SUB; ARTIFICIAL INTELLIGENCES AND MACHINE LEARNING

ARTIFICIAL INTELLIGENCES

Def; AI is a Human intelligence of a computer sciences that aims to create tasks of solving,
learning, reasoning, language understanding and perceptions.

GOALS OF ARTIFICIAL INTELLIGENCE

- Replicate human intelligence

- Solve knowledge-intensive tasks
- An intelligent connection of perception and action
- Building a machine which can perform tasks that requires human intelligence such as: -
o Proving a theorem
o Playing chess
o Plan some surgical operations
o Driving a car in traffic
- Creating system which can exhibit intelligent behavior, learn new things by itself,
demonstrate, explain, and can advise to its user.

HISTORY OF ARTIFICIAL INTELLIGENCE

Thinkers like “Aristotle and Ramon Llull” laid the groundwork of AI by describing how human
thinking works using symbols.

Charles Babbage and Ada Lovelace designed machine that could be program in the 1880s. In the
1940s, John von Neumann came up with the idea of storing computer programs at the same time
Warren McCulloch and Walter Pitts started building the base of neural networks.

The 1950s brought us modern computers which allow scientist to dig into it intelligence. Alan
test become a big deal computer smarts. The term “Artificial intelligence” was first used in a
1956 Dartmouth college meeting where they introduced the first AI program, the logic theorist.

DIADVANTAGES OF ARTIFICIAL INTELLIGENCES

 Job Displacement: Automation through AI can lead to job losses, especially in industries that
rely heavily on manual or routine tasks. This can create economic and social challenges for
affected workers.

 Bias and Discrimination: AI systems can inherit biases present in the data they are trained on.
This can result in discriminatory outcomes, especially in areas like hiring, lending, and law
enforcement.

 Privacy Concerns: AI systems often rely on large amounts of data, which can raise privacy
issues. The collection and use of personal information can lead to concerns about data security
and misuse.
 Security Risks: AI can be exploited for malicious purposes, such as creating deepfakes,
automating cyberattacks, or developing autonomous weapons. This poses significant security
threats.

 High Costs: Developing and maintaining AI systems can be expensive. This can limit access
to AI technology for smaller businesses or developing countries, potentially widening the
economic divide.

 Lack of Transparency: AI algorithms can be complex and difficult to understand, even for
their developers. This lack of transparency can make it hard to trust AI systems and hold them
accountable for their decisions.

 Ethical Concerns: The use of AI in decision-making processes raises ethical questions, such as
who is responsible when AI makes a mistake or causes harm. There is also debate over the
ethical use of AI in areas like surveillance and data collection.

 Dependency: Over-reliance on AI systems can lead to a loss of critical skills and knowledge.
For example, if people rely too much on AI for navigation, they might lose their ability to
navigate without technology.

 Unemployment and Economic Impact: The displacement of jobs by AI can lead to economic
instability and increased inequality. This can create social and political challenges that need to be
addressed.

 Environment Impact: AI systems, particularly those requiring significant computational

power, can have a large carbon footprint and contribute to environmental degradation.

EXAMPLES OF ARTIFICIAL INTELLIGENCES

- Voice assistants (Siri, Alexa, and Google assistant)

- Autonomous vehicles like Tesla and Waymo
- Chatbots e.g. ChatGPT, Copilot, and Meta
- Healthcare diagnostic like IBM Watson

APPLICATION OF AI IN HEALTHCARE

1. Medical Diagnosis

AI algorithms can analyze vast amounts of medical data, such as electronic health records
(EHRs), to assist in diagnosing diseases. For example, AI can help detect patterns in imaging
data that might be missed by human eyes, leading to earlier and more accurate diagnoses2.

2. Personalized Treatment Plans

 AI can analyze a patient's medical history, genetic information, and lifestyle factors to create
personalized treatment plans. This approach ensures that patients receive the most effective
treatments tailored to their unique needs.

3. Drug Discovery and Development

AI accelerates the drug discovery process by predicting how different compounds will
interact with targets in the body. This reduces the time and cost associated with bringing new
drugs to market3.

