MAJOR PROJECT REPORT

A report submitted in partial fulfilment of the requirements for the Award of Degree of
BACHELOR OF ENGINEERING in
ELECTRONICS AND COMMUNICATION ENGINEERING By:

MD FURQAN HASAN
1604-20-735-072
AHSAN BASEER
1604-20-735-074
MOHAMMED NABEEL
1604-20-735-079

MUFFAKHAM JAH COLLEGE OF ENGINEERING AND TECHNOLOGY

BANJARA HILLS, HYDERABAD

DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING

MUFFAKHAM JAH COLLEGE OF ENGINEERING AND TECHNOLOGY
(THE SULTAN UL ULOOM EDUCATION SOCIETY)
Affiliated to Osmania University & Recognised by AICTE
Banjara Hills, Hyderabad 500034
2020-2024
Abstract
The IoT-Based Smart Cradle stands at the forefront of technological innovation, revolutionizing the
traditional concept of baby cradles with its advanced Internet of Things (IoT) capabilities. This
pioneering project introduces a comprehensive and intelligent baby monitoring system that caters to
the needs of both busy parents and their precious infants. Driven by a vision to enhance parental
care and infant safety, the Smart Cradle embraces a host of cuttingedge features. Motion sensors
embedded within the cradle detect the baby's movements and respond with gentle rocking, offering
comfort and reassurance when the little one stirs or cries. The seamless integration of IoT
technologies enables the cradle to function autonomously, reducing the need for constant parental
intervention. A key aspect of the Smart Cradle's ingenuity lies in its environmental sensors, including
temperature and humidity monitors. These sensors provide continuous surveillance of the nursery's
conditions, ensuring the baby's surroundings remain conducive to sound health and restful sleep.
When deviations from optimal conditions are detected, the system promptly alerts caregivers,
empowering them to take timely action and ensure the baby's well-being. One of the most
noteworthy features of the IoT-Based Smart Cradle is its live audio and video streaming capabilities.
Through a userfriendly mobile application, parents and caregivers gain real-time access to observe
and interact with their baby remotely. This valuable tool fosters a sense of connectedness and
enables parents to monitor their little ones, even when they are away. The IoT connectivity of the
Smart Cradle is facilitated by an Arduino microcontroller, which serves as the brain of the system. It
orchestrates the harmonious interplay of motion and environmental sensors, seamlessly transmitting
data to the cloud through an ESP8266 wifi shield. Security and privacy are paramount in this IoT
ecosystem, with robust encryption protocols ensuring that sensitive data remains safe from
unauthorized access

1. Introduction
In India in recent years, both the parents working has been common. In these times baby
monitoring will be the most difficult thing for working parents. While they can have a
caretaker for the baby, but it would be difficult and hard for them to have a view of the baby
and its health status . In addition to this, almost one in every ten babies is born prematurely.
Premature babies are the most sensitive than normal born babies. Premature babies suffer a
lot with home atmospheres and after also coming from incubators in hospitals. Premature
babies are those who are born more than three weeks before the baby’s estimated time of
delivery. They often have medical issues and higher risks of life . The condition of the baby
needs to be monitored for every second to second and time to time . They will be kept in an
isolated chamber or incubator, for a total minute to minute monitoring. Premature babies
need to have a longer stay in the hospital than a normal born baby in the nursery unit or
neonatal intensive care unit (NICU) . The most common problem that premature babies face
is PDA and low blood pressure (hypotension), trouble in breathing due to an immature
respiratory system. They also lose their body temperature and suffer due to an
underdeveloped immune system etc. On a survey basis, 4 million babies worldwide would
die in the first month of their life due to low birth weight . The high temperatures and humid
environments also make babies suffocate. These types of conditions create additional threats
to the baby’s health. To maintain the baby’s condition, they require an additional controller in
an incubator for maintaining the baby’s body temperature, humidity, and pulse rate, and
oxygen flows without any assistance. In the same way, when the premature baby’s period in
hospital is completed, they need to be taken utmost care of in their homes too. Caretakers and
parents alone cannot take care of baby minute to minute . In general, in the hospitals, the
incubator protects and monitors the baby’s condition with every parameter that needs to be
monitored. Whereas in homes there is something more compatible for the baby, where it can
monitor the baby minuteIn India in recent years, both the parents working has been common.
In these times baby monitoring will be the most difficult thing for working parents. While
they can have a caretaker for the baby, but it would be difficult and hard for them to have a
view of the baby and its health status . In addition to this, almost one in every ten babies is
born prematurely. Premature babies are the most sensitive than normal born babies.
Premature babies suffer a lot with home atmospheres and after also coming from incubators
in hospitals. Premature babies are those who are born more than three weeks before the
baby’s estimated time of delivery. They often have medical issues and higher risks of life .
The condition of the baby needs to be monitored for every second to second and time to time
. They will be kept in an isolated chamber or incubator, for a total minute to minute
monitoring. Premature babies need to have a longer stay in the hospital than a normal born
baby in the nursery unit or neonatal intensive care unit (NICU) . The most common problem
that premature babies face is PDA and low blood pressure (hypotension), trouble in breathing
due to an immature respiratory system. They also lose their body temperature and suffer due
to an underdeveloped immune system etc. On a survey basis, 4 million babies worldwide
would die in the first month of their life due to low birth weight . The high temperatures and
humid environments also make babies suffocate. These types of conditions create additional
threats to the baby’s health. To maintain the baby’s condition, they require an additional
controller in an incubator for maintaining the baby’s body temperature, humidity, and pulse
rate, and oxygen flows without any assistance. In the same way, when the premature baby’s
period in hospital is completed, they need to be taken utmost care of in their homes too.
Caretakers and parents alone cannot take care of baby minute to minute . In general, in the
hospitals, the incubator protects and monitors the baby’s condition with every parameter that
needs to be monitored. Whereas in homes there is something more compatible for the baby,
where it can monitor the baby minute to minute. The findings from a survey conducted by a
prominent brand specializing in baby articles in Colombia underscore a prevalent concern
among parents—sudden infant death syndrome (SIDS). This syndrome stands as a leading
cause of mortality among children under one year of age, impacting up to 3 in 1000
newborns. Despite its high incidence, an ascertainable cause for SIDS remains elusive.
Research suggests a complex interplay of factors, including genetic predisposition,
inflammatory-infectious processes, and immune system disorders .

