ST2103 – Computer Aided Design : Unit-5 Artificial Intelligence

Artificial Intelligence
An Overview of Artificial Intelligence:

Business and other organizations are significantly increasing their attempts to assist the human
intelligence and productivity of their knowledge workers with artificial intelligence tools and techniques.
AI includes natural languages, industrial robots, expert systems, and intelligent agents.

Artificial intelligence (AI) is a science and technology based on disciplines such as computer
science, biology, psychology, linguistics, mathematics, and engineering. The goal of AI is to develop
computers that can think, as well as see, hear, walk, talk, and feel. A major thrust of AI is the development
of computer functions normally associated with human intelligence, such as reasoning, learning, and
problem solving.

The Domains of Artificial Intelligence:

AI application can be grouped into three major areas:

• Cognitive Science - This area of artificial intelligence is based on research in biology, neurology,
psychology, mathematics, and many allied disciplines. It focuses on researching how the human brain
works and how humans think and learn. The results of such research in human information processing
are the basis for the development of a variety of computer-based applications in artificial intelligence.

Applications in the cognitive science area of AI include:

Expert Systems - A computer-based information system that uses its knowledge about a specific
complex application area to act as an expert consultant to users. The system consists of a knowledge
base and software modules that perform inferences on the knowledge, and communicates answers
to a user’s questions.

Knowledge-Based Systems - An information system which adds a knowledge-base and some

reasoning capability to the database and other components found in other types of computer-based
information systems.

Adaptive Learning Systems - An information system that can modify its behaviour based on
information acquired as it operates.

Fuzzy Logic Systems - Computer-based systems that can process data that are incomplete or
only partially correct. Such systems can solve unstructured problems with incomplete knowledge
by developing approximate inferences and answers.

Neural Network - software can learn by processing sample problems and their solutions. As

Prepared based on syllabus 2015-2016 curriculum | <A. VIJAY, ASST. PROF./CIVIL SRMIST
@VJENGR>
 ST2103 – Computer Aided Design : Unit-5 Artificial Intelligence

neural nets start to recognize patterns, they can begin to program themselves to solve such problems
on their own.

Genetic Algorithm - software uses Darwinian (survival of the fittest), randomizing, and other
mathematical functions to simulate evolutionary processes that can generate increasingly better
solutions to problems.

Intelligent Agents - Use expert system and other AI technologies to serve as software surrogates
for a variety of end user applications.

• Robotics: - AI, engineering, and physiology are the basic disciplines of robotics. This technology
produces robot machines with computer intelligence and computer-controlled, humanlike physical
capabilities.

Robotics applications include:

1. Visual perception (sight)
2. Tactility (touch)
3. Dexterity (skill in handling and manipulation)
4. Locomotion (ability to move over any terrain)
5. Navigation (properly find ones way to a destination)

• Natural Interface: - The development of natural interfaces is considered a major area of AI applications
and is essential to the natural use of computers by humans. For example, the development of natural
languages and speech recognition are major thrusts of this area. Being able to talk to computers and
robots in conversational human languages and have then “understand” us is the goal of AI researchers.
This application area involves research and development in linguistics, psychology, computer science,
and other disciplines. Efforts in this area include:

Natural Languages - A programming language that is very close to human language. Also,
called very high-level language.

Multisensory Interfaces - The ability of computer systems to recognize a variety of human

body movement which allows them to operate.

Speech Recognition - The ability of a computer system to recognizes speech patterns, and
to operate using these patterns.

Virtual Reality - The use of multisensory human/computer interfaces that enables human
users to experience computer-simulated objects, entities, spaces, and Aworlds@ as if they actually
existed.

Neural networks:

Prepared based on syllabus 2015-2016 curriculum | <A. VIJAY, ASST. PROF./CIVIL SRMIST
@VJENGR>
 ST2103 – Computer Aided Design : Unit-5 Artificial Intelligence

Neural networks are computing systems modelled on the human brain's mesh-like network of
interconnected processing elements, called neurons. Of course, neural networks are much simpler than the
human brain (estimated to have more than 100 billion neuron brain cells). Like the brain, however, such
networks can process many pieces of information simultaneously and can learn to recognize patterns and
programs themselves to solve related problems on their own.

Neural networks can be implemented on microcomputers and other computer systems via software
packages which simulate the activities of a neural network of many processing elements. Specialized neural
network coprocessor circuit boards are also available. Special-purpose neural net microprocessor chips are
used in some application areas.

Uses include:
1. Military weapons systems
2. Voice recognition
3. Check signature verification
4. Manufacturing quality control
5. Image processing
6. Credit risk assessment
7. Investment forecasting

EXAMPLE - Data Mining a Bank of America:

The Bank of America is using neural net technology in data mining software to develop more
accuracy in marketing and pricing financial products, such as home equity loans.