4. Robotic Surgery

AI-powered robotic systems assist surgeons in performing precise and minimally invasive
surgeries. These systems can reduce human error and improve surgical outcomes.

5. Administrative Tasks

AI automates administrative tasks such as scheduling appointments, managing patient

records, and processing insurance claims. This allows healthcare professionals to focus more
on patient care.

6. Patient Monitoring

AI-enabled devices can continuously monitor patients' vital signs and alert healthcare
providers to any abnormalities. This is particularly useful for patients with chronic
conditions who require constant monitoring.

APPLICATION OF AI IN EDUCATION

1. Personalized Learning

AI can provide customized lesson plans and resources that cater to each student's needs. This
helps in keeping students engaged and improving their overall learning outcomes.

2. Intelligent Tutoring Systems

AI-powered tutors offer personalized assistance to students, providing explanations, feedback,

and additional practice on specific topics. These systems adapt to the student's learning progress
and can offer targeted help where it's most needed.

3. Automated Grading

AI automates the grading of assignments, quizzes, and exams, providing quick and consistent
evaluation. This reduces the burden on educators and allows them to focus more on teaching and
less on administrative tasks
5. Virtual Classrooms and Teaching Assistants

AI facilitates virtual classrooms where students can interact with teachers and peers remotely. AI
teaching assistants can help manage these virtual environments by answering common questions,
moderating discussions, and providing resources.

6. Administrative Efficiency

AI streamlines administrative tasks such as scheduling, enrollment, and communication. This

reduces the workload on school staff and improves overall efficiency.

APPLICATION OF AI IN GAMING

1. Smart game characters: AI is like the brains behind game characters that aren’t control by
players, making them act real people or clever enemies. They can learn from what players
do and change their behavior.
2. Creating Game world with AI: AI can make parts of video games all on its own. It can
create levels, maps, and places to explore without people having to make them by hand.
3. Making Games look and feel real: AI helps to make games look and act more like the real
world.

APPLICATION OF AI IN TRANSPORTATION

1. Autonomous Vehicles: Self-Driving Cars: AI enables vehicles to navigate roads,

recognize obstacles, and make real-time decisions. Companies like Tesla and Waymo are
at the forefront of developing self-driving technology.
2. Traffic Management: Smart Traffic Lights: AI algorithms optimize traffic light timings
based on real-time traffic conditions, reducing congestion and improving traffic flow.

3. Other applications may include: Public Transportation, Air Travel, Railway

Systems, Maritime Transportation, Drone Delivery

APPLICATION OF AI IN ENTERTAINMENT.

1. Personalized Recommendations: Streaming Services, Streaming platforms like Netflix,

Spotify, and YouTube use AI to provide personalized content recommendations, keeping
users engaged and satisfied.
2. AI as creative assistance” AI helps artists and creators by creating music, arts, videos or
contents and also can improve what they have created.

APPLICATION OF AI IN SOCIAL MEDIA

1. Smart suggestions: AI helps in suggesting contents, videos, ads according to an interest

of the person after analyzing what you like, creating a joyful environment for you.
 2. Virtual assistance and chatbots: AI helps answering your questions on searching for
certain things on internet by answering things like human, creating safe and searchable
environment
3. Sentiment analysis: AI can analyze post, comments and can describe the feelings whether
its happy, sad, tired or any feelings.
4. Trend Analysis: AI also study people reactions and comments of ongoing things helping
companies know what’s going on and act smartly.

APPLICATION OF AI IN FINANCE

1. Fraud Detection: Real-Time Monitoring AI systems continuously monitor transactions

and flag suspicious activities for further investigation.
2. Customer Service: AI helps customers and assisting them to improve on their financial
data structures.

APPLICATION OF AI IN E-COMMERCE

1. Personalized product suggestions: AI can help in online shopping making it more fun and
helping you discover new things you might want to buy.
2. Managing inventory: AI takes care of a store’s shelves. It predicts how much of each
product people will buy and automatically orders more when needed.
3. Dynamic Pricing: AI dynamically adjusts pricing according to demand, market
competition, and inventory levels, ensuring customers receive optimal value while
enhancing store’s profitability.