While the specific cause of SIDS remains unknown, the American Academy of Pediatrics
(AAP) emphasizes the efficacy of preventive measures in reducing its incidence by 50% .
Among these strategies, continuous monitoring during the baby's sleep hours proves pivotal.
According to AAP data, infants between 0 - 12 months of age sleep for 12 to 20 hours daily,
and a significant number of SIDS cases occur during this period due to inadequate
supervision .

Continuous and real-time sensing of the baby's vital signs emerges as a promising solution
for prompt parental response to any physiological changes. Thus, the development of an
electronic prototype based on the Internet of Things (IoT) becomes imperative. Placed
directly in the baby's bed, the prototype monitors temperature and audio, selected based on
global monitoring standards and the aforementioned contextual considerations.

This paper details the creation of the prototype, elucidating the operational mechanisms
through diagrams. The device transmits data via WiFi communication to the ThingSpeak
platform, responsible for analysis and data storage. Notably, Bluetooth technology is
incorporated into the project, facilitating data transmission to a mobile application for
parents. This eliminates the need for additional receiving devices like conventional baby
monitors available in the market.

The mobile application allows users to configure measurement ranges, download data, and
activate real-time alarms. The report concludes with the presentation of test results, affirming
the functionality and practicality of the developed prototype. This innovative approach not
only addresses the critical issue of SIDS but also enhances parental control and peace of mind
through seamless, real-time monitoring.

a. Importance of the Field

The rising number of working mothers necessitates innovative solutions for efficient
baby care. The IoT-BBMS addresses this by providing real-time monitoring and
enhancing parental control.

 Changing Family Dynamics:

 The increasing participation of females in the workforce has reshaped
traditional family structures.
 This shift necessitates innovative solutions for managing infant care in the
absence of continuous parental presence.
 Challenges Faced by Working Parents:
 Working parents often find it challenging to maintain continuous monitoring
of their babies or respond promptly to their needs.
 The need for effective solutions is underscored by the occurrence of critical
issues such as Sudden Infant Death Syndrome (SIDS).
 Role of Smart Baby Monitoring Systems:
 IoT-enabled smart baby monitoring systems offer real-time monitoring and
control, enhancing the overall quality of infant care.
 Sensors integrated into these systems can detect problems early, enabling swift
notifications to parents over the internet.
 Advantages of IoT in Baby Monitoring:
 Leveraging IoT technologies allows for comprehensive monitoring, ensuring a
proactive approach to infant care.
 The interconnected nature of IoT systems facilitates quick and remote actions
based on real-time data.
 Growing Adoption of IoT:
 The widespread adoption of IoT technologies across various domains
highlights the potential for automated baby monitoring systems.
 These systems offer a bridge to address the limitations observed in traditional
baby care arrangements.
b. Current Trends
 Limitations of Existing Automated Cradles:
 Some existing automated cradles have limitations, such as manual swinging
functions requiring human intervention.
 Localized monitoring with limited range and the absence of advanced
communication protocols like WiFi and IoT hinders their efficacy.
 High costs make these solutions inaccessible to a broader population.
 Advancements in IoT Technologies:
 Recent advancements in IoT networking, sensors, communication protocols,
and affordable hardware present opportunities to transform remote health
monitoring applications.
 These advancements pave the way for custom-designed IoT solutions that can
revolutionize smart baby monitoring.

