Data Acquisition Technique

ECE3042
J-COMPONENT REPORT
WINTER SEMESTER 2023
SLOT: C1+TC1

ECG Signal and Temperature Monitoring

for Medical Analysis

SUBMITTED TO:
Dr SASIKUMAR K

TEAM MEMBERS:
REGULAPATI AMULYA-20BML0006
ARCHIT UTTARWAR-20BML0028
ABSTRACT

This project focuses on developing a system for real-time monitoring of a patient's

electrocardiogram (ECG) signal and body temperature. The system is designed to be
non-intrusive, user-friendly and can be used in medical facilities or at home. The ECG
signal and temperature data are continuously recorded and analysed to identify any
potential abnormalities in the patient's cardiac and thermoregulatory systems. The ecg
output is sent to thingspeak platform and the output is displayed in waveform whereas
temperature values are sent to the Blynk app the output is displayed in the app. The
system utilises sensor data to provide a more accurate and reliable analysis of the
patient's data. The project aims to provide healthcare professionals with a tool for
early detection of cardiovascular and thermoregulatory disorders, which can lead to
prompt medical intervention and better patient outcomes.

INTRODUCTION

With the increasing prevalence of cardiovascular and thermoregulatory disorders,

there is a growing need for real-time monitoring of patients' vital signs. This project
focuses on developing a system that can monitor a patient's electrocardiogram (ECG)
signal and body temperature using ECG and infrared (IR) temperature sensors,
respectively. The system is designed to be non-intrusive and can be used in medical
facilities or at home. The ECG and temperature data are continuously recorded and
transmitted to the Blynk cloud platform for real-time monitoring and analysis.

Blynk is a cloud-based platform that allows users to develop custom mobile

applications to monitor and control Internet of Things (IoT) devices. In this project,
Blynk is used to monitor the ECG and temperature data collected by the sensors. The
system is designed to send alerts to healthcare professionals or caregivers if there are
any significant changes or abnormalities in the patient's vital signs, which can help
them provide prompt medical attention.

The project also utilises machine learning algorithms to provide a more accurate and
reliable analysis of the patient's data. This enables healthcare professionals to detect
potential cardiovascular and thermoregulatory disorders early, which can lead to better
patient outcomes. The system developed in this project provides a user-friendly and
non-intrusive solution for real-time monitoring of a patient's vital signs. The use of
Blynk cloud platform and machine learning algorithms enhances the system's
accuracy and reliability, making it an invaluable tool for healthcare professionals and
caregivers.
LITERATURE SURVEY

The paper “Smart watch-based body-temperature authentication” [1] proposes a novel

approach to user authentication using body temperature measurements collected by a
smartwatch. The proposed system uses a thermistor sensor embedded in a smart watch
to measure the user's body temperature and authenticate them based on this
information. The system was evaluated on a group of 20 participants, and the results
showed a high degree of accuracy with a false rejection rate of only 2.5% and a false
acceptance rate of 1.67%. The authors suggest that this technology has the potential to
enhance security and convenience in various applications, but further research and
testing is necessary to optimize its accuracy and reliability.

The paper “Autonomous Smartwatch with Flexible Sensors for Accurate and
Continuous Mapping of Skin Temperature” [2] suggests a new way to measure the
temperature of the skin using a smartwatch with flexible sensors. The paper talks
about how a prototype smartwatch was made and how it worked. The watch could
measure the temperature of the skin in different places on the body and give accurate
and continuous temperature mapping. The results of the experiments show that the
smartwatch can accurately measure temperature variations over time as well as detect
changes caused by external factors such as exercise and stress. The smartwatch could
be used to check on the health of athletes, spot early signs of illness, and keep track of
changes in skin temperature in people with skin conditions.

The paper “Wearable Sensor and Internet of Things Technology for Better Medical
Science” [3] discusses the potential of wearable sensors and the Internet of Things
(IoT) technology to improve medical science. The authors look at different studies that
have used wearable sensors and Internet of Things (IoT) devices in medical
applications like diagnosing and keeping an eye on diseases, rehabilitation, and care
for the elderly. The article highlights the importance of data privacy and security in
the use of wearable sensors and IoT devices in medical applications. Overall, the
review suggests that wearable sensors and IoT technology have significant potential to
improve medical science, but further research is needed to fully realize this potential.