APPLICATION OF AI IN SECURITY

1. Cybersecurity: Threat Detection AI analyzes network traffic and system behaviors to

detect anomalies and potential security threats. 2. Physical Security
2. Security Information and Event Management (SIEM): AI analyzes security logs and
event data from various sources to identify potential security incidents

DIFFERRENCE BETWEEN ARTIFICIAL INTELLIGENCE AND HUMAN

INTELLLIGENCE

S/N ARTIFICIAL INTELLIGENCE HUMAN INTELLIGENCE

1 Process vast amounts of data fast Process amount of data slow
2 Can work around the clock without Limited by its physical and mental
needing breaks or rest capabilities
3 Performs tasks that are dangerous and Prone to biases and may make errors or
difficult poor decisions
4 Lacks creativity and intuition Has creativity, intuition and emotional
intelligence
5 Limited by its programming and may not Can adapt to new and unexpected
be able to adapt to new or unexpected situations
situations
 6 May make errors if not programmed and Can provide ethical and moral
trained properly considerations in decision making.

SIMILARITIES BETWEEN ARTIFICIAL INTELLIGENCE AND HUMAN

INTELLIGENCE

S/N FEATURES ARTIFICIAL HUMAN INTELLIGENCE

INTELLIGENCE
1 Processing Based on algorithms and Based on cognitive
mathematical models processes and biological
structures
2 Learning Based on data and feedback Based on experience,
loops intuition, and creativity
3 Speed Can process data and perform Slower than AI in
tasks much faster than humans processing large amounts of
data, but can make complex
decisions quickly
4 Adaptability Can quickly adapt to new data Can adapt to new situations,
and situations learning from experience,
and make decisions based
on context
5 Emotions Lacks emotions and empathy Capable of feeling emotion
and empathy
6 Creativity Limited ability to be creative or Capable of creativity,
think outside the box imagination, and innovation
7 Ethics Does not have a moral code or Has a moral code and
conscience conscience that guides
decision-making
8 Physical limitations Does not have physical Limited by physical
limitations and can work 24/7 capabilities and requires rest
and maintenance

AI SYSTEM

Defined as the study of the rational agent and its environment.

AN AGENT

Can be anything that perceive its environment through sensors and act upon that environment
through actuators. An Agent runs in the cycle of perceiving, thinking, and acting.

Example:

- Human agent has eyes, ears, and other organs which work as sensors and hand, legs,
vocal tract work for actuators.
 - A robotic agent can have cameras, infrared range finder, NLP for sensors and various
motors for actuators.
- Software agent can have keystrokes, file contents as sensory input and act on those inputs
and display output on the screen.

Sensor: Sensor is a device which detects the change in the environment and sends the
information to other electronic devices. An agent observes its environment through sensors.

Actuators: Actuators are the component of machines that converts energy into motion. The
actuators are only responsible for moving and controlling a system. An actuator can be an
electric motor, gears, rails, etc.

Effectors: Effectors are the devices which affect the environment. Effectors can be legs, wheels,
arms, fingers, wings, fins, and display screen.

INTELLIGENT AGENT

An intelligent agent is an autonomous entity which act upon an environment using sensors and
actuators for achieving goals. An intelligent agent may learn from the environment to achieve
their goals. A thermostat is an example of an intelligent agent.

MAIN RULES OF AI AGENT

- Rule 1: An AI agent must have the ability to perceive the environment.

- Rule 2: The observation must be used to make decisions.
- Rule 3: Decision should result in an action.
- Rule 4: The action taken by an AI agent must be a rational action

TYPES OF AI AGENT

1. Simple Reflex Agent

- The Simple reflex agents are the simplest agents.

- These agents take decisions on the basis of the current percepts and ignore the rest of the
percepts history.
- Only succeed in the fully observable environment.
Example- Room cleaner agent.
Problems for the simple reflex agent design approach:
- They have very limited intelligence
- They do not have knowledge of non-perceptual parts of the current state
- Mostly too big to generate and to store.
- Not adaptive to changes in the environment.