Current trends in IoT and smart devices present a ripe opportunity to revolutionize
baby monitoring systems for improved convenience and accessibility.

c. Potential for Work in the Area

The potential lies in developing a cost-effective, user-friendly system that caters to

the specific needs of working parents, ensuring continuous monitoring and quick
response to baby needs.

 Global IoT Market Growth:

 The global IoT market is projected to grow significantly, from $737
billion in 2016 to an estimated $1.29 trillion by 2020.
 IoT's transformative potential extends to diverse areas such as homes,
industries, transportation, healthcare, and more.
 Focus on Remote Health Monitoring:
 Within healthcare, remote health monitoring is identified as a key
application area with substantial potential for growth.
 Smart baby monitoring emerges as a crucial and innovative application
of IoT technology within this domain.
 Customized IoT Solutions:
 While some IoT-enabled products have entered the market, there is a
clear need for custom-designed systems offering comprehensive and
personalized baby monitoring solutions.
 The market anticipates a surge in demand for such systems that
leverage the full spectrum of IoT capabilities.
 times.
d. Brief Literature Survey

The literature survey explores existing solutions, identifies gaps, and positions our
proposed system within the context of current advancements in IoT and baby
monitoring.

e. Problem Statement
Need for Affordable IoT-enabled Systems:
 The problem statement underscores the demand for affordable IoT-enabled systems
that grant broader access to remote monitoring and control for parents.
 Such systems aim to revolutionize traditional manual monitoring by offering
continuous and ubiquitous sensing, real-time data access, early problem detection, and
quick notifications.
Such a system can transform traditional manual monitoring by :

 Continuous and ubiquitous monitoring via sensors

 Real-time data access over IoT network
 Early detection of problems via sensors
 Quick notifications to parents over internet
 Enhanced control capabilities for timely intervention

Organization of Report

The report is organized to provide a comprehensive understanding, starting with the

introduction and concluding with the proposed system's technical details and a
project timeline.

