1. ICT619 Intelligent Systems
Unit Coordinator:
Graham Mann
Room ECL Building
Phone:

2. Unit aims
to be aware of the rationale of the artificial intelligence and soft computing paradigms with their advantages over traditional computing
to gain an understanding of the theoretical foundations of various types of intelligent systems technologies to a level adequate for achieving objectives as stated below
to develop the ability to evaluate intelligent systems, and in particular, their suitability for specific applications
to be able to manage the application of various tools available for developing intelligent systems

3. Unit delivery and learning structure
3 hours of lecture/workshop per week
Lecture/WS time will be spent discussing the relevant topic after an introduction by the lecturer
Topic lecture notes will be available early in the week
Students should make use of the topic reading material in advance for the topic to be covered
Bringing up issues and questions for discussion are encouraged to create an interactive learning environment (this is assessed).

4. Resources and Textbooks
Main text:
Negnevitsky, M. Artificial Intelligence: A Guide to Intelligent Systems, nd Edition.
The main text to be supplemented by chapters/articles from other books/journals/magazines as well as notes provided by the unit coordinator.
A list of recommended readings and other resources will be provided for each topic.
Unit website: will enable access to unit reading materials and links to other resources.

5. Assessment ACTIVITY DUE WEIGHT Workshop participation Continuous 10%
Project
Week 12
35%
Closed-book Exam
Nov exams period
55%

6. Topic schedule
Topic 1: Introduction to Intelligent Systems: Tools, Techniques and Applications
Topic 2: Rule-Based Expert Systems
Topic 3: Fuzzy Systems
Topic 4: Neural Computing
Topic 5: Genetic Algorithms
Topic 6: Case-based Reasoning
Topic 7: Data Mining
Topic 8: Intelligent Software Agents
Topic 9: Language Technology

7. Topic 1: Introduction to Intelligent Systems
What is an intelligent system?
Significance of intelligent systems in business
Characteristics of intelligent systems
The field of Artificial Intelligence (AI)
The Soft Computing paradigm
An Overview of Intelligent System Methodologies
Expert Systems
Fuzzy Systems
Artificial Neural Networks
Genetic Algorithms (GA)
Case-based reasoning (CBR)
Data Mining
Intelligent Software Agents
Language Technology

8. What is an intelligent system?
What is intelligence?
Hard to define unless you list characteristics eg,
Reasoning
Learning
Adaptivity
A truly intelligent system adapts itself to deal with changes in problems (automatic learning)
Few machines can do that at present
Machine intelligence has a computer follow problem solving processes something like that in humans
Intelligent systems display machine-level intelligence, reasoning, often learning, not necessarily self-adapting

9. Intelligent systems in business
Intelligent systems in business utilise one or more intelligence tools, usually to aid decision making
Provides business intelligence to
Increase productivity
Gain competitive advantage
Examples of business intelligence – information on
Customer behaviour patterns
Market trend
Efficiency bottlenecks
Examples of successful intelligent systems applications in business:
Customer service (Customer Relations Modelling)
Scheduling (eg Mine Operations)
Data mining
Financial market prediction
Quality control

10. Intelligent systems in business – some examples
HNC (now Fair Isaac) software’s credit card fraud detector Falcon offers 30-70% improvement over existing methods (an example of a neural network).
MetLife insurance uses automated extraction of information from applications in MITA (an example of language technology use)
Personalized, Internet-based TV listings (an intelligent agent)
Hyundai’s development apartment construction plans FASTrak-Apt (a Case Based Reasoning project)
US Occupational Safety and Health Administration (OSHA uses "expert advisors" to help identify fire and other safety hazards at work sites (an expert system).
Source:

11. Characteristics of intelligent systems
Possess one or more of these:
Capability to extract and store knowledge
Human like reasoning process
Learning from experience (or training)
Dealing with imprecise expressions of facts
Finding solutions through processes similar to natural evolution
Recent trend
More sophisticated Interaction with the user through
natural language understanding
speech recognition and synthesis
image analysis
Most current intelligent systems are based on
rule based expert systems
one or more of the methodologies belonging to soft computing

12. The field of Artificial Intelligence (AI)
Primary goal:
Development of software aimed at enabling machines to solve problems through human-like reasoning
Attempts to build systems based on a model of knowledge representation and processing in the human mind
Encompasses study of the brain to understand its structure and functions
In existence as a discipline since 1956
Failed to live up to initial expectations due to
inadequate understanding of intelligence, brain function
complexity of problems to be solved
Expert systems – an AI success story of the 80s
Case Based Reasoning systems - partial success

13. The Soft Computing (SC) paradigm
Also known as Computational Intelligence
Unlike conventional computing, SC techniques
can be tolerant of imprecise, incomplete or corrupt input data
solve problems without explicit solution steps
learn the solution through repeated observation and adaptation
can handle information expressed in vague linguistic terms
arrive at an acceptable solution through evolution

14. The Soft Computing (SC) paradigm (cont’d)
The first four characteristics are common in problem solving by individual humans
The fifth characteristic (evolution) is common in nature
The predominant SC methodologies found in current intelligent systems are:
Artificial Neural Networks (ANN)
Fuzzy Systems
Genetic Algorithms (GA)

15. Overview of Intelligent System Methodologies - Expert Systems (ES)
Designed to solve problems in a specific domain,
eg, an ES to assist foreign currency traders
Built by
interrogating domain experts
storing acquired knowledge in a form suitable for solving problems, using simple reasoning
Used by
Querying the user for problem-specific information
Using the information to draw inferences from the knowledge base
Supplies answers or suggested ways to collect further inputs

