Review 2 Final

Bhujbal Knowledge City
MET Institute of Engineering
Diabetes Prediction Using Machine

Learning
Project Guide:- Prof. Kanchan Dhomse
Presented By :
Sakshi Gore:- B190478531
Mayank Gupta:- B190478532
Prince Karavadiya:- B190478542
Shubham Ubale:- B190478579
05/24/23
Contents
•Introduction
•Literature Survey
•Problem Statement
•Aim & Objective
•Motivation
•System Architecture
•Dataflow Diagrams
•UML Diagrams
•Project Plan
•Project Methodology
•Software & Hardware Requirements
•Functional & Non Functional Requirements
•Applications
•Conclusion
•References
05/24/23
Introduction
• Diabetes is a situation which causes deficiency due to less amount of
insulin in the blood.
• Warning sign of high blood sugar results in frequent urination, feeling

thirsty, increased hunger.
• Severe difficulties lead to cardiovascular disease foot sores, and eye

blurriness. When there is a rise within the sugar level within the blood,
it is referred to as prior diabetes.
05/24/23
Literature Survey
Sr. No. Authors Title Details Technical Findings / (Advantage dis-
advantage)
1 Malini M Diabetic Patient Prediction Using Machine Learning Machine Learning algorithms and
Algorithm, 2021 Smart statistics are used to predict the disease
Technologies, Communication with the help of current and past data
and Robotics (STCR)
2 B.V. Baiju Disease Influence Measure Using Medical Data Set Using A Disease Influence Measure (DIM)
Data Mining, 2019 1st based diabetic prediction has been
Based Diabetic Prediction.
International Conference on presented
Innovations in Information and
Communication Technology
(ICIICT)
05/24/23
Literature Survey
3 Siddharekh S. Patil Implementation of Using Data Mining, 2019 3rd We use neural network (NN) and
Diabetic Retinopathy International Conference on
Prediction System. naïve bayes for classification.
Computing Methodologies and
Communication (ICCMC).
4 Lifeng Qiao Diabetic Retinopathy Using Prognosis of Microaneurysm Easy to used , but has low accuracy
and Early Diagnosis System for as compare to other system
Detection
Non-Proliferative Diabetic
Retinopathy Based on Deep
Learning Algorithms, IEEE Access
( Volume: 8)
05/24/23
Problem Statement
The diabetes is one of lethal diseases in the world. It is additional a
inventor of various varieties of disorders for example: coronary failure,
blindness, urinary organ diseases etc. In such case the patient is required to
visit a diagnostic center, to get their reports after consultation. Every time
they have to invest their time and money.
05/24/23
Aim
Diabetics Prediction Using Machine Learning at early stage.
Objectives: -
To predict the diabetes at early stage.
To Avoid the Time-consuming task of feature extraction.
To increase the accuracy from 70-75% to 80-85 % .
To provide a cost-effective solution in market.
1
05/24/23
Motivation
Diabetes is emerging as a predominant disease in the developing

countries like India. The disease is becoming very serious and cause many
other problems in the human body. Many factors are responsible for the
cause of this disease in the human body. The disease is not curable and can
only be controlled.
1
05/24/23
05/24/23
System Architecture
05/24/23
Mathematical Model
System Description:
S = (I,O,F) F = {A, DCT,DP, P} are set of Function
Where, Where,
S: System A: Authentication
DCT: Dataset Creation & Trained
I = {UL, SP} are set of Inputs
DP: Data Extraction parameter
Where,
P: Prediction
UL: User Login
SP: Select Parameters
05/24/23
O = {{DON, N} are set of Output

Where,
N: Notification
DON: Diabetics or not
Success Conditions:
Proper dataset , Network
Failure Conditions:
Internet connection
05/24/23
Dataflow Level 0
05/24/23
Dataflow Level 1
05/24/23
Dataflow Level 2
05/24/23
UML Diagrams (Sequence Diagram)
05/24/23
Activity Diagram
05/24/23
Project Plan
Sr.NO Activity Schedule Duration

SEMESTER 1
1 Registration of Project Group Week 2
2 Project Topic Revisit and submission Week 3
3 Allocation of Guide Week 4
4 Submission of Abstract to Project Guide Week 4
and Project
Coordinator in the prescribed Format
5 Project Review-1 Week 6

6 Project Review-2 Week 10
7 Verification of Project Work Book By Week 11
Internal Guide (before submission of
Preliminary Project Report)
8 Submission of Final Preliminary Project Week 12

Report in Prescribed Format
9 Term-Work Evaluation As per Departmental Schedule
05/24/23
Methodology
• Problem Solving Methods are concerned with efficient realization of
functionality. This is an important characteristics of Problem Solving Methods
and should be deal with it explicitly.
• Problem Solving Methods achieve this efficiency by making assumptions about

resources provided by their context (such as domain knowledge) and by
assumptions about the precise definition of the task.
• It is important to make these assumptions explicit as it give the reason about

Problem Solving Methods.
• The process of constructing Problem Solving Methods is assumption-based.