2. Model-based reflex Agent

- Can work in a partially observable environment and track the situation.
- Model-based reflex agent has two important factors:
o Model (Knowledge of the world)
o Internal state (present action).
- Updating the agent state requires information about how the world evolves and how the
agent’s action affects the world.

3. Goal-based Agents
- Goal-base agents expand the capabilities of the model-based agent by having the goal
information.
- They choose an action so that they can consider a goal.
- These agents may have to consider a long sequence of possible actions before deciding
whether the goal is achieved or not.
- Such considerations are called searching and planning making the agent proactive.

4. Utility-based Agents
- These agents provide extra component of utility measurement.
- They act based not only the goals but also the best way to achieve the goals.
- In multiple alternatives, they map all the achieved goals and hence choosing the best
action
5. Learning Agents
- Can learn from its past experiences. Or it has learning capabilities.
- Learning agent have four conceptual components which are: -
o Learning element: Responsible for improving learning capabilities
o Critic: Gives feedbacks to the learning element, describing how well the agent is
doing.
o Performance element: Responsible for selecting external action
o Problem generator: Responsible for suggesting actions that will lead to new and
informative experience
- Learning agents are able to learn, analyze performance and look for new ways to improve
performance.
6. Agent environment in AI
- An environment is everything in the world which surround the agent but it’s not part of
the agent itself
- The environment is where the agent lives, operates and provide the agent with something
to sense and act upon it.
Properties of environment in AI
Features
o Fully observable Vs partially observable
o Static Vs Dynamic
o Discrete Vs continuous
o Deterministic Vs stochastic
o Single-agent Vs multi-agents
o Episodic Vs sequential
o Known Vs unknown
 o Accessible Vs inaccessible
SEARCH ALGORITHMS

Search algorithms in AI are created to aid the searchers in getting the right solution. Search
algorithms terminologies includes: -

- Search: Searching is step by step procedure to solve a search-problem. It has three factors
o Search space
o Start state
o Search tree
- Actions: It gives the description of all the available actions to the agent
- Transition model: A description of what each action
- Path Cost: it is a function which assigns a numeric cost to each path.
- Solution: action hat leads from the start node to the goal node
- Optimal solution: a solution having the lowest cost among all solutions

PROPERTIES OF SEARCH ALGORITHMS

- Completeness
- Optimality
- Time complexity
- Space complexity

TYPES OF SEARCH ALGORITHMS

- Uniformed/blind search
o Breadth first search
o Uniform cost search
o Depth first search
o Depth limited search
- Informed search
o Best first search
o A*search

BRUTE FORCE APPROACH

Is an approach that finds out all the possible solutions to find a satisfactory solution to a given
problem. Can be of two types include: -

- Optimizing: in this case the best solution is found.

- Satisficing: it stops finding the solution as soon as the satisfactory solution is found

Often Brute force algorithms require exponential time. Various heuristics and optimization can
be used; -
 - Heuristic: A rule of thumb that helps you to decide which possibilities we should look at
first.
- Optimization: Certain possibilities are eliminated without exploring all of them.

ADVANTAGES OF BRUTE FORCE ALGORITHMS

- This algorithm finds all the possible solutions, and it also guarantees that it finds the
correct solution to a problem.
- This type of algorithm is applicable to a wide range of domains.
- It is mainly used for solving simpler and small problems.
- It can be considered a comparison benchmark to solve a simple problem and does not
require any particular domain knowledge.
DISADVANTAGES OF BRUTE FORCE ALGORITHMS
- It is an inefficient algorithm as it requires solving each and every state.
- It is a very slow algorithm to find the correct solution as it solves each state without
considering whether the solution is feasible or not.
- The brute force algorithm is neither constructive nor creative as compared to other
algorithms.

BFS ALGORITHM

Breadth first search is a graph traversal algorithm that starts traversing the graph from the root
node and explores all the neighboring nodes. Then selects the nearest node and explore all the
unexplored nodes.