16. Overview of Expert Systems (cont’d)
Usual form of the expert system knowledge base is a collection of IF … THEN … rules
Note: not IF statements in procedural code
Some areas of ES application:
banking and finance (credit assessment, project viability)
maintenance (diagnosis of machine faults)
retail (suggest optimal purchasing pattern)
emergency services (equipment configuration)
law (application of law in complex scenarios)

17. Artificial Neural Networks (ANN)
Human brain consists of 100 billion densely interconnected simple processing elements known as neurons
ANNs are based on a simplified model of the neurons and their operation
ANNs usually learn from experience – repeated presentation of example problems with their corresponding solutions
After learning the ANN is able to solve problems, even with newish input
The learning phase may or may not involve human intervention (supervised vs unsupervised learning)
The problem solving 'model' developed remains implicit and unknown to the user
Particularly suitable for problems not prone to algorithmic solutions, eg, pattern recognition, decision support

18. Artificial Neural Networks (cont’d)
Different models of ANNs depending on
Architecture
learning method
other operational characteristics (eg type of activation function)
Good at pattern recognition and classification problems
Major strength - ability to handle previously unseen, incomplete or corrupted data
Some application examples:
- explosive detection at airports
- face recognition
- financial risk assessment
- optimisation and scheduling

19. Genetic Algorithms (GA)
Belongs to a broader field known as evolutionary computation
Solution obtained by evolving solutions through a process consisting of
survival of the fittest
crossbreeding, and
mutation
A population of candidate solutions is initialised (the chromosomes)
New generations of solutions are produced beginning with the intial population, using specific genetic operations: selection, crossover and mutation

20. Genetic Algorithms (cont’d)
Next generation of solutions produced from the current population using
crossover (splicing and joining peices of the solution from parents) and
mutation (random change in the parameters defining the solution)
The fitness of newly evolved solution evaluated using a fitness function
The steps of solution generation and evaluation continue until an acceptable solution is found
GAs have been used in
portfolio optimisation
bankruptcy prediction
financial forecasting
design of jet engines
scheduling

21. Fuzzy Systems
Traditional logic is two-valued – any proposition is either true or false
Problem solving in real-life must deal with partially true or partially false propositions
Imposing precision may be difficult and lead to less than optimal solutions
Fuzzy systems handle imprecise information by assigning degrees of truth - using fuzzy logic

22. Fuzzy Systems (cont’d)
FL allow us to express knowledge in vague linguistic terms
Flexibility and power of fuzzy systems now well recognised (eg simplification of rules in control systems where imprecision is found)
Some applications of fuzzy systems:
Control of manufacturing processes
appliances such as air conditioners, washing machines and video cameras
Used in combination with other intelligent system methodologies to develop hybrid fuzzy-expert, neuro-fuzzy,
or fuzzy-GA systems

23. Case-based reasoning (CBR)
CBR systems solve problems by making use of knowledge about similar problems encountered in the past
The knowledge used in the past is built up as a case-base
CBR systems search the case-base for cases with attributes similar to given problem
A solution created by synthesizing similar cases, and adjusting to cater for differences between given problem and similar cases
Difficult to do well in practice, but very powerful if you can do it

24. Case-based reasoning (cont’d)
CBR systems can improve over time by learning from mistakes made with past problems
Application examples:
Utilisation of shop floor expertise in aircraft repairs
Legal reasoning
Dispute mediation
Data mining
Fault diagnosis
Scheduling

25. Data mining
The process of exploring and analysing data for discovering new and useful information
Huge volumes of mostly point-of-sale (POS) data are generated or captured electronically every day, eg,
data generated by bar code scanners
customer call detail databases
web log files in e-commerce etc.
Organizations are ending up with huge amounts of mostly day-to-day transaction data

26. Data mining (cont’d)
It is possible to extract useful information on market and customer behaviour by “mining" the data
Note: This goes far beyond simple statistical analysis of numerical data, to classification and analysis of non-numerical data
Such information might
reveal important underlying trends and associations in market behaviour, and
help gain competitive advantage by improving marketing effectiveness
Techniques such as artificial neural networks and decision trees have made it possible to perform data mining involving large volumes of data (from "data warehouses").
Growing interest in applying data mining in areas such direct target marketing campaigns, fraud detection, and development of models to aid in financial predictions, antiterrorism systems

27. Intelligent software agents (ISA)
ISAs are computer programs that provide active assistance to information system users
Help users cope with information overload
Act in many ways like a personal assistant to the user by attempting to adapt to the specific needs of the user
Capable of learning from the user as well as other intelligent software agents
Application examples:
News and Collection, Filtering and Management
Online Shopping
Event Notification
Personal scheduling
Online help desks, interactive characters
Rapid Response Implementation

28. Language Technology (LT)
“[The] application of knowledge about human language in computer-based solutions” (Dale 2004)
Communication between people and computers is an important aspect of any intelligent information system
Applications of LT:
Natural Language Processing (NLP)
Knowledge Representation
Speech recognition
Optical character recognition (OCR)
Handwriting recognition
Machine translation
Text summarisation
Speech synthesis
A LT-based system can be the front-end of information systems themselves based on other intelligence tools
Hi, I am Cybelle.
What is your name?

29. For Next Week
Get hold of the textbook
Visit the library and find the section on artificial intelligence, browse some titles
Get onto the unit website, download and read papers concerning Expert Systems
We will study the theory and practice developing a simple expert system
Have a look at the AAAI Applications webpage at