M OTION S PIKE

A Project Report

Submitted By

HINSU TWISHA KAMLESH

2203031280003
PATEL HIL ARUN
2303031287001
PATEL PARAMKUMAR NARESHBHAI
2303031287002
PATEL NISARG KALPESHBHAI
2203031280012

in Partial Fulfilment for the Award of

the Degree of
BACHELOR OF TECHNOLOGY
in
COMPUTER SCIENCE & ENGINEERING

Under the Guidance of

Dr. Amit Barve
(Head of Department, CSE, PIET)

PARUL UNIVERSITY
(NAAC A++)

VADODARA
April - 2025
 PARUL UNIVERSITY
C ERTIFICATE
This is to Certify that Project - 1 (303105300) of 6th Semester entitled “MOTION SPIKE” of Group
No. PUIOT 3 has been successfully completed by

• HINSU TWISHA KAMLESH- 2203031280003

• PATEL HIL ARUN- 2303031287001

• PATEL PARAMKUMAR NARESHBHAI- 2303031287002

• PATEL NISARG KALPESHBHAI- 2203031280012

under my guidance in partial fulfillment of the Bachelor of Technology (B.Tech) in Computer

Science & Engineering of Parul University in Academic Year 2024- 2025.

Date of Submission :

Dr. Amit Barve, Dr. Amit Barve,

Project Guide Head of Department,

CSE, PIET,

Project Coordinator:- Yatinkumar Sukla Parul University.

ii
 Acknowledgements

“The single greatest cause of happiness is gratitude.”

-Auliq-Ice

I would like to express my deepest gratitude to everyone who contributed to the successful
completion of this project, Motion Spike – A Smart Wearable for Health, Learning & Fitness.
First and foremost, I sincerely thank Dr. Amit Barve for their guidance, encouragement, and
valuable insights throughout this journey. Their expertise and support were instrumental in shaping
this project.
I am also grateful to my institution, faculty members, and peers for providing the necessary
resources, feedback, and motivation to refine and improve this work. A special thanks to my family
and friends, whose constant support and encouragement kept me inspired.
Lastly, I extend my appreciation to all participants and testers, especially those involved in
the early trials, for their valuable feedback, which helped validate the impact and effectiveness of
Motion Spike. This project would not have been possible without their contributions.

Thank you all for being a part of this journey.

HINSU TWISHA KAMLESH- 2203031280003

PATEL HIL ARUN- 2303031287001
PATEL PARAMKUMAR NARESHBHAI- 2303031287002
PATEL NISARG KALPESHBHAI- 2203031280012
CSE, PIET
Parul University,
Vadodara
 Abstract

Millions of people struggle with poor posture, limited physical activity, and learning challenges,
especially those undergoing rehabilitation or living with ADHD. Traditional therapy and learning
methods often lack engagement and real-time feedback, making it difficult for individuals to stay
motivated and track progress. Similarly, fitness enthusiasts and those recovering from injuries need
better posture correction and movement tracking to avoid long-term health issues.
Motion Spike is a smart wearable system designed to bridge this gap. It helps users improve
posture, movement, and overall well-being through real-time motion tracking and interactive
feedback. By turning exercise, therapy, and learning into engaging experiences, Motion Spike
supports rehabilitation, ADHD therapy, and fitness routines. Early trials show improved focus in
children with ADHD and better physical recovery in rehabilitation patients.
Designed for accessibility and affordability, Motion Spike aligns with Digital India and Make
in India initiatives, making smart rehabilitation and motion-based learning available to schools,
therapy centers, and fitness programs. This innovation has the potential to transform healthcare,
education, and fitness, empowering individuals to live healthier, more active lives.
Table of Contents

