Ch-2 AI PROJECT CYCLE:

Introduction To AI Project Cycle:

Start with listing down all the factors which you need to consider while framing a security
system. While finalizing the aim of this system, you scope the problem which you with solve
with the help of your project. This is Problem Scoping.

First you have to define the list of people who are allowed to enter the politician’s house and
which designated areas they are allowed to go to and for how long Certain key officials, VIPS,
etc, may have access to any area within the pr but this would be a defined list. The focus is to
ensure that no unauthorized p is entering the premises.

Potential steps here could be:

1. Profiles of authorized people and tag with their designated areas where they are allowed
2. Get photographs of people who are a possible threat to the politician (this list you can have
from the intelligence agency)
3. Get photographs of all the visitors to the premises at the entry gate
4. GPS coordinates of the locations
5. RFID tags data at the entry/exit

As you start collecting the above data, you actually acquire data in multiple formats-
coordinates, texts, photos, video, etc. This is known as Data Acquisition.

After acquiring the required data, you realize that it is not readily usable. Some images are low
resolution, small in size, while others are better. Some images are missing and GPS coordinates
are wrong. Now you need to do Data Cleaning as under:
• Create a database and put the names of the designated people whose profiles you have.
• Put all the photographs in a model and try to derive a pattern out of it.
• Make a database to store the clean data.
• At this stage, you try to interpret some useful information out of the data you pave
acquired. For this, you explore the data and try to put it uniformly for a better
understanding. This is known as Data Exploration.
After exploring the data, you now know that you need to develop a system which detects the
face of the person entering the premises and matches it with the image data in your system to
check whether this person is authorized or not. For this, you put all your data into an AI-
enabled model and train it in such a way that it alerts the officials if an unknown person tries
to enter the premises. To implement this, you need to define the variables or parameters you
need.

To implement your idea, you now look at different Al-enabled algorithms which work on
Computer Vision (since you are working on visual data). You go through several models and
select the one that matches your requirement. After choosing the model, you implement it.
This is known as the Modelling stage.

As you move towards deploying your model in the real world, you test it in various ways. The
stage of testing the models is known as Evaluation.

Problem Scoping:
It means to solve using our AI knowledge. After listing the problems, go down till the
root cause of the problem is found.
The causes are plotted through analysis, brainstorming sessions and are grouped into
categories on the main branches of the fishbone. To help structure the approach, the
categories are often selected from one of the common models shown below but may
emerge as something unique to the application in a specific case.

We will now use the another tool called 4Ws Problem Canvas.
4W’s refer to Who, What, Where, Why.
▶ Who : in this stage we look for the person who is having the problem, they are
also known as the stakeholders of the problem.
▶ What : here we consider the nature of the problem. What is the problem and
how do we know that it is a problem? Is there any evidence to support that it is a
real problem?
▶ Where : Where does the problem arise? Here we describe the context of the
problem.
▶ Why : it refers to understanding the cause of the problem.

4W’s Problem Canvas in Data Acquisition:

Who:
• Who are the stakeholders?
• What do you know about them?
What:
• What is the exact problem?
• How do you know that it is a problem? (is there any evidence?)
Where:
 • What is the context/ situation/ frequency of the problem?
• Where is the problem located?
Why:
• What would be beneficial for the stakeholders?
• How will the solution improve their situation?

What is Data Acquisition?

Data can be a piece of information or facts and statistics collected together for reference
or analysis. Whenever we want an AI 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 Intelligent 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. The previous
salary data here is known as Training Data while the next salary prediction data set is
known as the Testing Data.

Data Features:
▶ Data features refer to the type of data you want to collect.
▶ In our previous example, data features would be day, in time, out time, biometric
machine attendance data, leave record, etc.
Acquiring Data from Reliable Sources:
▶ Question arises from where and how you will collect data? What are the sources
of data collection?
▶ Sources of data collection
• Surveys
• Web scrapping
• Sensors
• Cameras
• Observations
• APIs (Application Programming Interface)
• Interviews

System Maps:
The Water Cycle The concept of Water cycle is very simple to understand and is
known to all. It explains how water completes its cycle transforming from one form to
another. It also adds other elements which affect the water cycle in some way. The
elements which define the Water cycle system are:
The Water Cycle The concept of Water cycle is very simple to understand and is
known to all. It explains how water completes its cycle transforming from one form to
another. It also adds other elements which affect the water cycle in some way. The
elements which define the Water cycle system are:
The Water Cycle The concept of Water cycle is very simple to understand and is
known to all. It explains how water completes its cycle transforming from one form to
another. It also adds other elements which affect the water cycle in some way. The
elements which define the Water cycle system are:

Let us draw the System Map for the Water Cycle now.

