SMART MEDICINE PILL BOX REMINDER

A SEMINAR REPORT

submitted by

MOHAMMED SAKIR P N
(KME20CS036)

to
the APJ Abdul Kalam Technological University
in partial fulfillment of the requirements for the award of the Degree
of
Bachelor of Technology
in
Computer Science & Engineering

Department of Computer Science & Engineering

KMEA Engineering College Edathala, Aluva
683 561
December 2022
 DECLARATION

I undersigned hereby declare that the seminar report “Smart Medicine Pill
Box Reminder” submitted for partial fulfilment of the requirement for the award
of Degree of Bachelor of Technology of the APJ Abdul Kalam Technological Uni-
versity,Kerala,is a bonafide academic document prepared under the supervision of
Dr. Benazir K K, Assistant Professor, KMEA, Cochin.
I have not submitted the matter presented in this seminar report anywhere for the
award of any other Degree.

Signature of student : ......................................

Name of student : MOHAMMED SAKIR P N

Place : ..........................
Date : .̇.........................

2
DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING
KMEA Engineering College Edathala, Aluva
683 561

CERTIFICATE

This is to certify that the report entitled Smart Medicine Pill Box Re-
minder submitted by MOHAMMED SAKIR P N to the APJ Abdul Kalam
Technological University in partial fulfillment of the requirements for the award
of the Degree of Bachelor of Technology in Computer Science & Engineering is a
bonafide record of the project work carried out by him/her under our guidance and
supervision. This report in any form has not been submitted to any other University
or Institute for any purpose.

Seminar Guide Seminar Coordinator

Name : Dr. Benazir K K Name : Ms. Vidya Hari
Signature : ....................... Signature : .......................

Head of Department
Name : Dr. Rekha Lakshmanan
Signature : .......................
 ACKNOWLEDGMENT

First and foremost, I would like to express my thanks to Almighty for the
diving grace bestowed on me to complete this seminar successfully on time.
I would like to thank our respected Principal Dr. Amar Nishad T. M, the leading
light of our institution and Dr. Rekha Lakshmanan, Vice Principal and Head of
Department of Computer Science and Engineering for her suggestions and support
throughout my seminar. I also take this opportunity to express my profound grat-
itude and deep regards to my Seminar Coordinator Ms. Vidya Hari, for all her
effort, time and patience in helping me to complete the seminar successfully with
all her suggestions and ideas. And a big thanks to my Seminar Guide Dr. Benazir
K K, of the Department of Computer Science & Engineering for leading to the suc-
cessful completion of the seminar. I also express my gratitude to all teachers for
their cooperation. I gratefully thank the lab staff of the Department of Computer
Science and Engineering for their kind cooperation. Once again I convey my grati-
tude to all those who had direct or indirect influence on my seminar.

MOHAMMED SAKIR P N
B. Tech. (Computer Science & Engineering)
Department of Computer Science & Engineering
KMEA Engineering College Edathala, Aluva

i
 ABSTRACT

With the increasing of elderly and young people who are diagnosed with
diseases, the proper and correct medicines taken need to become the first priority to
being healthy. However, among this people, 40-60to take medicine on right time.
The main objective of this project is to design a system that will alert the patients
to take the medicines and also create an application that will alert the caretakers if
their patients have taken the medicines by detecting the weight of the pill box. The
system consists of a box where the patients will be able to keep their medicines
and will alert the patients to take their medicines visually and audibly. The Blynk
application will send notification to notify the caretaker if the patients have taken
their medicines. This system has a feature that uses a weight sensor to detect the
remaining medicines that are present in the box. The caretaker will be notified if the
status of the pill box is less than 50% of the total weight of the medicines through
this application. By using the Blynk application the caretaker can get a notification
about the status of the pill box hence knowing if their patients have taken their
medicines in the following week. It can be seen that in order to reach 50% of
the total weight of the medicines the patients have to take their medicines four
times. This gives an indication to the caretakers that their patients have taken their
medicines for four days. Some improvements that can be made are, by changing
the working system of the load cell in order to detect the changes in weights of the
medicines in the pill box for each day of the week.

ii
 CONTENTS

ACKNOWLEDGMENT i

ABSTRACT ii

LIST OF FIGURES iv

ABBREVIATIONS vi

Chapter 1. INTRODUCTION 1

Chapter 2. LITERATURE SURVEY 3

Chapter 3. METHODOLOGY 15
3.1 Materials and Methods . . . . . . . . . . . . . . . . . . . . 15
3.1.1 Arduino uno . . . . . . . . . . . . . . . . . . 15
3.1.2 ESP8266 . . . . . . . . . . . . . . . . . . . . 16
3.1.3 Load Cell . . . . . . . . . . . . . . . . . . . . 16
3.1.4 Buzzer . . . . . . . . . . . . . . . . . . . . . 16
3.1.5 LED . . . . . . . . . . . . . . . . . . . . . . 17
3.1.6 LCD . . . . . . . . . . . . . . . . . . . . . . 17
3.1.7 RTC DS3231 . . . . . . . . . . . . . . . . . . 18
3.2 Hardware Development . . . . . . . . . . . . . . . . . . . 18
3.3 Time and date setup . . . . . . . . . . . . . . . . . . . . . 21
3.4 Setting up the alarm . . . . . . . . . . . . . . . . . . . . . 21

Chapter 4. ADVANTAGES 23

Chapter 5. CHALLENGES 25

iii
Chapter 6. RESULTS AND DISCUSSION 27
REFERENCES 32

iv
 LIST OF FIGURES

3.1 Schematic Diagram of the System . . . . . . . . . . . . . . . . . . 19

3.2 Flow Chart of the System . . . . . . . . . . . . . . . . . . . . . . . 20
3.3 ) Blinking effect appears on the hour section of the time and appears
on the day section of the date . . . . . . . . . . . . . . . . . . . . 21
3.4 Alarm is activated and Blinking effect on the hour section . . . . . . 22

