Grade IX & X

AI
Topic: AI Project Cycle
 Entry Ticket- Think and answer…
The world’s largest diamond is in danger as Mr. X
has threatened to steal it. No one is able to track
Mr. X and so the situation is critical. You have
been appointed as the Chief Security Officer and
your job is to enhance the security of the diamond
to make the area impossible for Mr X to break into
and steal the diamond.
Start with listing down all the factors which you need to
consider while framing a security system.
These steps show how we plan to execute the tasks
around us. Consciously or Subconsciously our mind
makes up plans for every task which we have to
accomplish which is why things become clearer in our
mind.
 What is AI Project Cycle?
The AI Project Cycle is a cycle/order of an AI Project which defines
every step an organization must take to harness/get value (Monetary or
others) from that AI Project to get more ROI (Return on Investment).

Identify the problem

statement
Test the build solution
(product) and launch it to
Understand the problem
targeted end-users.
statement

Building the
solution(algorithm) to solve Collect the required data to
the problem. solve the identified problem

Analyse and visualize the problem

and pick a suitable model to build the
solution.
AI Project Cycle framework?
The AI Project Cycle has various phases and subphases.
 Stage 1: Problem Identification
• Problem identification is
the Clear identification of
the problem by finding the
root cause of the problem.
• This stage is complete
when we frame the
problem statement clearly.
• 17 SDGs can be the
source of problem
identification.
Let’s learn this by solving an example
problem
Topic: AI in Fitness
Problem Identification : Predict new fitness trends.
Stage 2: Problem Scoping

• Problem scoping is the process by which we figure out the

problem that we need to solve.
• 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.
● Who?: Refers that who is facing a problem, who the stakeholders of the problem are and who are

affected because of the problem.

● What?: Refers to what the problem is and what you know about the problem. What is the nature of the

problem? Can it be explained simply? How do you know it’s a problem? What is the evidence to support

that the problem exists? What solutions are possible in this situation? etc. At this stage, you need to

determine the exact nature of the problem.

● Where?: It is related to the context or situation or location of the problem, focus on the

context/situation/location of the problem.

● Why?: Refers to the reason we need to solve the problem, the benefits which the stakeholders would

get from the solution and how would it benefit them as well as the society, what are the benefits to the

stakeholders after solving the problem.

Problem scoping involves…
Let’s learn this by solving an example problem
(contd..)
Problem Scoping: 4W Canvas

Who ? Fitness enthusiasts, gym owners, health coaches, AI developers.

What? Limited ability to foresee upcoming fitness trends accurately.
Where? Across gyms, fitness centers, and wellness communities seeking to
stay current.
Why? Early identification of popular fitness activities and habits. Enables
proactive adaptation to evolving fitness preferences, enhancing
service offerings and user satisfaction.
 Stage 3: Data Acquisition
Data Acquisition consists of two words:

● Data: Data refers to the raw facts,

figures, information, or statistics.
● Acquisition: Acquisition refers to
acquiring data for the project.

So, Data Acquisition means Acquiring

Data needed to solve the problem.

Data can be collected in many ways;

• Whenever we want an AI project to be able to predict an output,
we need to train it first using data.
• Data is of two types;
• Training data - data fed to the AI system to predict the
outcome.
• Testing data - the unseen data used it to evaluate the
performance and progress of AI system’s training and adjust
or optimize it for improved results.
• For example, If you want to make an AI 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.
This is the data with which the machine can be trained. Now,
once it is ready, it will predict his next salary efficiently.
• Here, the previous salary data here is known as Training Data
while the next salary prediction data set is known as the Testing
Data.
Let’s learn this by solving an example problem
(contd..)
Data Acquisition:
List the sources of data collected.

Source Citation
Fitness Trends Dataset - A dataset of fitness Link
trends and how they change with exercise.

