patterns/ characteristics in      unseen input, it can generalize
 situations where the logic or     to produce a reasonable
 rules are not known.              response.

 Fault tolerance. If there are     Adaptability. The network
 many processing nodes,            learns in new environments.
 damage to a few nodes or
 links does not bring the          Forecasting capabilities. Similar
 system to a halt.                 to statistics, prediction is made
                                   based on historical data.
Suitable Business Areas for ANNs


 Data mining                   Resource allocation
 Tax fraud                     Identifying takeover targets

 Financial services            Signature validation
 Loan application evaluation   Prediction
 Solvency prediction
                               Insurance fraud detection
 New product analysis
                               Credit card fraud detection
 Airline fare management
                               Evaluation of personnel & job
                               candidates
Case: Visa Cracks Down on Fraud


  Problem:
  Only 0.2% of Visa International’s turnover in 1995 was lost to fraud,
  but at $655 million it is a loss well worth addressing.

  Solution:
  Visa invested in a cardholder risk identification system (CRIS)
  designed to notice inconsistent use, such as sudden expensive non-
  essentials.

  Results:
  Visa’s participating banks believe the neural technology has been
  successful. Bank of America has cut fraudulent card use by two-
  thirds.

  By 1995, Visa member banks loss to counterfeiters dropped by more
  than 16 percent.
Hybrid Systems


Intelligent systems are frequently integrated with other intelligent
systems or with conventional systems such as decision support systems.
These form what is known as Hybrid Systems.

The integrated technologies and their roles are:

    Neural Networks. These are used to predict future market share
     and growth.
    Expert Systems. These provide intelligent advice on developing
     market strategy to individuals and to the planning team.
    Fuzzy Logic. This helps deal with uncertainties by simulating the
     process of human reasoning, allowing the computer to behave less
     precisely and logically than conventional computers do.
Intelligent Agents

Intelligent agents are software entities that carry out some
set of operations on behalf of a user or another program
with some degree of independence or autonomy, and in so
doing, employ some knowledge or representation of the
user's goals or desires.

An intelligent agent may also be referred to as a "knowbot"
or "bot" (short for robot).
Applications of Intelligent Agents


User Interface. Intelligent agent    Workflow & Task Management
technology allows systems to         Agents. Intelligent agents can be
monitor the user’s actions,          used to ascertain, then automate,
develop models of user abilities,    user wishes or business
and automatically help out when      processes.
interface problems arise.

Operating Systems Agents. Agents     Negotiation in e-Commerce. A
can assist in the use of operating   challenging system is one in
systems.                             which agents need to negotiate
                                     with each other. Such systems are
Spreadsheet Agents. Spreadsheet      especially applicable to EC.
agents make the software more
friendly.
Managerial Issues


Cost-benefit and justification.
While some of the benefits of
intelligent systems are tangible, it
is difficult to put a dollar value
on the intangible benefits of
many intelligent systems.
                                       Acquiring knowledge. Intelligent
Heightened expectations. When          systems are built up on experts’
there is too much expectation          knowledge. How can an expert be
and hope associated with               motivated to contribute his or her
intelligent technologies,              knowledge?
management may get
discouraged.
Managerial Issues (cont.)


 System acceptance. The              Embedded technologies.
 acceptance of intelligent systems   Intelligent systems are expected
 by the IS department and the        to be embedded in at least 20 %
 integration of such systems with    of all IT applications in about ten
 mainstream IT is a critical         years.
 success factor.
                                     Ethical issues. Finally, there are
 System integration. Intelligent     several issues related to the use
 systems can succeed as              of intelligent systems. The
 standalone systems, but they        actions performed by an ES can
 have a broader area of              be unethical, or even illegal.
 applications when integrated with   There is also the issue of using
 other computer-based                knowledge extracted from
 information systems.                people and replacing people
                                     with machines.

				
DOCUMENT INFO
Shared By:
Categories:
Tags:
Stats:
views:18
posted:12/18/2011
language:English
pages:42