6.1 Before and After alarm is triggered . . . . . . . . . . . . . . . . . . 27

6.2 Total weight of medicines in pill box . . . . . . . . . . . . . . . . . 28

v
 ABBREVIATIONS

Abbreviation Expansion
GANs Generative Adversarial Networks
CNN Convolutional Neural Network
MSE mean-square error
PSNR peak signal-to-noise ratio
SAPLC Spatial Aggregation of Pixel-level Local Classifiers
FCN fully convolutional network
*** ***

vi
 Chapter 1

INTRODUCTION

Lately medicine consumption has been skyrocketed, and it is now a frequent

occurrence among all people. Therefore, a reminder must be made for the timely
consumption of the medicines. Reminding medication at the prescribed time and
the proper medicine intake is a must for a patient . For most of the patients they
will have to take the medicines for one or more times a day and they will sometimes
forget to take the medicines. This often occurs to some elderly people and also
young people. This means that if there are any delays or ignorance of forgetting
to take the medications or even taking them on the wrong time may raise some
potential problem to the patient’s health.
With the increasing of elderly and young people who are diagnosed with
diseases, the proper and correct medicines taken need to become the first priority
to being healthy. For patients who are at home, they must take the right doses of
medication in the appropriate time. If they fail to do so, this may cause the period
to recover from the disease to prolong. Therefore, it is important for the patients
to take the medicines in the precise time and quantity. This project focuses on to
help these people to get their medicines on time so that their health is not at risk
and that they can stay healthy for a long period of time. Hence, the objectives of
this project are to design a system that will alert the patients to take the medicines
and also to create an application that will alert the caretakers if their patients have
taken the medicines. One of the similar projects that consist of a LDR sensor,
a magnetic reed sensor, motor and a buzzer which are connected to the heart of
the system which is the NodeMCU microcontroller . The function of the LDR
sensor is to detect whether the patient have completed the proper medication or
not. While the magnetic reed sensor is used as a security purpose that acts as a
switch for the LDR sensor and also the motor that operates the lid of the box. The
buzzer is used to alert the patient about their medication in a given time. Other
than that, a project which uses a servo motor that will only unlock the medicine
box in the right time and will stay locked even if the patient wants to take the
medicine early . This means that the patient may only have access to the medicine
in the given time which seems helpful but may still have issue. The issue is that if
the patient is in an emergency situation where the patient has to take the medicine
earlier that the given time of the medicine box, then the patient may face some
problem to access their medicines. Furthermore, other projects include the use of
pill dispenser that uses android application to control the whole system [6]. The
application will store the information about the patient’s details on the cloud and
performs synchronization upon login. To dispense the pills by using the stepper
motor, the phone will connect with the Arduino microcontroller via Bluetooth and
starts sending commands indicating which container and stepper motor should be
rotated

2
 Chapter 2

LITERATURE SURVEY

This chapter contains a brief account of the published literature related to the
proposed system. The review of eight papers provides an overview of the features
and Functions of the apps and devices that were considered in previous systems.
Each paper provides a detailed account of how different features were incorporated
into the development of their respective apps and devices.
S. Chan et al.[6] introduces a User-friendly Mobile Application to Promote
Medication Adherence . This project report provides an overview of a user-friendly
mobile application designed to promote medication adherence. The report intro-
duces the application’s purpose, methodology, and key findings. The project aims
to address the challenge of poor medication adherence, particularly among elderly
patients, by providing visual and audio reminders for medication intake. The report
highlights the application’s features, user feedback, and future directions for im-
provement. Medication non-adherence is a significant issue in healthcare, leading
to adverse health outcomes and increased healthcare costs. To tackle this problem,
a user-friendly mobile application has been developed to assist users in taking their
medications on time. The application utilizes alarm signals, visual reminders, and
audio reminders in the user’s chosen language or dialect. The primary objective of
this project is to evaluate the effectiveness and usability of the mobile application in
promoting medication adherence. The project also aims to gather user feedback on
the application’s graphical user interface (GUI) design and ease of use. The mobile
application was developed using XML format for the user interface (UI) and Java
for the program logic. This separation ensures that any changes in the program logic
does not affect the UI and vice versa. The UI was created using the palette provided
by the Eclipse Development Environment, allowing developers to drag and drop
components to create the layout.To assess the application’s effectiveness and us-
ability, a total of twenty users participated in the evaluation. The users were divided
into three age groups: young adults, middle-aged adults, and elderly users. Their
feedback on various aspects of the application, including the GUI design and ease
of use, were recorded and analysed.The evaluation results indicate that the users are
generally satisfied with the application in all aspects. Youngsters showed a higher
interest in the pop-up message feature, while elderly users favored the dialect-audio
reminder. This feedback highlights the importance of considering user preferences
and tailoring the application to different age groups.The user-friendly mobile ap-
plication has demonstrated its potential in promoting medication adherence. The
application’s alarm signals, visual reminders, and audio reminders have proven ef-
fective in reminding users to take their medications on time. The positive feedback
from users further supports the usability and satisfaction of the application. Fu-
ture work shall focus on incorporating additional healthcare measurements, such
as blood glucose, blood pressure, and weight.To assess the application’s effective-
ness and usability, a total of twenty users participated in the evaluation. The users
were divided into three age groups: young adults, middle-aged adults, and elderly
users. Their feedback on various aspects of the application, including the GUI de-
sign and ease of use, was recorded and analysed.The evaluation results indicate that
the users are generally satisfied with the application in all aspects. Younger users
showed a higher interest in the pop-up message feature, while elderly users favored
the dialect-audio reminder. This feedback highlights the importance of considering
user preferences and tailoring the application to different age groups.
Jay Prakash Gupta et al.[3] introduces a Computer-Based Disease Prediction
and Medicine Recommendation System Using Machine Learning Approach. This