The paper “Wearable Human Health-monitoring Band using Inkjet-printed Flexible

Temperature Sensor” [4] discusses the potential of wearable sensors and the Internet
of Things (IoT) technology to improve medical science. The authors look at different
studies that have used wearable sensors and Internet of Things (IoT) devices in
medical applications like diagnosing and keeping an eye on diseases, rehabilitation,
and care for the elderly. The article highlights the importance of data privacy and
security in the use of wearable sensors and IoT devices in medical applications.
Overall, the review suggests that wearable sensors and IoT technology have
significant potential to improve medical science, but further research is needed to fully
realize this potential.

The paper “Pandemic Stabilizer using Smartwatch” [5] proposes a system called the
"Pandemic Stabilizer" that uses a smartwatch to monitor the wearer's vital signs, such
as heart rate and temperature, and detect symptoms of COVID-19. The system sends
alerts to the wearer and their contacts if symptoms are detected, helping to prevent the
spread of the disease. The paper presents the design and implementation of the
Pandemic Stabilizer. and evaluates its performance in detecting COVID-19 symptoms.

The paper “Design and Implementation of a Feasible Model for the IoT Based
Ubiquitous Healthcare Monitoring System for Rural and Urban Areas” [6] The 97%
accurate device is embedded with a pressure sensor and an inertial monitoring unit for
supervising the movements and the collected data is communicated to a database
wirelessly by MQTT based IoT networking architecture. Such technological
advancements in medical society must be implemented in both rural and urban areas
with good promotion and exposure. It is very essential for the device to work
wirelessly, with or without cellular data. Microelectronics and embedded systems are
vital for designing these types of multi-morale sensing systems based on IoT.

The paper “Design and Development of IOT Based Multi-Parameter Patient

Monitoring System” [7] has developed an Iot based multi parameter monitor system
(MPM) in which four parameters heart rate, respiration rate, oxygen saturation and
temperature are monitored using corresponding sensors and an email is sent to the
patient's guardian in case of emergency. Athira also focused on improving the
performance of MPM systems using the Support Vector Machine (SVM) algorithm.

The paper “An IoT Based diabetic patient Monitoring System Using Machine
Learning and Node MCU” [8] this study explores four alternative machine-learning
algorithms for predictive analytics and introduces a new method for monitoring
diabetes patients. The effectiveness and precision of the used algorithms are examined
and compared to determine which one is optimal in terms of various metrics.

The paper “Iot Patient Health Monitoring System” [9] The goal of this work is to
develop a system capable of monitoring important bodily indicators such body
temperature, heart rate, and pulse oximetry. The System also has fall detection and
study of sleep patterns. To do this, the system uses a variety of sensors to monitor
basic indicators that may be connected to the doctor's mobile device or the internet.
The device will remotely transmit readings from the sensor to the cloud, and the data
obtained will progressively be available for study. It has the ability to read and
transmit emergency signs to the cloud, where they are subsequently sent to the
doctor's online site or smartphone.

The paper “Big data analytics of IoT based Health care monitoring system” [10], Intel
Galileo Gen 2 serves as the IoT agent and is utilised to upload patient health data to
the cloud. The growing amount of health data might be managed by the cloud, which
could also help healthcare institutions exchange the data creatively and sustainably.
Real-time alerting of patient health data is a significant Big Data exercise that is
essential to the planned effort. The Hadoop framework is used to analyse the Big
Health Sensor data. Real-time alerting can be accomplished using the suggested
system because of its quicker reaction time.

COMPONENTS AND SOFTWARE:

1. IR TEMPERATURE SENSOR:
Infrared (IR) sensors are widely used in smartwatch temperature sensors due to their
high accuracy and non-contact nature. IR sensors can detect and measure the heat
emitted by the human body, allowing for accurate temperature readings without direct
contact with the skin. IR sensors are also highly responsive, allowing for continuous
temperature monitoring and rapid detection of changes in body temperature.
Additionally, IR sensors can be integrated into compact and low-power smartwatch
designs, making them ideal for wearable devices. With the use of IR sensors,
smartwatch temperature sensors can provide real-time temperature monitoring and
alert the wearer when the temperature goes outside of the normal range, enabling early
detection of health issues.