Acknowledgements iii

Abstract iv

List of Tables ix

List of Figures x

1 Introduction 1

1.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1

1.2 Problem Statement . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1

1.2.1 The Challenge . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1

1.2.2 Who is Affected? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1

1.2.3 Why Immediate Action is Needed? . . . . . . . . . . . . . . . . . . . . . 2

1.3 Introducing Motion Spike – A Smart Wearable for Health, Learning & Fitness . . . 3

1.4 Solutions by Motion Spike . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3

1.4.1 Addressing ADHD & Enhancing Learning . . . . . . . . . . . . . . . . . 3

1.4.2 Improving Fitness & Posture Awareness . . . . . . . . . . . . . . . . . . . 3

1.4.3 Motion-Based Learning for Better Engagement . . . . . . . . . . . . . . . 3

1.4.4 Rehabilitation & Physiotherapy Support . . . . . . . . . . . . . . . . . . . 4

1.5 Key Features of Motion Spike . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4

v
 TABLE OF CONTENTS

2 Literature Survey 5

2.1 Enhancing Programming Practice: A Game-Based Coding Challenge Environment 5

2.2 Wearable Gaming Systems for Fitness Motivation . . . . . . . . . . . . . . . . . . 5

2.3 The Role of Gamification in Learning and Engagement . . . . . . . . . . . . . . . 6

2.4 Motion-Based Fitness Games: Analyzing User Engagement and Health Benefits . . 6

2.5 Sensor-Based Wearable Technologies for Fitness Tracking . . . . . . . . . . . . . 7

2.6 Gamification in Physical Rehabilitation: A Systematic Review . . . . . . . . . . . 7

2.7 Human-Computer Interaction in Wearable Motion Gaming Systems . . . . . . . . 7

3 Analysis / Software Requirements Specification (SRS) 8

3.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8

3.2 Document Conventions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8

3.3 Recommended Reading for Viewers . . . . . . . . . . . . . . . . . . . . . . . . . 9

3.4 Product Scope . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9

3.5 References . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9

3.6 User Interfaces . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10

3.6.1 Wearable Device Interface . . . . . . . . . . . . . . . . . . . . . . . . . . 10

3.6.2 Web Application Interface . . . . . . . . . . . . . . . . . . . . . . . . . . 10

3.7 Hardware Interfaces . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10

3.8 Functional Requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10

3.9 Other Nonfunctional Requirements . . . . . . . . . . . . . . . . . . . . . . . . . . 11

3.10 Software Quality Attributes . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11

4 System Design 12

4.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12

4.2 System Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12

4.2.1 Hardware Components . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13

vi
 TABLE OF CONTENTS

4.2.2 Software Components . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13

4.3 Data Flow Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13

4.4 System Implementation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15

4.4.1 Sensor Calibration & Data Collection . . . . . . . . . . . . . . . . . . . . 15

4.4.2 Deep Learning Model Training . . . . . . . . . . . . . . . . . . . . . . . . 15

4.4.3 Dashboard Development . . . . . . . . . . . . . . . . . . . . . . . . . . . 15

4.5 Block Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16

4.5.1 Block Diagram Components . . . . . . . . . . . . . . . . . . . . . . . . . 16

4.6 Circuit Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16

4.6.1 Circuit Diagram Components . . . . . . . . . . . . . . . . . . . . . . . . 17

4.7 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17

5 Methodology 18

5.1 Overall Approach . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18

5.2 Hardware Setup . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19

5.2.1 Wearable Bands . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19

5.2.2 Base Station . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19

5.2.3 Web Dashboard . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20

5.3 Software Development . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20

5.3.1 Firmware . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20

5.3.2 Web Application & Dashboard . . . . . . . . . . . . . . . . . . . . . . . . 21

5.3.3 Gamification Logic . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21

5.4 Data Processing & Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21

5.5 Evaluation & Testing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22

5.6 Ethical & Safety Considerations . . . . . . . . . . . . . . . . . . . . . . . . . . . 22

5.7 Implementation Timeline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23

vii
 TABLE OF CONTENTS

6 Implementation 24

6.1 System Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24

6.2 Hardware Implementation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24

6.2.1 Wearable Bands . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24

6.2.2 Base Station . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25

6.3 Software Implementation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28

6.3.1 Firmware . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28

6.3.2 AI & Gamification . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31

6.3.3 Web Dashboard . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33

6.3.4 Testing & Debugging . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34

6.3.5 Observations & Improvements . . . . . . . . . . . . . . . . . . . . . . . . 34

7 Conclusion 36

7.1 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36

8 Future Work 38

8.1 Future Enhancements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38

8.1.1 Enhanced Sensor Arrays . . . . . . . . . . . . . . . . . . . . . . . . . . . 38

8.1.2 Cloud Integration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38

8.1.3 Expanded Rehabilitation Modules . . . . . . . . . . . . . . . . . . . . . . 38

8.1.4 User Personalization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39

8.1.5 Improved Learning & ADHD Support . . . . . . . . . . . . . . . . . . . . 39

8.1.6 Wider Market Applications . . . . . . . . . . . . . . . . . . . . . . . . . . 39

8.1.7 Longitudinal Data Analysis . . . . . . . . . . . . . . . . . . . . . . . . . 39

viii
List of Tables

ix
List of Figures

4.1 System Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12

4.2 Base Station (Logic) Flow Chart . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
4.3 Wearable Band (Logic) Flow Chart . . . . . . . . . . . . . . . . . . . . . . . . . . 15
4.4 Block Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
4.5 Circuit Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17

6.1 MPU6050 Module . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24

6.2 HMC5883L Module . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
6.3 MAX30201 Module . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
6.4 ESP-WROOM-32 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
6.5 RASPBERRY PI 4 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
6.6 Band-1 Image . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
6.7 Band-2 Image . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27
6.8 Band-3 Image . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27
6.9 ESP-NOW Protocol . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
6.10 Transmitter Code . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
6.11 Receiver Code . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30
6.12 Motion Mapping Graph . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31
6.13 Motion Detection Code . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32
6.14 Home Screen . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33
6.15 Web-Page Gallery . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33
6.16 Dino Game . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34
6.17 Math-Battle Game . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34

x
Chapter 1

Introduction

1.1 Overview
In today’s fast-paced world, people face multiple challenges related to health, fitness, learning, and
rehabilitation. With increasing screen time and sedentary lifestyles, issues such as poor posture,
lack of physical activity, and cognitive difficulties are becoming more prevalent. Traditional fitness
routines, therapy sessions, and learning methods often fail to keep individuals engaged, leading to
low adherence and limited long-term benefits.
Motion Spike is designed to bridge this gap by providing an interactive, motion-driven solution
that enhances focus, improves posture, supports rehabilitation, and integrates physical activity into
learning. It is an innovative wearable technology that combines motion tracking, gamification, and
health monitoring to create a holistic approach to well-being.

1.2 Problem Statement

1.2.1 The Challenge

Modern lifestyles have led to reduced physical activity, poor posture, and limited engagement in
interactive learning, affecting health, focus, and overall well-being. Traditional methods of fitness,
therapy, and education often fail to keep users motivated, making it difficult for them to achieve
meaningful progress.

1.2.2 Who is Affected?

Children & Students

• Many children, particularly those with ADHD, struggle with focus, coordination, and
engagement in traditional learning settings.

1
 CHAPTER 1. INTRODUCTION

• Lack of movement-based learning affects cognitive development and retention.

• 80% of ADHD children experience focus challenges in classrooms (CDC, 2022).

• Motion-based learning improves attention span by 30%.

Working Professionals

• Prolonged sitting, improper posture, and limited physical activity lead to chronic pain, fatigue,
and reduced productivity.

• Poor ergonomics at workplaces further worsen the issue.

• 90% of desk job workers experience posture-related issues (Posture Research Institute, 2023).

• Poor posture can reduce lung capacity by 30% (Journal of Biomechanics, 2022).

Patients & Elderly

• Individuals recovering from injuries, surgeries, or age-related mobility issues require guided
physiotherapy and rehabilitation.

• Traditional therapy is costly, monotonous, and inaccessible to many.

• 1.71 billion people worldwide suffer from musculoskeletal conditions (WHO, 2023).

Fitness Enthusiasts

• Many struggle with maintaining proper posture, increasing the risk of injuries.

• Limited real-time feedback makes it difficult to track progress and prevent overuse injuries.

• 60% of gym-related injuries occur due to incorrect posture and movement (Sports Medicine
Journal, 2023).

1.2.3 Why Immediate Action is Needed?

• 7.1% of Indian children have ADHD, affecting academic and social development.