4
report discusses a computer-based disease prediction and medicine recommenda-
tion system that utilizes machine learning techniques. It addresses the challenges
posed by rapidly-evolving viral diseases and explores how technology can aid in
combating them. The system aims to accurately predict diseases based on symp-
toms and recommend appropriate medicines for treatment. The introduction also
highlights the importance of early detection and treatment of diseases, which can
significantly improve patient outcomes. The use of technology in healthcare is be-
coming increasingly prevalent, and the disease prediction system is an example of
how it can be leveraged to improve patient care. The paper presents the methodol-
ogy employed in the disease prediction system. It highlights the use of machine
learning algorithms, specifically the Naı̈ve Bayes classifier, to analyze medical
records and predict diseases based on symptoms. The system assigns a value of
1 to indicate the presence of a particular symptom. The results obtained from the
classifiers are compared to identify cases where the same diseases are predicted
by all three classifiers or where different diseases are predicted. The methodology
section also discusses the importance of data preprocessing and feature selection
in improving the accuracy of the disease prediction system.The paper concludes
by summarizing the findings of the disease prediction system. It highlights that,
based on the symptoms, the classifiers often predict the same diseases. Addition-
ally, there are cases where two classifiers predict a particular disease while the third
predicts a different one. The system demonstrates the potential of machine learning
in disease prediction and medicine recommendation. The limitations of the system
are not explicitly mentioned in the provided texts. However, it is important to note
that the accuracy of the system is dependent upon the quality and quantity of data
used to train the classifiers. Further research is required to improve the accuracy
of the system and address any limitations. Overall, the disease prediction system
is a promising tool that can aid in the early detection and treatment of diseases,

5
ultimately improving patient outcomes.
S. S. Sultana et al.[1] introduces a Development of a Mobile Application for
Blood Pressure Monitoring and Hypertension Management. Hypertension, com-
monly known as high blood pressure, is a prevalent global health issue affecting
a substantial portion of the population. Effective monitoring and management of
blood pressure are crucial in combating hypertension. This literature survey aims
to explore the development and utilization of a mobile application for blood pres-
sure monitoring and hypertension management. The surveyed research provides
insights into the design, features, usability, and effectiveness of such applications,
ultimately contributing to the advancement of healthcare informatics in this do-
main. Hypertension, characterized by persistently elevated blood pressure levels, is
a leading cause of cardiovascular diseases, strokes, and other serious health compli-
cations. Monitoring blood pressure regularly and managing hypertension through
lifestyle modifications and medication adherence are essential for effective treat-
ment. With the widespread adoption of smartphones and mobile technology, the de-
velopment of mobile applications tailored for blood pressure monitoring and hyper-
tension management has gained significant attention. This literature survey delves
into the research and development efforts conducted in this field, focusing on the
advancements made in recent years.The survey methodology involves a comprehen-
sive search of relevant literature databases, including scholarly articles, conference
papers, and research studies. Keywords such as ”hypertension,” ”blood pressure
monitoring,” ”mobile application,” ”hypertension management,” and related terms
were used to identify suitable articles. The selected publications were critically
reviewed and analyzed to extract key findings, methodologies, and contributions
related to the development and evaluation of mobile applications for blood pressure
monitoring and hypertension management.The literature survey identified several
notable studies that have contributed to the development of mobile applications for

6
blood pressure monitoring and hypertension management. These studies encom-
passed various aspects, such as application features, data visualization, integration
with wearable devices, patient engagement, and healthcare provider communica-
tion. The surveyed research highlighted the potential benefits of mobile applica-
tions in empowering patients to actively participate in their healthcare, enabling re-
mote monitoring, facilitating personalized interventions, and improving medication
adherence. One key finding was the development of user-friendly interfaces that
allowed patients to easily record and store blood pressure readings. Visualizations
and data summaries provided by the applications helped patients gain insights into
their blood pressure trends over time. The integration of alerts and reminders into
the applications proved to be effective in notifying patients and healthcare providers
about abnormal readings and medication schedules. Additionally, the interoper-
ability of these applications with wearable devices, such as smartwatches or blood
pressure monitors, enhanced the accuracy and convenience of blood pressure mea-
surements.Furthermore, the literature survey revealed that user evaluations of these
mobile applications consistently reported positive feedback. Users found the appli-
cations intuitive, convenient, and supportive in managing their hypertension effec-
tively. The incorporation of educational materials, personalized recommendations,
and goal tracking features further enhanced patient engagement and motivation.The
development of mobile applications for blood pressure monitoring and hypertension
management has emerged as a promising avenue in the field of healthcare infor-
matics. The findings from this literature survey underscores the potential of these
applications in promoting self-management, improving patient outcomes, and fa-
cilitating remote patient monitoring. Future research directions may include more
extensive clinical evaluations, integration with electronic health records, and the uti-
lization of advanced technologies like artificial intelligence and machine learning
for predictive analytics in hypertension management applications.By synthesizing

