VISVESVARAYA TECHNOLOGICAL UNIVERSITY

BELAGAVI, KARNATAKA-590 014

A Project Report of Phase-I

On

“APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE

SENSOR DATA TO DIAGNOSE & PREDICT CARDIOVASCULAR
DISEASE ”
Submitted in partial fulfillment of the requirements of B.E Computer Science and
Engineering Degree Award

Submitted by:

NIKITA (3BK20CS018)
PAWAN RAJU (3BK20CS020)
KASTURI (3BK20CS011)
ASHISH(3BK20CS004)

Under the Guidance of

Prof. Viresha Sugoor

DEPARTMENT OF COMPUTER SCIENCE ENGINEERING

BASAVAKALYAN ENGINEERING COLLEGE

BASAVAKALYAN – 585327 Dist: Bidar, Karnataka
ISO 9001:2015 Certified
Phone: 08481-254143, 254264 Fax: 08481-254143
www.betbkec.com
Academic Year 2023-24
 BET’s
BASAVAKALYAN ENGINEERING COLLEGE
BASAVAKALYAN – 585327
ISO 9001:2015 CERTIFIED

DEPARTMENT OF COMPUTER SCIENCE

ENGINEERING

Certificate
This is to Certify that the Project work entitled “APPLYING ARTIFICIAL
INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND
PREDICT CARDIOVASCULAR DISEASE” is a bonafide work carried out by
NIKITA (3BK20CS018), PAWAN RAJU (3BK20CS020), KASTURI (3BK20CS011)
, ASHISH(3BK20CS004) of VII semester in partial fulfillment for the award of
Bachelor of Engineering in Department of Computer Science & Engineering of
Visvesvaraya Technological University, Belagavi during the year 2023- 2024. It is
certified that corrections/suggestions indicated for internal assessments have been
incorporated in the report deposited in departmental library. The project work phase 1 has
been approved as it satisfies the academic requirements in respect of project work
prescribed for the Bachelor of Engineering Degree

Signature of Guide Signature of Coordinator

Prof. VIRESHA SUGOOR Prof. SUVARNALATA HIREMATH

Signature of HOD Signature of Principal

Prof. SUVARNALATA HIREMATH Dr.ASHOK KUMAR VANGERI

Name of the Examiners Signature

1…………………………………..

2…………………………………..
 ACKNOWLEDGMENT

It gives us immense pleasure to write an acknowledgement to this project, contribution of all

people who helped me realize it.

We would like to sincerely thank our Project Guide Prof. Viresha sugoor , and Project
Coordinator Prof. Suvarnalata hiremath for their valuable guidance, constant assistance,
support, endurance and constructive suggestions for the betterment of the project, without
which this project would not have been possible.

We would like to convey heart full thanks to our Head of Department Prof. Suvarnalata
Hiremath for giving us the opportunity to embark upon this topic and for her continue
encouragement throughout the preparation of this presentation.

We acknowledge and express our sincere thanks to our beloved Principal Dr.Ashok kumar
Vangeri for supporting our in the academic endeavors.

We also indebted to our friends for their continued moral and material support throughout the
course of the project report and in helping us finalize the presentation.
Our heartfelt thanks to all the staff members of CSE department, who have contributed bits,
bytes and words to accomplish this project.

NIKITA(3BK20CS018)

PAWAN RAJU (3BK20CS020)

KASTURI (3BK20CS011)

ASHISH(3BK20CS004)
 DECLARATION

We hereby declare that the project report entitled “APPLYING ARTIFICIAL INTILLEGENCE TO
WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT CARDIOVASCULAR DISEASE”
submitted by us to Institution/Visvesvaraya Technological University, Belagavi in Partial fulfillment of
the requirement for the award of the degree of BE in CSE is a record of bonafide Project work carried out
by us under the guidance of Prof.Viresha sugoor and Project coordinator Prof. Suvarnalata hiremath

We further declare that the work reported in this project followed the guidelines provided by the
VTU/Institute in preparing the project report.

Name : USN: Signature of the Student

NIKITA 3BK20CS018 ……………………………..