Fuzzy Logic Systems

Fuzzy Logic is a method of reasoning that resembles human reasoning since it allows for
approximate values and inferences (fuzzy logic) and incomplete or ambiguous data (fuzzy data) instead of
relying only on crisp data, such as binary (yes/no) choices.

Fuzzy Logic in Business:

An example of the use of fuzzy logic in business is to analyse the credit risk of a business.

Genetic Algorithms:

The use of genetic algorithms is a growing application of artificial intelligence. Genetic algorithm
software uses Darwinian (survival of the fittest), randomizing, and other mathematical functions to simulate
an evolutionary process that can yield increasingly better solutions to a problem. Genetic algorithms were
first used to simulate millions of years in biological, geological, and ecosystem evolution in just a few
minutes on a computer. Now genetic algorithm software is being used to model a variety of scientific,
technical, and business processes.

Prepared based on syllabus 2015-2016 curriculum | <A. VIJAY, ASST. PROF./CIVIL SRMIST
@VJENGR>
 ST2103 – Computer Aided Design : Unit-5 Artificial Intelligence

Genetic algorithms are especially useful for situations in which thousands of solutions are possible
and must be evaluated to produce an optimal solution. Genetic algorithm software uses sets of mathematical
process rules (algorithms) that specify how combinations of process components or steps are to be formed.

Virtual Reality (VR)

Virtual reality (VR) is computer-simulated reality. VR is the use of multisensory human/computer

interfaces that enable human users to experience computer-simulated objects, entities, spaces, and "worlds"
as if they actually existed (also called cyberspace and artificial reality).

VR Applications:

1. Computer-aided design (CAD)

2. Medical diagnostics and treatment
3. Scientific experimentation in many physical and biological sciences
4. Flight simulation for training pilots and astronauts
5. Product demonstrations
6. Employee training
7. Entertainment (3-D video games)

VR Limitations:

The use of virtual reality seems limited only by the performance and cost of its technology.
For example, some VR users develop:
• Cybersickness - eye strain, motion sickness, performance problems
• Cost of VR is quite expensive

Intelligent Agents

An intelligent agent (also called intelligent assistants/wizards) is a software surrogate for an end
user or a process that fulfills a stated need or activity. An intelligent agent uses a built-in and learned
knowledge base about a person or process to make decisions and accomplish tasks in a way that fulfills the
intentions of a user. One of the most well-known uses of intelligent agents are the Wizards found in
Microsoft Word, Excel, Access, and Powerpoint.

The use of intelligent agents is expected to grow rapidly as a way to for users to:
1. Simplify software use.
2. Access network resources.
3. Information screening and retrieval.

Prepared based on syllabus 2015-2016 curriculum | <A. VIJAY, ASST. PROF./CIVIL SRMIST
@VJENGR>
 ST2103 – Computer Aided Design : Unit-5 Artificial Intelligence

Expert Systems

One of the most practical and widely implemented application of artificial intelligence in business
is the development of expert systems and other knowledge-based information systems.

Knowledge-based information system - adds a knowledge base to the major components found in
other types of computer-based information systems.

Expert System - A computer-based information system that uses its knowledge about a specific
complex application area to act as an expert consultant to users. ES’s provide answers to questions in a
very specific problem area by making humanlike inferences about knowledge contained in a specialized
knowledge base. They must also be able to explain their reasoning process and conclusions to a user.

Expert systems can be used for either operational or management information systems, depending
on whether they are giving expert advice to control operational processes or to help managerial end users
make decisions.

Components of Expert Systems:

The components of an expert system include a knowledge base and software modules that perform
inferences on the knowledge and communicate answers to a user’s question. The interrelated components
of an expert system include:

• Knowledge base: - the knowledge base of an ES system contains:

1. Facts about a specific subject area
2. Heuristics (rule of thumb) that express the reasoning procedures of an expert on the subject.

• Software resources: - An ES software package contains:

1. Inference engine that processes the knowledge related to a specific problem.
2. User interface program that communicates with end users.
3. Explanation program to explain the reasoning process to the user.
4. Software tools for developing expert systems include knowledge acquisition programs and
expert system shells.

• Hardware resources: - These include:

1. Stand alone microcomputer systems
2. Microcomputer workstations and terminals connected to minicomputers or mainframes in a
telecommunications network.
3. Special-purpose computers.

• People resources: - People resources include:

1. Knowledge engineers

Prepared based on syllabus 2015-2016 curriculum | <A. VIJAY, ASST. PROF./CIVIL SRMIST
@VJENGR>
 ST2103 – Computer Aided Design : Unit-5 Artificial Intelligence

2. End users

Examples of Expert Systems:

Using an expert system involves an interactive computer-based session, in which:

1. The solution to a problem is explored with the expert-system acting as a consultant.
2. Expert system asks questions of the user, searches its knowledge base for facts and rules or other
knowledge.
3. Explains its reasoning process when asked
4. Gives expert advice to the user in the subject area being explored. Examples include: credit
management, customer service, and productivity management.