• Lack of movement increases health risks, leading to obesity, musculoskeletal issues, and
chronic conditions.

• Rehabilitation & therapy are costly and inaccessible for many individuals.

2
 CHAPTER 1. INTRODUCTION

1.3 Introducing Motion Spike – A Smart Wearable for Health, Learning &

Fitness
Motion Spike is an advanced wearable device designed to integrate motion tracking, posture
correction, gamified learning, and real-time health monitoring. It provides an engaging and effective
solution for individuals seeking better physical health, cognitive development, and rehabilitation
support.
This lightweight and comfortable wearable consists of motion sensors and health trackers that
capture body movement, posture, and vital signs. The data is processed and displayed on a web
dashboard, providing insights and feedback for users to improve their overall well-being.

1.4 Solutions by Motion Spike

1.4.1 Addressing ADHD & Enhancing Learning

Many children with ADHD struggle to maintain focus and stay engaged in traditional learning
environments. Studies indicate that motion-based learning can improve concentration, motor
coordination, and cognitive development.

• Motion-Controlled Games like Dino Jump & Math Battle enhance learning.

• Encourages active participation through jumping and hand movements.

• Real-time motion tracking improves coordination, making learning interactive.

1.4.2 Improving Fitness & Posture Awareness

Poor posture and lack of physical activity are leading causes of back pain and musculoskeletal
issues. Many desk job workers and fitness enthusiasts struggle with maintaining proper posture,
increasing their risk of injuries.

• Tracks body movements to detect incorrect posture.

• Provides real-time posture correction for injury prevention.

• Enables motion-driven workouts for a healthier, active lifestyle.

1.4.3 Motion-Based Learning for Better Engagement

Traditional learning methods often fail to engage students effectively, especially those who learn
better through movement. Active learning significantly improves retention and cognitive skills.

3
 CHAPTER 1. INTRODUCTION

• Interactive learning integrates math, science, and language with physical movement.

• Increases knowledge retention by 75% compared to passive learning.

• Enhances spatial awareness, problem-solving, and creativity.

1.4.4 Rehabilitation & Physiotherapy Support

Patients undergoing physiotherapy often struggle with motivation due to repetitive exercises and
lack of real-time feedback. Traditional therapy sessions are also expensive and inaccessible.

• Guided therapy using animated simulations & real-time feedback.

• Ensures movement accuracy for effective rehabilitation.

• Gamified physiotherapy increases adherence to treatment plans.

1.5 Key Features of Motion Spike

• Motion-Controlled Games – Play using jumps & hand motions for learning & fitness.

• Push-Up Detection – Tracks reps & form to improve strength training.

• Posture Correction – Helps prevent bad posture & related health issues.

• Rehab & Physiotherapy Support – Uses games & animations for guided recovery.

Motion Spike is more than just a wearable – it is a transformative solution that integrates
movement into everyday life, enhancing learning, fitness, and rehabilitation in an engaging and
effective way!

4
Chapter 2

Literature Survey

2.1 Enhancing Programming Practice: A Game-Based Coding Challenge

Environment
Paiva, J. C., Leal, J. P., & Queirós, R. (2020)
Abstract: Practice is essential for learning programming, and automated assessment plays a
key role in enhancing students’ learning experiences. This paper introduces Asura, a game-based
coding challenge environment that provides graphical feedback and gamification to increase student
engagement. The system enables students to develop software agents (SA) that compete in coding-
based challenges. The interactive nature of Asura encourages students to analyze, improve, and
optimize their code, promoting a deeper understanding of programming concepts. Furthermore, the
automated feedback system reduces the reliance on direct instructor intervention, allowing students
to learn independently.
Conclusion: The study demonstrates that game-based learning environments like Asura can
significantly enhance student motivation and engagement in programming practice. By incorporating
graphical feedback, competitive challenges, and automated assessment, the platform fosters a
positive learning experience.

2.2 Wearable Gaming Systems for Fitness Motivation

Malviya, A., Joy, J. E., & Phate, A. (2023)
Abstract: This study presents Jump Fit, a wearable gaming system designed to motivate
individuals to engage in physical exercise through interactive gameplay. Inspired by the Google
Chrome Dino game, Jump Fit requires users to physically jump in real life to control their in-
game character. The system consists of wearable sensors (MPU9250 IMU) and Arduino-based

5
 CHAPTER 2. LITERATURE SURVEY

hardware, which detect movement and translate it into gameplay actions. Wireless communication
via NRF24L01 transceivers ensures real-time responsiveness. The gamification aspect encourages
active participation, making exercise enjoyable and engaging.
Conclusion: The research highlights the potential of wearable technology in gamifying fitness
activities. Jump Fit successfully integrates motion-based controls with an interactive gaming
experience, enhancing user motivation to engage in physical activity.

2.3 The Role of Gamification in Learning and Engagement

Deterding, S., Dixon, D., Khaled, R., & Nacke, L. (2011)
Abstract: Gamification applies game design principles to non-gaming contexts to enhance
engagement, motivation, and learning outcomes. This paper explores how points, leaderboards,
challenges, and interactive feedback can improve learning experiences. Various educational and
training environments benefit from gamification by making tasks more rewarding and enjoyable.
The study also discusses the psychological effects of gamification, including intrinsic and extrinsic
motivation.
Conclusion: Gamification is a powerful tool in education and training, offering interactive,
engaging, and motivational experiences. The study concludes that when properly designed,
gamification can enhance learning outcomes, increase user engagement, and drive positive
behavioral changes.

2.4 Motion-Based Fitness Games: Analyzing User Engagement and Health

Benefits
Peng, W., Lin, J., Crouse, J. C., & Chiang, Y. (2019)
Abstract: Motion-based fitness games, such as exergames, are increasingly used to promote
physical activity and improve user engagement. This study analyzes the impact of sensor-based
gaming systems on exercise motivation, energy expenditure, and long-term fitness habits. The
research focuses on systems utilizing IMUs (Inertial Measurement Units) and real-time motion
tracking to create interactive fitness experiences. Findings indicate that active gameplay enhances
exercise adherence and provides a fun alternative to traditional workouts.
Conclusion: The study confirms that motion-based gaming systems improve physical activity
levels and user engagement. The integration of real-time movement tracking and gamification
encourages users to participate in workouts consistently.