PAWAN RAJU 3BK20CS020 .…………………………….
KASTURI 3BK20CS011 ……………………………..

ASHISH 3BK20CS004 ……………………………..

 BET’S
BASAVAKALYAN ENGINEERING COLLEGE
BASAVAKALYAN – 585327
2023 -2024

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

Department Vision

The Vision of the department is to provide high academic goals to the students and
make them the world leaders both in Educational and Research through effective
Teaching & Learning.

Department Mission

To provide a learning environment that helps students to enhance problem solving

skills, be successful in their professional lives and to prepare Students to be lifelong
learns by offering a solid theoretical foundation and exposure to the latest tools &
technologies in the area of Computer Hardware & Software.
 ABSTRACT

Cardiovascular disease (CVD) is the world’s leading cause of mortality.

There is significant interest in using Artificial Intelligence (AI) to analyse data from
novel sensors such as wearables to provide an earlier and more accurate prediction and
diagnosis of heart disease. Digital health technologies that fuse AI and sensing devices
may help disease prevention and reduce the substantial morbidity and mortality caused
by CVD worldwide. In this review, we identify and describe recent developments in the
application of digital health for CVD, focusing on AI approaches for CVD detection,
diagnosis, and prediction through AI models driven by data collected from wearables.
We summarise the literature on the use of wearables and AI in cardiovascular disease
diagnosis, followed by a detailed description of the dominant AI approaches applied for
modelling and prediction using data acquired from sensors such as wearables. We discuss
the AI algorithms and models and clinical applications and find that AI and machine-
learning-based approaches are superior to traditional or conventional statistical methods
for predicting cardiovascular events. However, further studies evaluating the applicability
of such algorithms in the real world are needed. In addition, improvements in wearable
device data accuracy and better management of their application are required. Lastly, we
discuss the challenges that the introduction of such technologies into routine healthcare
may face.
Sl.No Particulars Page No

Abstract
01 Introduction 01

1.1 Introduction 01
1.2 Overview 02

1.3 Objective 03

1.4 Problem Statement 03

1.5 Methodology 03

1.6 Scope of the project 04

02 Literature Survey 05

03 System Requirement 07

3.1 Software Requirements 07

3.2 Hardware Requirements 07

04 Design Of Projects 10

4.1 ML Model 10

4.2 High level Architecture 13

05 Implementation 14

5.1 Existing System 14

5.2 Proposed System 14

5.3 System implementation 14

5.4 Type of sensor data 15

06 Expected Outcomes Of Project 17

07 Conclusion 19

Reference 20
APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

CHAPTER 1
INTRODUCTION

1.1 Introduction
1.1.1 AI & ML:
Artificial Intelligence (AI) and Machine Learning (ML) stand at the
forefront of technological evolution, reshaping the landscape of computing and
human-machine interactions. AI, a broad concept, encapsulates the
development of intelligent agents capable of mimicking human-like cognitive
functions, while ML, a subset of AI, focuses on creating algorithms that enable
machines to learn and improve from experience. The surge in interest and
progress in these fields is fueled by increased computational power, the
availability of vast datasets, and algorithmic refinements. AI applications,
ranging from Narrow AI tailored for specific tasks to the aspirational concept
of General AI with human-like abilities, have found their way into diverse
domains, influencing healthcare, finance, autonomous vehicles, and natural
language processing. Machine Learning, a driving force behind AI
advancements, involves training algorithms on data, enabling them to identify
patterns and make predictions autonomously. While these technologies bring
about transformative changes, ethical considerations, including bias in
algorithms and data privacy concerns, underline the importance of responsible
development and deployment. The impact of AI and ML is palpable in everyday
life, from virtual assistants to personalized healthcare solutions, heralding an
era of innovation with implications that extend far beyond the realms of
technology.
Artificial Intelligence (AI) and Machine Learning (ML) represent
transformative fields at the intersection of computer science and technology,
promising to reshape the way we perceive and interact with information and
systems. AI, a broad concept, encompasses the development of intelligent
agents capable of performing tasks that typically require human intelligence,
such as problem-solving, perception, speech recognition, and decision-making.
Machine Learning, a subset of AI, focuses on the creation of algorithms and
statistical models that enable computer systems to learn and improve from
experience without being explicitly programmed.