In this System Map, all the elements of the Water cycle are put in circles. The map here
shows cause & effect relationship of elements with each other with the help of arrows.
The arrow- head depicts the direction of the effect and the sign (+ or -) shows their
relationship. If the arrow goes from X to Y with a + sign, it means that both are directly
related to each other. That is, If X increases, Y also increases and vice versa. On the
other hand, If the arrow goes from X to Y with a – sign, it means that both the elements
are inversely related to each other which means if X increases, Y would decrease and
vice versa.
Data Exploration:
▶ Why do you think we need to explore and visualize data before jumping to the AI
model?
▶ It is so because, when we pick up a library book, we tend to look at the book cover,
read the back cover and skim through the content of the book prior to choosing it.
▶ In the same way, when we get data set in our hands, spending time to explore it
will help us get a sense of the trends, relationships and patterns present in the data.
▶ In previous module you set the goal of your project and also found ways to acquire
data. While acquiring data, you must have noticed that the data consists of
numbers, words, media etc.
To analyse the data, you need to visualize it in some relationships and patterns contained
within the data.
▶ 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 the data, we can use
various types of visual representations like, Sketchy graphs.
Types of Data could be : CSV, Spreadsheet, SQL.
MODELLING:
To build an AI-based project, you need to wok around models or algorithms to predict
the output given a set of inputs. This could be done by either designing your own model.
or by using the pre-existing AI models. Before jumping to modelling, let us revise few
terms:
1. Artificial Intelligence: It is the science of making machines intelligent like
humans.
2. Machine Learning : The machine here learns from the new data fed into it while
testing and uses it for the next iteration.
3. Deep Learning : It enables the software to train itself to perform tasks with a vast
amount of data.
Generally, AI models can be classified as follows:

Rule Based Approach : Refers to the Al 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. For example, we have a dataset which tells us about the
conditions on the basis of which we can decide if child can go out to play golf or not. The
parameters are: Outlook, Temperature, Humidity and Wind.

Learning Based Approach : Refers to the Al modelling where the machine learns by itself.
Under the Learning Based approach, the Al model gets trained on the data fed to it and then is
able to design a model which is adaptive to the change in data. That is, if the model is trained
with X type of data and the machine designs the algorithm around it, the model would modify
itself according to the changes which occur in the data so that all the exceptions are handled in
this case.
For example, suppose you have a dataset comprising of 100 images of apples and bananas
each. These images depict apples and bananas in various shapes and sizes. These images are
then labelled as either apple or banana so that all apple images are labelled 'apple' and all the
banana images have 'banana' as their label. Now, the Al model is trained with this dataset and
the model is programmed in such a way that it can distinguish between an apple image and a
banana image according to their features and can predict the label of any image which is fed to
it as an apple or a banana. After training, the machine is now fed with testing data. Now, the
testing data might not have similar images as the ones on which the model has been trained.
So, the model adapts to the features on which it has been trained and accordingly predicts if the
image is of an apple or banana.
EVALUATION:
Once a model has been made and trained, it needs to go through proper testing so that
we calculate the efficiency and performance of the model.

Accuracy Precision Recall F1 score

Neural networks are loosely modelled after how neurons in the human brain behave. The key
advantage of neural networks is that they are able to extract data features automatically
without needing the input of the programmer.
Deployment
Deployment as the final stage in the AI project cycle where the AI model or solution is
implemented in a real-world scenario. Key Steps in Deployment Process the key steps
involved in the deployment process:
a. Testing and validation of the AI model
b. Integration of the model with existing systems
c. Monitoring and maintenance of the deployed model. Some examples of successful AI
projects that have been deployed in various industries, such as selfdriving cars, medical
diagnosis systems, and chatbots.

Ethics and Morality

Ethics and Personal Data
Ethics with Personal Data
▪ There are around 5.34 billion smartphone users in the world as of July 2022, with their
information available on the internet.
▪ AI can help us find out data related to a particular person, from all the available data.
▪ Such AI solutions are used by organizations to give us customized recommendations for
products, songs, videos, etc.
▪ In this way, AI can influence our decision-making at times
▪ This calls for a need for ethical principles that govern AI and people who are creating AI.

AI Ethics Principles

Identifying the principles

● To make AI better, we need to identify the factors responsible for it.
● The following principles in AI Ethics affect the quality of AI solutions
▪ Human Rights
▪ Bias
▪ Privacy
▪ Inclusion
a) Human Rights
● When building AI solutions, we need to ensure that they follow human rights.
● Here are a few things that you should take care of
▪ Does your AI take away Freedom?
▪ Does your AI discriminate against People?
▪ Does your AI deprive people of jobs?
▪ What are some other human rights which need to be protected when it comes
to AI?
b) Bias
● Bias (partiality or preference for one over the other) often comes from the
collected data. The bias in training data also appears in the results.
● Here are a few things that you should take care of
▪ Does your data equally represent all the sections of the included populations?
▪ Will your AI learn to discriminate against certain groups of people?
▪ Does your AI exclude some people?
▪ What are some other biases that might appear in an AI?

c) Privacy
● We need to have rules which keep our individual and private data safe.
● Here are a few things that you should take care of
▪ Does your AI collect personal data from people?
▪ What does it do with the data?
▪ Does your AI let people know about the data that it is collecting for its use?
▪ Will your AI ensure a person’s safety? Or will it compromise it?
▪ What are some other ways in which AI can breach someone’s privacy?
d) Inclusion
● AI MUST NOT discriminate against a particular group of population, causing
them any kind of disadvantage.
● Here are a few things you should take care of
▪ Does your AI leave out any person or a group?
▪ Is a rich person and a poor person benefitted equally from your AI?
▪ How easy is it to use your AI?
▪ Who does your AI help?
▪ How can we make AI more inclusive? Ask learners, “if they have felt excluded
from any group. H