UNIT II

Artificial Intelligence
Class 9

AI Project Cycle
 UNIT-II Al Project Cycle

Introduction
Steps ofAl Project Artificial Intelligence
Cycle
Problem Scoping
AW canvas
WHO
WHAT
WHERE
WHY

- Data Acquisition
- Data Exploration
- Modelling

Evaluation

Objective of Topic

Understanding of
Problem Scoping
4W Canvas
Data Acquisition
Sources of Data
Data Exploration
Modelling and its types
Evaluation of Project
 Problem Scoping: 4W CANWAS
What? Where? Why
Wly.de yeubelire ik in arotdem.wsrth.solvingt
Why? What would be of hey vnlan tn ther atakrhulden?
Why you want to solve this problem.
Thus, in the "Why" canvas, think
about the benefits which the OW wouoE p r o v e their stuation

stakeholders would get from the

solution and how it will benefit them
as well as the society.

Here is the Why Canvas:

14

Problem Scoping: 4W CANWAS

After filling 4Ws Problem

(otakeholder(o))
the canvas, you now need to
Our
summarise all the cards into one
What
template. has ssue.problem,
The Problem Statement Template /have a
problem
helps us to summarise all the key th1at

points into one single Template so when/ Icontext Where

that in future, whenever there is while aituation
need to look back at the basis of benefit.of aolution for
An why
the problem, we can take a look at Ihem
ideal
the Problem Statement Template solution
and understand the key elements WOuld

of it.

15
 Data Exploration

D a t a is a complex entity - it is full of numbers and i f anyone wants to make

some sense out of it, they have to work some patterns out ofit.
For example, if you go to the library and pick up a random book, you first try to
go through its content quickly by turning pages and by reading the
description before borrowing it for yourself, because it helps you in
understanding if the book is appropriate to your needs and interests or not.
Thus, to analyze the data, you need to visualize it in some user-friendly
format so that you can:
Quickly get a sense of the trends, relationships and patterns contained
within the data.
Define strategy for which model to use at a later stage.
Communicate the same to others effectively. To visualize data, we can use
various types of visual representations.

24 24

Modelling

I n the previous module of Data exploration, we have seen various types of

graphical representations which can be usedfor
representing
parameters of data. different
The graphical representation makes
we can discover trends and patterns out Br9Hdata understandable for humans as

But when it comes to machines accessing and analysing data, it needs the
data in the most basic form of numbers (which is binary -Os and 1s) and when
it comes to discovering patterns and trends in data, the machine goes in for
mathematical representations of the same.
The ability to mathematically describe the relationship between parameters is
the heart of every Al model.
Thus, whenever we talk about developing Al models, it is the mathematical
approach towards analy sing data which we refer to.

25 25
 Steps of Al Project Cycle

The Al Project Cycle mainly has 5 stages:

Problem Data Evaluation

Scoping Exploration

Data Modelling
Acquisition

Problem Scoping

I t is a fact that we are surrounded by problems.

Identifying such a problem and having a vision to solve it, is what
Problem Scoping is about.
' A lot of times we are unable toobserve any problem in our
surroundings
 Are you aware of visual representations of data? Fill them
belov

Bar
Graphs

Visual
Representations (

To explore various data visualisation

echniques, visit this link: https:/

Let us solve:

Data Visualisation Technique 1,2,3,4and 5

Name of the
Representation

One-lir
Description

How to draw it

Suitable for
which data
23
 Daily Quiz & MCQ

FillUps:
1)AI project cycle has.steps.
2)AI Modelling is of_types.

3)Third step of Project cycle is

4 ) s the first step of Al Project cycle.

E$GD stands for

Daily Quiz & MCQ

MCQ:
1) 4W canvas means:
a. Who, what, where, why
b. what, whom, where,
why
C. whose, whom, who,
what
2) Data fanbeNHLEed by
a. Surveys b. Web c. Sensors d. All of
these
3)Last step of Project cycle is
a. Modelling b. Data
b. Evaluation d. aioration
Acquisition

45
 System map for water cycle:

River

malt

Ocean

Clouds

42

Write difference between Data Acquisition & Data Exploration

Difference between Data Acquisition &Data Exploration.

Ans: Data acquisition is the process of gathering and filtering

the data from various sources, while data exploration is
analysing and visualizing the patterns and hidden insights from
the data

43
 Decision Tree:
It is a rule-based Al model which helpsthe machinein
predicting what an element is with the help of various
decisions (or rules) fed to it. A basic structure of
decision tree is shown below:

Am I hungry?
-Root

Yes No -Branches

Have 125$ ? Go to sleep

Leaves

Wo
(es

Go to restaurant Buy a Burger

36
Explanation:

Here, the Decision tree starts from the

question Am I Hungry? The beginning point of
any Decision Tree is known as its Root. It then
forks into two different ways or conditions:
Yes or No. The torks or diversions are known
as Branches of the tree. The branches either
lead to another question, or they lead toa
decision like Go to Sleep which is known as
the leaf. If you look closely at the image above,
you would notice that it looks like an inverted
tree with root above and the leaves below.
37ence the name Decision Tree!
 Problem Scoping: 4W CANWAS

4Ws Problem Canvas

The 4Ws Problem canvas helps in identifying the key elements related to the
problem.