APPLICATION OF BFS

- BFS can be used to find the neighboring locations from a given source location.
- In a peer-to-peer network, BFS algorithm can be used as a traversal method to find all the
neighboring nodes
- BFS can be used in web crawlers to create web page indexes.
- BFS is used to determine the shortest path and minimum spanning tree.
- BFS is also used in Cheney's technique to duplicate the garbage collection.
- It can be used in Ford-Fulkerson method to compute the maximum flow in a flow
network

DFS (DEPTH FIRST SEARCH) ALGORITHM

It is a recursive algorithm to search all the vertices of a tree data structure or a graph. It starts
with the initial node going deeper until finding the goal node or node with no children

APPLICATION OF DFS ALGORITHM

 - DFS algorithm can be used to implement the topological sorting.
- It can be used to find the paths between two vertices.
- It can also be used to detect cycles in the graph.
- DFS algorithm is also used for one solution puzzles.
- DFS is used to determine if a graph is bipartite or not.

HEURISTICS
Definition: is a technique used to solve a problem faster than the classic methods, those
techniques are used to find the approximate solutions of a problem when classic methods do not.

HISTORY OF HEURISTICS

Psychologists “Daniel Kahneman and Amos tversky” have developed the study of heuristics in
human decision-making in the year 1970s and 1980s. However, this concept was first introduced
by the “Nobel Laureate Herbert A. Simon” whose primary object of reach was problem-solving.

COMMON USES OF HEURISTICS

- Reduces mental efforts needed to make decisions

- Simplify complexes and difficult questions
- They are fast and accurate way to arrive at a conclusion
- Help with problem solving

The heuristic techniques can be perform into two categories:

1. Direct Heuristics search techniques in AI
It includes: -
o Blind search
o Uninformed search
o Blind control strategy
The examples include: -
o Breadth-first search (BFS)
o Depth-first search (DFS)
2. Weak Heuristics search techniques in AI
It includes: -
o Informed search
o Heuristics search
o Heuristic control
The examples include: -
o Best-first search (BFS)
o A* search
HEURISTICS SEARCH TECHNIQUES IN AI
- Hill climbing
- Best –first search
- Simulated Annealing
- Constraint satisfaction problem
EXAMPLES OF HEURISTICS
 a) Stereotyping:
b) Educated Guess: it allows a person to reach a conclusion without doing exhaustive
search.
c) Rule of thumb: in heuristics we also used the rule of thumb, the heuristics allows an
individual to make approximation without doing exhaustive search.
d) Profiling
e) Common sense: it is heuristics that is used to solve a problem based on the observation of
an individual.
f) Familiarity heuristics: it allows a person to approach a problem on the fact that an
individual is familiar with the same situation, so one should act similarly as he/she act in
the same situation before.
g) Working Backward: it lets an individual solve a problem by assuming that the problem is
already solved by them and working backward in their minds to see how to see how
much a solution has been reach.

TYPES OF HEURISTICS
1. Availability heuristics
Is said to be the judgment that make people make regarding the likehood of an event
based on information that quickly comes into mind. On making decisions, people
typically rely on the past knowledge or experience of an event. It allows a person to judge
a situation based on the examples of similar situation that comes to mind.
2. Representative heuristics
It occurs when we evaluate an events probability on the basis of its similarity with
another event
Example: we can understand the representative heuristics by the example of product
packaging, as consumers tend to associate the products quality with the external
packaging of a products.
3. Affect heuristics
It based on the negative and positive feeling that are linked with a certain stimulus. It
includes quick feelings that are based on past beliefs.
Example: it can be understanding by the example of advertisement which can influence
the emotion of the consumers.
LIMITATIONS OF HEURISTICS
- Although heuristics speed up our decision making process and also help us to solve
problems, they can also introduce errors just because something has worked in the past,
so it doesn’t meant that it will work again.
- It will hard to find alternative solution or ideas if we rely on the existing solutions or
heuristics.
-

LOCAL SEARCH ALGORITHM IN ARTIFICIAL INTELLIGENCE

Defined as the essential tools in AI and optimization, employed to find high quality solutions in
large and complex problem space.