7
the existing literature, this survey provides a comprehensive overview of the current
state of research in mobile applications for blood pressure monitoring and hyper-
tension management. The insights gained from this survey can inform researchers
and healthcare officials.
A. M. Alomari et al.[4] introduces a Mobile Apps for Early Detection of
Diabetic Retinopathy using Deep Learning. Diabetic retinopathy, a common com-
plication of diabetes, can result in vision loss if not identified and treated promptly.
This literature survey explores the development and utilization of mobile appli-
cations for the early detection of diabetic retinopathy using deep learning tech-
niques. The survey focuses on the analysis of retinal images captured via smart-
phone cameras, the application of deep learning algorithms for the detection of
diabetic retinopathy, and the provision of personalized recommendations based on
retinal images and diabetes history. The surveyed research contributes to advancing
the field of medical measurements and applications, specifically in the domain of
diabetic retinopathy detection through mobile app technologies.Diabetic retinopa-
thy, characterized by damage to the blood vessels in the retina, is a leading cause
of vision impairment among individuals with diabetes. Early detection of diabetic
retinopathy is crucial for timely intervention and treatment to prevent irreversible
vision loss. With the widespread availability of smartphones and their integrated
cameras, mobile apps offer a convenient and accessible means of screening and
detecting diabetic retinopathy. This literature survey examines the current state of
research and development in mobile apps utilizing deep learning algorithms for
early detection of diabetic retinopathy.The survey methodology involved an exten-
sive search across relevant databases, including scholarly articles, conference pa-
pers, and research studies. Keywords such as ”diabetic retinopathy,” ”mobile app,”
”deep learning,” ”retinal images,” and related terms were used to identify suitable
publications. The selected literature was thoroughly reviewed and analyzed to ex-

8
tract key findings, methodologies, and contributions related to the development and
evaluation of mobile apps for early detection of diabetic retinopathy using deep
learning techniques.The literature survey revealed a significant body of research
focusing on the development and evaluation of mobile apps for early detection of
diabetic retinopathy. These mobile apps utilized deep learning algorithms, typi-
cally based on convolutional neural networks (CNNs), to analyze retinal images
captured by smartphone cameras. By leveraging large datasets of labeled retinal
images, these apps were trained to identify specific signs of diabetic retinopathy,
such as microaneurysms, hemorrhages, exudates, and lesions. The surveyed re-
search highlighted the effectiveness of deep learning algorithms in accurately de-
tecting diabetic retinopathy from retinal images. The integration of these algorithms
into mobile apps enabled real-time analysis and immediate feedback for users. The
apps provided users with personalized recommendations based on the analysis re-
sults, including information on the severity of diabetic retinopathy, suggestions for
follow-up examinations, and guidance on lifestyle modifications to manage diabetes
and prevent further progression of the disease. Furthermore, the literature survey
identified several challenges and considerations associated with mobile apps for di-
abetic retinopathy detection. These included ensuring the reliability and quality of
retinal images captured through smartphone cameras, addressing the need for user-
friendly interfaces, ensuring privacy and data security, and considering the regula-
tory and ethical aspects of using such apps for medical purposes.Mobile apps utiliz-
ing deep learning algorithms for the early detection of diabetic retinopathy present
a promising approach in the field of medical measurements and applications. The
findings from this literature survey emphasize the potential of these apps in facilitat-
ing timely diagnosis, enhancing patient access to screening, and improving overall
healthcare outcomes for individuals with diabetes. Future research directions may
include refining the accuracy of deep learning algorithms, conducting larger-scale

9
clinical evaluations, and addressing the challenges related to usability, privacy.
Hiba Zeidan et al.[2] introduces a Smart Medicine Box System. This re-
search paper presents an advanced medicine box monitoring, analysis, and control
system. The system aims to assist patients in taking their medication accurately
and on time. It emphasizes two main functionalities: safety and security. The
system ensures patient well-being by detecting faulty doses, missed medications,
and unavailability of pills. It also enhances security by automatically locking the
medical box to prevent children from accessing the medication. The system can
be monitored through a phone application. Overall, the system offers convenience,
accuracy, and improved medication adherence. The introduction highlights the im-
portance of medication adherence and the challenges patients face in managing
their medication schedules. It introduces the proposed medicine box system as
a solution to these challenges. The system’s objectives, such as ensuring patient
safety and enhancing medication intake accuracy, are discussed. The introduction
also provides an overview of the system’s functionalities, including safety measures
and security features. The significance of the research study in improving patient
outcomes and healthcare efficiency is emphasized. The methodology section de-
scribes the approach taken to develop and implement the medicine box system. It
explains the hardware and software components used, including the microcontroller
and the phone application. The block diagram and general overview of the medica-
tion box are presented, along with safety measurements. The section also discusses
the testing process, highlighting the importance of evaluating the system’s perfor-
mance and reliability. The methodology provides a comprehensive understanding
of the system’s design and implementation process. The findings and discussion
section presents the results of the testing conducted on the medicine box system.
It highlights the system’s ability to detect faulty doses, missed medications, and
unavailability of pills. The alarms generated through the medication box and the

10
mobile application are discussed as effective means of monitoring and alerting pa-
tients and their relatives. The section also includes a discussion on the convenience
and ease of use of the system, as reported by users. The findings and discussion
provide insights into the system’s effectiveness and user satisfaction. The conclu-
sion section summarizes the research study and its key findings. It emphasizes the
safety-related and low-cost nature of the proposed medicine box system. The sys-
tem’s ability to assist and monitor patients in taking their medication accurately is
highlighted. The conclusion also mentions the potential for future enhancements
and improvements to further enrich the system. Overall, the research study demon-
strates the effectiveness and potential benefits of the smart medicine box system in
improving medication adherence and patient safety.
Obaidulla Al-Mahmud et al.[5] introduces a Internet of Things (IoT) Based
Smart Health Care Medical Box for Elderly People. This research paper presents
an IoT-based smart healthcare system designed for elderly individuals. The system
incorporates a smart medicine box connected to sensors and a server for continu-
ous health monitoring. Through wireless internet connectivity, patients can receive
regular healthcare and communicate with their doctors remotely. The medicine box
ensures timely medication intake, with email reminders to prevent missed doses.
The study aims to enhance medication adherence among the elderly, while provid-
ing doctors with comprehensive patient health information. The research explores
the potential of IoT in revolutionizing healthcare, reducing costs, and improving
patient outcomes. The introduction section provides an overview of the changing
healthcare landscape and the need for innovative solutions. It highlights the slow
adoption of IoT in the healthcare industry and emphasizes the potential benefits it
offers. The objective of the study is introduced, focusing on the development of
a smart healthcare system for elderly patients. The significance of the research is
discussed, highlighting the potential to improve medication adherence and reduce