Who? What? Where? Why?

Let us go through each of the blocks one by one.

10

Problem Scoping: 4W CANWAS

Who? Whe it havirng the aroBe

The "Who" block helps in

analysing the people getting
Who am the sta krhnldern?

affected directly or indirectly .What d yn knnw aout them?

due to it.
Under this, we find out who the
Stakeholders' to this problem
are and what we know about
them.
Here is the Who Canvas:
Stakeholders are the people
who face this problem and
would be benefitted with the
solution.

11
 Activity on Problem Scooping:
Let us now start scoping a problem. Look around you and select a theme which interests you
the most. Suggested themes are:

Environ-
ment
Agricu-
ture
Traffic nfrast-
ucture

Health Security
Educa- Digital
tion Literacy

Women
Safety
Trans
port
Enterta-
inment
Cyber
Security

Travel Social
Disability weltareP
Research
Tourism

You can either select any one out of these or you can think of one on your own. For more
options, you can also refer to the 17 Sustainable Development Goals we discussed in the
Purpose module.

Questions:
1) Your selected theme is:

Ans.

2) Why did you select this theme?

sss *******n************ ************ ***********s*a* *an *en *t*******************************

*********** ***
*** **********************************

3) List the Problems related to your theme.

4******

********************************************* **a sassns a***ss sas

aas aes ses e e s a a s ********nene*** sessesean***

*******************************
As you can see in the Venn Diagram, Artificial Intelligence is the
umbrella terminology which covers machine and deep learning
under it and Deep Learning comes under Machine Learning. It is a
funnel type approach where there are a lot of applications of Al
out of which few are those which come under ML out of which
very few go in-

Artificial
Intelligence

Machine
Learning

Deep
Learning

28

Deep Leaming Vs Machine Learning

Factors Deep Leaming Machine Learning

Data Requirement Requires large data Can train on lesser data

ACcuracy Provides high accuracy Gives lesser accuracy

Training Time Takes longer to train Takes les time to train

Hardware Dependency Requires GPU to train properly Trains on CPU

Can be tuned in various

Hyperparameter Tuning Limited tuning capabilities
different ways

29
 Evaluation

Once a model has been made and trained, it needs to go through proper
so that one can calculate the efficiency and performance of the
testing
model.
Hence, the model is tested with the Test Data (which was
separated out of the acquired dataset at Data Acquisition stage) and the
efficiency of the model is calculated on the basis of the parameters
mentioned below:

Accuracy Precision Rcall F1 Score

40 AD

The elements which define the Water cycle system are:

Clouds Snow Underground Soil Rivers

Oceans Trees Land Animals

 Weekly Assignment/ Activity

Think about any problem and fill the 4W canvas and finally
create a
Problem statement out of it.

Activit Teachable machlne actlvity

https://teachablemachine.withgoogle.com/
train

Explore it and enjoy the interesting

46

Expected Questions for Board Exam

Write any one method to visualize the data. (1)

What are the types of Al Modelling. (2)
Differentiate between Data Acquisition and Data
Exploration. (3)
What is SDG? (3)
Explain 4W canvas with some example.(4)
What is AI Project cycle? Explain all the steps briefly.(5)
 Evolution of Artificial Intelligence

ARTIFICIAL
INTELLIGENCE
Early artificial inteligence MACHINE
stirs excitement
LEARNING
Machine learning begins DEEP
to flourish
LEARNING
Desp larning bresithroughs
drive Al b

1950's 1960's 1970's 1980s 1990's 2000's 2010's

30
Funl1itinn nf Artifirial Intallinonra

Modelling

Generally, Al models can be classified as follows:

MACHIN
LEARNIN E

Al G DEEP
EASED LEARNIN
MODELSS
RULE G

31
 Data Acquisition

Data Acquisition, as the term clearly mentions, this stage is about

acquiring data for the project.
Data can be a piece of information or facts and statistics collected
together for reference or analysis.
Whenever we want an Al project to be able to predict an output, we need
to train it first using data.
For example, If you want to make an Artificially lntelligent system which
can predict the salary of any employee based on his previous salaries, you
would feed the data of his previous salaries into the machine.
The previous salary data here is known as Training Data while the next
salary prediction data set is known as the Testing Data.

Note: For better efficiency of an Al project, the Training data

needs to be relevant and authentic.

18

Sources for Data Acquisition

Surveys
Web Scraping

Cameras

Sensors

Observations

19
 Problem Scoping: 4W CANWAS

Who? Where? Why

What? ehat.in the.aaturn.t.thm.arohem
Under the "What" block, you need to What in the
problem
look into what you have on hand.
At this stage, you need to Huw 0O Y0u now It # prooiern
determine the nature of the
problem.
What is the problem and how do
you know that it is a problem?
Under this block, you also gather
evidence to prove that the problem
you have selected actually exists. Here is the What Canvas:
Newspaper articles, Media,
announcements, etc are some
examples. Here is the What
Canvas:

12

Problem Scoping: 4W CANWAS

hati Where?