6
 CHAPTER 2. LITERATURE SURVEY

2.5 Sensor-Based Wearable Technologies for Fitness Tracking

Patel, S., Park, H., Bonato, P., Chan, L., & Rodgers, M. (2012)
Abstract: Wearable sensor-based fitness tracking devices are revolutionizing personal health
monitoring. This study explores the role of accelerometers, gyroscopes, and IMUs in capturing real-
time movement data for fitness applications. The research highlights the accuracy of sensor-based
systems in tracking steps, motion, and physical activity levels. Wearable devices have significantly
improved engagement in fitness activities by providing real-time feedback and data-driven insights.
Conclusion: The findings support the growing importance of wearable fitness technologies in
personal health monitoring and exercise tracking. These devices offer accurate motion detection,
improve fitness motivation, and enable personalized workout recommendations.

2.6 Gamification in Physical Rehabilitation: A Systematic Review

Lohse, K. R., Hilderman, C. G. E., Cheung, K. L., Tatla, S., & Van der Loos, H. (2014)
Abstract: This paper reviews the application of gamification in physical rehabilitation. Digital
rehabilitation systems that incorporate motion-tracking sensors and interactive gameplay have been
found to increase patient engagement and improve recovery outcomes. The research evaluates
how virtual reality (VR) and gamified physical therapy can make rehabilitation more effective and
enjoyable.
Conclusion: Gamified rehabilitation offers an innovative approach to physical therapy,
enhancing motivation, compliance, and treatment effectiveness.

2.7 Human-Computer Interaction in Wearable Motion Gaming Systems

LaViola, J. J., & Zhai, S. (2017)
Abstract: Wearable motion gaming systems rely on human-computer interaction (HCI)
principles to enhance user experience and responsiveness. This paper explores gesture recognition,
sensor fusion, and real-time feedback mechanisms in wearable gaming. The study focuses on how
motion tracking systems use accelerometers and gyroscopes to improve gaming interactivity.
Conclusion: The research confirms that HCI advancements in motion gaming systems have
significantly improved user experience and engagement.

7
Chapter 3

Analysis / Software Requirements

Specification (SRS)

3.1 Introduction
The purpose of this chapter is to define the Software Requirements Specification (SRS) for the
Motion Spike Wearable Device. This document provides a structured analysis of the project,
outlining functional and non-functional requirements, user interface specifications, and
hardware/software interfaces. The aim is to develop a wearable motion-tracking device that detects
and counts push-ups, jumping, and running, integrating sensors such as the ESP Xiao, ADXL354,
MPU6050, MAX30201, and a magnetometer into a web application.

3.2 Document Conventions

• Font Style: Times New Roman

• Font Size: 12pt (Headings in Bold, Body in Regular)

• Numbering Format: Section numbering follows ”3.x” format for easy reference.

• Terminology:

–”Device” refers to the Motion Spike wearable band.

–”User” refers to individuals wearing the device to track motion-based activities.

–”Sensor Module” refers to the combination of ESP Xiao, ADXL354, MPU6050,

MAX30201, and magnetometer.

–”Web Application” refers to the platform for real-time data analysis.

8
 CHAPTER 3. ANALYSIS / SOFTWARE REQUIREMENTS SPECIFICATION (SRS)

3.3 Recommended Reading for Viewers

To better understand the development and implementation of this project, the following materials
are recommended:

• ESP Xiao, MPU6050, and MAX30201 Datasheets – for understanding sensor

communication.

• TensorFlow Lite for Microcontrollers – for optimizing real-time data processing.

• WebSocket and MQTT Protocols – for real-time data transmission.

• Machine Learning Algorithms for Motion Recognition – to improve detection accuracy.

3.4 Product Scope

The Motion Spike project focuses on real-time motion tracking using IMU sensors and a web-based
platform for data visualization. The core objectives include:

• Accurately detecting and counting push-ups, jumps, and running movements.

• Monitoring heart rate and SpO2 levels using MAX30201.

• Providing real-time feedback through a web-based dashboard.

• Ensuring seamless wireless communication between the wearable device and the web app.

• Offering low-power consumption for prolonged usage.

• Enhancing accuracy through sensor fusion techniques.

3.5 References
• ADXL354 Datasheet

• MPU6050 Datasheet

• MAX30201 Datasheet

• ESP Xiao Development Guide

• IEEE Research Papers on Wearable Motion Detection

9
 CHAPTER 3. ANALYSIS / SOFTWARE REQUIREMENTS SPECIFICATION (SRS)

3.6 User Interfaces

3.6.1 Wearable Device Interface

• LED Indicator: Shows device status (active/inactive, connection status).

• Button Input: For manual calibration or reset.

• Heart Rate & SpO2 Display: Real-time health monitoring using MAX30201.

3.6.2 Web Application Interface

• Dashboard: Displays real-time motion data, heart rate, SpO2 levels, activity logs, and
statistics.

• Graphical Visuals: Bar charts and line graphs for tracking progress.

• Settings Page: Allows users to configure thresholds for motion detection and health
monitoring.

• User Authentication: Secure login system.

3.7 Hardware Interfaces

The hardware components integrated into the system include:

• ESP Xiao: Microcontroller handling sensor data processing and wireless communication.

• ADXL354 Accelerometer: Measures acceleration in three axes.

• MPU6050: Combines gyroscope and accelerometer for motion tracking.

• MAX30201: Monitors heart rate and SpO2 levels.

• Magnetometer: Provides orientation data for improved movement detection.

• Battery Module: Ensures uninterrupted power supply.

3.8 Functional Requirements

1. Motion Detection

• The system should accurately detect push-ups, jumps, and running.

• Sensor fusion techniques should enhance accuracy.

10
 CHAPTER 3. ANALYSIS / SOFTWARE REQUIREMENTS SPECIFICATION (SRS)

2. Heart Rate & SpO2 Monitoring

• MAX30201 should continuously monitor heart rate and SpO2.

• Data should be displayed on both the wearable device and web app.