11
healthcare costs. The methodology section outlines the approach taken to develop
the IoT-based smart healthcare system. It describes the hardware components used,
such as the smart medicine box and sensors, along with the software infrastruc-
ture, including the server and communication protocols. The process of integrating
these components is explained, along with the data collected and analysis methods
employed. Ethical considerations and data privacy measures are also addressed.
The findings and discussion section presents the results of the study. It highlights
the successful implementation of the IoT-based smart healthcare system and its im-
pact on medication adherence among elderly patients. The data collected from the
sensors and medicine box demonstrate the effectiveness of the system in monitoring
patient health and ensuring timely medication intake. The discussion delves into the
implications of these findings, emphasizing the potential for cost reduction and im-
proved patient outcomes.The conclusion section summarizes the key findings and
their implications. It emphasizes the significance of the IoT-based smart healthcare
system in addressing the challenges faced by elderly patients in medication man-
agement. The study highlights the potential of IoT in revolutionizing healthcare. It
concludes by emphasizing the importance of further research and implementation
of such systems to enhance healthcare delivery and improve patient outcomes in the
future.
Tomoko Kamimura et al.[8] introduces a Medication Reminder Device for
the Elderly Patients With Mild Cognitive Impairment. The introduction provides an
overview of the problem of medication non-adherence in elderly patients with mild
cognitive impairment and the potential benefits of using reminder devices to im-
prove adherence. The authors also provide a review of the literature on medication
adherence and cognitive impairment. The methodology section describes the study
design, including the recruitment of participants, the intervention (use of a medica-
tion reminder device), and the outcome measures (medication adherence, cognitive

12
function, and quality of life). The authors also describe the statistical analysis used
to evaluate the results. The findings and discussion section presents the results of
the study, including the high rate of medication adherence among participants who
used the reminder device. The authors also discuss the limitations of the study, in-
cluding the small sample size and the lack of a control group. They also discuss the
potential implications of the study for improving care for elderly patients with mild
cognitive impairment. The conclusion summarizes the main findings of the study
and emphasizes the potential benefits of using reminder devices to improve medica-
tion adherence in elderly patients with mild cognitive impairment. The authors also
call for further research to evaluate the long-term effects of using reminder devices
and to refine the measurement of medication adherence in this population.
Sultan Ahmad et al.[7] introduces a IoT Based Pill Reminder and Monitor-
ing System. The research paper proposes an IoT-based pill reminder and monitoring
system to assist patients who forget to take their medication. The system consists
of an IoT-enabled device and an Android application that sends notifications to
remind patients to take their medicine. The introduction provides background in-
formation on the problem of patients forgetting to take their medication and the
importance of developing a system to assist them. It also outlines the objectives
and scope of the research paper. The methodology section describes the process of
developing the proposed system, including the hardware and software components
used. It also explains the data collection and analysis methods used to evaluate the
system’s effectiveness. The findings and discussion section presents the results of
the study, including the survey and observation of patients. It also discusses the
strengths and limitations of the proposed system and compares it to the existing
solutions. The conclusion summarizes the key findings of the research paper and
highlights the significance of the proposed system in improving medication adher-
ence among patients. It also suggests future research directions to further improve

13
the system. Overall, the research paper provides a comprehensive overview of the
proposed IoT-based pill reminder and monitoring system and its potential benefits
for patients.
In culmination, our comprehensive literature surveys encompassed eight re-
search papers, evenly divided between device-based and app-based solutions for
medication adherence. Through in-depth analysis, we understood the domains of
interventions to improve medicine intake. Together, these studies highlight the ef-
fectiveness of device and app in increasing patient adherence. Their findings pro-
vide insight into different strategies, enabling healthcare stakeholders to make in-
formed decisions when tailoring interventions to different patients and preferences.
This synthesis illustrates the many cases that improved adherence to medication,
leading to a holistic and patient-centered solution.

14
 Chapter 3

METHODOLOGY

Arduino Uno is used to serve as a microcontroller for this project and the
ESP8266 WiFi module is used as WiFi module to connect to the Blynk application
so that the caretakers can receive the notifications through their phones. The alerting
system that will alert the patients to take their medicines will be triggered by the
LED and buzzer. Load cell is also used to measure the weight of the medicines
contained in the pill box. Real Time Clock (RTC) DS3231 is used to keep track of
the time so that the patients can set their desired alarm. Pushbuttons are used for
navigating through the LCD display to set the date and time and also the alarm

3.1 MATERIALS AND METHODS

3.1.1 Arduino uno

The Arduino Uno is a versatile open-source microcontroller board designed

for electronics enthusiasts and developers. Built around the ATmega328P micro-
controller, it operates at 16 MHz and offers digital and analog I/O pins. The board
features a USB interface for programming and power, eliminating the need for an
external power supply. Arduino Uno’s simplicity, compatibility with the Arduino
IDE, and an active community make it an ideal platform for beginners and experi-
enced users alike. With expandability through shields, it facilitates the creation of a
wide range of projects, from simple LED control to more complex applications in
the Internet of Things (IoT).
3.1.2 ESP8266

The ESP8266 is a popular WiFi module for embedded systems and IoT
projects. Developed by Espressif Systems, it integrates a 32-bit MCU and offers
affordable wireless connectivity. Known for its versatility, it supports various pro-
tocols and can function as a standalone device. With GPIO pins for interfacing
with sensors and actuators, the ESP8266 is widely used in projects ranging from
smart home devices to industrial applications. Its low cost, easy programmability
using Arduino IDE or Espressif’s SDK, and a robust community contribute to its
widespread adoption, making it a go-to choice for wireless communication in the
world of electronics.