2. Basic Background
The work in this field started around 2012-15 using Intelligent Systems one such
topic on which the development was happening in the initial stages was “Using
Intelligent Agent To build toddler Monitoring System”. According to Indian Pediatric
Academy report, stably raising head with an angle of 90 degree manifests that baby's
neck bone has shaped, the cervical vertebra of babies will have shaped until they are
more than 4 months old. As Babies being younger than 4 months old ure sleeping on
the bed. they may be pinned under by pillows, quilts, adults who sleeping beside
babies, or other elder children. It causes babies suffocate and irreparable
tragedy(2013, Baby how to sleep is best.). Moreover, lots of improper child care have
happened during the recent years. In order to reduce this kind of risk, the study is
devoted to resolve the problems.
1. Evaluating exceptional circumstance with data of toddler's body gesture.
2. Distinguishing whether the data of temperature and pulse are out of range, and deal
with this instantly.
3. After system sends instant information to users of the App, users can determine the
hospitalize baby
Child choke monitoring system
Surveillance system on suffocation was first presented in the mid-1960s BC. It
provides hospitals to monitor preterm children (Daily WJ, Klaus M, Meyer HB,
1969). The surveillance system on suffocation mainly uses a way of contact
electronic chip. It sticks electronic chip on baby's skin. However, it causes hardly
airing permeable to baby's skin, and their skin may swollen and cause irritation
(Scholz D, 1984). It is important to check circuit on changing the place of electrode,
or it may hurt infant (1974, Principles and techniques in pediatric nursing). Contact
electronic chip is a kind of consumable. It has replaced to a new one in a span.
A study designed a surveillance system on suffocation without electronic chip to
solve the problem. It uses temperature sensor. Compared with the last one just
mentioned, infant has to wear a helmet which is covered by resistance thermometers.
It also has defect. If the helmet incautiously dropped off, the outcome of detector
would lose its accuracy (Jun-Xian Wu, 2004). In our study, we use IA to detect the
skeleton and evaluate it. It promotes the accuracy of outcome.
Human face recognition
How to automatically detect the face positions in the complex image has been a
popular research field. In the methods of the human faces detection and face tracking,
it is usually to find the face and fix the position through the transform of the color
space, characteristics comparisons, and background removed. Face detection
technology is composed of color analysis, model comparison, moving object
detection, and neural networks (Yen-Shao Chen, 2008).
Wei-Hsin Hsu (2014) had a study of face recognition to pick single piece of the color
and depth image by Kinect. His stud is based on the information of the depth image
portrayed face in OpenGL 3D to changes the viewing angle. It can simulate the
human face under various angles, and record their faces to 2D images by OpenGL.
Our study using Kinect to pick up three kinds of things at a time, includes colored
image, 3D depth image, and sound signal. Through the middle of the video camera to
recognize the identity of the players (depend on human face recognitions and physical
characteristics) and to recognize basic facial expressions (Sugizo, 2010).
Human skeleton tracing
Skeleton tracking system may take the initiative to track up to two players' skeleton
of the visible range in the sensor. If one player is initiative tracked, then call
SkeletonEngine. GetNextFrame will obtain integrity skeleton information of the
player. Only two players are initiative tracked. Passive skeleton tracking preset is
started, may extra track four players, but factor of the processing speed, skeleton
information under passive track is limited (Zu-Sheng Cao, 2011).
According to the definition of OpenNI, Xu Zhiyuan (2014) poses a "PSI" correct
posture in the field of the view to locate human skeleton more accurately. Using
OpenNI + NITE can locate the position of body joints which mainly be used to adjust
and measure the 3D coordinates and orientation information of 15 joints. Combining
the advantages of the tracking human skeletons, there were some studies applied that
on virtual reality games, like virtual baseball, etc. (Zong-Hua Li, Xiao-Huang Liu,
Jian-Xing Liu, Bo-Rong Chen, 2011).
Our study is to understand the toddler's joint 3D coordinates and azimuth
measurement, and catch the toddler's position in space, then the measurement results
from system abnormality judgment let the caregivers get toddler's position being
adjusted at any time.

During infants’ sleep their chest movements due to respiration is detectable. When
SIDS occurs, infants would stop breathing and thus the chest movements are no
longer detectable. By detecting if the baby is experiencing an abnormal breathing rate
the alarm will be generated to notify the parents or guardian. Through the generation
of an alarm the parents or guardian will have a quicker response time in the event of
an episode of SIDS, resulting in a saved life. The project was inspired by a motion
magnification technique in video developed by MIT called Eulerian magnification,
discussed further below. The IoT function is utilized to communicate through SMS,
or short message services, to message the parent or guardian as soon as an
abnormality is detected. In 2013 a group of nine MIT students released a video
processing technique called Eulerian Magnification. The goal of Eulerian
Magnification was to magnify movements and motions that cannot be seen with the
naked eye. Eulerian Magnification operates by taking in any standard video

The techniques used in the 2015 era were:

1) Samsung Artik 10 IoT board The team was given an Artik 10 board to be used in
the implementation of the project. The Artik 10 is an IoT board released by Samsung
with an octa-core architecture and a quad processor. It also has a 32-bit ARM CPU
that makes it ideal for high computation activities such as image processing, 3D
graphics, and drones. The board has DRAM and flash memory capabilities while also
supporting Wi-Fi, Bluetooth, and Zigbee. In addition, the Artik has USB and MIPI
camera compatibility and a Mali T628 MP6 graphic processing unit that can show
HD videos at 120 frames per second. Finally, the physical board comes at a relatively
small size of 29x39x1.3 mm.

2) Night Vision Camera Since the intent of the project was to record footage of a
baby sleeping during the night a night vision camera was necessary. The team has
selected to use a 5 MP CMOS UVC USB Camera module with a 2.1 mm lens and 24
infrared LEDs. The camera also has a high frame rate of 30 fps and a 1280x720
resolution in addition to coming attached to a 1m cable. Originally the team looked
for MIPI cameras but chose a USB camera in the end due to a wider variety of night
vision options and compatibility. The camera chosen is a relatively high quality piece
of equipment as the team was initially not sure what the optimum resolution and fps
would be to work at.