3. Wireless Data Transmission

• Data must be transmitted from the wearable device to the web app in real time.

• WebSocket/MQTT protocol ensures low latency.

4. Data Logging & Visualization

• The web app should store and visualize activity and health data for user insights.

• Users should be able to filter data based on time range.

5. User Authentication & Profile Management

• Secure login mechanism for personalized tracking.

• User preferences should be saved.

3.9 Other Nonfunctional Requirements

• Performance: The system should process and transmit data with minimal latency (¡50ms).

• Security: Data encryption should be implemented for secure transmission.

• Portability: The wearable device should be lightweight and ergonomic.

• Power Efficiency: The device should run for at least 8 hours on a single charge.

3.10 Software Quality Attributes

• Reliability: The system should function correctly over extended periods.

• Usability: The web application should be intuitive and easy to navigate.

• Scalability: The system should support multiple users simultaneously.

• Maintainability: The software should be modular for easy updates and bug fixes.

11
Chapter 4

System Design

4.1 Introduction
System design plays a crucial role in developing a wearable health monitoring and motion tracking
system. This chapter provides a detailed overview of the hardware and software components, system
architecture, data flow, and implementation details. The system aims to collect real-time health
and motion data, process it using a deep learning model, and display meaningful insights on a web
dashboard.

4.2 System Architecture

The proposed system consists of multiple sensors, a microcontroller, a microprocessor, and a
cloud-based web dashboard. The architecture is divided into three main components:

Figure 4.1: System Architecture

12
 CHAPTER 4. SYSTEM DESIGN

1. Sensor Unit - Responsible for collecting raw data from various sensors.

2. Processing Unit - Includes a microcontroller and a microprocessor to process and transmit

the collected data.

3. Dashboard & Cloud Storage - Displays real-time analytics and logs historical data for
analysis.

4.2.1 Hardware Components

The system integrates the following sensors and hardware components:

• Accelerometer, Gyroscope, Magnetometer: Tracks motion, orientation, and acceleration.

• Heart Rate and SpO2 Sensor: Measures heart rate and blood oxygen levels.

• Temperature Sensor: Monitors body temperature.

• Microcontroller (ESP32/Arduino): Collects sensor data and transmits it wirelessly.

• Microprocessor (Raspberry Pi): Processes data using a deep learning model for activity
recognition.

4.2.2 Software Components

The system is powered by a combination of firmware, machine learning models, and a web interface:

• Embedded Software (C/Python): Runs on the microcontroller to collect and send data.

• Deep Learning Model (TensorFlow/Keras): Classifies different physical activities.

• Web Dashboard (HTML, JavaScript, Flask/Django): Displays real-time health and activity
data.

4.3 Data Flow Diagram

The data flow in the system follows these steps:

13
 CHAPTER 4. SYSTEM DESIGN

Figure 4.2: Base Station (Logic) Flow Chart

14
 CHAPTER 4. SYSTEM DESIGN

Figure 4.3: Wearable Band (Logic) Flow Chart

1. Sensors capture real-time data (motion, heart rate, temperature, etc.).

2. The microcontroller processes the raw data and transmits it to the microprocessor.

3. The deep learning model classifies activities based on motion data.

4. The processed data is sent to the cloud storage.

5. The web dashboard retrieves and displays data for users.

4.4 System Implementation

The system implementation is divided into the following stages:

4.4.1 Sensor Calibration & Data Collection

Each sensor undergoes calibration to ensure accuracy. Data is collected in real-time and stored in
CSV format for model training.

4.4.2 Deep Learning Model Training

A machine learning model is trained using labeled activity data. The model is optimized for
real-time classification.

4.4.3 Dashboard Development

The dashboard provides a user-friendly interface, displaying real-time health metrics and motion
tracking results.

15
 CHAPTER 4. SYSTEM DESIGN

4.5 Block Diagram

The block diagram visually represents the system’s major components and their interactions. It
provides a high-level understanding of the flow of data and processes.

Figure 4.4: Block Diagram

4.5.1 Block Diagram Components

• Input Devices: e.g., sensors, user inputs.

• Processing Unit: e.g., microcontroller, server, cloud computing unit.

• Storage Unit: e.g., database, file system.

• Output Devices: e.g., display, actuators, network responses.

• Communication Links: e.g., wired or wireless protocols.

4.6 Circuit Diagram

The circuit diagram illustrates the electrical connections and components of the system. It helps in
understanding how different hardware components are wired together and interact.

16
 CHAPTER 4. SYSTEM DESIGN

Figure 4.5: Circuit Diagram

4.6.1 Circuit Diagram Components

The components of the circuit diagram include:

• Power supply connections

• Microcontroller or processing unit

• Sensors and actuators

• Input/output devices

• Communication interfaces

4.7 Conclusion
The system design integrates hardware and software to provide a real-time wearable monitoring
solution. By combining sensors, machine learning, and a web interface, users can track their health
and activity efficiently. The next chapter will focus on the system’s implementation details and
performance evaluation.

17
Chapter 5

Methodology

5.1 Overall Approach

The methodology for developing Motion Spike is rooted in iterative design, combining both
hardware prototyping and software refinement. The project follows an agile process where smaller
modules—such as sensor integration, data transmission, and web dashboard visualization—are
developed, tested, and refined continuously. This approach ensures quick feedback and rapid
iteration based on user testing and performance metrics.

1. Requirement Gathering

• Analyzed user needs (ADHD support, physiotherapy, fitness tracking) through literature
reviews and stakeholder discussions.

• Finalized features: motion tracking, posture correction, health monitoring, and gamified
learning.

2. Modular Development

• Separated the system into hardware, firmware, and software modules.

• Allowed parallel work on sensor integration, AI algorithms, and user interface design.

3. Iterative Testing

• Conducted regular tests on sensor accuracy, data latency, and user experience.

• Incorporated feedback to improve posture correction algorithms and game mechanics.

18
 CHAPTER 5. METHODOLOGY

5.2 Hardware Setup

The Motion Spike system integrates advanced sensors and microcontrollers to ensure precise motion
tracking, health monitoring, and real-time data processing. The hardware setup consists of three
main components: Wearable Bands, Base Station, and Web Dashboard.