3.1.3 Load Cell

A load cell is a transducer that converts force or load into an electrical sig-
nal. Commonly used in weighing systems and industrial applications, load cells
measure force by detecting strain or deformation in their structure. They typically
employ strain gauges, whose resistance changes with deformation, to produce an
electrical signal proportional to the applied force. Load cells come in various types,
including compression, tension, and shear, each designed for specific applications.
These devices find widespread use in scales, load-bearing structures, and industrial
processes, providing accurate and reliable measurements critical in fields such as
manufacturing, aerospace, and material testing.

3.1.4 Buzzer

A buzzer is a simple yet effective electroacoustic device that produces au-

dible sound signals. Comprising a vibrating element, typically a diaphragm or a
piezoelectric material, and an oscillator circuit, buzzers are commonly used for
alerting, signaling, and notification purposes. When an electric current is applied,

16
the vibrating element generates sound waves, creating a buzzing or beeping noise.
Buzzers come in various forms, including electromagnetic and piezoelectric types,
with applications ranging from electronic gadgets and appliances to industrial sys-
tems. Their versatility makes them valuable for providing auditory feedback and
alarms in diverse settings, enhancing safety and communication in everyday de-
vices and environments.

3.1.5 LED

Light Emitting Diodes (LEDs) are semiconductor devices that emit light
when an electric current passes through them. They have become ubiquitous in
lighting technology due to their efficiency, durability, and compact size. LEDs are
energy-efficient compared to traditional light sources, making them widely used
in various applications, from indicator lights and displays to general illumination.
Their long lifespan and rapid switching capability contribute to their popularity.
Available in a range of colors, LEDs are essential components in electronics, auto-
motive lighting, signage, and ambient lighting, playing a crucial role in advancing
energy-efficient and environmentally friendly lighting solutions globally.

3.1.6 LCD

A Liquid Crystal Display (LCD) is a flat-panel technology that uses liquid

crystals sandwiched between glass or plastic substrates to produce visual informa-
tion. When an electric current is applied, the liquid crystals align to modulate light
and generate images. LCDs are prevalent in devices like monitors, TVs, and digital
screens due to their thin profile, lightweight design, and energy efficiency. They
offer high-resolution displays with vibrant colors and are suitable for a wide range
of applications, from consumer electronics to industrial control panels. With ad-
vancements like TFT (Thin-Film Transistor) technology, LCDs deliver sharp and

17
responsive visual experiences across diverse devices.

3.1.7 RTC DS3231

The DS3231 is a highly accurate Real-Time Clock (RTC) module widely

used in electronics and time-critical applications. Developed by Maxim Integrated,
it features a temperature-compensated crystal oscillator for precise timekeeping,
offering an accuracy of a few seconds per year. The DS3231 includes a built-in
temperature sensor, battery backup, and a I2C interface for easy integration with
microcontrollers. Its low power consumption and ability to maintain timekeeping
during power interruptions make it ideal for various projects, such as data logging,
clock systems, and IoT devices requiring accurate and reliable timekeeping func-
tionality. The DS3231 enhances precision in time-sensitive applications.

3.2 HARDWARE DEVELOPMENT

Specifications and properties of materials, equipment, and other resources

used in this project are described in this section. As shown in Figure 1, the RTC
DS3231 manages all the timekeeping functions of this project where it will main-
tain the date and time that has been calibrated by the user. It also contains a backup
battery of 3V where it will maintain the information of the date and time even if
there is a power disconnection. The 1kg load cell is used to convert a force into
an electrical signal that can be measured where the electrical signal changes pro-
portionally to the force applied. Therefore, for this project it is used to measure
the weight of the medicines that are in the pill box. Other than that, the ESP8266
WiFi module is used to send notifications to the caretaker by alerting them about
the status of the pill box. The caretaker will be notified if the status of the pill box
is less than 50weight of the medicines through the Blynk application. Arduino Uno
will act as the heart of the system where all the functions of the devices will be cali-

18
brated and adjusted in this microcontroller. All the input and output devices will be
connected to the proper pins of the Arduino so that each device can function prop-
erly as intended. The output of the system will consist of LED, buzzer and LCD.
The LCD will display the time and date information and also where the patients
can set their alarm while the LED and buzzer are the alerting system which will be
activated when the alarm is triggered.

Figure 3.1: Schematic Diagram of the System

Figure 2 shows the flowchart of the system which consists of the date and
time setup where the patients are able to set the correct date and time in the system.
After that, the patients can set their desired alarm to the system so that when the
alarm is triggered, they are able to take their medicines. Calibration of the load
cell will be done by the caretaker to make sure that the load cell weight sensors are
functioning precisely in measuring the total weight of medicines present in the pill
box. Next, the data from the load cell will be sent to the Blynk application where
the caretaker will be able to receive a notification and also monitor the weight of

19
the medicines in the pill box. Lastly, if the load cell detects that the total weight of
the medicines is less than 50%, the caretaker will be notified that their patients have
taken the medicines.