1.1.2 Application of AI & ML:

❖ Virtual Personal Assistants

❖ Healthcare Diagnostics
❖ Financial Fraud Detection
❖ Recommendation Systems

Dept of CSE ,BKEC Page 1

APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

❖ Autonomous Vehicles
❖ Language Translation
❖ Image and Speech Recognition
❖ Predictive Maintenance in Manufacturing
❖ Customer Service Chatbots
❖ Credit Scoring and Risk Assessment
❖ Supply Chain Optimization
❖ Human Resources and Recruitment

1.1.3WHAT IS PYTHON :

Python is a high-level, interpreted programming language known for its

readability, versatility, and ease of use. Created by Guido van Rossum and first
released in 1991, Python has gained immense popularity for its simple syntax,
extensive standard libraries, and support for multiple programming paradigms,
including procedural, object-oriented, and functional programming. Python is
widely used in various domains, including web development, data science,
artificial intelligence, automation, and scientific computing. Its open-source
nature and vibrant community contribute to its continuous growth and
widespread adoption.

Python finds applications in diverse domains, including web

development, data science, artificial intelligence, and automation. Its dynamic
typing, automatic memory management, and cross-platform compatibility
contribute to its positive evaluation. The language's open-source nature fosters
a vibrant community, ensuring continuous improvement and industry
relevance. Overall, Python's strengths lie in its versatility, readability, and
extensive community support, making it a top choice for various programming
tasks.

1.2 Overview
According to the World Health Organization, heart disease is the first
leading cause of death in the high and second leading cause of death in low-
income countries. It has remained the leading cause of death at the global level
for the last 20 years. This project aims to analyze several data mining
techniques implemented in recent years for diagnosing heart disease.

At present, there are plenty of algorithms available that could detect and
predict heart anomalies from clinical reports. However, in this project, the
focus is more on discovering and extracting patterns from Electrocardiogram

Dept of CSE ,BKEC Page 2

APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

(ECG or EKG) image reports. By digitizing ECG records, the need for time
consuming manual intervention for comprehending the report can be
eliminated. With digitization, the automation of diagnosis and analysis can be
achieved quicker.

1.3 Objective
This project seeks to address the pervasive issue of heart disease,
acknowledged as the foremost cause of death globally by the World Health
Organization for the past two decades. The primary objective is to scrutinize
and evaluate various data mining techniques implemented in recent years for
diagnosing heart disease. While numerous algorithms currently exist for
detecting and predicting heart anomalies from clinical reports, this project
uniquely shifts its focus to the realm of Electrocardiogram (ECG or EKG)
image reports. The pivotal goal is to discover and extract patterns within these
ECG records, a departure from traditional approaches, with the specific intent
of reducing the need for time-consuming manual intervention in
comprehending the reports. By advocating for the digitization of ECG records,
the project aims to streamline and expedite the automation of diagnosis and
analysis

1.4 Problem Statement

This project addresses the global prevalence of heart disease by
concentrating on data mining techniques for analyzing Electrocardiogram
(ECG) images. Despite existing algorithms for clinical reports, the focus is on
digitizing ECG records to eliminate manual interpretation, expediting
automated diagnosis. The goal is to enhance efficiency and accuracy in
detecting heart anomalies, contributing to improved healthcare
outcomes worldwide.
1.5 Methodology
The methodology for this research involves a multi-faceted approach to
comprehensively analyze and implement data mining techniques for diagnosing
heart disease, as outlined in the introduction.

The first step is an extensive review and selection of relevant data

mining techniques, encompassing Machine learning algorithms such as
decision tree, support vector machines, neural networks, and Ensemble
methods. This review will consider the strengths and limitations of reach
technique in the Context of heart disease diagnosis .