5.2.1 Wearable Bands

Sensors Configuration

• MPU6050: This sensor combines a 3-axis accelerometer and a 3-axis gyroscope, enabling
accurate detection of linear acceleration, angular velocity, and tilt. It tracks body movement,
posture, and sudden spikes in motion.

• HMC5883L Magnetometer: Enhances orientation tracking by detecting the Earth’s magnetic

field, providing compass-like directional data. This improves posture analysis and helps
prevent sensor drift.

• Additional Sensors: Temperature, heart rate, and SpO2 sensors monitor vital signs to support
health tracking.

Wireless Data Transmission

• ESP-NOW Protocol: The wearable bands use ESP-NOW for fast, low-power, peer-to-peer
data communication, ensuring quick data delivery to the base station without relying on a
WiFi network.

5.2.2 Base Station

Processing Unit

• Microcontroller (ESP32): Acts as the primary receiver, collecting data from the wearable
bands and managing the data stream efficiently.

• Raspberry Pi: Performs advanced data processing, including running machine learning
algorithms for posture correction and movement analysis.

Data Transfer and Communication

• ESP-NOW to UART Pipeline: Data from the wearable bands is received by the ESP32
and forwarded to the Raspberry Pi through UART communication. This ensures seamless,
error-free data transfer for further analysis.

19
 CHAPTER 5. METHODOLOGY

• HDMI Output: The Raspberry Pi outputs processed data to the web dashboard via HDMI,
providing a user-friendly visual interface.

5.2.3 Web Dashboard

User Interface

• Displays real-time health metrics and movement data.

• Visuals include posture tracking models, heart rate graphs, and activity breakdowns.

AI-Powered Analysis

• Deep learning models analyze collected data to detect poor posture, irregular movement
patterns, or fatigue indicators.

• Provides corrective suggestions to improve posture and movement.

Gamified Rehabilitation Support

• Encourages physical activity through interactive games.

• Exercises adapt to the user’s performance, supporting gradual rehabilitation and engagement.

5.3 Software Development

5.3.1 Firmware

• Sensor Data Acquisition:

– The firmware polls IMU data from MPU6050 and HMC5883L sensors at a fixed sampling
rate (e.g., 50–100 Hz).

– Reads heart rate and SpO data at intervals defined by the MAX30201’s specifications.

• Signal Filtering & Calibration:

– Implements low-pass filters to reduce noise in acceleration, gyro, and magnetometer

signals.

– Calibration routines for orientation and offset correction ensure accurate posture
detection.

• Data Encoding & Transmission:

– Uses ESP-NOW for wireless data transfer to the base station, ensuring low latency and
minimal packet loss.

20
 CHAPTER 5. METHODOLOGY

5.3.2 Web Application & Dashboard

• Front-End (UI/UX):

– Designed with HTML5, CSS3, and JavaScript or a modern framework (React, Vue, etc.).

– Real-time charts display user motion, posture, and health metrics.

– Gamified interfaces (e.g., Dino Jump, Math Battle) use keyboard/mouse or motion inputs
to control on-screen characters.

• Back-End & Database:

– Node.js or Python (Flask/Django) handles incoming sensor data, user authentication, and
data storage.

– A NoSQL or SQL database (e.g., MongoDB, MySQL) records user sessions, health stats,
and progress logs.

5.3.3 Gamification Logic

• Posture Correction Algorithm:

– Compares real-time IMU readings against ideal posture baselines.

– Alerts users through vibration or on-screen cues when deviations exceed a threshold.

• ADHD Gamification:

– Integrates motion-based tasks requiring focus and controlled movements (e.g., jumping
in place to make a character jump on screen).

– Adjusts difficulty based on user performance to keep them engaged and challenged.

5.4 Data Processing & Analysis

• Sensor Fusion:

– Combines accelerometer, gyroscope, and magnetometer data to derive precise orientation

and motion vectors.

– A Kalman filter or complementary filter helps smooth out noise and drift.

• Motion Recognition:

21
 CHAPTER 5. METHODOLOGY

– Identifies specific movements (push-ups, jumping, running) using threshold-based

detection or machine learning classifiers.

– Logs each recognized movement event in the database.

• Real-Time Feedback & Insights:

– Processes data every few milliseconds to offer immediate posture correction cues.

– Stores aggregated data for long-term trend analysis.

5.5 Evaluation & Testing

• Unit Testing:

– Tested each sensor module independently to validate data accuracy and communication
protocols.

• Integration Testing:

– Combined hardware and firmware to ensure seamless data flow from sensors to the web
dashboard.

• User Testing:

– Recruited ADHD-diagnosed children, physiotherapy patients, and fitness enthusiasts for

pilot trials.

– Collected feedback on usability, comfort, and engagement.

5.6 Ethical & Safety Considerations

• User Data Privacy:

– All personal and health data is encrypted and stored securely.

• Medical Advice Disclaimer:

– Motion Spike is not a replacement for professional medical advice; it is a supplementary

tool for therapy and fitness.

• Physical Safety:

– Encourages proper warm-ups and cool-downs to prevent injuries during motion-based

exercises.

22
 CHAPTER 5. METHODOLOGY

5.7 Implementation Timeline

• Month 1–2:

– Hardware prototyping, sensor selection, and basic firmware development.

• Month 3–4:

– Web dashboard design, AI posture correction algorithm implementation, preliminary

user testing.

• Month 5–6:

– Integration testing, bug fixes, and performance optimizations.

– Expanded user trials with ADHD children and rehabilitation patients.

• Month 7–8:

– Final refinements, documentation, and readiness for a pilot study or product launch.

23
Chapter 6

Implementation

6.1 System Architecture

Motion Spike’s implementation is divided into three main components—Wearable Bands, Base
Station, and Web Dashboard—linked by low-latency wireless communication and AI-driven data
analysis.

6.2 Hardware Implementation

6.2.1 Wearable Bands

• Sensors:

– MPU6050: Tracks tilt, rotation, and movement.

Figure 6.1: MPU6050 Module

– HMC5883L: Adds orientation data for posture analysis.

