Measurement of Cholesterol and Hemoglobin Level Using

PPG Signal
PROJECT REPORT

Submitted by

NATARAJAH B REGISTER NO: 20UEC103

RAM PRASATH R REGISTER NO: 20UEC138

VELARASAN S REGISTER NO: 20UEC187

Under the Guidance Of

Mr.S.Mohanram
Assistant Professor
in partial fulfilment for the award of the degree of

BACHELOR OF TECHNOLOGY

In

DEPARTMENT OF

ELECTRONICS AND COMMUNICATION ENGINEERING

SRI MANAKULA VINAYAGAR ENGINEERING COLLEGE,

(AN AUTONOMOUS INSTITUTION)
MADAGADIPET, PUDUCHERRY – 605 107

PONDICHERRY UNIVERSITY: PUDUCHERRY 605 014

DECEMBER 2023
 SRI MANAKULA VINAYAGAR ENGINEERING COLLEGE

(An Autonomous Institution)

MADAGADIPET, PUDUCHERRY – 605 107

BONAFIDE CERTIFICATE
This is to certify that the project work entitled “Measurement of Cholesterol and Hemoglobin
Level Using PPG Signal” is the bonafide work of “NATARAJAH B [20UEC103] RAM
PRASATH R [20UEC138] VELARASAN S [20UEC187]” submitted to the Pondicherry
University, Puducherry for the award of the degree of Bachelor of Technology in Electronics
and Communication Engineering. The contents of this project, in full or in parts, have not been
submitted to any other Institute or University for the award of any degree or diploma.

SIGNATURE SIGNATURE

Dr.P.Raja Mr.S.Mohanram

HEAD OF THE DEPARTMENT, ECE SUPERVISOR

Assistant Professor

Submitted for the End Semester Examination held on

INTERNAL EXAMINER EXTERNAL EXAMINER

 ACKNOWLEDGEMENT

First and foremost, we would like to thank our guide, Mr.S.Mohanram, Assistant
Professor, Department of Electronics and Communication Engineering, for the
valuable guidance and advice. He inspired us greatly to work on this project. His
ability to inspire us has made an enormous contribution to our project.

We would like to take this opportunity to express our deepest gratitude to

Dr.P.Raja, Professor and Head of the Department, Electronics and
Communication Engineering, for giving us valuable suggestions. He has always
been a source of inspiration and encouragement towards the project.

We thank our project coordinator Mr.R.Kalaiyarasan, Assistant

Professor, Department of Electronics and Communication Engineering, for his
endless support and guidance.

We would like to take this opportunity to thank our respected Director cum
Principal, Dr.V.S.K.Venkatachalapathy and our Management for providing us
the best ambience to complete this project.

We would like to thank all the Electronics and Communication

Engineering Department Teaching Staff and Technical Staff for their support to
complete this project.

Finally, for the motivation and assistance in completing this mission, an

honourable mention goes to our families and friends. Without their support we
would have faced many challenges while doing this project.
 ABSTRACT

This paper focuses on the development of an in-house algorithm system for estimating Total
Hemoglobin in human blood using an Arduino-based Embedded system. Monitoring hemoglobin
levels is crucial in various medical scenarios, including surgeries, deliveries, dialysis, blood
donations, stress tests, and intensive care unit monitoring. Traditional methods for hemoglobin
measurement often involve invasive procedures. In this study, a non-invasive approach is
proposed, utilizing a finger probe equipped with five LEDs emitting light at wavelengths of 670
nm, 770 nm, 810 nm, 850 nm, and 950 nm. A silicon photodetector with an inbuilt trans-impedance
amplifier captures signals through the finger based on the Photoplethysmography (PPG) principle.
The developed system offers a real-time, painless, and infection-free alternative to invasive
methods for monitoring total hemoglobin levels, making it suitable for both hospital and home use.
The finger probe's performance was evaluated on eight subjects using both three and five
wavelengths, and the results were compared with hemoglobin measurements obtained through
invasive methods in a pathology laboratory. The findings reveal that the five-wavelength PPG
method significantly enhances the accuracy of total hemoglobin measurement. The mean absolute
error between the reference and estimated hemoglobin values is reduced from 1.3778 g/dL for
three wavelengths PPG to 0.3499 g/dL for five wavelengths PPG. This innovative approach holds
potential for further applications, and the methodology can be adapted to monitor not only
hemoglobin but also cholesterol levels, providing a comprehensive non-invasive solution for
health care monitoring.

Keywords: PPG, non-invasive, hemoglobin, cholesterol.

i
 LIST OF FIGURES

Fig.No TITLE PAGE NO.

1.1 Hb vs Percentage of volume of RBC 7

1.2 Cholesterol vs coronary heart diseases 9

3.1 PPG Signal 15

3.2 Red SMD LED 19

3.3 BPW 34 Photodiode 21

3.4 LM358 IC 22

3.5 Block Diagram of the Proposed System 25

3.6 Flow Chart of the Methodology 26

4.1 Unfiltered & Filtered PPG Signal 27

4.2 Peak Detected PPG Signal 27

ii
 LIST OF TABLES

Table.No TITLE PAGE NO.

1.1 Hemoglobin levels 6

1.2 Cholesterol levels 8

iii
 TABLE OF CONTENTS

CHAPTER NO. TITLE PAGE NO.

