Chapter-4

Expert System
❖ What is an Expert System?

An expert system is a computer program that is designed to solve

complex problems and to provide decision-making ability like a human
expert. It performs this by extracting knowledge from its knowledge
base using the reasoning and inference rules according to the user
queries.

The expert system is a part of AI, and the first ES was developed in the
year 1970, which was the first successful approach of artificial
intelligence. It solves the most complex issue as an expert by
extracting the knowledge stored in its knowledge base. The system
helps in decision making for complex problems using both facts and
heuristics like a human expert. It is called so because it contains the
expert knowledge of a specific domain and can solve any complex
problem of that particular domain. These systems are designed for a
specific domain, such as medicine, science, etc.
The performance of an expert system is based on the expert's
knowledge stored in its knowledge base. The more knowledge stored
in the KB, the more that system improves its performance. One of the
common examples of an ES is a suggestion of spelling errors while
typing in the Google search box.
Examples of the Expert System:
DENDRAL
MYCIN
PXDES
CaDeT

Characteristics of Expert System:

High Performance: The expert system provides high performance for
solving any type of complex problem of a specific domain with high
efficiency and accuracy.
Understandable: It responds in a way that can be easily
understandable by the user. It can take input in human language and
provides the output in the same way.
Reliable: It is much reliable for generating an efficient and accurate
output.
Highly responsive: ES provides the result for any complex query
within a very short period of time.
❖ Components of Expert System/Building Blocks of Expert
System:
An expert system mainly consists of three components:
User Interface
Inference Engine
Knowledge Base
1. User Interface

With the help of a user interface, the expert system interacts with the
user, takes queries as an input in a readable format, and passes it to
the inference engine. After getting the response from the inference
engine, it displays the output to the user. In other words, it is an
interface that helps a non-expert user to communicate with the
expert system to find a solution.

2. Inference Engine(Rules of Engine)

The inference engine is known as the brain of the expert system as it

is the main processing unit of the system. It applies inference rules to
the knowledge base to derive a conclusion or deduce new
information. It helps in deriving an error-free solution of queries
asked by the user.
With the help of an inference engine, the system extracts the
knowledge from the knowledge base.
There are two types of inference engine:

Deterministic Inference engine: The conclusions drawn from this

type of inference engine are assumed to be true. It is based
on facts and rules.

Probabilistic Inference engine: This type of inference engine contains

uncertainty in conclusions, and based on the probability.

Inference engine uses the below modes to derive the solutions:

Forward Chaining: It starts from the known facts and rules, and
applies the inference rules to add their conclusion to the known facts.

Backward Chaining: It is a backward reasoning method that starts

from the goal and works backward to prove the known facts.
3. Knowledge Base
The knowledgebase is a type of storage that stores knowledge acquired
from the different experts of the particular domain. It is considered as
big storage of knowledge. The more the knowledge base, the more
precise will be the Expert System.

It is similar to a database that contains information and rules of a

particular domain or subject.

One can also view the knowledge base as collections of objects and
their attributes. Such as a Lion is an object and its attributes are it is a
mammal, it is not a domestic animal, etc.
Advantages of Expert System

• These systems are highly reproducible.

• They can be used for risky places where the human presence is not
safe.

• Error possibilities are less if the KB contains correct knowledge.

• The performance of these systems remains steady as it is not

affected by emotions, tension, or fatigue.

• They provide a very high speed to respond to a particular query.

Components of Knowledge Base

Factual Knowledge: The knowledge which is based on facts and

accepted by knowledge engineers comes under factual knowledge.
Heuristic Knowledge: This knowledge is based on practice, the ability
to guess, evaluation, and experiences.
Knowledge Representation: It is used to formalize the knowledge
stored in the knowledge base using the If-else rules.
Knowledge Acquisitions: It is the process of extracting, organizing,
and structuring the domain knowledge, specifying the rules to acquire
the knowledge from various experts, and store that knowledge into
the knowledge base.
Limitations of Expert System

• The response of the expert system may get wrong if the knowledge
base contains the wrong information.

• Like a human being, it cannot produce a creative output for

different scenarios.

• Its maintenance and development costs are very high.

• Knowledge acquisition for designing is much difficult.