Expert System Applications:

Expert systems typically accomplish one or more generic uses. Seven activities include:
1. Decision Management
2. Maintenance/Scheduling
3. Design/configuration
4. Process monitoring/control
5. Diagnostic Troubleshooting
6. Intelligent text/documentation
7. Selection/classification

Example - Advertising Strategy

ADCAD (Advertising Communications Approach Designer) is an expert system that assists advertising
agencies in:
1. Setting marketing and communications objectives
2. Selecting creative strategies
3. Identifying effective communications approaches

In particular it is designed to help advertisers of consumer products with the:

1. Development of advertising objectives
2. Ad copy strategies
3. Selection of communications techniques

Developing Expert Systems

Expert Systems Shells. The easiest way to develop an expert system is to use an expert system shell as a
developmental tool. An expert system shell is a software package consisting of an expert system without a
kernel, that is, its knowledge base. This leaves a shell of software (the inference engine and user interface
programs) with generic inferencing and user interface capabilities). Other development tools (such as rule

Prepared based on syllabus 2015-2016 curriculum | <A. VIJAY, ASST. PROF./CIVIL SRMIST
@VJENGR>
 ST2103 – Computer Aided Design : Unit-5 Artificial Intelligence

editors and user interface generations) are added in making the shell a powerful expert system development
tool.

Knowledge Engineering

A knowledge engineer is a professional who works with experts to capture the knowledge (facts and rules
of thumb) they possess. The knowledge engineer then builds the knowledge base using an interactive,
prototyping process until the expert system is acceptable. Thus, knowledge engineers perform a role similar
to that of systems analysts in conventional information systems development. Obviously, knowledge
engineers must be able to understand and work with experts in many subject areas. Therefore, this
information systems speciality requires good people skills, as well as a background in artificial intelligence
and information systems.

The Value of Expert Systems

Expert systems are not the answer to every problem facing an organization. The question becomes “what
types of problems are most suitable to expert system solutions?” Ways to answer this question include:
1. Look at examples of the applications of current expert systems, including the generic tasks they
accomplish.
2. Identify criteria that make a problem situation suitable for an expert system. Some of this important
criteria include: Domain, expertise, complexity, structure, and availability.

Domain: The domain, or subject area, of the problem is relatively small and limited to a well-
defined problem area.

Expertise: Solutions to the problem require the efforts of an expert. That is, a body of
knowledge, techniques, and intuition is needed that only a few people possess.

Complexity: Solution of the problem is a complex task that requires logical inference processing, which
would not be handled as well by conventional information processing.

Structure: The solution process must be able to cope with ill-structured, uncertain, missing, and
conflicting data, and a problem situation that changes with the passage of time.

Availability: An expert exists who is articulate and cooperative, and who has the support of the
management and end users involved in the development of the proposed system.

Before deciding to acquire or develop an expert system, it is important that managerial end users evaluate
its benefits and limitations. In particular, they must decide whether the benefits of a proposed expert system
will exceed its costs.

Prepared based on syllabus 2015-2016 curriculum | <A. VIJAY, ASST. PROF./CIVIL SRMIST
@VJENGR>
 ST2103 – Computer Aided Design : Unit-5 Artificial Intelligence

Benefits of Expert Systems:

1. Captures the expertise of experts. It may outperform a single human expert in many problem
situations.
2. Is faster and more consistent than a human expert.
3. Can have the knowledge of several experts.
4. Does not get tired or distracted by too much work or stress.
5. Is available at all times, whereas a human expert may be away, sick, or may have left the company.
6. Can be used to train the novice.
7. Effective use of expert systems can allow a firm to:
a. improve the efficiency of its operations
b. produce new products and services
c. lock in customers and suppliers with new business relationships
d. build knowledge-based strategic information resources.

Limitations of Expert Systems

1. Limited focus (specific problems & specific domains)
2. Inability to learn
3. Difficulties in maintaining expert systems
4. Cost involved in developing them.

Hybrid AI Systems:

Increasingly, AI developers are constructing products which integrate several AI technologies into a single
hybrid AI system. This frequently includes two popular AI technologies: expert systems and neural nets.

Most integrated AI systems are designed to provide the best features of expert systems, neural nets, or fuzzy
logic technologies, and to offset each other’s strengths and weaknesses.

Prepared based on syllabus 2015-2016 curriculum | <A. VIJAY, ASST. PROF./CIVIL SRMIST
@VJENGR>