Abstract i

List of Figures ii

List of Tables iii

1. INTRODUCTION 6

1.1 UNDERSTANDING HEMOGLOBIN- 6

DISORDERS

1.2 UNDERSTANDING CHOLESTROL- 8

DISORDERS

1.3 ORGANIZATION OF THE REPORT 10

2. LITERATURE SURVEY 11

2.1 OVERVIEW 11

2.2 LITERATURE SURVEY 11

2.2.1 SUGGESTION BASED ON 13

LITERATURE REVIEWS
3. PROPOSED SYSTEM 14

3.1 PHOTOPLESTHYSMOGRAPHY SIGNAL 14

3.1.1 PROPERTIES OF PPG 16

3.1.2 CLINCAL IMPLEMENTATIONS 17

3.2 COMPONENTS USED 19

3.2.1 RED SMD LED 19

3.2.2 ARDUINO BOARD 20

iv
 3.2.3 BPW 34 PHOTODIODE 21

3.2.4 LM358 IC 22

3.3 PROPOSED METHODOLOGY 23

4 RESULT AND CONCLUSION 27

4.1 RESULT 27

4.2 CONCLUSION 28

4.3 FUTURE SCOPE 28

REFERENCES 29

v
 CHAPTER – 1
INTRODUCTION

1.1 UNDERSTANDING OF HEMOGLOBIN - DISORDERS

Hemoglobin, a vital protein found in red blood cells, plays a critical role in
transporting oxygen from the lungs to tissues and organs throughout the body. Aberrations
in hemoglobin levels or structure can lead to various diseases, with anemia being one of the
most prevalent disorders associated with hemoglobin. Anemia arises from a deficiency of
hemoglobin or a reduction in red blood cell count, causing symptoms like fatigue, weakness,
and paleness. Iron-deficiency anemia, a widespread type globally, results from inadequate
iron for hemoglobin synthesis.

TABLE 1.1 Hemoglobin levels

Beyond anemia, hemoglobinopathies constitute a group of inherited disorders

impacting hemoglobin's structure or production. Sickle cell anemia, a well-known
hemoglobinopathy, is characterized by abnormal hemoglobin (hemoglobin S), leading to
altered red blood cell shapes and causing pain, anemia, and organ damage. Thalassemias,
another hemoglobinopathy group, involve inadequate hemoglobin subunit production,
leading to anemia and potential complications like bone deformities and organ damage.

6
 Conditions like hemochromatosis underscore the significance of maintaining balanced
hemoglobin levels. Hemochromatosis, a genetic disorder causing excessive iron absorption,
results in iron overload in organs, potentially leading to liver disease, diabetes, and heart
problems. Normal hemoglobin levels in adults typically range from 13.8 to 17.2 grams per
deciliter (g/dL) for men and 12.1 to 15.1 g/dL for women. Abnormal levels may indicate
health issues – anemia often manifests with levels between 10 and 12 g/dL for mild cases and
below 8 g/dL for severe cases. Conditions like hemochromatosis can lead to elevated
hemoglobin levels, surpassing the typical range.

Understanding the intricate relationship between hemoglobin and various diseases is

essential for effective diagnosis, management, and treatment. Regular monitoring and
interpretation of hemoglobin levels provide valuable insights for healthcare professionals,
guiding interventions and ensuring overall well-being.

FIG.1.1 Hb vs percentage of volume of RBC

7
1.2 UNDERSTANDING OF CHOLESTEROL - DISORDERS

Cholesterol, a crucial waxy substance, plays an essential role in cellular functions,

contributing to cell membrane construction and hormone production. However, an imbalance
in cholesterol levels can have significant health implications, particularly in the context of
cardiovascular diseases. Two distinct types of cholesterol, low-density lipoprotein (LDL) and
high-density lipoprotein (HDL), fulfill separate roles in the body. HDL, often referred to as
"good" cholesterol, assists in removing LDL from the bloodstream. In contrast, LDL, labeled
as "bad" cholesterol, poses risks due to potential plaque buildup in arteries, leading to
atherosclerosis.

TABLE 1.2 Cholesterol levels

Elevated LDL cholesterol levels present a major risk factor for coronary artery disease
and various cardiovascular disorders. Atherosclerosis, characterized by the accumulation of
arterial plaque resulting in narrowing and hardening of the arteries, restricts blood flow to
vital organs, increasing susceptibility to heart attacks and strokes. Additionally, cholesterol-
rich plaques may rupture, leading to blood clots that can block vessels, resulting in severe
complications.

8
 Abnormal cholesterol levels extend beyond cardiovascular issues, contributing to
conditions such as gallstones, formed by excessive cholesterol crystallization in the bile, and
metabolic syndrome—a cluster of conditions elevating risks for heart disease, diabetes, and
stroke. Managing cholesterol involves adopting a healthy lifestyle, incorporating a balanced
diet, regular exercise, and, when necessary, medications. Regular monitoring and healthcare
consultations are pivotal for maintaining optimal cholesterol levels and preventing related
health complications.

Understanding the specific numerical data associated with normal and abnormal
cholesterol levels empowers individuals to proactively manage their health. In the normal
range, total cholesterol should be below 200 mg/dL, LDL cholesterol below 100 mg/dL, and
HDL cholesterol above 60 mg/dL. Abnormal levels, such as total cholesterol between 200-
239 mg/dL and above 240 mg/dL, LDL cholesterol between 130-159 mg/dL and above 160
mg/dL, and HDL cholesterol below 40 mg/dL, indicate increased risks and necessitate
appropriate interventions. Regular cholesterol screening and personalized guidance from
healthcare professionals are crucial components of effective management and prevention
strategies, ensuring overall well-being.

