UNIT-2 AI PROJECT CYCLE

SESSION 1: INTRODUCTION TO AI PROJECT CYCLE

1.1 INTRODUCTION
Artificial intelligence is making computers think and act like humans. Now AI technology has entered
our lives in the form of various devices and applications. Behind this technology a major role is
played by the AI project cycle.
1.2 AI PROJECT CYCLE- A BRIEF DISCUSSION
The Artificial Intelligent project cycle is all about how to convert a real-life problem or a challenge
into a computer based AI model. The AI model works on the problem solving area and collects the
data required for solving the problem.

Data Modelling
acquisition

Problem
scoping Data Evaluation
Exploration

1. Problem Scoping:
The first step of the AI life cycle is to identify the problematic student area which needs a
solution. The project outlines the challenges of the system and briefly describes the area
where AI can serve as a solution. Problem scoping is the process by which students “figure
out” the problem that they need to solve. It is the process by which the problem is defined.
2. Data Acquisition:
The next step is to collect and prepare all of the relevant data for use machine learning. The
data is collected to ensure that the system operates in a proper manner.
3. Data Exploration:
The data collected should be arranged in a proper manner for better understanding. The
analysis of the data can be done only if it is arranged in a systematic manner.
4. Modelling:
It is the process in machine language which can be done either manually or automated by
selecting which specific machine learning algorithms we can use in building a model-
essentially software- to work with our data.
5. Evaluation:
Finally, evaluation of the machine learning project is done. The more accurate the result of
your model, the easier it is to meet the requirements of the stakeholders and
communication its value to management and other key stakeholders.
 SESSION 2: UNDERSTANDING PROBLEM SCOPING AND SUSTAINABLE DEVELOPMENT GOALS

In this stage, we focus at the factors causing the problem. The main elements of the problem
are noted down. Problem scoping in itself is a skill where the students need to focus the relevant details
related to the problem.

Problems are everywhere in any system you choose. Whether a problem is big or small, it must
be sorted out. Sometimes we become used to problems as if it is a part of our life. Still we need to
identify the problem and make a vision to solve it.

4W’s Problem Composition/Canvas

The 4W’s problem composition/canvas helps us in identifying the key elements related to the
problem.

 Who
The “Who” block helps in finding the people who are getting affected directly or indirectly due
to the problem under analysis.
 What
The “What” block is used for finding the kind of problem we are facing. At this stage, we need to
find the nature of the problem. In brief we can say, what is the problem and how do we know
that it is a problem?
 Where
Till now we know, what the problem is and who the stakeholders associated with the problem
are. Let us now focus on the context/situation/ location of the problem.
 Why?
After finding all the main components of the problem, we should now analyze why we want to
solve this problem. In this “Why” canvas, we think about the benefits which the stakeholders
would get from the solution and how it would benefit them as well as the society.

SESSION 3: SIMPLIFYING DATA ACQUISITION

3.1 Introduction

The second stage in the AI Project Cycle is Data Acquisition. We acquire data for project goal. To
do so we should first understand what ‘Data’ is raw facts and figures. Data acquisition is also known as
data collection.

If we want to make an Artificial intelligent system which can predict the weather of any geographical
area based on the previous weather analysis, then we would feed the weather data of some previous
years into the machine. This is the data with which the machine can be trained. Now once it is ready, it
will make the weather forecast. The previous weather data is known as Training Data while the
predicted weather data set is known as testing Data.

3.1.1 Data Features

Data features refers to the type of data you want to collect. Data can be acquired from various
sources but these sources should be reliable correct and authentic.
 1. Surveys:
Survey is one way in which we can collect the information directly by asking the customers.
Surveys can collect either quantitative or qualitative data or both. A survey consist of a list of
queries which respondents can answer I just one or two words. We can conduct surveys online,
over emails, over the phone or in person for collecting data.
2. Web Scraping:
Web data extraction is a technique for extracting huge amounts of data from websites
on the internet using a web browser. The data collected from websites is arranged in an
organized format such as a table.
3. Sensors:
Sensors, often called transducers, convert real-world phenomena like temperature,
force, and movement to voltage or current signals that can be used as inputs.
4. Cameras:
Camera is an important part of data collection in the form of images. Live data can be
acquired using the web-camera, CCTV, chat-bot interface, etc.
5. Observations:
Observation means the careful and systematic viewing of facts as they occur.
Observation require movement of the eyes and carefully listening through ears.
6. API (Application Program Interface):
Application programming interfaces is the pieces of codes which help one applications
to connect to another. For ex. When you copy and paste text from one applications to
another, it is the API that allows that to work.

3.1.2 System Maps

System Maps help us to find relationships between different elements of the problem
which we have scoped. It helps us in strategizing the solution for achieving the goal of our
project.
SESSION 4: VISUALIZING DATA

Data exploration is a process of arranging the collected data into form which can be analyzed or
through which we can derive useful information. Once the data is collected, then it is observed
carefully for making patterns to elicit the trends or relationship. We need to visualize our data
using any method for understanding the data in a through manner.
SESSION 5: INTRODUCTION TO MODLING

Modelling is the stage where we select the technique required for building the model using
prepared data. The model built can be trained using various learning algorithms. To build an AI-
based project, we need to work around artificially intelligent models or algorithms.
Modelling Approaches
 1.Rule-based Approach
2.Learning Approach
1.Supervised learning
2.Unsupervised Learning
3.Reinforcement Learning
Neural Networks
Neural networks is similar to how human brain works, behaves and interprets the
situation. Neurons are messengers of information. A neural network is a machine learning
algorithm based o the model of a human neuron. The human brain consists of millions of
neurons. It sends and processes signals in the form of electrical and chemical signals
SESSION 6: EVALUATING THE IDEA

In this stage, we evaluate each and every model tried and choose the model which gives the
most efficient and reliable results. The model is evaluated by giving some input of different
types and observe the output it gives.
Evaluation involves the following steps:
1.Accuracy: while evaluating, we need to find out the accuracy in the results from the
trained model.
2.Precision: out of the total predicted true output, what is the %age of actual true? How
often is the model giving us correct results?
3.Recall: how sensitive the model is to predict an actual value of a true?
4.F1 Score: F1 score or F measure, is a measure of a test’s accuracy.