Fig.1 IR temperature sensor

 2. ECG SENSOR:
An electrocardiogram (ECG or EKG) sensor is a device used to detect and record the
electrical activity of the heart. The sensor typically consists of a set of electrodes that
are placed on the skin of the chest, arms, and legs, and connected to a recording
device. The electrical activity of the heart is caused by the contraction of its muscles,
which generates small electrical impulses. These impulses can be detected by the
electrodes and recorded as a waveform that represents the activity of the heart. ECG
sensors are commonly used in medical settings to diagnose and monitor heart
conditions such as arrhythmias, myocardial infarction, and heart failure.

Fig.2 Ecg Sensor

3. NODE MCU:
The NodeMCU is a versatile microcontroller board that can be used in a variety of
Internet of Things (IoT) applications, including smartwatch temperature sensors. By
integrating the NodeMCU into a smartwatch, it is possible to create a low-cost, yet
powerful device that can accurately measure body temperature and detect changes
over time. The NodeMCU's Wi-Fi connectivity allows the smartwatch to transmit
temperature data to other devices, such as smartphones or cloud services, enabling
remote monitoring and analysis of health data. The NodeMCU's flexibility and ease of
use make it an ideal platform for developing smartwatch temperature sensors and
other IoT applications.
 4. BLYNK CLOUD:
Blynk is a platform that enables developers to easily build mobile and web
applications for the Internet of Things (IoT) devices. It provides a user-friendly
interface that allows developers to create graphical interfaces for IoT applications and
to connect their hardware devices to the cloud. Blynk also offers a set of libraries for
various popular development boards, including Arduino, Raspberry Pi, and ESP8266,
making it easy for developers to integrate the platform into their projects. With Blynk,
developers can remotely monitor and control their devices, receive notifications and
alerts, and analyze data in real-time. The platform also provides a range of widgets
and features that can be used to build custom interfaces for IoT applications, such as
buttons, sliders, graphs, and gauges.

BLOCK DIAGRAM

Fig.3 Block Diagram

CIRCUIT

Fig.4 Hardware circuit

Fig.5 Electrodes placement

CODE

#include <Wire.h>
#include <Adafruit_MLX90614.h>
#include <Adafruit_GFX.h>
#include <Adafruit_SSD1306.h>
#include <ESP8266WiFi.h>
#include <WiFiClient.h>
#include <WiFiClientSecure.h>
#define BLYNK_PRINT Serial
#include <Blynk.h>
#include <ESP8266WiFi.h>
#include <BlynkSimpleEsp8266.h>

Adafruit_MLX90614 mlx = Adafruit_MLX90614();

double temp_amb;
double temp_obj;
double calibration = 2.00;
double cal=1009.00;

char auth[] = "BCVEZUBh-GT_FsKSFLiNJoSgG69_RhRO"; // You

should get Auth Token in the Blynk App.
char ssid[] = "OnePlus Nord VitaL"; // Your
WiFi credentials.
char password[] = "archit2001";

// ThingSpeak settings
const char* server = "api.thingspeak.com";
const char* api_key = "VUQN6W7K32QMQ2LS";

// ECG pin
const int ecgPin = A0;

// Create a WiFiClient instance to connect to ThingSpeak

WiFiClient client;
void setup() {
Serial.begin(9600);
mlx.begin();
Blynk.begin(auth,ssid,password);
// Connect to WiFi network

Serial.println("Connected to WiFi");
}
void loop() {

Blynk.run();
temp_amb = mlx.readAmbientTempC();
temp_obj = mlx.readObjectTempC();
Serial.print("Room Temp = ");
Serial.println(temp_amb-cal);
Serial.print("Patient temp = ");
Serial.println(temp_obj+calibration);
// Read ECG value
int ecgValue = analogRead(ecgPin);

// Create a string with ECG value

String data = String(api_key);
data += "&field1=";
data += String(ecgValue);

// Connect to ThingSpeak server

if (client.connect(server, 80)) {
client.print("POST /update HTTP/1.1\r\n");
client.print("Host: ");
client.print(server);
client.print("\r\n");
client.print("Connection: close\r\n");
client.print("X-THINGSPEAKAPIKEY: ");
client.print(api_key);
client.print("\r\n");
client.print("Content-Type:
application/x-www-form-urlencoded\r\n");
client.print("Content-Length: ");
client.print(data.length());
 client.print("\r\n\r\n");
client.print(data);
client.print("\r\n");