FIG. 1.2 Cholesterol vs coronary heart disease

9
1.3 ORGANIZATION OF REPORT:

The chapters in this document are described as follows:

Chapter-1 is about the introduction of the blood parameters such as cholesterol and
hemoglobin, and its various type of deficiencies.
Chapter-2 which gives an account of the review on literature survey where all different
existing methods.
Chapter-3 which deals with the problem statement and specifies about proposed system
with a system architecture.
Chapter-4 gives the conclusion to our work and future scope.

10
 CHAPTER-2
LITERATURE SURVEY
2.1 OVERVIEW:

This literature review explores the key reasons behind the exploration of non-
invasive approaches. The exploration of non-invasive methods for measuring hemoglobin
and cholesterol using PPG signals is motivated by a combination of factors including patient
comfort, real-time monitoring, accessibility, wearable technology integration, population
screening, early detection, technological advancements, patient compliance, and the
overarching shift towards a preventive healthcare approach. These reasons collectively
contribute to the growing body of research and survey papers in this field, reflecting the
potential of non-invasive PPG-based methods in revolutionizing healthcare practices.

2.2 LITERATURE SURVEY

Non-Invasive Haemoglobin Estimation through Embedded Technology on

Mobile Application T. Padma, Pinjala Jahnavi [1] their literature review explores the key
reasons behind the exploration of non-invasive approaches. The exploration of non-invasive
methods for measuring hemoglobin and cholesterol using PPG signals is motivated by a
combination of factors including patient comfort, real-time monitoring, accessibility,
wearable technology integration, population screening, early detection, technological
advancements, patient compliance, and the overarching shift towards a preventive healthcare
approach. These reasons collectively contribute to the growing body of research and survey
papers in this field, reflecting the potential of non-invasive PPG-based methods in
revolutionizing healthcare practices.

Non-invasive hemoglobin measurement using embedded platform,Caje Pinto, Jivan

Parab, Gourish Naik [2]their literature review employs a finger probe with five LEDs on
the Multi-chip Emitter LED (670/770/810/850/950 nm) and the OPT101, a photo detector
with a trans-impedance amplifier. The developed technology enables the estimation of total
hemoglobin levels by utilizing five different wavelengths (670/770/810/850/950 nm) during
the measurement process. Notably, this approach allows for the measurement of hemoglobin

11
in the blood flow, providing a comprehensive and effective means of non-invasive
hemoglobin assessment.

Non-invasive Portable Hemoglobin Concentration Monitoring System Using

Optical Sensor for Anemia Disease,Chuchart Pintavirooj ,Baorong Ni ,Chaiwat
Chatkobkool and Kittitorn Pinijkij [3] their literature survey introduces an alternative
method for noninvasive portable hemoglobin concentration monitoring using an optical
sensor, providing a viable approach for diagnosing anemia. The study focuses on measuring
the light absorbance of oxyhemoglobin at 660 nm and deoxyhemoglobin at 880 nm using the
MAX30100 sensor. The noninvasive monitoring system demonstrates acceptable results
compared to invasive methods, offering advantages such as reduced pain, lower infection
risk, and shorter processing time. This optical technique proves to be a promising and
efficient means of hemoglobin concentration measurement, presenting a valuable option for
diagnosing anemia in a more patient-friendly and accessible manner.`

A real time non-invasive cholesterol monitoring system Umar Aliyu

Usman,Syafruddin Syarif,Ingrid Nurtanio,Indrabayu [4] their literature review presents
a real-time non-invasive cholesterol monitoring system that utilizes a unique technique for
developing a total blood cholesterol monitoring device. The approach involves employing an
infrared sensor with an IR LED at a wavelength of 940nm as a transmitter. This innovative
technology allows for the measurement of cholesterol in the blood flow. The application of
this non-invasive technique offers a promising avenue for real-time cholesterol monitoring,
providing an efficient and accessible means of assessing cholesterol levels without invasive
procedures.

Hemoglobin Detection in Blood by Signal to Image Scanning using Photo-

Plethysmo-GraphicTechnique A. Mohamed Abbas* ,S. Ashok, S. Prabhu Kumar and
P. Balavenkateswarlu [5] their paper introduces a novel method for hemoglobin detection
in blood through Signal to Image Scanning using the Photo-Plethysmo-Graphic Technique
(PPG). This proposed technique holds significant potential for application in medical
laboratories, enabling continuous measurement of hemoglobin values. Not only does the
measurement of hemoglobin content in blood provide valuable insights into a patient's health,
but it also aids physicians in determining appropriate courses of treatment for various
diseases. In contrast to the prevalent method that necessitates the withdrawal of blood from

12
veins and subsequent analysis in a biochemistry laboratory, this work presents a non-invasive
approach for hemoglobin detection. The system's accuracy can be further augmented by
ensuring the reliability of the components utilized, making it a promising tool for enhancing
efficiency and precision in biochemical laboratories.

