This document summarizes a student's MCA IV semester project on developing a diabetes prediction system using machine learning techniques. The student proposes building a system that uses support vector machines and neural networks to accurately predict diabetes using a PIMA Indian diabetes dataset. The system is designed to have several modules, including an intelligent meal recommender, educational module with food recognition, activity tracking, and medication reminders. It aims to help diabetic patients manage their condition through personalized recommendations, education, and reminders.

1. Student Name : Ganesh Guturu
Roll No : 20BF1F0037
Seminar Title : Diabetes prediction system
( Python, Django and Machine Learning )
Guide Name : P. Ravindra
MCA IV Semester Project I Review Presentation

2. ABSTRACT
-> Diabetes mellitus is the most common disease worldwide and keeps increasing
everyday due to changing lifestyles, unhealthy food habits and over weight
problems.
-> In the proposed system, an efficient way of detecting diabetes is proposed
through machine learning and deep leaning. Under machine learning, we used the
classification algorithm Support Vector machine (SVM) and neural network (NN) for
deep learning algorithm.
-> The experiment results shows that the prediction of diabetes done at high
accuracy.

3. Diabetes mellitus is a chronic, lifelong disease caused by excessively high blood sugar
levels. Diabetes is a disease that affects the body's ability to produce the hormone
insulin, thereby making carbohydrate metabolism abnormal and raising blood sugar
levels. As reported by the World Health Organization in 2020 were 463 millions are
with diabetes, 1.5 million deaths, the report indicates that is not difficult to guess how
much diabetes is very serious and chronic.
Many researchers conduct experiments to diagnose diseases using different machine
learning approach classification algorithms such as K-Nearest Neighbor (KNN), Logistic
Regression (LR), Decision Tree (DT), Support Vector Machine (SVM), Gradient Boosting
(GB) and Random Forest (RF) because researchers have proven demonstrated that
machine learning algorithms are more effective.
Introduction

4. Doctors rely on common knowledge for treatment. When common knowledge is
lacking, studies are summarized after some number of cases have been studied. But
this process takes time,
whereas if machine learning is used
-> the patterns can be identified earlier.
-> For using machine learning, a huge amount of data is required. There is very
limited amount of data available depending on the disease. Also,
-> The number of samples having no diseases is very high compared to number of
samples actually having the disease.
Problem Statement

5. -> Data mining approach like clustering, classification were studied in existing system.
-> Diabetes prediction using algorithms such as k- Nearest Neighbour (k-NN), k-
means, branch and bound algorithm was proposed.
-> A basic diabetic dataset is chosen for carrying out the comparative analysis.
-> The importance of feature analysis for predicting diabetes by employing machine
learning technique is discussed.
Existing system

6. -> The proposed system study is classification of Indian PIMA dataset for diabetes as
binary classification problem.
-> This is proposed to achieve through machine learning and deep learning
classification algorithm.
-> For machine learning, SVM algorithm is proposed
-> For deep learning, Neural network is used.
-> The proposed system improves accuracy of prediction through deep learning
techniques.
Proposed system

7. 1. Windows 9 or higher
2. Python 3.9 and related libraries
3. Anaconda
4. IDE ( PyCharm )
5. Web Browser
Software Requirements

8. DELL Inspiron 15 3000 laptop (Intel)
Processor : 11th Gen Intel® Core™ i3-1115G4
Display : 15.6", FHD 1920x1080
Memory : 8 GB, 1 x 8 GB, DDR4, 2666 MHz
Hard Drive : 512 GB, M.2, PCIe NVMe, SSD
Input device : Standard Keyboard and Mouse
Hardware Requirements

9. System Design and Development :
1. The System’s Requirements and Design Analysis
-> Scheduling and reminding diabetic patients to take their medication and blood
glucose readings,
-> recommending healthy meals for diabetics to keep their blood glucose levels in
check, and
-> encouraging and tracking the activity of diabetic patients,
-> providing a visual interface to help them make meaning of their readings and
establishing a sufficient connection between the doctor and the diabetic patient using
e-mail.
Modules

10. 2. System Architecture
Sub Modules
-> Diabetes Intelligent Meal
Recommender Module,
-> Educational Module for
Diabetics with Food Recognition
Engine,
-> Activity Tracking Module, and
-> Medication Reminder Module.

11. 3. The Diabetes Intelligent Meal Recommender Module
Sub Modules
3.1. Data Collection
3.2. Calorie Requirements
Determination
3.3. K-Nearest Neighbour
Algorithm

12. 4. The Educational Module with Food Recognition Capabilities
UML Diagrams

13. 5. The Activity and Reminder Module
-> Activity Tracker -> Medication Reminder

14. The testing results are categorized into
(1) Diabetes Intelligent Meal Recommender Module results,
(2) Educational Module for Diabetics with Food Recognition Engine results,
(3) Activity Tracking Module results, and
(4) Medication Reminder Module results.
Testing Strategies

15. Thank you