• For each domain, we require a specific ES, which is one of the big
limitations.

• It cannot learn from itself and hence requires manual updates.

❖ Development phases of Expert System :
Problem Identification Phase:

Identifying the problem and opportunity where the organization can

obtain benefits from an ES, and establishing the ES general goals.

Feasibility Study Phase:

Assessing the feasibility of the ES development in terms of its

technical, economical, and operational feasibility.

Project Planning Phase:

Planning for the ES project, including development team members,

working environment, project schedule, and budget.
Knowledge Acquisition Phase:

Extracting domain knowledge from domain experts and determining

the system’s requirements.

Knowledge Representation Phase:

Representing key concepts from the domain, and interrelationship

between these concepts, using formal representation methods.

Knowledge Implementation Phase:

Coding the formalized knowledge into a working prototype.

Verification and validation Phase:

Verifying and validating a working prototype against the system’s
requirement, and revising it as necessary according to domain Expert’s
feedback.
Installation/Transaction/Training:

Installing the final prototype in an operating environment, training

the users, and developing documentation/user’s manual.

Operation/Evaluation/Maintenance:

Running the system in an operating environment, evaluating its

performance and benefits, and maintaining the system.
❖ Expert System-shell:

An expert system shell is a software framework designed to simplify

the process of developing expert systems. It provides a set of tools,
libraries, and interfaces that developers can use to build expert
systems without having to create the entire system from scratch.
Expert system shells typically include components for knowledge
representation, inference mechanisms, explanation generation, and
user interaction. Here are the key components and functionalities
commonly found in expert system shells:

1. Knowledge Base:
Definition: A repository where domain-specific knowledge is stored.
This knowledge includes facts, rules, heuristics, and other forms of
information used by the expert system.
Functionality: Expert system shells provide a way to define and
organize knowledge within the knowledge base.
2. Inference Engine:
Definition: The core component that processes the knowledge base
to make inferences and draw conclusions. It uses various inference
algorithms to reason through the available information.
Functionality: Expert system shells include built-in or customizable
inference engines that perform tasks such as forward chaining,
backward chaining, and rule-based reasoning.

3. User Interface:
Definition: The part of the expert system that interacts with
end-users or other systems. It can be a text-based interface, a
graphical user interface (GUI), or an API for integration with other
applications.
Functionality: Expert system shells often provide tools for creating
user interfaces, allowing developers to design interfaces for users to
input queries and receive explanations for system outputs.
4. Explanation Generator:
Definition: A component that generates explanations for the
system's decisions or recommendations. Explanations help users
understand why the expert system arrived at a specific conclusion.
Functionality: Expert system shells may include modules for
generating human-readable explanations based on the system's
reasoning process. This is especially important for applications where
transparency and user trust are critical.

5. Knowledge Acquisition Tools:

Definition: Tools and interfaces that facilitate the process of
capturing domain knowledge from experts and translating it into a
format suitable for the expert system.
Functionality: Expert system shells may provide utilities to assist
knowledge engineers in acquiring, organizing, and inputting
knowledge into the knowledge base.
6. Development Environment:
Definition: A set of tools and resources for developing, testing, and
debugging expert system applications.
Functionality: Expert system shells offer integrated development
environments (IDEs) with features like syntax checking, debugging
tools, and simulation capabilities, making it easier for developers to
build and refine expert systems.

7. Integration Capabilities:
Definition: The ability to integrate the expert system with other
software applications and systems.
Functionality: Expert system shells often provide APIs and interfaces
that allow seamless integration with databases, external APIs, and
other software components.
Examples of popular expert system shells include CLIPS, Jess, and
Drools. These shells provide the necessary infrastructure and tools for
building rule-based expert systems efficiently. Developers can focus
on defining the domain-specific knowledge and rules, leveraging the
capabilities provided by the expert system shell to handle the
underlying complexities of inference and user interaction. Examples
of popular expert system shells include CLIPS, Jess, and Drools. These
shells provide the necessary infrastructure and tools for building
rule-based expert systems efficiently. Developers can focus on
defining the domain-specific knowledge and rules, leveraging the
capabilities provided by the expert system shell to handle the
underlying complexities of inference and user interaction.
❖ Explanations:
Explanations in AI are essential for making machine learning models
more transparent, interpretable, and trustworthy. They provide
insights into how AI systems arrive at specific decisions, predictions, or
actions. Here are several common techniques and concepts related to
explanations in AI:
1. Feature Importance:
•Definition: Determining the contribution of each input feature to the
model's output.
•Usage: Helps users understand which features the model relies on the
most when making decisions.
2. Local Explanations:
•Definition: Providing explanations for individual predictions or
decisions made by the AI system.
•Usage: Useful when understanding the reasoning behind a specific
output is more important than understanding the entire model.
 3. Global Explanations:
•Definition: Explaining the overall behavior of the AI model across all
data points.
•Usage: Offers a broad overview of the model's decision-making
process, helping users grasp its general tendencies.