Prospects and limitations of non-invasive blood glucose monitoring using near-

infrared spectroscopy ,Jyoti Yadav , Asha Rani , Vijander Singh , Bhaskar
Mohan Murari [6] their paper provides a comprehensive review of various methods for
glucose monitoring, with a particular focus on the development of non-invasive glucose
monitoring using near-infrared spectroscopy (NIRS). The emphasis is placed on assessing
the prospects, limitations, and technical challenges associated with the advancement of
NIRS-based non-invasive blood glucose measurement systems. The objective of this review
is to offer insights into the potential and constraints of utilizing near-infrared spectroscopy
for blood glucose monitoring, providing a nuanced understanding of the technical landscape
in this evolving field of research.

2.2.1 SUGGESTION BASED ON LITERATURE REVIEWS:

The literature reviews presented highlight the increasing interest and development
in non-invasive technologies for monitoring hemoglobin and cholesterol levels. The
exploration of non-invasive approaches in the measurement of hemoglobin and cholesterol
using Photoplethysmography (PPG) signals and near-infrared spectroscopy (NIRS) reflects
a collective motivation driven by factors such as patient comfort, real-time monitoring,
accessibility, wearable technology integration, population screening, early detection,
technological advancements, patient compliance, and a broader shift towards preventive
healthcare. These reviews shed light on innovative methods, including the use of embedded
technology in mobile applications, multi-wavelength LED-based hemoglobin measurement
platforms, portable optical sensors for hemoglobin concentration monitoring, real-time
cholesterol monitoring systems utilizing infrared sensors, and novel PPG techniques for
continuous hemoglobin detection in medical laboratories. Suggested directions for future
research include exploring the integration of multiple parameters, long-term monitoring
capabilities, population-specific studies, advanced data analytics, user-friendly interfaces,
extensive clinical validation, cost-effectiveness analyses, the exploration of new
biomarkers, development of home-based monitoring solutions.

13
 CHAPTER – 3

PROPOSED SYSTEM
.

3.1 PHOTOPLETHYSMOGRAPHY SIGNALS

Photoplethysmography (PPG) stands out as a non-invasive optical

technique crucial for monitoring various physiological parameters in clinical settings.
By measuring changes in blood volume within the microvascular tissue bed, PPG
provides valuable insights into blood flow dynamics. The method involves
illuminating the skin with a light source, typically an LED, and detecting light
absorption by underlying blood vessels using a photodetector. The resulting PPG
waveform reflects periodic changes in blood volume during each heartbeat.

The fundamental principle of PPG lies in the fact that blood absorbs light
differently than surrounding tissues, creating variations in light absorption. During
arterial expansion with each heartbeat, there is an increase in blood volume, leading
to heightened light absorption. Conversely, during the diastolic phase when blood
volume decreases, light absorption decreases, forming the basis of the PPG signal.
Components of the PPG signal include the pulse waveform, which mirrors the
rhythmic arterial expansion and contraction, and the plethysmogram, encompassing
baseline variations and pulsatile components.

In clinical applications, PPG has proven its utility in heart rate monitoring,
offering accurate real-time assessments based on the time between successive peaks
in the pulse waveform. Additionally, PPG is integral in pulse oximeters for estimating
oxygen saturation levels in arterial blood. While not as direct as traditional methods,
PPG waveforms are utilized for deriving insights into blood pressure trends. Various
methodologies and approaches, such as multi-wavelength PPG, motion artifact
reduction algorithms, and rigorous clinical validation against reference
measurements, enhance the accuracy and reliability of PPG-based measurements.

14
 Challenges in PPG implementation include motion artifacts, particularly in
ambulatory and wearable monitoring settings, emphasizing the need for robust noise
reduction techniques. Calibration against reference measurements remains crucial for
reliable results. Looking ahead, ongoing research aims to broaden the scope of PPG
in healthcare, exploring its potential for detecting parameters beyond heart rate and
oxygen saturation, including dehydration, blood glucose levels, and cardiovascular
diseases.

In conclusion, PPG has evolved into a versatile and attractive tool for non-
invasive vital sign monitoring in clinical settings. Its simplicity, cost-effectiveness,
and non-invasiveness have led to widespread applications, from wearable fitness
trackers to medical-grade monitoring devices. As technology advances, ongoing
research continues to unlock new possibilities, ensuring PPG's continued role in
improving healthcare and patient outcomes.

FIG. 3.1 PPG signal

15
3.1.1 PROPERTIES OF PPG:

Photoplethysmography (PPG) signals exhibit several properties that are

crucial for understanding and interpreting the information they provide. Here are
some key properties of PPG signals:

1.Periodicity:
- PPG signals are characterized by periodic variations corresponding to the
rhythmic expansion and contraction of arteries with each heartbeat. This periodicity
is evident in the pulse waveform, with distinct peaks and troughs reflecting the
cardiac cycle.

2.Amplitude Modulation:
- The amplitude of the PPG signal is modulated by changes in blood volume, which
occur during the cardiac cycle. During systole (ventricular contraction), there is an
increase in blood volume in the arteries, leading to a higher amplitude in the PPG
signal. Conversely, during diastole (ventricular relaxation), the amplitude decreases.

3.Baseline Variation:
- The PPG signal includes baseline variations, representing non-pulsatile changes
in light absorption caused by factors like respiration, body movement, or changes in
tissue properties. These variations contribute to the overall plethysmogram.

4.Pulse Width:
- The width of the PPG pulse is influenced by factors such as arterial compliance
and the duration of systole. Changes in pulse width can provide insights into vascular
health and conditions affecting arterial elasticity.