KEY ALGORITMS INCLUDE: -

1. Hill climbing: is a straightforward local algorithm that iteratively moves towards better
solutions.
a. Process:
i. Start: Begin with initial solution
ii. Evaluate: asses the neighboring solutions
iii. Move: it improves the current solution
iv. Repeat: continue this process until no better neighboring solutions exist.
b. Types:
i. Simple Hill climbing: chooses the first neighbor that improves solution
ii. Steepest-Ascent Hill climbing: Randomly selects neighbor to explore.
c. Pros:
i. Easy to implement
ii. Works well in small or smooth search spaces
d. Cons:
i. May get stuck in local optima
ii. Limited exploration of the search spaces
2. Simulated Annealing; is inspired by the annealing process in metallurgy, where materials
are heated and then gradually cooled to remove defects.
a. Process:
i. Start: begin with an initial solution and an initial temperature
ii. Move: transition to a neighboring solution with a certain probability.
iii. Cooling schedule: gradually reduce the temperature according to a
predefined schedule
iv. Probability function: accept worse solution with a probability decreases as
the temperature decreases
b. Pros:
i. Can escape local optima
ii. Computationally expensive due to repeated evaluation
3. Local Beam search: is a variant of local search that maintains multiple states at each level
of the search.
a. Process:
i. Start: begin with a set of initial solution
ii. Generate: expand all current solution to their neighbors
iii. Select; choose a subset of the best neighbors to form the new beam
iv. Repeat: continue expanding and selecting until a solution meets the
criteria
b. Pros:
i. More likely to find a good solution than single-state local search
ii. Reduces the risk of getting stuck in local optima.
c. Cons:
i. Requires managing multiple states and their neighbors
ii. Computationally intensive as the number of beams increases.
4. Genetic algorithm: Are inspired by the process of natural selection and evolution.
a. process:
i. initialize: start with population of random solutions
ii. evaluate: asses the fitness of each solution
 iii. select; choose the best solutions for reproduction based on their fitness
iv. crossover: combine pairs of solution to produce new offspring
v. mutate: apply random changes to offspring to maintain diversity
vi. replace: form a new population by selecting which solutions to help.
b. Pros:
i. Can explore a broad solution space and find high quality
ii. Suitable for complex problems with large search space
c. Cons;
i. Computationally expensive
ii. Requires tuning of various parameters size and mutation rate
5. Tabu search: enhance local search by using structure called the tabu list to avoid
revisiting previously explored solution
a. Process:
i. Start; begin with an initial solution and initialized the tabu list
ii. Move: transition to a neighboring solution while considering the tabu list
iii. Update: add the current solution to the tabu list and potentially remove
older entries
iv. Aspiration criteria: allow moves that lead to better solutions even if they
are in the tabu list
b. Pros:
i. Reduces the chance of getting stuck in local optima
ii. Effective in exploring large and complex search space
c. Cons:
i. Requires careful management of the tabu list and aspiration criteria
ii. Computational complexity can be high

FUZZY LOGIC
Definition: the word fuzzy means the things that are not clear, sometimes we don’t know
whether things are true or false, at that time this concept provides many value between the true
and false and gives the flexibility to find the best solution to that problem

Example of fuzzy logic as comparing to Boolean logic

CHARACTERISTICS OF FUZZY LOGIC
1. This concept is flexible and we can easily understand and implement it.
2. It is used for helping the minimization of the logics created by the human.
3. It is the best method for finding the solution of those problems which are suitable for
approximate or uncertain reasoning.
4. It always offers two values, which denote the two possible solutions for a problem and
statement.
5. It allows users to build or create the functions which are non-linear of arbitrary
complexity.
6. In fuzzy logic, everything is a matter of degree.
7. In the Fuzzy logic, any system which is logical can be easily fuzzified.
8. It is based on natural language processing.
9. It is also used by the quantitative analysts for improving their algorithm's execution.
10. It also allows users to integrate with the programming.