4. Rule-Based Explanations:
•Definition: Representing the decision-making process of the model as
a set of rules.
•Usage: Enhances interpretability by presenting the model's logic in a
human-readable format.

.
 5. Counterfactual Explanations:
•Definition: Demonstrating how changes in input variables would lead
to different outcomes.
•Usage: Helps users understand the factors influencing the model's
decision by showing what could have happened under different
conditions
6. Visual Explanations:
• Definition: Using visual aids like charts, graphs, or heatmaps to
explain model predictions.
•Usage: Simplifies complex relationships within the data, making it
easier for non-experts to comprehend the model's decisions.

7. Shapley Values:
• Definition: A concept from cooperative game theory, used to
fairly distribute a value among a group of contributors.
•Usage: Applied in AI to attribute a prediction to different features,
providing a clear breakdown of feature importance for each
prediction.
❖ Knowledge Acquisition:

In AI, knowledge acquisition is the process of extracting knowledge

from data. This can be done manually, through a process of
observation and experimentation, or automatically, using a variety of
techniques such as machine learning.

In artificial intelligence, knowledge acquisition is the process of

gathering, selecting, and interpreting information and experiences to
create and maintain knowledge within a specific domain. It is a key
component of machine learning and knowledge-based systems.

There are many different methods of knowledge acquisition,

including rule-based systems, decision trees, artificial neural
networks, and fuzzy logic systems. The most appropriate method for
a given application depends on the nature of the problem and the
type of data available.
Rule-based systems are the simplest form of knowledge-based
system. They use a set of rules, or heuristics, to make decisions.
Decision trees are another common method, which use a series of
if-then-else statements to arrive at a decision.

The most important part of knowledge acquisition is the

interpretation of information. This is where human expertise is
required. Machines are not able to interpret information in the same
way humans can. They can only make sense of data if it is presented in
a certain way.

Humans need to select the right data and experiences to create

knowledge. They also need to interpret that data correctly. This is
where artificial intelligence can help. AI systems can automate the
process of knowledge acquisition, making it faster and more accurate.
goals of knowledge acquisition:

In artificial intelligence, knowledge acquisition is the process of

gathering, selecting, and interpreting information that can be used to
solve problems. The goals of knowledge acquisition are to reduce the
amount of time and effort required to solve problems, and to improve
the quality of the solutions.

One of the challenges in knowledge acquisition is that it is often

difficult to know what information is relevant to the problem at hand.
Another challenge is that the process of acquiring knowledge can be
time-consuming and expensive.

Despite these challenges, knowledge acquisition is an essential part of

artificial intelligence. By gathering and interpreting information,
artificial intelligence can identify patterns and relationships that would
be difficult for humans to find. This allows artificial intelligence to
solve problems more efficiently and effectively.
Methods of knowledge acquisition:

There are a few methods of knowledge acquisition in AI:

1. Expert systems: In this method, experts in a particular field provide

rules and knowledge to a computer system, which can then be used
to make decisions or solve problems in that domain.

2. Learning from examples: This is a common method used in

machine learning, where a system is presented with a set of
training data, and it “learns” from these examples to generalize to
new data.

3. Natural language processing: This is a method of extracting

knowledge from text data, using techniques like text mining and
information extraction.
4. Semantic web: The semantic web is a way of representing
knowledge on the internet using standards like RDF and OWL, which
can be processed by computers.

5. Knowledge representation and reasoning: This is a method of

representing knowledge in a formal way, using logic or other
formalisms, which can then be used for automated reasoning.

challenges of knowledge acquisition?