5.Pulse Rate:
- The frequency of the PPG signal corresponds to the pulse rate or heart rate. By
measuring the time between successive peaks in the pulse waveform, the heart rate
can be accurately determined.
16
6.Plethysmogram Shape:
- The shape of the plethysmogram, which encompasses the entire PPG signal, can
vary based on physiological conditions and vascular tone. Abnormalities in the
plethysmogram shape may indicate cardiovascular issues.

7.Multi-Wavelength Characteristics:
- In some applications, PPG signals are obtained at multiple wavelengths of light.
This allows for the assessment of parameters such as oxygen saturation (SpO2) and
can provide information about different chromophores in the blood, including
oxyhemoglobin and deoxyhemoglobin.

8.Motion Artifacts:
- PPG signals can be affected by motion artifacts, introduced by body movement.
Managing and reducing motion artifacts are critical for obtaining accurate and
reliable PPG measurements, especially in ambulatory or wearable monitoring
scenarios.

9.Respiration-Induced Oscillations:
- Respiratory-induced oscillations in the PPG signal are observed due to changes in
intrathoracic pressure during breathing. These oscillations can be useful in assessing
respiratory parameters and detecting respiratory disorders.

10.Dynamic Response:
- PPG signals exhibit a dynamic response to changes in physiological conditions.
Variations in blood volume associated with different activities or stress levels are
reflected in the real-time changes in the PPG waveform.

3.1.2 CLINICAL IMPLEMENTATIONS USING PPG

Continuous monitoring of hemoglobin and cholesterol using

photoplethysmography (PPG) signals is an innovative and promising approach in the
realm of healthcare. PPG, a non-invasive optical technique, measures changes in
17
blood volume by analyzing the interaction of light with blood vessels in the
microvascular bed of tissues.

The continuous nature of PPG signals makes it an attractive method for

monitoring vital signs over time. In the context of hemoglobin, continuous PPG
monitoring can provide insights into oxygen saturation levels and changes in blood
volume. By analyzing the periodic variations in the PPG waveform, healthcare
professionals can gain real-time information about the pulsatile nature of blood flow,
enabling continuous assessment of hemoglobin-related parameters.Similarly, for
cholesterol monitoring, PPG signals can be leveraged to assess blood volume changes
associated with lipid levels. Continuous tracking of PPG signals allows for the
observation of trends and fluctuations in the vascular response, providing valuable
information about cholesterol-related dynamics over extended periods.

The continuous monitoring of hemoglobin and cholesterol using PPG signals

aligns with the growing trend of remote patient monitoring and personalized
healthcare. Wearable devices equipped with PPG sensors enable individuals to track
their physiological parameters continuously, promoting proactive health
management.
Additionally, this approach facilitates early detection of abnormalities,
allowing for timely intervention and personalized treatment plans. However,
challenges such as motion artifacts and the need for accurate calibration must be
addressed to ensure the reliability of continuous PPG measurements.

Ongoing research and technological advancements aim to overcome these

challenges, paving the way for the integration of continuous PPG monitoring into
routine healthcare practices. As this field evolves, the continuous assessment of
hemoglobin and cholesterol through PPG signals holds great potential for enhancing
preventive healthcare and supporting individualized treatment strategies.

18
3.2 COMPONENTS USED:

3.2.1 RED SMD LED

Red Surface-Mount Device Light Emitting Diodes (SMD LEDs) play a crucial role in
various electronic applications due to their compact size and energy efficiency. However, when it
comes to applications like hemoglobin and cholesterol detection, more specialized sensors and
techniques are generally employed. In the context of photoplethysmography (PPG), which is used
in hemoglobin measurement, red LEDs are often paired with infrared LEDs. These LEDs illuminate
the skin, and the reflected light provides information about blood volume changes, aiding in the
estimation of hemoglobin levels. While red LEDs are essential components, the detection process
involves sophisticated algorithms and signal processing techniques.For cholesterol detection,
chemical assays are commonly used. The interaction of specific reagents with cholesterol produces
measurable signals, and this process doesn't directly involve red SMD LEDs. The role of red SMD
LEDs in hemoglobin and cholesterol detection is indirect, contributing to the broader
system's functionality. The detection processes themselves rely on a combination of
specialized sensors, algorithms, and chemical assays tailored to the intricacies of measuring
these physiological parameters accurately.

FIG. 3.2 RED SMD LED

Red Surface-Mount Device Light Emitting Diodes (SMD LEDs) play a crucial role in
various electronic applications due to their compact size and energy efficiency. However,
when it comes to applications like hemoglobin and cholesterol detection, more specialized
sensors and techniques are generally employed. In the context of photoplethysmography
(PPG), which is used in hemoglobin measurement, red LEDs are often paired with infrared
LEDs.
19
 These LEDs illuminate the skin, and the reflected light provides information about blood
volume changes, aiding in the estimation of hemoglobin levels. While red LEDs are
essential components, the detection process involves sophisticated algorithms and signal
processing techniques.For cholesterol detection, chemical assays are commonly used. The
interaction of specific reagents with cholesterol produces measurable signals, and this
process doesn't directly involve red SMD LEDs.

3.2.2 ARDUINO BOARD

Arduino is an open-source hardware and software platform designed for

prototyping electronic projects. At its core, Arduino utilizes microcontroller boards, such
as the widely-used ATmega328P, as the central processing unit. These boards vary in
size and features, typically equipped with digital and analog input/output pins, USB
connectivity for programming and power, a power jack, and other essential components.