ARCHITECTURE OF A FUZZY LOGIC SYSTEM

a) Rule base: Rule Base is a component used for storing the set of rules and the If-Then conditions
given by the experts are used for controlling the decision-making systems.
b) Fuzzification: is a module or component for transforming the system inputs,
o Large Positive (LP)
o Medium Positive (MP)
o Small (S)
o Medium Negative (MN)
o Large negative (LN)
c) Interference engine: it’s the main component in any fuzzy logic system. It allows users to find the
matching degree between the current fuzzy inputs and the rules.
 d) Deffuzification: is the process of converting a fuzzy output into a crisp value. It’s the last step in
fuzzy logic system.

MEMBERSHIP FUNCTION
Definition: is a function which represents the graph of fuzzy sets, and allows users to quantify the
linguistic term.
It is a graph which is used for mapping each element of x to the value between 0 and 1.
This function is also known as indicator or characteristics function. This function of Membership was
introduced in the first papers of fuzzy set by Zadeh. For the Fuzzy Set B, the membership function for X
is defined as: μB:X → [0,1]. In this function X, each element of set B is mapped to the value between 0
and 1. This is called a degree of membership or membership value.

APPLICATION OF FUZZY LOGIC

1. It is used in Businesses for decision-making support system.

2. It is used in Automotive systems for controlling the traffic and speed, and for improving the
efficiency of automatic transmissions. Automotive systems also use the shift scheduling method
for automatic transmissions.
3. This concept is also used in the Defence in various areas. Defence mainly uses the Fuzzy logic
systems for underwater target recognition and the automatic target recognition of thermal infrared
images.
4. It is also widely used in the Pattern Recognition and Classification in the form of Fuzzy logic-
based recognition and handwriting recognition.
5. It is also used in the searching of fuzzy images. Fuzzy logic systems also used in Securities.
6. It is also used in microwave oven for setting the lunes power and cooking strategy.
7. This technique is also used in the area of modern control systems such as expert systems.
8. Finance is also another application where this concept is used for predicting the stock market, and
for managing the funds.
9. It is also used for controlling the brakes.
10. It is also used in the industries of chemicals for controlling the ph, and chemical distillation
process.
11. It is also used in the industries of manufacturing for the optimization of milk and cheese
production.
12. It is also used in the vacuum cleaners, and the timings of washing machines.
13. It is also used in heaters, air conditioners, and humidifiers.
ADVANTAGES OF FUZZY LOGIC
1. Fuzzy Logic has various advantages or benefits. Some of them are as follows:
2. 1. The methodology of this concept works similarly as the human reasoning.
3. 2. Any user can easily understand the structure of Fuzzy Logic.
4. 3. It does not need a large memory, because the algorithms can be easily described with fewer
data.
5. 4. It is widely used in all fields of life and easily provides effective solutions to the problems
which
6. have high complexity.
7. 5. This concept is based on the set theory of mathematics, so that's why it is simple.
8. 6. It allows users for controlling the control machines and consumer products.
9. 7. The development time of fuzzy logic is short as compared to conventional methods.
10. 8. Due to its flexibility, any user can easily add and delete rules in the FLS system.

DISADVANTAGES OF FUZZY LOGIC

1. CFuzzy Logic has various disadvantages or limitations. Some of them are as follows:
 2. 1. The run time of fuzzy logic systems is slow and takes a long time to produce outputs.
3. 2. Users can understand it easily if they are simple.
4. 3. The possibilities produced by the fuzzy logic system are not always accurate.
5. 4. Many researchers give various ways for solving a given statement using this technique which
6. leads to ambiguity.
7. 5. Fuzzy logics are not suitable for those problems that require high accuracy.
8. 6. The systems of a Fuzzy logic need a lot of testing for verification and validation.