Given the project's unique emphasis on Electrocardiogram (ECG or

EKG) image reports, the subsequent phase involves the development of a robust
framework for the extraction and analysis of patterns within these reports. This

Dept of CSE ,BKEC Page 3

APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

includes the creation of algorithms tailored to identify specific abnormalities in

waveforms and irregularities in heart rhythms. The methodology will
incorporate feature extraction techniques that are essential for capturing
nuanced patterns indicative of potential cardiac issues.

1.6 SCOPE
❖ Global Significance of Heart Disease
❖ Focus on Analyzing Data Mining Techniques
❖ Multidimensional Exploration
❖ Automation of Diagnosis and Analysis
❖ Elimination of Manual Intervention
❖ Digitization of ECG Records

Dept of CSE ,BKEC Page 4

APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

CHAPTER 2

LITERATURE SURVEY

Abdul Hannan a, Sehrish,Munawar Cheema b, IvanMiguel Pires c

d Biomedical Signal Processing and Control Volume 87, Part B, January 2024,
105519 Machine learning-based smart wearable system for cardiac arrest
monitoring using hybrid computing Every year, the percentage of people
affected by cardiovascular diseases increases drastically. Out of them, a heart
attack is the most prominent and painful disease. According to the World Health
Organization, approximately 17.5 million people lose their lives yearly due to
this disease, which is alarming. The remarkable advancement in wearable
technology has opened doors to propose many effective smart solutions to
tackle this disease efficiently. Furthermore, early diagnosis of heart attack
proliferates the compatibility of meditation. Considering this problem’s
sensitivity, we proposed a wearable smart and early Heart Attack diagnosis
system and adopted a decentralized computational phenomenon using hybrid
computing architecture.

Muhammad Shafiq,1Changqing Du,1Nasir Jamal,2Junaid Hussain

Abro,2Tahir Kamal,3Salman Afsar,4and Md. Solaiman Mia
Volume 2023 | Article ID 6383099 | https://doi.org/10.1155/2023/6383099
Smart E-Health System for Heart Disease Detection Using Artificial
Intelligence and Internet of Things Integrated Next-Generation Sensor
Networks According to the World Health Organization, heart disease is the
biggest cause of death worldwide. It may be possible to bring down the overall
death rate of individuals if cardiovascular disease can be detected in its earlier
stages. If the cardiac disease is detected at an earlier stage, there is a greater
possibility that it may be successfully treated and managed under the guidance
of a physician. Recent advances in areas such as the Internet of Things, cloud
storage, and machine learning have given rise to renewed optimism over the
capacity of technology to bring about a paradigm change on a global scale. At
the bedside, the use of sensors to capture vital signs has grown increasingly
commonplace in recent years. Patients are manually monitored using a monitor
located at the patient’s bedside; there is no automatic data processing taking
place. These results, which came from an investigation of cardiovascular
disease carried out across a large number of hospitals, have been used in the
development of a protocol for the early, automated, and intelligent identification
of heart disorders. The PASCAL data set is prepared by collecting data from
different hospitals using the digital stethoscope. This data set is publicly
available, and it is used by many researchers around the world in experimental
work.