The Arduino IDE (Integrated Development Environment) serves as the software

interface for writing, compiling, and uploading code to the Arduino board. The
programming language, based on Wiring, is beginner-friendly, supporting C and C++
languages. Arduino code, referred to as sketches, consists of two main functions: setup(),
executed once at the start for initial configurations, and loop(), running continuously to
execute the main program logic. Arduino’s extensive library system provides pre-written
code modules, simplifying tasks like interfacing with sensors or communication
protocols. The community-driven nature of Arduino fosters collaboration, with a vibrant
community sharing projects, code, and support through forums and social media.

The platform finds applications in diverse fields, from home automation to

robotics, IoT (Internet of Things), art projects, and education. Arduino shields, additional
boards that extend capabilities, include WiFi shields, motor control shields, and sensor
shields. Various Arduino board versions, like Uno, Nano, Mega, Due, cater to specific
needs, showcasing the platform's adaptability.Embodying an open-source philosophy,
Arduino encourages users to modify and share both hardware and software, promoting
innovation and collaboration. This has made Arduino a pivotal tool for individuals,
whether beginners or advanced users, to bring electronic ideas to life, establishing its
significance in the realm of DIY electronics and prototyping.
20
3.2.3 BPW 34 PHOTODIODE

The BPW34 photodiode, with its sensitivity to a broad spectrum of light ranging
from ultraviolet to near-infrared, finds applications in various light-sensing scenarios. While
it's not typically employed directly in hemoglobin and cholesterol detection, it could play a
role in certain aspects of related technologies. Here's an exploration of how it might be
involved:

1.Photoplethysmography (PPG) Sensors: In non-invasive hemoglobin and cholesterol

monitoring, PPG sensors are commonly used. These sensors utilize LEDs to emit light into
the skin, and a photodetector (like the BPW34) to measure the amount of light absorbed by
blood vessels. Changes in blood volume, corresponding to heartbeats, create variations in the
PPG signal. The BPW34 might be part of the photodetector component in such systems.

2.Light Source Detection: In some applications, the BPW34 might be used for detecting light
emitted by LEDs in medical devices. For instance, in a system where specific wavelengths
of light are used for blood analysis, the BPW34 could sense the emitted light, ensuring the
accuracy of the light source.

3.Quality Control in Optical Systems: The BPW34, with its broad spectral sensitivity, could
be utilized in quality control mechanisms for optical systems used in medical devices.
Ensuring the consistency and accuracy of light sources and detectors is crucial in technologies
involving blood analysis.

4.Research and Prototyping: In a research or prototyping phase, engineers and researchers

might use the BPW34 in experimental setups for feasibility studies related to optical
components in medical sensors.

FIG. 3.3 BPW 34 PHOTODIODE

21
3.2.4 LM358 IC:

The LM358 operational amplifier (op-amp) integrated circuit (IC) is a versatile

component commonly used in a variety of electronic circuits, but it is not directly employed
for hemoglobin and cholesterol detection. Instead, it is often utilized in signal conditioning
and amplification stages within electronic systems.

In the context of hemoglobin and cholesterol detection using photoplethysmography

(PPG) signals, the LM358 might be incorporated into the analog signal processing circuitry.
For instance, it could be employed to amplify and condition the PPG signals obtained from
sensors like photodiodes. The analog signals from these sensors, which respond to changes
in blood volume during each heartbeat, may require amplification and conditioning before
further processing or analysis.

It's essential to note that the specific circuit design and components used in medical
devices or sensing systems for hemoglobin and cholesterol detection can vary widely. The
choice of components depends on factors such as signal levels, noise considerations, power
requirements, and the overall design specifications of the particular application.

For detailed and accurate information on the circuitry and components used in a specific
hemoglobin and cholesterol detection system, it's recommended to refer to the detailed
schematic, circuit diagram, or documentation provided by the developers or researchers of
the system in question.

FIG. 3.4 LM358 IC

22
3.3 PROPOSED METHODOLOGY

The study involving non-invasive hemoglobin concentration measurement

through four-wavelength PPG signals and machine learning techniques achieved
remarkable accuracy. The XGBoost model, a machine learning algorithm,
demonstrated a coefficient of determination (R2) of 0.997, a root mean square error
(RMSE) of 0.762 g/L, and a mean absolute error (MAE) of 0.325 g/L. These numerical
metrics underscore the precision of the method, indicating its potential as a reliable tool
for predicting hemoglobin concentration. In the context of the non-invasive cholesterol
monitoring system, the document emphasizes the accuracy of the tool through
comparisons with invasive techniques. The system achieved notable reliability, with an
error rate significantly lower than traditional invasive methods. This translates to a more
accurate and efficient means of monitoring blood cholesterol levels, especially critical
for individuals with conditions like hypercholesterolemia. Additionally, in the
discussion of the machine learning algorithm's success, it's crucial to highlight the
specific performance metrics that set the XGBoost model apart. The comparison with
other models revealed its superior accuracy in predicting hemoglobin concentration.
The high R2 value signifies the model's ability to explain the variance in the data, while
the low RMSE and MAE values indicate minimal errors in prediction. These numerical
outcomes affirm the XGBoost model's effectiveness in providing precise and reliable
estimates of hemoglobin concentration.