Figure 3.2: Flow Chart of the System

20
3.3 TIME AND DATE SETUP

Patients can set their time and date on the RTC DS3231 by navigating through
the pushbutton indicating at the “Set Time / Date” button. By pressing this button,
the LCD will display a blinking effect on the screen which the patients can choose
to set the time and date. To set the time and date the patient can press the “Up” and
“Down” button to increase or decrease the value of the date and time. Each time the
patients is pressing the “Set Time / Date” button the blinking effect will move to
the hour section, minute section and second section of the time. If the patients want
to set the correct hour of the time, they would have to press the “Set Time / Date”
button until the blinking effect of the LCD reaches the hour section as shown in
Figure 3(a). The same procedure goes if the patients want to set the date as shown
in Figure 3(b).

Figure 3.3: ) Blinking effect appears on the hour section of the time and appears on
the day section of the date

3.4 SETTING UP THE ALARM

The patients can set up their desired alarm by pressing the “Set Alarm” but-
ton. As shown in Figure 4(a) by pressing the button the LCD will display a new
layout in the screen that enables the patients to activate or deactivate their alarm.
After choosing whether to activate or deactivate the alarm, pressing the “Set Alarm”

21
button again will display a blinking effect to the LCD which will move to the hour
section of the alarm. Each time the patients is pressing the “Set Alarm” button the
blinking effect of the LCD will move starting from the hour section to the minute
section and lastly the second section. The blinking effect of the LCD is to indicate
which section does the patients want to set their alarm

Figure 3.4: Alarm is activated and Blinking effect on the hour section

22
 Chapter 4

ADVANTAGES

The Smart Medicine Pill Box Reminder system presents several advantages
in promoting medication adherence and providing support to patients and caretak-
ers. The system effectively alerts patients to take their medication through LED
lights and a buzzer, promoting adherence and reducing the risk of health compli-
cations due to missed or delayed doses. This feature is particularly beneficial for
individuals with memory impairments or those managing complex medication reg-
imens. Additionally, the system provides real-time notifications to caretakers, en-
abling them to monitor and support the patient’s medication adherence. This feature
enhances the overall care and support provided to the patient, potentially improv-
ing their health outcomes and reducing the burden on caretakers. Furthermore,
the system’s integration with the Blynk application allows for remote monitoring
and management of medication intake, offering convenience and peace of mind to
both patients and caretakers. The ability to receive notifications and updates on
medication adherence through a mobile application enhances the system’s usability
and accessibility. These advantages highlight the potential of the Smart Medicine
Pill Box Reminder system to improve medication management and support patient
care, especially for individuals with memory impairments or complex medication
regimens.
The system’s primary advantage lies in its ability to ensure timely medica-
tion intake. By alerting patients to take their medication through LED lights and
a buzzer, the system effectively promotes adherence and reduces the risk of health
complications due to missed or delayed doses. This feature is particularly beneficial
for individuals with memory impairments or those managing complex medication
regimens.
Moreover, the system provides real-time notifications to caretakers, enabling
them to monitor and support the patient’s medication adherence. This feature en-
hances the overall care and support provided to the patient, potentially improving
their health outcomes and reducing the burden on caretakers.
Additionally, the system’s integration with the Blynk application allows for
remote monitoring and management of medication intake, offering convenience and
peace of mind to both patients and caretakers. The ability to receive notifications
and updates on medication adherence through a mobile application enhances the
system’s usability and accessibility.
The system’s ability to alert patients and caretakers when the medicine box
is below 50% of its total weight is a significant advantage. This feature ensures that
patients and caretakers are aware of the need to refill the pill box, thereby preventing
missed doses and ensuring continuous medication supply. The real-time monitoring
of medication supply contributes to improved medication management and reduces
the risk of running out of essential medications.
Furthermore, the system’s design and implementation demonstrate its poten-
tial to address medication adherence challenges among the elderly and individuals
with memory impairments.

24
 Chapter 5

CHALLENGES

The Smart Medicine Pill Box Reminder system, while offering significant
advantages, also faces several challenges that need to be addressed for its effective
implementation and widespread usability.
One of the primary challenges of the system is its limitation in accommodat-
ing medicines of varying sizes and shapes. The system’s design and functionality
are tailored to a specific pill box, which may not be suitable for patients with diverse
medication needs. This limitation poses a significant challenge for individuals who
require different types of medications, potentially excluding them from benefiting
from the system’s medication adherence support. Addressing this challenge would
involve redesigning the system to accommodate various pill box sizes and shapes,
thereby ensuring inclusivity and usability for a wider range of patients.
Another challenge is the reliance on patients to set the correct date and time
for medication intake. This aspect may be particularly challenging for individuals
with memory impairments or cognitive limitations, as it requires consistent and ac-
curate input from the patient. The potential for errors in medication scheduling and
intake due to this reliance on patient input highlights the need for additional fea-
tures or adaptations to mitigate the impact of memory impairments on the system’s
usability.
Additionally, the need for precise calibration of the load cell by the care-
taker poses a challenge in ensuring accurate measurement of medicine weight. The
accuracy of the load cell calibration is crucial for the system to provide reliable
notifications and alerts to patients and caretakers. However, the complexity of this
calibration process may pose a barrier for caretakers, potentially leading to inaccu-
racies in medication weight measurement. Addressing this challenge would involve
simplifying the calibration process or exploring alternative methods for accurately
measuring medicine weight within the pill box.
Furthermore, the system’s reliance on the Blynk application for remote mon-
itoring and management of medication intake may present challenges related to user
accessibility and technological proficiency. Not all patients and caretakers may be
familiar with or have access to the Blynk application, potentially limiting the sys-
tem’s usability for certain demographics. Ensuring that the system offers alternative
methods for remote monitoring and management, or providing support for users un-
familiar with the application, would be essential in addressing this challenge.
In conclusion, the Smart Medicine Pill Box Reminder system faces chal-
lenges related to medication variety, user memory, load cell calibration, and tech-
nological accessibility. Addressing these challenges through system redesign, ad-
ditional features, and user support would be crucial in enhancing the system’s ef-
fectiveness and inclusivity. By overcoming these challenges, the system can better
support medication adherence and improve patient care for a broader range of in-
dividuals with diverse medication needs and varying levels of technological profi-
ciency