Dept of CSE ,BKEC Page 5

APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

Solam Lee, Y. Chu, Jiseung Ryu, Y. Park, Sejung Yang, S. Koh

Published in Yonsei medical journal 1 January 2022 Artificial Intelligence for
Detection of Cardiovascular-Related Diseases from Wearable Devices: A
Systematic Review and Meta-Analysis Purpose Several artificial intelligence
(AI) models for the detection and prediction of cardiovascular-related diseases,
including arrhythmias, diabetes, and sleep apnea, have been reported. This
systematic review and meta-analysis aimed to identify AI models developed for
or applicable to wearable and mobile devices for diverse cardiovascular-related
diseases. Materials and Methods The searched databases included Medline,
Embase, and Cochrane Library. For AI models for atrial fibrillation (AF)
detection, a meta-analysis of diagnostic accuracy was performed to summarize
sensitivity and specificity. Results A total of 102 studies were included in the
qualitative review. There were AI models for the detection of arrythmia (n=62),
followed by sleep apnea (n=11), peripheral vascular diseases (n=6), diabetes
mellitus (n=5), hyper/hypotension (n=5), valvular heart disease (n=4), heart
failure (n=3), myocardial infarction and cardiac arrest (n=2), and others (n=4).
For quantitative analysis of 26 studies reporting AI models for AF detection,
meta-analyzed sensitivity was 94.80% and specificity was 96.96%. Deep neural
networks showed superior performance [meta-analyzed area under receiver
operating characteristics curve (AUROC) of 0.981] compared to conventional
machine learning algorithms (meta-analyzed AUROC of 0.961). However, AI
models tested with proprietary dataset (meta-analyzed AUROC of 0.972) or
data acquired from wearable devices (meta-analyzed AUROC of 0.977) showed
inferior performance than those with public dataset (meta-analyzed AUROC of
0.986) or data from in-hospital devices (meta-analyzed AUROC of 0.983).
Conclusion This review found that AI models for diverse cardiovascular-related
diseases are being developed, and that they are gradually developing into a form
that is suitable for wearable and mobile devices.

Dept of CSE ,BKEC Page 6

APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

CHAPTER 3

SYSTEM REQUIREMENT

3.1 Software Requirement:

➢ Python
➢ Google Collab
➢ Github
➢ Docker
➢ Stream It
➢ Browser
➢ Arduino IDE
➢ Jupyter
➢ Windows

3.2 Hardware Requirement:

3.2.1 Arduino IDE:

The Arduino Uno is a microcontroller board based on the ATmega328

(datasheet). It has 14 digital input/output pins (of which 6 can be used as
PWM outputs), 6 analog inputs, a 16 MHz ceramic resonator, a USB
connection, a power jack, an ICSP header, and a reset button. It contains
everything needed to support the microcontroller; simply connect it to a
computer with a USB cable or power it with a AC-to-DC adapter or battery
to get started.

Fig 3.1 Arduino UNO

Dept of CSE ,BKEC Page 7

APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

The Uno differs from all preceding boards in that it does not use the
FTDI USB-to-serial driver chip. Instead, it features the Atmega16U2
(Atmega8U2 up to version R2) programmed as a USB-to-serial converter.
Revision 2 of the Uno board has a resistor pulling the 8U2 HWB line to ground,
making it easier to put into DFU mode. Revision 3 of the board has the
following new features:

Microcontroller ATmega328
Operating Voltage 5V
Input Voltage (recommended) 7-12V
Input Voltage (limits) 6-20V
Digital I/O Pins 14 (of which 6 provide PWM output)
Analog Input Pins 6
DC Current per I/O Pin 40 mA
DC Current for 3.3V Pin 50 mA
Flash Memory 32 KB of which 0.5 KB used bybbootloader
SRAM 2 KB
EEPROM 1 KB
Clock Speed 16 MHz

3.2.2 AECG Module AD8232:

The AD8232 ECG module is a specialized component designed for
acquiring and processing Electrocardiogram (ECG) signals. This integrated
module features an instrumentation amplifier to accurately amplify the minute
electrical signals generated by the heart. Equipped with filters, the module
efficiently eliminates noise and interference, ensuring a clear and reliable ECG
signal. With support for multiple leads, it allows for comprehensive monitoring
of the heart's electrical activity from different body positions. The AD8232
module is often seamlessly integrated with microcontrollers like Arduino or
Raspberry Pi, providing a convenient interface for developers to incorporate
ECG monitoring into various projects, including wearable health devices and
portable ECG monitors. Its low power consumption and user-friendly design
make it a popular choice for applications demanding real-time cardiac activity
monitoring.

In health-related projects, the AD8232 ECG module plays a pivotal

role in capturing and processing biopotential signals. Its versatility extends
beyond ECG monitoring, enabling the measurement of other biopotential
signals such as electromyography (EMG) or electroencephalography (EEG).
With a focus on accuracy, ease of integration, and compatibility with
microcontrollers, the AD8232 module serves as a foundational component for
developers and healthcare professionals working on projects that demand
reliable and real-time analysis of cardiac activity.