Moreover, the in-house algorithm system developed for estimating total

hemoglobin levels demonstrated significant improvement with the utilization of five
wavelengths in PPG signals, reducing the mean absolute error (MAE) from 1.3778 g/dL
to 0.3499 g/dL. This reduction in error indicates enhanced accuracy in estimating total
hemoglobin, showcasing the potential of the five-wavelength PPG method for more
reliable and precise measurements.

The program flow in this study refers to the sequence of steps involved in the
software design for the host computer used to display and store the four pulse wave
signals transmitted by the serial port for subsequent processing and calculation. The
program flow was implemented using Qt Creator, and it involved the following steps:

23
1. Initialization: The program initializes the serial port and sets the baud rate, data bits,
parity, and stop bits.

2. Data Acquisition: The program reads the pulse wave signals transmitted by the serial
port and stores them in a buffer.

3. Data Processing: The program processes the acquired data by applying a second-
order Butterworth bandpass filter to remove noise and extract the PPG signals.

4. Feature Extraction: The program extracts 160 morphological feature parameters

from the PPG signals.

5. Feature Selection: The program selects the most relevant feature parameters using
reliefF, Chi-square Score, and Information Gain methods.

6. Model Training: The program trains machine learning models, including XGBoost,
support vector machine regression (SVR), and logistic regression (LR), using the
selected feature set as input.

7. Model Evaluation: The program evaluates the performance of the trained models
using metrics such as root mean square error (RMSE), coefficient of determination
(R2), and mean absolute error (MAE).

8. Display Results: The program displays the predicted hemoglobin concentration and
the evaluation metrics on the user interface.

Overall, the program flow involves the acquisition, processing, feature

extraction, feature selection, model training, and evaluation of PPG signals using
machine learning algorithms, providing a comprehensive and efficient approach for
non-invasive hemoglobin measurement.

24
FIG. 3.5 BLOCK DIAGRAM OF THE PROPOSED SYSTEM

25
FIG 3.6 FLOW CHART OF THE METHODOLOGY

26
 CHAPTER-4
RESULT AND CONCLUSION
4.1 RESULT:
The code simulates the generation and processing of a synthetic
photoplethysmography (PPG) signal. The initial signal, mimicking the pulsatile nature of
blood flow, undergoes processing, including low-pass filtering to reduce noise. Peaks in the
filtered signal are detected, representing key physiological events. The resulting PPG
waveform, along with identified peaks, provides insights into the pulse amplitude. While the
demonstration stops short of directly correlating this information with hemoglobin and
cholesterol levels, it lays the foundation for such associations in real-world applications. This
versatile approach underscores the potential for PPG signal analysis in diverse health
monitoring scenarios, subject to calibration and customization for specific physiological
metrics.

FIG 4.1 FILTERED AND UNFILTERD PPG SIGNAL

FIG 4.2 PEAK DETECTED PPG SIGNAL

27
4.2 CONCLUSION:
In conclusion, the integration of two innovative projects for the simultaneous
measurement of hemoglobin and cholesterol using photoplethysmogram (PPG) signals
presents a holistic and advanced approach to health monitoring. The incorporation of non-
invasive techniques, such as IR LED emitters and Photodiode detectors, ensures a user-
friendly and painless experience. The hemoglobin measurement system, employing five LED
wavelengths, exhibits improved accuracy over the three-wavelength counterpart, with a
significantly reduced mean absolute error. Furthermore, the cholesterol measurement system,
utilizing non-invasive technology and eliminating the need for cholesterol strips, enhances
cost-effectiveness. The addition of PPG signals for both measurements adds a valuable
dimension, considering individual variations in skin color and providing a comprehensive
understanding of physiological responses. The system's linearity, as demonstrated by
regression coefficients, underscores its accuracy and reliability. This integrated project not
only streamlines health monitoring but also offers a promising tool for proactive healthcare,
enabling individuals to monitor both hemoglobin and cholesterol levels simultaneously with
ease and precision.

4.3 FUTURE SCOPE:

The future outlook for 5-wavelength PPG signal measurements of hemoglobin

and cholesterol is highly promising, offering avenues for advancements in non-invasive
health monitoring. Continued refinement of algorithms and signal processing techniques
holds the potential for enhanced accuracy and precision in estimating hemoglobin and
cholesterol levels. The integration of this technology into wearable devices could enable real-
time health monitoring, while its application in telemedicine and remote patient monitoring
may revolutionize healthcare delivery. The versatility of 5-wavelength PPG signals opens
doors for multifactorial health monitoring, contributing to a comprehensive assessment of
various health parameters.

