Professional Documents
Culture Documents
BACHELOR OF ENGINEERING
IN
Submitted by:
SUPERVISORS NAME
SHUBHAM GARGRISH
1. INTRODUCTION* 1
1.1 Problem Definition 1
1.2 Project Overview/Specifications* (page-1 and 3) 2
1.3 Hardware Specification 3
1.4 Software Specification 4
2. LITERATURE SURVEY 5
2.1 Existing System 5
2.2 Proposed System 6
3. PROBLEM FORMULATION
4. RESEARCH OBJECTIVES 7
5. METHODOLOGY 8
6. TENTATIVE CHAPTER PLAN FOR THE PROPOSED WORK
7. REFERENCES
8. APPENDICES
List of Figures
Figure Title page
RAM – 2 GB or more
i3 or i5 Intel Core Processor
Windows 10 x64
Google Colaboratory/ Jupyter Notebook
Python 3.9
Flask
Heroku
2 LITERATURE SURVEY
2.1 EXISTING SYSTEM: Looking at the present scenario of Diabetes prediction the
chances of accurate provision of a result is really shaky due to various problems, the
genetic features even when sharing the correct base patient record might give out a
falsifies information about whether the patient has diabetes or not, Diagnosis of diabetes is
considered a challenging problem for quantitative research. Some parameters like A1c ,
fructosamine, white blood cell count, fibrinogen and hematological indices were shown to
be ineffective due to some limitations.Since Diabetes is an immune disorder hence at
many times it might be correlated along with thyroid and other immuno-deficiency
diseases.
Therefore, the problem lies at various levels while correctly detecting and diagnosing a
patient with diabetes some being-
• Many people don’t have enough resources to go for regular diabetes checkup.
• There might be errors while the report collection.
• Portable machines for home checkup are costly hence people avoid buying them.
• Record maintenance and Human error while diagnosing, ignorance due to personal
reasons
2.2 PROPOSED SYSTEM: Due to the recent advancements in the computer science field,
there are several studies showing us that diabetes can be accurately predicted before
handedly by using machine learning algorithms and making a proper generated result
using the persons previous medical records. This system can be deployed on a cloud
architecture or on a server in inside of a hospital or medical institution and then can be
used to monitor the patient records while keeping in check and maintaining their privacy
and security. This system will not only help us rule out and predict an outcome which is
correct and useful, but also help us identify early symptom and rectify the problem
occurring before handedly and treat the patient before he/she reaches a chronic state of the
disease. The following are the advantages of the proposed system:
From the literature review, it is observed that studies highlight the need of efficient and
scalable approach for diabetes system. The existing techniques come with disadvantages like
there is always a risk of human error, record maintenance, and report generation is very time-
consuming. It is also an ineffective and outdated approach which can cause keyboard and
printing errors and incorrect entry may lead to harmful outcomes. This is a classification
problem of supervised machine learning. The objective is to predict whether or not a patient
has diabetes, based on certain diagnostic measurements included in the dataset.
0 – Absence of Diabetes
1 – Presence of Diabetes
Data will be collected from National Institute of Diabetes and Digestive and Kidney
Diseases and pre-processed to be analyzed further.
Dataset will be visualized using libraries like Matplotlib and Seaborn for better
understanding.
Data will be divided into training and test data, former being used to train models on the
basis of algorithms like Random Forest, KNN, SVM and Logistic Regression.
Accuracies from all models will be evaluated and the best model will be chosen to be
deployed on web using Flask on local server.
Using Heroku we will deploy the model on cloud based server to be easy to use for any
organization/ individual.
The result would be an end-to-end Machine Learning model which will easily predict
whether an individual has diabetes or not and help the society to check their health with
considerable accuracy.
5 METHODOLOGY
The following methodology will be followed to achieve the objectives defined for proposed
research work:
Various parameters will be identified to evaluate the proposed system.
CHAPTER 1: INTRODUCTION
This chapter will cover the overview of problem definition, software and hardware
requirements details regarding proposed project.
This chapter will cover the objectives and work flow of the proposed approach.
CHAPTER 5: METHODOLOGY
This chapter will cover the technical details of the proposed approach.