Figure 6.2: HMC5883L Module

24
 CHAPTER 6. IMPLEMENTATION

– Heart Rate & SpO2 Sensors: Monitors health metrics during activity.

Figure 6.3: MAX30201 Module

• Microcontroller (ESP XIAO-C3): Collects and pre-processes sensor data, then sends packets
via ESP-NOW.

• Physical Enclosure: Lightweight, comfortable design to suit children with ADHD and users
needing extended wear.

6.2.2 Base Station

• ESP-WROOM-32: Receives data from the wearable bands and communicates with the
Raspberry Pi via UART.

Figure 6.4: ESP-WROOM-32

• Raspberry Pi:

– Runs sensor fusion algorithms (Kalman/Complementary filters).

– Hosts AI models for posture correction and ADHD motion detection.

– Outputs processed data to the web dashboard.

25
 CHAPTER 6. IMPLEMENTATION

Figure 6.5: RASPBERRY PI 4

IMAGES OF BAND

Figure 6.6: Band-1 Image

26
 CHAPTER 6. IMPLEMENTATION

Figure 6.7: Band-2 Image

Figure 6.8: Band-3 Image

27
 CHAPTER 6. IMPLEMENTATION

6.3 Software Implementation

6.3.1 Firmware

• Sensor Polling: Acquires data from MPU6050, HMC5883L, and vital sign sensors at defined
intervals.

• Filtering & Calibration: Reduces noise, aligns sensor axes, and normalizes readings.

• ESP-NOW Transmission: Sends processed data frames to the base station in near real-time.

Figure 6.9: ESP-NOW Protocol

28
 CHAPTER 6. IMPLEMENTATION

Figure 6.10: Transmitter Code

29
 CHAPTER 6. IMPLEMENTATION

Figure 6.11: Receiver Code

30
 CHAPTER 6. IMPLEMENTATION

6.3.2 AI & Gamification

• Posture Correction: Identifies suboptimal angles or orientations, prompting corrective

actions.

• ADHD-Focused Algorithms: Detects fidgeting, hyperactivity, or inactivity, suggesting mini-

games or breaks.

• Gamified Rehab: Offers exercises that reward steady movements and discourage abrupt,
impulsive motions.

Figure 6.12: Motion Mapping Graph

31
 CHAPTER 6. IMPLEMENTATION

Figure 6.13: Motion Detection Code

32
 CHAPTER 6. IMPLEMENTATION

6.3.3 Web Dashboard

• Real-Time Visualization: Displays orientation, health metrics, posture alerts, and ADHD
movement flags.

• Interactive Controls: Lets caregivers or users set thresholds, difficulty levels, or therapy
goals.

• Session Logging: Archives user performance data for long-term tracking and analysis.

• IMAGES OF WEB PAGES

Figure 6.14: Home Screen

Figure 6.15: Web-Page Gallery

33
 CHAPTER 6. IMPLEMENTATION

Figure 6.16: Dino Game

Figure 6.17: Math-Battle Game

6.3.4 Testing & Debugging

1. Unit Tests: Confirm sensor readings match expected values under controlled conditions.

2. Integration Tests: Validate data flow from wearable bands → base station → web dashboard.

3. User Testing: Conduct short trials with ADHD children, rehabilitation patients, or fitness
enthusiasts to gauge usability and comfort.

4. Performance Metrics: Measure system latency, battery life, and accuracy in detecting posture
errors and ADHD-related motions.

6.3.5 Observations & Improvements

• Latency Reduction: ESP-NOW consistently delivers low-latency performance, essential for

real-time feedback.

• Battery Optimization: Duty cycling sensor polling intervals prolongs battery life without
sacrificing accuracy.

34
 CHAPTER 6. IMPLEMENTATION

• Enhanced Engagement: Gamified exercises significantly increase user adherence and

enjoyment.

35
Chapter 7

Conclusion

7.1 Conclusion
The Motion Spike project set out to create a holistic wearable solution for tracking motion,
monitoring health metrics, and supporting therapy—particularly for ADHD and rehabilitation. By
combining MPU6050 and HMC5883L sensors for accurate motion detection, vital sign monitoring,
and ESP-NOW for low-latency communication, the system delivers real-time posture correction
and interactive learning experiences.
Through iterative methodology and implementation, Motion Spike has demonstrated the
following key outcomes:

1. Improved Posture & Motor Skills: Real-time feedback and sensor fusion help users maintain
proper form, reducing injury risks and enhancing movement control.

2. ADHD-Friendly Engagement: Gamified tasks and motion alerts keep children with ADHD
focused and motivated, transforming therapy sessions into engaging, goal-oriented activities.

3. Seamless Data Flow & Analysis: ESP-NOW ensures near-instant data transmission from
wearable bands to the base station, where motion tracking and posture correction insights are
generated.

4. Scalable & Versatile Design: The system’s modular approach enables easy expansion into
additional features, such as VR integration, advanced physiotherapy modules, and broader
fitness applications.

5. User-Centric Interface: The web dashboard offers a clean, intuitive layout, allowing users,
caregivers, and therapists to monitor progress, adjust settings, and access historical
performance data.

36
 CHAPTER 7. CONCLUSION

Overall, Motion Spike successfully addresses health, fitness, and cognitive challenges through
real-time motion tracking, interactive gamification, and posture correction. The positive feedback
from early user trials indicates its potential for broader adoption in educational settings, rehabilitation
clinics, and home therapy programs.

37
Chapter 8

Future Work

8.1 Future Enhancements

8.1.1 Enhanced Sensor Arrays

Why: Adding more sophisticated sensors—such as electromyography (EMG) to measure muscle

activity—can capture subtle details about user movements, helping to identify muscle fatigue or
imbalances more precisely. How: Upgrading to advanced IMUs with higher sampling rates and
lower noise allows Motion Spike to track rapid movements or small changes in posture with greater
accuracy, providing improved feedback for users and therapists.

8.1.2 Cloud Integration

Why: Storing user data on a secure cloud platform enables real-time remote monitoring, making
it easier for caregivers and therapists to support users without requiring in-person sessions. How:
Implementing a secure API (Application Programming Interface) or database solution allows
streaming and storing of sensor data. Authorized users can log in from anywhere to review progress,
download reports, and adjust therapy protocols as needed.