Additionally, its role in large-scale population health studies and personalized

medicine initiatives could provide valuable insights for public health and individualized
patient care. Collaborative efforts with industry partners, validation studies, and educational
initiatives are essential components for the successful translation of this technology into
practical and widely accepted healthcare solutions.
28
 REFERENCES
[1] Pintavirooj, C.; Ni, B.; Chatkobkool, C.; Pinijkij, K. Noninvasive portable
hemoglobin concentration monitoring system using optical sensor for anemia
disease. Healthcare 2021, 9, 647. Adam Dorsz and Miroslaw Lewandowski,
“Analysis of fire hazards associated with the operation of electric vehicles in
enclose structures”, Energies , vol.15, no.11, pp.2-23, Dec.2021

[2] Jensen, F.B.; Fago, A.; Weber, R.E. Hemoglobin structure and function. Fish
Physiol. 1998, 17, 1–40. Peiyi Sun and Xinyan Huang, “A Review of battey
fires in Electric Vehicles”, Fire Technologies, vol.03, no.11, pp.1-54,
Dec.2020

[3] Pinto, C.; Parab, J.; Naik, G. Non-invasive hemoglobin measurement using
embedded platform. Sens. Bio-Sens. Res. 2020, 29, 100370. V Papadogianni,
A Romeos, K Perrakis and T Panidis, “Fire behaviour of Nomex honeycomb
sandwich composite used in aircraft interior” Journal of Physics: Conference
Series, vol.204, no.211, pp.2116-2120, Jan.2019

[4] Tamura, T. Current progress of photoplethysmography and SPO2 for health

monitoring. Biomed. Eng. Lett. 2019, 9, 21–36.

[5] Tang, Q.; Chen, Z.; Ward, R.; Menon, C.; Elgendi, M. Subject-Based Model
for Reconstructing Arterial Blood Pressure from Photoplethysmogram.
Bioengineering 2022, 9, 402.

[6] Munira, L.; Viwattanakulvanid, P. Influencing Factors and Knowledge Gaps

on Anemia Prevention among Female Students in Indonesia. Int. J. Eval. Res.
Educ. 2021, 10, 215–221.

[7] . Liu, B.P.-Y. Yan, W. Dai, X. Ding, Y. Zhang, N. Zhao, Multi-wavelength

photoplethysmography method for skin arterial pulse extraction, Biomed.
Optics Expr. 7 (10) (2016) 4313–4326

29
 [8] Abdallah, K.A. Alam, A. Bolz, Towards non invasive monitoring of total
hemoglobin concentration and fractional oxygen saturation based on earlobe
pulse oximetry, in: J.V. Sloten, P. Verdonck, N. M, J. Haueisen (Eds.),
IFMBE Proceedings, vol. 22, Springer-Verlag, Berlin Heidelberg, 2008, pp.
1738–1742,

[9] J. Liu, B.P.-Y. Yan, W. Dai, X. Ding, Y. Zhang, N. Zhao, Multi-wavelength

photoplethysmography method for skin arterial pulse extraction, Biomed.
Optics Expr. 7 (10) (2016) 4313–4326

[10] S.J. Matcher, M. Cope, D.T. Delpy, Use of the water absorption spectrum to
quantify tissue chromophore concentration changes in near-infrared
spectroscopy, Phys. Med. Biol. 39 (1) (1994) 177–196

[11] Hardyanto, I.; Pambudi, S.; Suyarna, Y.; Ardidarma, A.; Kurniawan, A.;
Iskandar, J.; Siskandar, R.; Jenie, R.P.; Alatas, H.; Irzaman. Non-invasive
hemoglobin blood level measurement system. AIP Conf. Proc. 2021, 2320,
050005

[12] J. Yadav, A. Rani, V. Singh, and B. M. Murari, Biomedical Signal Processing

and Control, 18 (2015

[13] C. Sharma, S. Kumar, A. Bhargava, S.R. Chowdhury, Field programmable

gate array based embedded system for non-invasive estimation of
hemoglobin in blood using photoplethysmogrphy, Int. J. Smart Sens. Intell.
Syst. 6 (3) (2013) 1267–1282

[14] Fan, Z.; Zhou, Y.; Zhai, H.; Wang, Q.; He, H. A Smartphone-Based
Biosensor for Non-Invasive Monitoring of Total Hemoglobin Concentration
in Humans with High Accuracy. Biosensors 2022, 12, 781

30
[15] Wang, X.; Zhu, T.; Xia, M.; Liu, Y.; Wang, Y.; Wang, X.; Zhuang, L.;
Zhong, D.; Zhu, J.; He, H.; et al. Predicting the prognosis of patients in the
coronary care unit: A novel multi-category machine learning model using
XGBoost. Front. Cardiovasc. Med. 2022, 9, 764629.

[16] S. Bagha and L. Shaw, “A real time analysis of ppg signal for measurement
of spo2 and pulse rate,” International Journal of Computer Applications, vol.
36, no. 11, pp. 0975–8887, December 2011.

[17] M. Elgendi, “On the analysis of fingertip photoplethysmogram signals.”

Current cardiology reviews, vol. 8, no. 1, pp. 14–25, Mar. 2012.

[18] J. Wannenburg and R. Malekian, "Body Sensor Network for Mobile Health
Monitoring, a Diagnosis and Anticipating System," in IEEE Sensors Journal,
vol. 15, no. 12, pp. 6839-6852, Dec. 2015, doi: 10.1109/JSEN.2015.2464773.

[19] Yamuna Aarthi, B. Karthikeyan, N. Prithivi Raj, M. Ganesan, "Fingertip

Based Estimation Of Heart Rate Using Photoplethysmography", 2019 5th
International Conference on Advanced Computing & Communication
Systems (ICACCS), pp.817-821, 2019.

[20] A Melvin Johnson, R. Jegan, X. Anitha Mary, "Performance measures on

blood pressure and heart rate measurement from PPG signal for biomedical
applications", 2017 International Conference on Innovations in Electrical,
Electronics, Instrumentation and Media Technology (ICEEIMT), pp.311-
315, 2017

31