You are on page 1of 12

A Project Report on

CLASSIFICATION OF DIABETES USING


MACHINE LEARNING ALGORITHM
Submitted in partial fulfilment of the requirements for the award of
degree of
BACHELOR OF TECHNOLOGY (B.Tech)
In
ELECTRONICS AND COMMUNICATION
ENGINEERING
Under the Esteemed Guidance of
Smt. B. Mahalakshmi, M.Tech (Ph.D)
Asst. professor
Dept. of E.C.E
Submitted by
R. Tejaswini (Y19EC2640) K. Supraja (Y19EC2646)
A. Ramya (L20EC2721) V. Sumythri (Y19EC2650)

Department of Electronics and Communication Engineering


BAPATLA WOMEN’S ENGINEERING COLLEGE
(Affiliated to Acharya Nagarjuna University)
BAPATLA-522101, A.P, INDIA
A.Y:2022-2023
Department of Electronics and Communication
Engineering
BAPATLA WOMEN’S ENGINEERING COLLEGE
(Affiliated to Acharya Nagarjuna University)

CERTIFICATE
This is to certify that the Project report on
“CLASSIFICATION OF DIABETES USING MACHINE
LEARNING ALGORITHM” is the bonafide record of work done
by R.TEJASWINI(Y19EC2640),K. SUPRAJA(Y19EC2646), A.
RAMYA(L20EC2721), and V.SUMYTHRI(Y19EC2650) under
the guidance and supervision of Smt. B.MAHALAKSHMI
submitted in partial fulfilment of the requirements for the award of
Electronics and Communication Engineering by Acharya
Nagarjuna University During the academic year 2022-2023.

Guide: Head of the Department:

Smt. B. Mahalakshmi Smt. B. Mahalakshmi

Asst. Professor Asst . Professor

Department of ECE Department of ECE

Bapatla Women’s Engineering Bapatla Women’s Engineering

College , Bapatla college , Bapatla


ACKNOWLEDGEMENT
At the outset we thank god almighty for making our endeavor a success.

It is great pleasure for us to express our gratitude to our Honorable


President Mr.M.Srinivasa Rao garu, Bapatla Education Society, Bapatla for
kindly providing facilities in accomplishing this project.

We also express our gratitude to Dr. G. Srinivasa Rao, Principal,


BWEC, for providing us adequate facilities, ways and means by which we are
able to complete this.

We express our sincere gratitude to Smt. B. MAHALAKSHMI HoD,


Department of Electronics and Communication Engineering, BWEC, for her
support without which the successful completion of this project would not have
been possible.

We express our immense pleasure and thanks to our Guide Smt. B.


MAHALAKSHMI Assistant. Professor , Department of Electronics and
Communication Engineering, BWEC, for her constant cooperation and support.

By

Project Associates

R. Tejaswini (Y19EC2640)

K. Supraja (Y19EC2646)

A. Ramya (L20EC2721)

V. Sumythri (Y19EC2650)

i
DECLARATION
We, the students of BAPATLA WOMEN’S ENGINEERING
COLLEGE, Bapatla here by declared that dissertation titled,
“CLASSIFICATION OF DIABETES USING MACHINE LEARNING
ALGORITHM” being submitted to the department of ECE, affliated to
Archarya Nagarjuna University, GUNTUR for the award of B.Tech degree, is a
record of bonafide work done by us at college and it has not been submitted to
any other institute or university for the award of any degree.

By project associates

R. Tejaswini (Y19EC2640)

K. Supraja (Y19EC2646)

A. Ramya (L20EC2721)

V. Sumythri (Y19EC2650)

ii
ABSTRACT

Diabetes is the one of the fast-growing diseases among the people.


Usually identifying diabetes level in patients lead more time. For reducing this
problem, we are using machine learning algorithms for the prediction and
classification of diabetes either it is Type-1 or Type2. Then by using Liquid
Crystal Display (LCD) to display the level of diabetes and giving the alerts
through Internet of Things (IoT) and send the messages to doctors as well as
patients regarding diabetes level for further medication. Our project is useful
for the early-stage identification and it also presents an IoT-based hypothetical
diabetes monitoring system for a healthy and affected person to monitor his
blood glucose (BG) level. Tools we are using in our project are Raspberry-pi,
IR sensor and Random Forest Algorithm. The main component we are using is
Random Forest Algorithm. It can be used for both Classification and
Regression problems in ML. It has high accuracy than other ML Algorithms.

Key Words: Random Forest Algorithm, Raspberry-Pi, IR sensor, LCD, IoT.

iii
iv
INDEX
S.No Contents Page No

I Acknowledgement i

II Declaration ii

III Abstract iii

IV Index iv-v

V List of Figures vi

VI List of Acronyms vii

VII List of Tables viii

1 Introduction 1-2

1.1 Methods to measure Glucose 2

2 Literature Review 3-6

3 7-9

3.1 Existing Method 7-8

3.2 Proposed Method 8-9

3.3 Block Diagram 9

4 Components 10-23

4.1 Raspberry -pi 3 10

4.2 Features of Raspberry-pi model 10-11


3B+

4.3 IR Sensor 11-12

4.4 Features of IR Sensor 13

4.5 GSM Module 13

4.6 Features of GSM Module 14

4.7 LCD Display 14-15

v
4.8 Features of LCD Display 15

4.9 Relay 15-16

4.10 Features of Relay 16

4.11 Buzzer 17

4.12 Features of Buzzer 17

4.13 Software Reqirements 17-18

4.14 Types of Machine Learning 18


Algorithms

4.14.1 Decision Tree 19

4.14.2 Navie Bayes 19-20

4.14.3 Linear Regression 20

4.14.4 Logistic Regression 20

4.14.5 Support Vector Machine 21

4.14.6 KNN(K_Nearest Neighbour) 21

4.14.7 K_Means Clustering 21-22

4.15 Random Forest Algorithm 22-23

4.16 Features of Random Forest 23


Algorithm

6 Conclusion and Future Scope

6.1 Conclusion

6.2 Future Scope

vi
List of figures

Fig.No. Figure Name Page No.


3.1 Block Diagram of Proposed 9
method
4.1 Raspberry-Pi 3B Model 10
4.2 InfraRed Sensor for Non- 11
Invasive Glucose Level
Sensing
4.3 IR Led 12
4.4 Photo Diode 12
4.5 GSM Module 13
4.6 LCD Display 14
4.7 Relay Switch 15
4.8 Buzzer 17
4.9 Working of Random Forest 23
Algorithm

vii
LIST OF ACRONYMS

S.NO ACRONYM ABBREVATION


.
1. ANN Artificial Neural Network
2. BLE Bluetooth Low Energy
3. CGM Continous Glucose Meter
4. DM Diabetes Mellitus
5. DT Decision Tree
6. GPIO General Purpose Inputs and
Outputs
7. GPU General Processing Unit
8. GSM Global System for Mobile
Communication
9. HDMI High-Definition Multimedia
Interface
10. IoT Internet of Things
11. IR InfraRed
12. KNN K-Nearest Neighbour
13. LCD Liquid Crystal Display
14. LMT Logistic Model Tree
15. LR Logistic Regression/Linear
Regression
16. ML Machine Learning
17. NB Naive Bayes
18. RAM Random Access Memory
19. RF Random Forest
20. SoC System-on-Chip
21. SVM Support Vector Machine
22. WHO World Health Organisation

viii
ix

You might also like