Dept of CSE ,BKEC Page 8

APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

Fig.3.2. AECG Module AD8232

Dept of CSE ,BKEC Page 9

APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

CHAPTER 4

DESIGN OF PROJECT

4.1 ML MODEL :
We tested various algorithms and then utilized the enable technique
to stack algorithms to enhance performance because it was a classification
problem.

Algorithms tested:
1. k-nearest neighbors (KNN)
2. Logistic Regression
3. Support Vector Machine (SVM)
4. Xgboost
5. GridSearchCV

4.1.1 k-nearest neighbors (KNN) :

K-nearest neighbors (KNN) algorithm is a type of supervised ML
algorithm that can be used for both classifications as well as regression
predictive problems. However, it is mainly used for the classification of
predictive problems in the industry.

4.1.2 Logistic Regression :

Logistic regression is a statistical method for analyzing a dataset
in which there are one or more independent variables that determine an
outcome. The outcome is measured with a dichotomous variable (in
which there are only two possible outcomes).

Dept of CSE ,BKEC Page 10

APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

4.1.3 Support Vector Machine (SVM) :

Support vector machines (SVMs) are powerful yet flexible
supervised machine learning algorithms that are used both for
classification and regression. But generally, they are used in
classification problems. SVMs have their unique way of
implementation as compared to other machine learning algorithms.

4.1.4 Xgboost :
XGBoost is an implementation of gradient boosted decision trees
designed for speed and performance that is dominative competitive
machine learning.

Dept of CSE ,BKEC Page 11

APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

4.1.4 GridSearchCV :
Under Voting-based Ensemble classification, three Machine
learning models like k-nearest neighbors (KNN), Support Vector Machine
(SVM) and Random Forest Classifier are stacked and voted to pick one
model which gives the highest accuracy.

Dept of CSE ,BKEC Page 12

APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

4.2 HIGH LEVEL ARCHITECTURE :

user internet upload ecg image in web

app ecg image processing

Results pretrained ML model

Fig4.1. High Level Architecture Diagram

A high-level architecture diagram is a visual representation of a

system that shows how different components interact with each other.
The diagram you shared appears to depict a system where a user interacts
with the internet, which in turn communicates with some backend
processing represented by gears, and then to a database represented by
the red cylinder. The backend processing is likely where data is
processed and handled before it’s stored or retrieved from the database.

Dept of CSE ,BKEC Page 13

 APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

CHAPTER 5
IMPLIMENTATION

5.1 EXISTING SYSTEM

The existing system relies on algorithms for heart disease detection from
clinical reports. Despite this, the project proposes an advancement by emphasizing
the analysis of Electrocardiogram (ECG or EKG) image reports. Digitizing ECG
records is advocated to eliminate time-consuming manual interpretation, aiming for
quicker automation of diagnosis and analysis. This shift addresses the persistent
global challenge of heart disease, enhancing efficiency in healthcare processes.

5.2 PROPOSED SYSTEM

The proposed system introduces a paradigm shift by prioritizing the analysis of
Electrocardiogram (ECG or EKG) image reports over conventional algorithms used
in clinical reports for heart disease detection. Emphasizing digitization of ECG
records aims to eliminate the time-consuming manual interpretation, facilitating
quicker automation of diagnosis and analysis. This innovative approach seeks to
enhance the efficiency of healthcare processes in addressing the persistent global
challenge of heart disease.

5.3 SYSTEM IMPLEMENTATION

Fig.5.1.DEVELOPMENT ARCHITECTURE

Dept of CSE ,BKEC Page 14

APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

5.3.1 Python :
Python is a high-level, versatile programming language known for its
readability and simplicity. It's widely used for diverse applications, from web
development to data analysis and artificial intelligence. With a dynamic typing
system, Python supports object-oriented programming and emphasizes code
readability through indentation. It is interpreted, facilitating rapid development
and debugging. Python's extensive standard library includes modules for
various tasks, reducing reliance on external libraries. The language has a vibrant
community, contributing to its rich ecosystem of third-party libraries. Python is
cross-platform, making it compatible with Windows, macOS, and Linux. A
classic "Hello, World!" program demonstrates its straightforward syntax.

