Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
39 views

Project Cycle Notes For All

Uploaded by

incredibleman653
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
39 views

Project Cycle Notes For All

Uploaded by

incredibleman653
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 5

What is an AI Project Cycle?

Project Cycle is a step-by-step process of developing ai machines which help us to solve real life
problems.

Need of ai project cycle-: it help to ensure that an ai project is developed successfully and efficiently

a. It increases success rate


b. Reduces risk
c. Enhance quality of solution
d. Improve efficiency

ai project cycle includes the following stages :

 Problem Scoping - Understanding the problem


 Data Acquisition - Collecting accurate and reliable data
 Data Exploration - Arranging the data uniformly
 Modelling - Creating Models from the data
 Evaluation - Evaluating the project
 Deployment

Problem Scoping- finalizing the aim of your system after identifying the problem which you are going to
solve with the help of AI is called problem scoping.

Data Acquisition –the process of acquire data related to your problem is called data Acquisition.
The data can in form of text, numbers, image etc.

Data Exploration –the process of interpret some useful information from acquire data trying to make it
uniform for a batter understanding by identify patterns and trends is called data exploration.

Modelling – the process of selecting the right technique/algorithm which we are using for building our ai
model from the prepared data.

Evaluation – testing the efficiency, and reliability of an Ai model using testing data is known as
evaluation.

Deployment – the last stage where you deploy your solution based on the model you have selected is
known as deployment.

1. Problem Scoping
Sustainable Development Goals Sustainable Development: To Develop for the present without
exploiting the resources of the future.
 17 goals announced by United Nations.
 Aim to achieve them by 2030.
 Pledge taken by all the member nations of the UN
4 w’s problem canvas
This canvas is help us in identifying 4 crucial parameters we need to know for solving a problem.
This W’s helps in identifying and understanding the problem in a better and efficient manner.
The 4W’s of Problem Scoping are -Who, What, Where, and Why.

Who- under this we find out who are the “Stakeholders” to this problem.
Stakeholders are the people who are directly or indirectly getting affected by the problem and
would be benefited with the solution.
What-what block helps to understand the nature of the problem, under this you also gather
evidence to prove that the problem you have selected is actually exists.
Where- This block will help you look into the situation in which the problem arises, the context
of it, and the locations where it is prominent.
Why- “Why” canvas, think about the benefits which the stakeholders would get from the
solution and how would it benefit them as well as the society.

Problem Statement Template


Problem Statement Template helps us to summaries all the key points into one single Template
so that in future, whenever there is a need to look back at the basis of the problem, we can take
a look at the Problem Statement Template and understand the key elements of it.

The /our (Stakeholder) Who


Has a problem (Problem) what
When/while (context/location) Where
An ideal solution would be (solution) why

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 AI project to be able to predict an output, we need to train it first using data.

Training data- it is data on which we train our ai project model.

Testing data- it is used to check the performance of an ai model.

Data features- Data features refers to the type of data that you want to collect.

Acquiring Data from reliable sources

There can be various ways in which you can collect data. Some of them are:

1. surveys
2. web scraping

3. sensors

4. cameras

5. observations

6. API(APPLICATION PROGRAMMING INTERFACE)

Some of the open-sourced Govt. portals are: data.gov.in, & india.gov.in

SYSTEM MAPS- SYSTEM MAPS IS A DIAGRAMMATIC REPRESENTATION OF A SET OF THINGS WORKING


TOGETHER.IT ALSO help us to find relationships between different elements of the problem which we
have scoped.

RULE OF SYSTEM MAPS

1. CIRCLE REPRESENT ELEMENT

2. ARROW ARE USED TO RELATIONSHIPS

3. (+) SIGNS INDICATE DIRECT RELATION

4. (– )SIGNS INDICATE OPPOSITE RELATION

DATA EXPLORATION-Data Exploration In this stage of project cycle, we try to interpret some useful
information out of the data we have acquired. For this purpose, we need to explore the data and try to
put it uniformly for a better understanding.

The data is according to the specifications decided.

➢ The data is free from errors.

➢ The data is meeting our needs

This stage is divided into 2 sub stages.

1) Data Cleaning

2) Data Visualization.

Data Cleaning -Data cleaning helps in getting rid of commonly found errors and mistakes in a data set.
These are the 3 commonly found errors in data.

THE OUTLIERS- An outlier is something that behaves differently from the combination/ collection of the
data.
Erroneous Data - Erroneous data is test data that falls outside of what is acceptable and should be
rejected by the system.

Missing Data- missing values in the data set.

DATA VISUALISATION – DATA VISUALISATION IS THE GRAPHICAL REPRESENTATION OF DATA AND


INFORMATION. By using graphical tools like chart and graphs, it is an easier way to understand the
trends and patterns in data.

NEED OF VISUALISING DATA

1. IS SIMPLIFIES THE COMPLEX INFORMATIONS

2. IT ANALYES AND EXPLORES BIG DATA EASILY

3. IT EXPLORED NEW PATTERNS AND REVEAL HIDDEN PATTERNS.

WAYS OF DATA VISUALISATION

1. BAR GRAPH

2. PIE CHART

3. LINE GRAPH

4. HISTOGRAM

5. HEAT MAP et c.

MODELING

MODELLING IS DEFINED AS THE PROCESS OF DESIGNING DECISION MAKING ALGORITHMS THAT HAS
TO BE TRAINED ON A SET OF DATA.

RULE BASE AI- 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.

A drawback/feature for this approach is that the learning is static. The machine once trained, does not
take into consideration any changes made in the original training dataset.

LEARNING BASE AI- 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.

Evaluation Evaluation is a process of understanding the reliability of any AI model, based on outputs by
feeding the test dataset into the model and comparing it with actual answers.

the efficiency of the model is calculated on the basis of the parameters mentioned below:
1. ACCURACY
2. PRECISION
3. RECALL
4. F1 SCORE

TRUE POSITIVE PREDICTION IS TRUE (POSITIVE)


PREDICTION & REALITY MATCHES (TRUE)

TRUE NEGATIVE PREDICTION IS FALSE (NEGAITVE)


PREDICTION & REALITY MATCHS (TRUE)

FALSE POSITIVE PREDICTION & REALITY DO NOT MATCH (FALSE)


PREDICTION IS TRUE (POSITIVE)

FALSE NEGATIVE PREDICTION & REALITY DO NOT MATCH (FALSE)


PREDICTION IS FALSE (NEGAITVE)

You might also like