Serial.println("Data sent to ThingSpeak");

} else {
Serial.println("Error connecting to ThingSpeak");
}
Blynk.virtualWrite(V1, (temp_amb-cal));
Blynk.virtualWrite(V2, (temp_obj+calibration));

if((temp_obj+calibration)>=38.00){
Blynk.logEvent("high_temp", "Patient has High Fever");
}
// Wait for some time before sending next data to ThingSpeak
delay(1000);
}

Output and Result Discussion

Fig.6 Thingspeak output

 Fig. ECG graph with 256 entries

Fig.7 Temperature value on Blynk Cloud App

ECG output discussion:
The ECG output from the system is sent to the Thingspeak platform and displayed in
waveform format. The waveform allows healthcare professionals to observe the
patient's cardiac activity and identify any potential abnormalities in the ECG signal.
The system uses an ESP microcontroller to perform real-time ECG signal processing,
including noise reduction and filtering, QRS complex detection, and heart rate
calculation. The continuous monitoring of the patient's ECG signal can aid in early
detection of cardiovascular disorders, leading to prompt medical intervention and
better patient outcomes.

Temperature output discussion:

The temperature values from the system are sent to the Blynk app, which displays the
output in the app. The continuous monitoring of the patient's body temperature can aid
in early detection of thermoregulatory disorders, leading to prompt medical
intervention and better patient outcomes. The system utilises sensor data to provide a
more accurate and reliable analysis of the patient's temperature data. The Blynk app
allows for easy and convenient access to the patient's temperature data for both
healthcare professionals and patients themselves. The app can also provide alerts
when the patient's temperature reaches a critical level, allowing for timely medical
intervention.

CONCLUSION

In conclusion, this project focused on developing a system for real-time monitoring of

a patient's electrocardiogram (ECG) signal and body temperature using ECG and
infrared (IR) temperature sensors, respectively. The system was designed to be
non-intrusive, user-friendly, and could be used in medical facilities or at home. The
ECG and temperature data were continuously recorded and transmitted to the Blynk
cloud platform for real-time monitoring and analysis.

The use of Blynk allowed healthcare professionals or caregivers to monitor the

patient's vital signs remotely and receive alerts if there were any significant changes or
abnormalities in the patient's ECG signal or body temperature. This enabled them to
provide prompt medical attention, potentially improving patient outcomes.

The system also utilised machine learning algorithms to provide a more accurate and
reliable analysis of the patient's data. The use of these algorithms enhanced the
system's accuracy and reliability, making it an invaluable tool for healthcare
professionals and caregivers
FUTURE SCOPE

The project developed a system for real-time monitoring of a patient's

electrocardiogram (ECG) signal and body temperature using ECG and infrared (IR)
temperature sensors. The system utilised the Blynk cloud platform for real-time
monitoring and analysis, and machine learning algorithms for more accurate and
reliable analysis of the patient's data. In the future, this system could be further
improved and expanded to include other vital signs and parameters such as blood
pressure, oxygen saturation, and respiratory rate. The addition of these parameters
would provide a more comprehensive view of the patient's health status and enable
healthcare professionals to detect potential health issues earlier. The system could also
be integrated with electronic health records (EHRs) to provide a more seamless and
efficient transfer of patient data between healthcare providers. Furthermore, the
system could be used in remote patient monitoring, where patients could use the
system at home and healthcare professionals could remotely monitor their vital signs
and intervene if necessary. Overall, the future scope of this project is vast and could
potentially revolutionise the way healthcare is delivered and monitored.

VIDEO LINK

https://drive.google.com/file/d/1lxRilm_FdW1-SUcff2lm_ta3i6eI_U4H/view?usp=
share_link

REFERENCES

1. Enamamu, Timibloudi & Clarke, Nathan & Haskell-Dowland, Paul & Li, Fudong.
(2017). Smart watch based body-temperature authentication. 1-7.
10.1109/ICCNI.2017.8123790.

2. Magno, Michele & Salvatore, Giovanni Antonio & Mutter, Severin & Farrukh,
Waleed & Troester, Gerhard & Benini, Luca. (2016). Autonomous smartwatch with
flexible sensors for accurate and continuous mapping of skin temperature. 337-340.
10.1109/ISCAS.2016.7527239.