5.3.2 Github Respiratory :

A GitHub repository is a storage space on the GitHub platform where
software projects are managed using the Git version control system. It houses
code, files, and project assets, serving as a collaborative hub for developers.
Repositories can be public or private, with README files offering project
documentation. Branches enable parallel development, and commits represent
snapshots of code changes. Pull requests facilitate code review before merging
changes, while issues track bugs and tasks. Collaborators have varying access
permissions, and forks allow users to create independent copies for
modifications. GitHub repositories are integral to modern software
development, fostering collaboration and efficient version control.

5.3.3 Docker :
Docker is a containerization platform simplifying application
deployment. It encapsulates applications and their dependencies into
lightweight, portable containers for consistent performance across diverse
environments. Operating as standalone units, these containers ensure seamless
deployment and scalability. Docker's client-server model facilitates easy
management, allowing developers to build, run, and share applications
efficiently. This technology has revolutionized software development, offering
a standardized approach that enhances portability and accelerates the
deployment process, making it a fundamental tool for modern DevOps
practices.

5.4 TYPE OF SENSOR DATA

5.4.1 ECG(ELECTROCARDIOGRAM):
What is ECG:- An electrocardiogram (ECG) is a simple test
that can be used to check your heart's rhythm and electrical activity

Dept of CSE ,BKEC Page 15

APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

12-lead Electrocardiogram (EKG) Characteristics of ECG

ECG images: https://data.mendeley.com/datasets/gwbz3fsgp8/2

The above dataset contains ECG image signals from both healthy
individuals and persons with cardiovascular problems.

All the ECG images from the above Mendeley dataset are parsed and
transformed per our business requirements. This is the most important phrase
of our application (data preparation, data cleaning, data engineering and feature
extraction).Each one of the images goes through various processes to extract
the data in resultant format.

5.4.1 Input Image :

Dept of CSE ,BKEC Page 16

APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

CHAPTER 6

EXPECTED OUTCOMES OF PROJECT

Fig.6.1. Generated ECG waveforms

Fig.6.2. Upload Generated files

Dept of CSE ,BKEC Page 17

APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

Fig.6.3. Prediction of the ECG image

Dept of CSE ,BKEC Page 18

APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

CHAPTER 7

CONCLUSION

In conclusion, this project addresses the critical global health concern of

heart disease, reaffirming its sustained status as the leading cause of death
worldwide. The analysis of various data mining techniques underscores the
potential for advancements in heart disease diagnosis.

By concentrating on digitizing Electrocardiogram (ECG or EKG) image

reports, the project advocates for a transformative approach, eliminating the
need for labor-intensive manual intervention and accelerating the automation of
diagnosis. This shift towards digitization aligns with the contemporary
landscape of healthcare technology, promising quicker and more efficient
outcomes in the ongoing battle against heart disease on a global scale.

In summary, this project addresses the global urgency of heart disease

by analyzing modern data mining techniques. By prioritizing the digitization of
Electrocardiogram (ECG) image reports, the research streamlines and expedites
heart disease diagnosis, eliminating manual intervention. This approach aligns
with contemporary healthcare technology, promising swift and efficient
outcomes globally

Dept of CSE ,BKEC Page 19

 APPLYING ARTIFICIAL INTELLIGENCE TO WEARABLE SENSOR DATA TO DIAGNOSE AND PREDICT
CARDIOVASCULAR DISEASE

REFERENCE

• Abdul Hannan a, Sehrish,Munawar Cheema b, IvanMiguel Pires c d

Biomedical Signal Processing and Control Volume 87, Part B, January 2024,
105519

• Muhammad Shafiq,1Changqing Du,1Nasir Jamal,2Junaid Hussain Abro,2Tahir

Kamal,3Salman Afsar,4and Md. Solaiman Mia Volume 2023 | Article
ID 6383099 | https://doi.org/10.1155/2023/6383099

• Solam Lee, Y. Chu, Jiseung Ryu, Y. Park, Sejung Yang, S. Koh Published
in Yonsei medical journal 1 January 2022

Dept of CSE ,BKEC Page 20