During this process assumptions are added that facilitate efficient
operationalization of the desired functionality
05/24/23
J48 Algorithm
05/24/23
H/w & S/w Requirements
Tools :
Hardware: Notepad ++ / VS Code
RAM 3 GB or Above Pycharm / Jupyter
Hard Disk 250 GB or Above Browser
Processor i3 or Above Kaggle
Technology:
MySQL 3.2 or Above
Windows Operating System 7
Python 3.7 or above
05/24/23
Functional Requirements
• The System should be able to retrieve the results stored on

database by using algorithm
• The system application of modules must able to detect
Diabetics.
05/24/23
Non-Functional Requirements
• There should be minimal lag between taking of the input

and result
• The processing should be as efficient with maximum
accuracy.
• The system should give valid result for positive as well as
negative test cases.
05/24/23
Dataset (diabetes.csv)
05/24/23
Applications
[1] Hospital: - In hospitals this can be used. As we know that the traditional
method of diabetes prediction is very time consuming. When we come across
any symptom, we need to test for it.
[2] Personal: - Going to Doctor just to show the report can be a little time
consuming for the patient. If we use this system for the personal use than we
can see if we have diabetes or not. This can be used at home also just by
entering the data from our reports.
05/24/23
Conclusion
Hence, We are overcoming the drawback of existing
system and providing a smart system that will not only monitor
and control our data with security but also supply it to whenever
necessary. We are trying achieved more than 85% detection
accuracy
05/24/23
References
1. Dhomse Kanchan B., M.K.M., 2016. Study of Machine Learning Algorithms for Special Disease Prediction
using Principal of Component Analysis, in: 2016 International Conference on Global Trends in Signal
Processing, Information Computing and Communication, IEEE. pp. 5–10
2. Aljumah, A.A., Ahamad, M.G., Siddiqui, M.K., 2013. Application of data mining: Diabetes health care in
young and old patients. Journal of King Saud University - Computer and Information Sciences 25, 127–136.
doi:10.1016/j.jksuci.2012.10.003.
3. Choubey, D.K., Paul, S., Kumar, S., Kumar, S., 2017. Classification of Pima Indian diabetes dataset using
naive bayes with genetic algorithm as an attribute selection, in: Communication and Computing Systems:
Proceedings of the International Conference on Communication and Computing System (ICCCS 2016), pp.
451– 455
4. Bamnote, M.P., G.R., 2014. Design of Classifier for Detection of Diabetes Mellitus Using Genetic
Programming. Advances in Intelligent Systems and Computing 1, 763–770. doi:10.1007/978-3- 319-11933-
5.
05/24/23
5. [9]. https://www.kaggle.com/johndasilva/diabetes

Review 2 Final

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Review 2 Final

Uploaded by

Copyright:

Available Formats

Bhujbal Knowledge City

MET Institute of Engineering

Diabetes Prediction Using Machine

Project Guide:- Prof. Kanchan Dhomse

• Warning sign of high blood sugar results in frequent urination, feeling

• Severe difficulties lead to cardiovascular disease foot sores, and eye

Diabetics Prediction Using Machine Learning at early stage.

To predict the diabetes at early stage.

To Avoid the Time-consuming task of feature extraction.

To increase the accuracy from 70-75% to 80-85 % .

To provide a cost-effective solution in market.

Diabetes is emerging as a predominant disease in the developing

O = {{DON, N} are set of Output

UML Diagrams (Sequence Diagram)

Sr.NO Activity Schedule Duration

Coordinator in the prescribed Format

5 Project Review-1 Week 6

8 Submission of Final Preliminary Project Week 12

• Problem Solving Methods achieve this efficiency by making assumptions about

• It is important to make these assumptions explicit as it give the reason about

• The process of constructing Problem Solving Methods is assumption-based.

H/w & S/w Requirements

• The System should be able to retrieve the results stored on

• There should be minimal lag between taking of the input

You might also like