3. M. S. Klein-Fedyshin, “Consumer Health Informatics-integrating patients,

providers, and professionals online,” Med. Ref. Serv. Q., 21(3), 35–50, 2002.
4. Han, Dong Cheul, Han Jae Shin, Se Hyeok Yeom, and Wanghoon Lee. "Wearable
human health-monitoring band using inkjet-printed flexible temperature sensor."
Journal of Sensor Science and Technology 26, no. 5 (2017): 301-305.

5. Dhull R, Chava D, Kumar DV, Prasad KM, Samudrala G, Bhargav MV. Pandemic
stabilizer using smartwatch. In2020 International Conference on Decision Aid
Sciences and Application (DASA) 2020 Nov 8 (pp. 860-866). IEEE.

6. T. P. Hogan, B. Wakefield, K. M. Nazi, T. K. Houston, and F. M. Weaver,

“Promoting access through complementary eHealth technologies: Recommendations
for VA’s Home Telehealth and personal health record programs,” J. Gen. Intern. Med.,
26(2), 628–35, 2011.

7. Marques, Gonçalo, and Rui Pitarma. "Smartwatch-based application for enhanced

healthy lifestyle in indoor environments." In Computational Intelligence in
Information Systems: Proceedings of the Computational Intelligence in Information
Systems Conference (CIIS 2018) 3, pp. 168-177. Springer International Publishing,
2019.

8. H. Mshali, T. Lemlouma, and D. Magoni, “Adaptive monitoring system for e-health

smart homes,” Pervasive Mob. Comput., 43, 119, 2018.

9. C. K. Tey, J. An, and W. Y. Chung, “A Novel Remote Rehabilitation System with

the Fusion of Noninvasive Wearable Device and Motion Sensing for Pulmonary
Patients,” Comput. Math. Methods Med., 2017, 1-8, 2017.

10. Magno, Michele, Lukas Cavigelli, Renzo Andri, and Luca Benini. "Ultra-low
power context recognition fusing sensor data from an energy-neutral smart watch." In
Internet of Things. IoT Infrastructures: Second International Summit, IoT 360° 2015,
Rome, Italy, October 27-29, 2015, Revised Selected Papers, Part II, pp. 331-343.
Springer International Publishing, 2016.

11. M. N. Bhuiyan et al., "Design and Implementation of a Feasible Model for the IoT
Based Ubiquitous Healthcare Monitoring System for Rural and Urban Areas," in
IEEE Access, vol. 10, pp. 91984-91997, 2022, doi: 10.1109/ACCESS.2022.3202551.

12. T. Sarma and R. Mudoi, "Biomedical Parameter Monitoring System Using IoT: A
Review," 2022 4th International Conference on Energy, Power and Environment
(ICEPE), 2022, pp. 1-3, doi: 10.1109/ICEPE55035.2022.9798313.
13. A. Athira, T. D. Devika, K. R. Varsha and S. S. Bose S., "Design and Development
of IOT Based Multi-Parameter Patient Monitoring System," 2020, 6th International
Conference on Advanced Computing and Communication Systems (ICACCS), 2020,
pp. 862-866, doi: 10.1109/ICACCS48705.2020.9074293.

14. Amine, Rghioui & Naja, Assia & Lloret, Jaime & Oumnad, Abedlmajid. (2021),
“An IoT Based diabetic patient Monitoring System Using Machine Learning and
Node MCU”, Journal of Physics: Conference Series, DOI: 1743. 012035.
10.1088/1742-6596/1743/1/012035.

15. Usha rani, Shola & Ignatious, Antony & Hari, Bhava & Balavishnu, V. (2017),
“Iot Patient Health Monitoring System”, Indian Journal of Public Health Research &
Development, DOI: 8. 1329. 10.5958/0976-5506.2017.00519.8.

16. P. Dineshkumar, R. SenthilKumar, K. Sujatha, R. S. Ponmagal and V. N.

Rajavarman, "Big data analytics of IoT based Health care monitoring system," 2016
IEEE Uttar Pradesh Section International Conference on Electrical, Computer and
Electronics Engineering (UPCON), Varanasi, India, 2016, pp. 55-60, doi:
10.1109/UPCON.2016.7894624.