Professional Documents
Culture Documents
CMTE Expert System
CMTE Expert System
CMTE Expert System
CMTE
02/12/24 1
What is Artificial Intelligence
02/12/24 2
Definitions
02/12/24 7
AI Viewpoint?
02/12/24 8
Different Approaches to AI
02/12/24 9
Where Are We Now?
02/12/24 10
AI Structure
02/12/24 11
AI is interdisciplinary
• Psychology
• Cognitive Science
• Linguistics
• Neuroscience
• Economics
• Philosophy
• Physics
02/12/24 12
EXPERT SYSTEMS
13
Traffic Signalling Expert System
14
Expert Systems
02/12/24 15
EXPERT SYSTEMS
16
Structure and Characteristics
AI programs
Knowledge-based systems
Expert systems
• AI programs:
intelligent problem solving tools
• KBSs
AI programs with special program structure
separated knowledge base
• ESs
KBSs applied in a specific narrow field
02/12/24 17
Expert Systems versus
Knowledge-based Systems
An expert system is one whose behavior is so specialized that we
would call a person who performed in a similar manner an
expert.
Knowledge-based systems Systems that use knowledge to
effectively and efficiently perform tasks (also known as advisory
systems, knowledge systems, intelligent systems). These
systems do not really need to behave as experts. Knowledge for
KBS can be acquired from different resources
02/12/24 18
Advantages: ES
Advantages
Provides consistent answers for repetitive decisions,
processes and tasks
Holds and maintains significant levels of information
Encourages organizations to clarify the logic of their decision-
making
Never "forgets" to ask a question, as a human might
02/12/24 19
Disadvantages: ES
Disadvantages
Lacks common sense needed in some decision making
Cannot make creative responses as human expert would in
unusual circumstances
Domain experts not always able to explain their logic and
reasoning
Errors may occur in the knowledge base, and lead to wrong
decisions
Cannot adapt to changing environments, unless knowledge
base is changed
02/12/24 20
Application of ES in Transportation Engg.
Examples
Lacks common sense needed in some decision making
Cannot make creative responses as human expert would in
unusual circumstances
Domain experts not always able to explain their logic and
reasoning
Errors may occur in the knowledge base, and lead to wrong
decisions
Cannot adapt to changing environments, unless knowledge
base is changed
02/12/24 21
Disadvantages: ES
Advantages
Lacks common sense needed in some decision making
Cannot make creative responses as human expert would in
unusual circumstances
Domain experts not always able to explain their logic and
reasoning
Errors may occur in the knowledge base, and lead to wrong
decisions
Cannot adapt to changing environments, unless knowledge
base is changed
02/12/24 22
Application of ES in Transportation Engg.
1. Connecticut DOT has developed the Pavement Rating and Analysis System. It is a
network-level pavement condition rating tool that uses laser videodisc. Cracks and
other type of distress are rated based on closeups of images.
2. In Traffic Adaptive Signal Control system, KBES has been suggested to be used in the
process of determining optimal strategy to control traffic signal under various traffic
condition
3. KBES assists operators in Transportation Management Center to work efficiently, when
unexpected incidents occur, by utilizing experts' knowledge accumulated in the system.
4. Knowledge based expert systems are used to develop a pavement condition
forecasting model and a treatment strategy selection model.
02/12/24 23
Members in the Development Team
02/12/24 24
Members in the Development Team
Expert System
Development Team
Project Manager
Expert System
End-user
02/12/24 25
Domain Expert
02/12/24 26
Knowledge Engineer
• The knowledge engineer is someone who is capable of designing,
building and testing an expert system.
• The knowledge engineer's main tasks are:
• to interview the domain expert to find out how a particular problem
is solved.
• to establish what reasoning methods the expert uses to handle facts
and rules, and decide how to represent them in the expert system.
• to choose some development software or an expert system shell, or
decide at programming languages for encoding the knowledge
• responsible for testing, revising and integrating the expert system
into the workplace.
02/12/24 27
Programmer
• The programmer is the person responsible for the actual
programming, describing the domain knowledge in terms that a
computer can understand.
02/12/24 28
Project Manager
02/12/24 29
End-User
• The end-user, often called just the user, is a person who uses
the expert system when it is developed
02/12/24 30
Key Components of ES
User Workstation
Knowledge
Engineering
Knowledge
Acquisition
Program
Expert and/or
Workstation Knowledge Engineer
02/12/24 31
The User Interface in an ES
02/12/24 32
The Knowledge Base
02/12/24 33
The Inference Engine
02/12/24 34
Knowledge
• Anyone can be considered a domain expert if he or she has deep knowledge (of both
facts and rules) and strong practical experience in a particular domain. The area of
the domain may be limited
02/12/24 35
Information
Information is a “class” that includes data and knowledge.
Data are facts about something. For example, this car is red; that
building has five stories; the temperature is 20°C; his name is Paul,
etc.
02/12/24 36
36
Knowledge Acquisition [1]
• knowledge acquisition: process of extracting knowledge from an
expert, organizing it, and encoding it into a knowledge base
• knowledge elicitation: extracting knowledge from an expert
• knowledge acquisition is the principle bottleneck in expert system
development
• many techniques and theories about how to best do this
• more tools are appearing to help in this
– early example: inductive inference tables
• active research area
– psychologists are especially interested in elicitation issues, as it
is a fundamental problem of human psychology
02/12/24 37
Knowledge Acquisition [2]
Expert
data, problems,
questions
knowledge
concepts Formalized
solutions structured
knowledge
Knowledge KNOWLEDGE
engineer BASE
Needs,
usability,
feedback
Prototypes,
needs queries
End user
Also: other experts, literature
02/12/24 38
Steps in knowledge acquisition
1. Collect: (elicitation)
- getting the knowledge out of the expert
- most difficult step
- lots of strategies
2. Interpret:
- review collected knowledge, organize, filter
3. Analyze:
- determining types of knowledge, conceptual relationships
- determining appropriate knowledge representation & inference
structure
4. Design: extracting more knowledge after using above principles
02/12/24 39