One of the key challenges in AI is knowledge acquisition – that is,
acquiring the right data and information to train AI models to be
effective. This can be a challenge for a number of reasons.

First, data can be expensive to acquire. In some cases, it may be

necessary to purchase data from third-party providers. This can be a
significant cost, especially for small businesses or start-ups.
Second, data can be difficult to obtain. In some cases, it may be
necessary to collect data manually. This can be time-consuming and
expensive.

Third, data can be noisy. That is, it can contain errors or be

incomplete. This can make it difficult to train AI models effectively.

Fourth, data can be biased. That is, it can be skewed to favor certain
outcomes. This can lead to AI models that are not effective or that
produce results that are unfair.

Finally, data can be dynamic. That is, it can change over time. This can
make it difficult to keep AI models up-to-date.
role of knowledge acquisition in AI:

In AI, knowledge acquisition is the process of acquiring knowledge

from data sources and then using that knowledge to improve the
performance of AI systems. This process can be used to improve the
accuracy of predictions made by AI systems, or to help them learn
new tasks faster.

One of the most important aspects of knowledge acquisition is

choosing the right data sources. This is because the quality of the data
that AI systems use to learn is crucial to the performance of the
system. For example, if an AI system is trying to learn how to identify
objects in images, it will need to be trained on a dataset of
high-quality images.
Once the data has been collected, it needs to be processed and
converted into a format that can be used by AI systems. This process
is known as feature engineering, and it is crucial to the success of AI
systems. After the data has been processed, it can be used to train AI
models.

Training AI models is a complex process, and it is important to choose

the right algorithm for the task at hand. There is a wide range of
different algorithms that can be used for training AI models, and each
has its own strengths and weaknesses.

After the AI model has been trained, it can be deployed in a

real-world environment. This is where knowledge acquisition can
really help to improve the performance of AI systems. By constantly
monitoring the data that is being generated by the system,
knowledge acquisition can help to identify areas where the system
can be improved.
❖ Applications of Expert System:

Medical Diagnosis: Expert systems are used to assist doctors in

diagnosing diseases based on symptoms, patient history, and medical
records.

Financial Services: They are employed in banking and finance for

tasks such as credit scoring, fraud detection, and investment advice.

Customer Support: Expert systems are utilized in chatbots to provide

instant support to customers, answering frequently asked questions
and resolving common issues.

Manufacturing: They are used for quality control, process monitoring,

and troubleshooting in manufacturing industries.
Aerospace and Defence: Expert systems are employed in aircraft for
diagnostics, decision support, and maintenance planning.

Environmental Monitoring: Expert systems help in analyzing

environmental data and making predictions about environmental
trends.

Education: In e-learning platforms, expert systems are used for

personalized tutoring, adaptive learning, and assessment.

Robotics: Expert systems are used in robotic systems for tasks such as
object recognition, path planning, and autonomous navigation.

Natural Language Processing: They are employed in language

translation, sentiment analysis, and chatbots to understand and
generate human-like responses.
Oil and Gas Industry: Expert systems assist in reservoir management,
drilling optimization, and equipment diagnostics in the oil and gas
sector.

Automotive Industry: They are used in vehicle diagnostics, design

optimization, and supply chain management.

Legal Services: Expert systems assist lawyers by providing legal

advice, analyzing case law, and generating legal documents.

Geology and Mining: Expert systems are used for mineral

exploration, geological modelling, and mine planning.

Urban Planning: They aid in traffic management, city development

planning, and optimizing public transportation systems.
Pharmaceutical Industry: Expert systems are used in drug discovery,
molecular modelling, and analysis of biological data.

Game Development: Expert systems are used to create intelligent

non-player characters (NPCs) in video games, providing realistic and
challenging gameplay.

Human Resources: They assist in resume screening, candidate

matching, and employee performance evaluation.

Psychology and Counselling: Expert systems are used for mental

health diagnosis, therapy recommendations, and counselling services.

Agriculture: Expert systems assist farmers in crop management, pest

control, and agricultural planning.

Cyber security: They are employed in intrusion detection systems,

malware analysis, and security incident response.
THANK-YOU!!!!