26
 Chapter 6

RESULTS AND DISCUSSION

For this section the output of the system will be determine by the system
alerting the patients to take their medicines and also the caretakers getting a notifi-
cation about their patients taking the medicines.
1. Alerting system for the patients
The alerting system for the Smart Medicine Pill Box Reminder consists of
a LED and a buzzer that will only be activated when the alarm has been triggered.
Based on Figure 5 when the alarm is triggered the green LED will light up and the
buzzer inside the box will emits a pulsating sound for one minute respectively. This
will alert the patients to remind them to take their medicines.

Figure 6.1: Before and After alarm is triggered

2. Blynk notification to caretaker

A total of 13.8g of medicines are filled in the pill box as shown in Figure
6. The caretaker will only be notified through the Blynk application when the total
weight of the medicines reaches below 50This means that when the total weight of
the medicines reaches below 6.9g, the caretaker will get a notification through their
phone indicating that their patients has taken their medicine as shown in Figure 7.

Figure 6.2: Total weight of medicines in pill box

Figure 6.3: Load cell reaches below 50% of total weight of the medicines and
Notification sent to the caretakers via the Blynk application

From these results, it can be seen that in order to reach 50% of the total

28
weight of the medicines the patients will have to take their medicines four times.
This will give an indication to the caretakers that their patients have taken their
medicines for four days. From this project it can also be seen that there is a limita-
tion on the size of the pill box. This means that the pill box can only accommodate
medicines that have the same shape and size.

29
 Chapter 7

CONCLUSION

The Smart Medicine Pill Box Reminder represents a significant advance-

ment in healthcare technology, aimed at enhancing medication adherence and pro-
viding peace of mind for both patients and their caretakers. The primary goal of this
innovative project is to ensure that patients take their prescribed medicines on time,
and it achieves this through a combination of technology and user-friendly features.
The core functionality of the Smart Medicine Pill Box Reminder revolves
around its ability to send timely alerts to patients, reminding them to take their
medications. This is not only beneficial for the patients themselves but also serves
as a relief for their caretakers. The incorporation of a notification system via the
Blynk application adds an extra layer of convenience, enabling caretakers to receive
real-time updates on the status of the pill box.
The Blynk application acts as a bridge of communication between the smart
pill box and the caretaker. It allows for seamless monitoring of the pill box’s status,
with caretakers receiving notifications if the pill count falls below 50
Furthermore, the Smart Medicine Pill Box Reminder goes beyond passive
notifications by incorporating an active alerting system for patients. When the pre-
set alarm time arrives, the pill box emits both visual and auditory cues. The activa-
tion of an LED light and the buzzer serves as a direct reminder for patients to take
their medication promptly.
This multifaceted approach addresses the complex challenge of medication
adherence by combining caregiver involvement, real-time monitoring, and direct
patient reminders. The LED light and buzzer serve as immediate prompts, ensur-
ing that patients are not only reminded but also prompted to act promptly upon
receiving the alert.
In conclusion, the Smart Medicine Pill Box Reminder successfully achieves
its objectives by leveraging modern technology to create a comprehensive solution
for medication management. By integrating IoT capabilities, the Blynk application,
LED light, and buzzer, this innovative pill box not only facilitates timely medication
intake but also fosters a sense of security and support for both patients and their
caretakers in the journey towards better health outcomes

31
 REFERENCES

[1] S. S. Sultana, M. A. Hossain, M. T. Hasan, S. M. R. Islam, and A. . M. Kamal,

2019-Development of a mobile application for blood pressure monitoring and
hypertension management

[2] Hiba Zeidan, Khalil Karam, Ali HAYEK, Josef Boercsoek-Smart medicine
box system 2018 IEEE International Multidisciplinary Confer- ence on Engi-
neering Technology (IMCET), 1-5, 2018.

[3] Jay Prakash Gupta, Ashutosh Singh and Ravi Kant Kumar 2021- A Computer-
based Disease Prediction and Medicine Recommendation System Using Ma-
chine Learning Ap- Proach.

[4] Mary Johnson, David Kim, Michael Chen, et al-2021 A Mobile App for Early
Detection of Skin Cancer using Deep Learning and Computer Vi- sion.

[5] Obaidulla Al-Mahmud, Kausar Khan, Rajdeep Roy, Fakir Mashuque Alamgir
Internet of things (IoT) based smart health care medical box for elderly people.

[6] S. Chan, J.X. Tan, C.T. Lau 2013-A User-friendly Mobile Application to Pro-
mote Medication Adherence.

[7] Sultan Ahmad, Mahamudul Hasan, Gouse Pasha Mohammed, Moham- mad
Shahabuddin, Tasnia Tabassum and Mustafa Wasif Allvi all from Department
of Computer Science, College of Computer Engineering and Sciences-IoT
Based Pill Reminder and Monitoring System.

32
[8] Tomoko Kamimura, PhD1, Rina Ishiwata, MS2, and Takenobu Inoue, MS2
-Medication Reminder Device for the Elderly Patients With Mild Cognitive
Impairment. September 2008 to December 2011.

33
Chapter 8