8.1.3 Expanded Rehabilitation Modules

Why: Different injuries or conditions (e.g., knee surgery recovery, spinal cord rehabilitation)
require specialized exercises. Providing a broader range of therapy options increases Motion Spike’s
utility in clinical and home settings. How: Creating custom motion-based exercises, along with a
progress-tracking feature for physiotherapists, ensures that users receive personalized, goal-oriented
rehabilitation programs with clear milestones.

38
 CHAPTER 8. FUTURE WORK

8.1.4 User Personalization

Why: Every individual has unique fitness levels, medical conditions, and learning styles. Tailoring
Motion Spike’s feedback and difficulty settings to each user makes the system more effective. How:
Adding user profiles with adjustable thresholds for posture alerts, exercise intensity, or rest intervals
ensures that the experience remains neither too easy nor too challenging.

8.1.5 Improved Learning & ADHD Support

Why: Children with ADHD benefit from varied and interactive activities that maintain their
attention. By expanding motion-based learning games, Motion Spike can help develop cognitive
skills alongside physical fitness. How: Designing new mini-games that focus on math, language,
or problem-solving skills in a motion-based format keeps the experience fresh and educational,
improving long-term engagement.

8.1.6 Wider Market Applications

Why: Beyond clinical rehabilitation and ADHD therapy, Motion Spike’s motion-tracking features
can be beneficial in corporate wellness programs and general fitness. Expanding into these markets
can help more people stay active and maintain proper posture at work. How: Collaborating with
corporate wellness providers or developing specialized modules for office exercises and posture
reminders helps integrate Motion Spike into daily routines, even for non-clinical users.

8.1.7 Longitudinal Data Analysis

Why: Collecting data over an extended period (weeks or months) can reveal trends in posture, motor
skills, and cognitive development. This is crucial for tailoring therapy plans and understanding
long-term effects. How: Storing user data and using analytical tools (such as statistical methods or
machine learning) to identify patterns or improvements over time can help refine therapy strategies
and predict future challenges.

39
References

1. J. C. Paiva, J. P. Leal, and R. Queirós, “Enhancing Programming Practice: A Game-Based

Coding Challenge Environment,” Proceedings of the International Conference on Learning
and Teaching in Computing and Engineering (LaTiCE), 2020, pp. 1–8. [Online]. Available:
https://drops.dagstuhl.de/storage/01oasics/oasics-vol081-icpec2020/OASIcs.ICPEC.2020.
18/OASIcs.ICPEC.2020.18.pdf

2. A. Malviya, J. E. Joy, and A. Phate, “Wearable Gaming Systems for Fitness Motivation,”
International Journal of Interactive Multimedia and Artificial Intelligence, vol. 5, no. 2, pp.
45–52, 2023.

3. S. Deterding, D. Dixon, R. Khaled, and L. Nacke, “Gamification: Toward a Definition,”

Proceedings of the CHI Conference on Human Factors in Computing Systems, 2011, pp.
1–4. [Online]. Available: https://gamification-research.org/wp-content/uploads/2011/04/
02-Deterding-Khaled-Nacke-Dixon.pdf

4. W. Peng, J. Lin, J. C. Crouse, and Y. Chiang, “Active Video Games for Improving Health-
Related Physical Fitness in Older Adults: A Systematic Review,” Journal of Aging and
Physical Activity, vol. 27, no. 4, pp. 647–661, 2019. [Online]. Available: https://www.ncbi.
nlm.nih.gov/pmc/articles/PMC11061467/

5. S. Patel, H. Park, P. Bonato, L. Chan, and M. Rodgers, “A Review of Wearable Sensors and
Systems with Application in Rehabilitation,” Journal of NeuroEngineering and Rehabilitation,
vol. 9, no. 1, 2012. [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/22520559/

6. K. R. Lohse, C. G. E. Hilderman, K. L. Cheung, S. Tatla, and H. Van der Loos, “Gamified

Neurorehabilitation Strategies for Post-Stroke Motor Recovery: A Systematic Review,”
Frontiers in Human Neuroscience, vol. 8, 2014. [Online]. Available:
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8917333/

40
 CHAPTER 8. FUTURE WORK

7. J. J. LaViola and S. Zhai, “A Comparative Study of Hand-Gesture Recognition Devices for

Games,” Proceedings of the ACM Symposium on User Interface Software and Technology
(UIST), 2017, pp. 1–10. [Online]. Available: https://par.nsf.gov/servlets/purl/10174270

8. C. Anderson, “The Impact of Gamification on Students’ Learning, Engagement and Behavior

Based on Their Personality Traits,” Smart Learning Environments, vol. 6, no. 1, 2019.
[Online]. Available: https://slejournal.springeropen.com/articles/10.1186/s40561-019-0098-x

9. M. S. Caroux, G. Isbister, and M. H. Denis, “A Survey on Gamification for Health

Rehabilitation Care Applications: Opportunities and Open Challenges,” Information, vol. 12,
no. 2, 2021. [Online]. Available: https://www.mdpi.com/2078-2489/12/2/91

10. Y. Xu, L. Liu, and R. Sun, “Smart Wearable Systems for Health Monitoring,” Sensors, vol.
23, no. 5, 2023. [Online]. Available: https://www.mdpi.com/1424-8220/23/5/2479

11. P. R. Haddad, T. Brown, and K. Williams, “A Play-Based Intervention for Children with
ADHD: A Pilot Study,” Journal of Attention Disorders, vol. 16, no. 6, pp. 527–537, 2012.
[Online]. Available: https://pubmed.ncbi.nlm.nih.gov/21770958/

12. L. G. Reiner and J. A. Martin, “Is This the Real Life, or Is This Just Laboratory? A Scoping
Review of IMUs in Running Gait Analysis,” Sensors, vol. 22, no. 5, 2022. [Online]. Available:
https://www.mdpi.com/1424-8220/22/5/1722

13. S. K. Gupta and P. Malhotra, “The Impact of Gamification on Students’ Motivation: A

Systematic Literature Review,” Journal of Educational Technology Systems, vol. 50, no. 1, pp.
113–130, 2021.

41