DEFFUZIFICATION

Definition: is the process of converting a fuzzy output into a crisp value. Two most commonly used
methods of Deffuzification are: -

- Center of area
- Center of Gravity

SOLUTION

- Center of area
1. ½ x b x h
= ½ x 1 x 0.3
= 0.15

2. L x W
= 2.5 x 0.3
= 0.75

3. L x W
 = 0.3 x 0.5
= 0.15

4. ½ x b x h
= ½ x 0.2 x 0.2
= 0.02

5. L x W
= 1.5 x 0.5
= 0.75
6. L x W
= 0.5 x 0.5
= 0.25
7. ½ x b x h
= ½ x 0.5 x 0.5
= 0.125
8. L x W
=1x1
=1
9. ½ x b x h
=½x1x1
= 0.5
- Center of gravity
1. 0+1+1
3
= 2/3 = 0.66
2. 1+3.5
2
= 4.5/2 = 2.25
3. 3.5+4
2
= 7.5/2 = 3.75
4. 3.5+4+4
3
= 11.5/3 = 3.83
5. 4+5.5
2
= 9.5/2 = 4.75
6. 5.5+6
2
= 11.5/2 = 5.75
7. 5.5+6+6
3
= 17.5/3 = 5.83
8. 6+7
2
= 13/2 = 6.5
9. 7+7+8
3
= 22/3 = 7.33
 NO- Ai Xi Ai x xi
1 0.15 0.66 0.099
2 0.75 2.25 1.687
3 0.15 3.75 0.562
4 0.02 3.83 0.0766
5 0.75 4.75 3.562
6 0.25 5.75 1.437
7 0.125 5.83 0.728
8 1 6.5 6.5
9 0.5 7.33 3.665
Total 3.695 40.65 18.316

∑n = Ai xi
Ai
= 18.316
3.695
= 4.956 : - The possible Centroid = 4 approximately

KEY DIFFERENCE AND APPLICATIONS

FEATURE COA (CENTER OF AREA) COG (CENTER OF GRAVITY)

Concept Find the centroid of the area under Find the center of mass of the fuzzy set
fuzzy set
Mathematics Uses integration or summation for Uses weight averages
discrete cases
Accuracy Most widely used, smooth, and Equivalent to COA in most cases
accurate
Use cases Control system, AI robotics, Decision-making, fuzzy control,
automation engineering

NEURAL NETWORK

Definition: Neural networks ar machine learning models that mimic the complex of functions of the
human brain.

KEY COMPONENTS: -

1. Neurons: the basic units that receive inputs, is governed by a threshold and an activation function
2. Connections: Links that carry information, regulated by weights and biases.
3. Weight and Biases: These parameters determine the strength and influence of connection
4. Propagation functions: mechanism that help process and transfer data across the layers of neurons
5. Learning rule: The method that adjust the weight and biases over time and improve accuracy.
Learning take three stages: -
a. Input computation: Data is fed into the network
b. Output generation: Based on the current parameters, the network generates an output
c. Iterative refinement: The network refines its output by adjusting weight and biases,
gradually improving the performance on diverse task.

IMPORTANCE OF NEURAL NETWORK

 - Pivotal in identifying complex patterns
- Solving intricate challenges
- Adapting to dynamic environment
- Ability to learn vast amount of data (transformative
- Impact on technologies like: -
o Natural language processing
o Self-driving vehicles
o Automated decision-making

EVOLUTION OF NEURAL NETWORK

Neural networks have evolved significantly since their inception in the mid-20th century.
Initially, McCulloch and Pitts introduced a mathematical model of artificial neurons, but
progress was slow due to limited computational power. In the 1960s-70s, Rosenblatt's perceptron
demonstrated basic learning capabilities but couldn't handle complex tasks. The 1980s saw a
breakthrough with backpropagation, enabling training of multilayer networks. Neural networks
gained popularity in the 1990s across multiple domains but faced setbacks during the "AI winter"
due to high costs and unrealistic expectations. The 2000s marked a resurgence driven by larger
datasets, better computational power, and deep learning architectures. Since the 2010s, deep
learning models like CNNs and RNNs have dominated the field, advancing applications in image
recognition, finance, and beyond.

LAYERS IN NEURAL NETWORK

1. Input Layer: This is where the network receives its input data. Each input neuron in the layer
corresponds to a feature in the input data.
2. Hidden Layers: These layers perform most of the computational heavy lifting. A neural network
can have one or multiple hidden layers. Each layer consists of units (neurons) that transform the
inputs into something that the output layer can use.
3. Output Layer: The final layer produces the output of the model. The format of these outputs
varies depending on the specific task (e.g., classification, regression).