Note: There are many ways to collect data, here we are using Web
scraping method to work with pre-existing dataset available freely for
public to use.
 Stage 4: Data Exploration
• Data exploration is the first step of data analysis which is used to
visualize data to uncover insights from the start or identify areas
or patterns to dive into and dig more.
• It allows for a deeper, more detailed, and better understanding of
the data.
• Data Visualization is a part of this where we visualize and present
the data in terms of tables, pie charts, bar graphs, line graphs,
bubble chart, choropleth map etc.
• This provides a common, consistent, and predictable way of
defining and managing data resources.
Let’s learn this by solving an example problem
(contd..)
Data Exploration:
There are many tools to visualize the data based on its complexity
and purpose. For our dataset MS Excel or Python libraries are
suitable.
Steps to Visualize the dataset:
1. Download the datset from trusted source. (As mentioned in
Data acquisition slide)
2. Open the downloaded .csv file in MS Excel.
3. Analyze the metrics (columns).
4. Use suitable charts to visualize.
5. Write conclusion.
Data Visualization:
1. Line chart for Step count over time.
Data Visualization:
2. Pie chart for active vs inactive days:
First calculate active and inactive days using COUNTIF function
then apply a 2D pie chart.
• Stage 5: Modelling
An AI model is a program or
algorithm that utilizes a set of
data that enables it to recognize
certain patterns. This allows it to
reach a conclusion or make a
prediction when provided with
sufficient information.
• Modelling is the process in which
different models based on the
visualized data can be created
and even checked for the
advantages and disadvantages of
the model.
• There are 2 Approaches to make
a Machine Learning Model.
Learning Based Approach: Learning Based Approach is
based on Machine Learning experience with the data fed.
There are 3 types;
Learning Based Approach:
● Refers to the AI modelling where the relationship or
patterns in data are not defined by the developer.
● 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.
Learning Based Approach - Example:
● 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 AI
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!
Rule Based Approach:
● Refers to the AI modelling where the rules are defined by
the developer. The machine follows the rules or instructions
mentioned by the developer and performs its task
accordingly.
● These AI system models are defined by ‘if-else’ coding
statements.
● For example, an expert system might help a doctor choose
the correct diagnosis based on a cluster of symptoms, or
select tactical moves to play a game.
Example of Rule based approach - Decision Tree
● Decision Trees are similar to the concept of Story Speaker. It
is a rule-based AI model which helps the machine in
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:
● Decision Trees are made on the basis of the dataset we
have and change according to the parameters which we
take into consideration for modelling.
● Many times, the dataset might have redundant data, that is,
some data might not hold importance while developing the
decision tree. For this, one needs to visualise the relation
amongst all the parameters given in the data and then
formulate the model.
Points to remember
● While making Decision Trees, one should take a good look
at the dataset given to them and try to figure out what
pattern does the output leaf follow. Try selecting any one
output and on its basis, find out the common links which all
the similar outputs have.
● Many times, the dataset might contain redundant data
which does not hold any value while creating a decision
tree. Hence, it is necessary that you note down which are
the parameters that affect the output directly and should
use only those while creating a decision tree.
● There might be multiple decision trees which lead to correct
prediction for a single dataset. The one which is the
simplest should be chosen as the best.
Let’s learn this by solving an example problem
(contd..)
Modelling:
Here I plan to have an user
friendly app powered by AI
models.
App UI:
Modelling:
Some of the AI models that can be used in this app are:

Recommends fitness activities, workout

routines, or nutritional plans based on user
preferences and behaviors.
Text Classification: Categorizes
Regression model - Predicts
user inputs (e.g., fitness goals,
fitness metrics such as Recommender dietary preferences) to
calories burned, steps taken, Systems personalize recommendations.
or sleep quality based on
historical data and user Predictive
inputs. Analytics NLP Models
Models AI Models

Object Detection: Identifies

and categorizes fitness Personalizati
equipment or exercises in CV Models on Algorithms
images or videos uploaded
by users.
ML Models Cluster Analysis: Groups users with
similar fitness profiles to tailor
Classification Algorithms: Identifies patterns recommendations and goals.
in health data (e.g., heart rate variability,
sleep patterns) to detect anomalies or
potential health risks.
 Stage 6: Evaluation & Deployment
• AI Evaluation is testing the model
developed by feeding the data into the
model and comparing the output with the
actual answers.
• Deployment is the process of making the
project available for the end user to use.
• Uses of Evaluation:
• Enhancing the research field.
• Identifying the fields that can be
replicated.
• Identifying the fields with shortcomings,
which
Can become the fields for he further
research.
Let’s learn this by solving an example problem
(contd..)
Evaluation:
• App can be built and tested internally using Evaluation metrics to
confirm the technical features.
• Beta testing can be done by choosing a small group of stakeholders.

Deployment:
• App can be made available in trustable app stores for end-users to
use.
• Stakeholders are contacted and advantages of app can be explained
and demonstrated.