Where?
you need to focuss on the
context/situation/location of the
problem.
This block willhelp you look into the situation in which the problem arises,
the context of it, and the locations where HeptePmihent-

Here is the r e Canvas:

13
 Rule Based Approach
Suppose you have a dataset comprising of 100
images of apples and 100 images of bananas. To
train your machine, you feed this data into the
machine and label each image as either apple or
banana. Now if you test the machine with the
image of an apple, it will compare the image with
the trained data and according to the labels of
trained images, it will identify the test image as an
apple. This is known as Rule based approach. The
rules given to the machine in this example are the
labels given to the machine for each image in the
training dataset.

32
Rule Based Al Model

Machine Trained using

Labelled Dataset

Rule-based Al Model

Labelled Dataset

OUTPUT

Testing Data

Machine identifies the image as

 Now, answer the following questions to test your understanding
on the basis of the example above:

1. How many branches does the tree shown above have?

1. 2. How many leaves does the tree shown above have?

Do It Yourself!

The following is a dataset comprising of 4 parameters which

lead to the prediction of whether an Elephant would be
spotted or not. The parameters which affect the prediction
are: Outlook, Temperature, Humidity and Wind. Draw a
Decision Tree for this dataset.

Outlook Temperature Humidity Wind Elephant

Spotted?
Sunny Hot High Weak No

Sunny Hot High Strong NO

Overcast Ho High Weak es

Rain Mild High Weak Yes

Rain Cool Normal Weak es

Rain Cool Normal Strong No

 Learning Based Approach
In this approach, random data is fed to the machine and it is
left on the machine to figure out patterns and trends out of it.
Generally this approach is followed when the data is unlabelled
and too random for a human to make sense out of it.
Thus, the machine looks at the data, tries to extract similar
features out of it and clusters same datasets together.
In the end as output, the machine tells us about the trends
which it observed in the training data.

For example, suppose you have a dataset of 1000 images of random

stray dogs of your area. Now you do not have any clue as to what trend
is being followed in this dataset as you don't know their breed, or colour
or any other feature. Thus, you would put this into a learning approach
based Al machine and the machine would come up with various
patterns it has observed in the features of these 1000 images. It might
cluster the data on the basis of colour, size, fur style, etc. It might also
come up with some very unusual clustering algorithm which you might
not have even thought of!

Learning Based Al Model

Training Dataset using

unlabelled data AL
e a r n i n A P p r o d c h Al M o d e l

Unlabelled Dataset

Clustering output based on patterns observed by the machine

(Left) Based on size; (Right) Based on colour
 Al,ML and DL
1. Artificial Intelligence, or Al, refers to any technique that
enables computers to mimic human intelligence. The Al
enabled machines think algorithmically and execute what they
have been asked for intelligently.

2. Machine Learning, or ML, enables machines to improve at tasks

with experience. The machine learns from its mistakes and
in the next execution. It
takes them into consideration
improvises itself using its own experiences.

3. Deep Learning, or DL, enables software to train itself to perform

tasks with vast amounts of data. In deep learning, the machine
is trained with huge amounts of data which helps it into training
itselfaround the data. Such machines are intelligent enough to
develop algorithms for themselves.

Deep Learning is the most advanced form of

Artificial Intelligence out of these three. Then comes
Machine Learning which is intermediately intelligent
and Artificial Intelligence covers all the concepts and
algorithms which, in some way or the other mimic
human intelligence.
 Let us Recapl

Quiz Time!

1. Which one of the following is the second stage of Al project cycle?

a. Data Exploration
b. Data Acquisition
C. Modeling
d. Problem Scoping
Which of the following comes under Problem Scoping?
a. System Mapping
b. 4Ws Canvas
Data Features
d. Web scraping
3. Which of the following is not valid for Data Acquisition?
a. Web scraping
b. Surveys
C. Sensors
d. Announcements

Quiz Continued..

4) Which of the following is not a part of the 4Ws Problem

Canvas?
a. Who?
b. Why?
C. What?
d.Which?
 Problem Scoping

I n that case, we can take a look at the Sustainable Development Goals.

17 goals have been announced by the United nations which Sustateatbled as the
Development Goals.
The aim is to achieve these goals by the end of 2030.
As you can see, many goals correspond to the problems which we might observe
around us too.
One should look for such problems and try to solve them as this would make
many lives better and help our country achieve these goals

DEVELOPMENT ALS
1 2. 3 4

Problem Scoping

Scoping a problem is not that easy as we need to have a deeper

understanding around it so that the picture becomes clearer while
we are working to solve it.

Hence, we use the 4Ws Problem Canvas to help us out.

 Prerequisite/Recap
What is Al

Understanding What is
Al
Youlnbe
What is Not Al 0eoot

Decision Making amazon

Sustainable NOTA
WHAT IS NOT A

Development Goals
Al Ethics

AI Project Cycle

If we have to develop an Al project, the Al

Project Cycle provides us with an appropriate
framework which can lead us towards the goal.
 Summary

Al Project cycle is a Must when you want to

develop any Al project. If all steps of this
cycle are followed successfully, the model
created will be effective.

Thank You