Introduction to Expert Systems

1
Introduction toExpert Systems
2
Expert Systems

• Expert System
• typically refers as an application of AI
  techniques in a business environment
• its main objective is to capture experts
  experience and transfer it to non-expert users
  via the use of a computer system

(p3)

3
Question

• Is ES really an expert???

(p4)
4
Answer

• it is an expert to a certain degree only
• Reasons
• it depends on the accuracy and availability of
  knowledge that being collected

(p5)
5
ES benefits

• capture of scarce expertise
• reduce decision-making time
• improve decision processes
• reduced downtime (in Mfg)
• easier for equipment operation
• elimination the need of expensive equipment
• Operation in hazardous environment (such as toxic
  environment)
• Improvement on the process and product quality

(p6)
6
How (and where) ES have been applied?

• 1. Concept of categorization

(p7)
(p8)
7
The Concept of Categorization
(p6)
8
Question

• Do Expert Systems always work in real life?

(p9)
9
Answer

• It depends on
• accuracy of knowledge collected
• availability of knowledge
• working within a narrow domain of problem
• evaluating criteria
• limitation in according to
• a) related issues
• b) ES task categories

(p10)
(p11)
(p12)
(p13)
10
Criteria for Evaluation of an Expert System

• The system should be responsive and easy to use.
• The design and functionality should conform with
  current diagnostic standards.
• The system should be able to function with
  incomplete knowledge.
• The user should always control the consulting
  process.
• The explanatory facility should be clear and
  user-friendly.
• The knowledge base should contain generally
  accepted knowledge.
• The system should be independent of any
  geographical constraints., that is mobility is an
  important success element
• The system should allow for integration with all
  other current information systems.

(to p9)
11
Limitations Associated with Expert Systems

• The needed knowledge is not always available.
• Experts use common sense. Programming common
  sense is not yet a reality.
• Expertise is difficult to extract and encode.
• Experts can recognize a problem outside the
  knowledge domain much faster than an ES.
• Expert systems cannot eliminate the cognitive
  limitations of the user.
• An ES is functional only within a narrow
  knowledge domain.
• Expert vocabulary is often limited and not easily
  understood by others.
• Human experts adapt to their environments
  naturally while an ES must be explicitly updated.
• An ES has a limited sensory experience compared
  to human experts.

(to p9)
12
Limitations Associated with Common ES Task
Categories

• Task Problems
• Interpretation Data may be noisy or missing
• Data may be inaccurate
• Prediction Must allow for contingencies and
  uncertainties
• Diagnosis Multiple symptoms can confound
  diagnosis
• Planning Multiple alternatives with complex
  scenarios
• Design Conflicting constraints and
  interaction among sub-designs
• Prescription Multiple problems may exist
• Monitoring Error conditions and nominal
  expectations are often context- specifi
  c
• Control Often requires interpretation based
  on common sense

(to p9)
13
Structure of EX

• Main components of ES
• 1. User
• 2. User Interface
• 3. Inference engine
• 4. Knowledge base/acquisition systems
• 5. Explanation systems
• Their relationships

(p14)
(p15)
(p16)
(p18)
(p19)
(p20)
(p21)
14
1. User

• refers to persons who interface with an ES
• these ppl could be technical or non-technical
  staff however, they should only seek ES for
  consult of qualitative instead of quantitative
  problems

(p13)
15
2. User Interface

• contains a communication system such as natural
  language processor , and some features described
  in DSS .. Menus, graphics ...
• The use of multimedia devices

(p13)
16
3. Inference Engine

• it is the main brain of ES
• i.e. it governs on how knowledge should be
  retrieved
• it also provides ways in which explanation,
  agenda and knowledge should be organized before
  presenting to end-users

(p17)
17
3. Inference Engine (cont)

• Three major elements in Inference Engine
• 1. Interpreter
• (executes the given chosen agenda)
• 2. Scheduler
• (guides how knowledge should be searched)
• 3. Consistency enforcer
• (maintains and compiles sensitive solution set)

(p13)
18
4. Knowledge base/Acquisition system

• involves ways in which knowledge should be
  represented in the system . (next lecture)
• includes on how knowledge could be acquired
  ranging from human, texts, documents, private and
  public databases, reports, and WWW
• includes on how knowledge should be searched

(p13)
19
5. Explanation System

• ES provides crucial explanations to users
  relating to
• a. how solutions are obtained/generated
• b. why questions/information are asked by the
  system etc.

(p13)
20
Explanation Systems
Knowledge Base systems
Inference Engine
User Interface (such as a PC platform)
Users
(to p13)
21
Additional components

• Blackboard (Workplace)
• Knowledge refining system

(p22)
(p23)
(p24)
22
Blackboard (Workplace)

• It is a workplace place to
• a) work on a plan to attack problems
• b) outline agenda for next execution steps
• c) document solutions and alternative courses

(p21)
23
Knowledge refining system

• it refers to ES learns and refines on its own
  knowledge
• this component is not generally available in most
  commercial ES mainly most ES are rather small in
  scale

(p21)
24
Types of ES

• 1. Rule-based
• 2. Frame-based
• 3. Semantic-based
• 4. Case-based
• 5. Model-based
• 6. Hybrid Systems
• 7. Ready-made systems (application packages)

25
Candidate Situations for ES Opportunities

• Need for diagnosis of a problem situation or
  variance (audit, troubleshooting, etc.)
• Need to understand the nature of a given
  situation
• Need to predict the outcome of a current or
  future event
• Need to control or govern a particular activity
  or process
• Need to prescribe a solution or course of action
• Need to evaluate and assess a prior event or
  process