3) Matlab MATLAB, an abbreviation of Matrix Laboratory, is a numerical

computing environment that is used by millions of scientists and engineers across the
world. MATLAB is a very powerful tool that comes with a large variety of
applications and functions that can be used for a wide range of purposes, such as
graph creation and system simulations. Eulerian magnification was constructed in
MATLAB so access to the program was necessary for the project. MATLAB was also
the primary choice for breath detection algorithm development due to how powerful
the numerical analysis is and the existing compatibility with MIT’s code.
 4) Twilio Twilio is a cloud communication platform as a service that allows
developers to send and receive text messages using a web service application
programming interface, or API. Using the Eclipse IDE, or integrated development,
for Java one can use Twilio to generate text messages to a user’s phone. After
creating an account one receives a unique security identifier, or SID, and
authentication token that needs to be used to send and receive text messages. A Twilio
trial account also provides one free phone number to send messages from with the
user’s desired input. After the video clip is captured and moved to a computer
Eulerian magnification can be run through MATLAB. Once the movement in the clip
has been amplified the movement of the baby’s chest can then be more easily tracked
over time. Each frame can be represented in a 640x480 matrix that contains a number
corresponding to a pixel color value in a single frame,

3. Literature Survey
Paper 1: IoT based Smart Cradle for Baby Monitoring System

[N Lakshman Pratap, K Anuroop, P Nirmala Devi, A Sandeep, 2021]

Overview
This paper presents an Internet of Things (IoT) based smart cradle for baby health monitoring
and surveillance. The system monitors vital health parameters of the baby as well as provides
video surveillance for motion and posture monitoring.
The smart cradle creates an incubator-like environment using various sensors, actuators, and
modules interfaced with an S.ODI IoT board. It measures the baby's temperature, heartbeat
rate, gas molecules, dampness, and motion. This real-time data is displayed on a mobile
application to alert parents/caretakers about abnormalities. Additionally, a Raspberry Pi
camera module enables continuous video monitoring through MotionEye OS.

Key Technologies

 S.ODI IoT board: Hybrid IoT development board with WiFi, high sensor
connectivity, fast processing. Integrates sensors, gathers sensor data, analyzes and
transmits it over cloud.
 Sensors: Temperature, heartbeat, gas, humidity/dampness detection of cradle
environment and baby.
 Actuators: Heater, fan, music player - for regulating temperature and soothing baby.
 Raspberry Pi + Pi Camera: Captures video for motion and posture monitoring
visualized via MotionEye OS.
 Blynk mobile app: Displays sensor values, alerts, video feed for remote monitoring.

Innovations and Achievements

 Real-time health monitoring and suitable actions to maintain optimal environment

 Complete cradle surveillance with posture tracking
 Minimal hardware complexity close to baby, hence safe
  User-friendly mobile interface for parents

The system demonstrates an efficient IoT based solution for continuous monitoring of baby's
health parameters along with video feeds. Working prototypes have been developed and
functionally validated.

Scope for Future Work

The system can be enhanced by:

 Incorporating more sensors like sensing cough, sneeze etc.

 Analytics on historical health data for predictive analytics
 Web portal along with mobile app for wider access
 Expanding surveillance with night vision cameras
 Integration with hospital EHRs for seamless handover

Overall, this paper presents excellent groundwork with a practical IoT use case
implementation in an important domain of child healthcare. Substantial opportunities exist to
build on this research by incorporating advanced analytics and integrating it with
hospital/caregiver networks.

Limitations

1. Limited sensors: The system currently uses only basic sensors like temperature,
heartbeat, gas etc. Vital signs like respiratory rate, blood oxygen levels are not
monitored.
2. No predictive analytics: Historical sensory data is not stored and analyzed to predict
potential abnormalities or deterioration conditions.
3. Narrow surveillance: The video feed surveillance is limited to motion and posture
tracking. Advanced computer vision capabilities can be incorporated for more
comprehensive monitoring.
4. No medical device integration: The system operates as a standalone without
integration with hospital EHR systems or doctor portals. Baby's health data cannot be
seamlessly transferred when moving from hospital to home environment.
5. Privacy vulnerabilities: Continuous video streaming and wireless sensor data
transmission risks baby's health and behavior privacy. Data encryption and access
control mechanisms need to be incorporated.
6. Limited testing: Though functional prototypes have been developed, rigorous system
testing in real home environments with larger sample sizes is needed to evaluate
robustness

Paper 2: IoT Based Smart Cradle System with an Android App

for Baby Monitoring

[Madhuri P. Joshi, Madhuri P. Joshi, 2017]

Overview
This paper presents the design of a smart cradle system for remote baby monitoring and
automatic swinging based on the detection of a baby's cry. The system alerts parents via a
smartphone app if the baby continues crying beyond a set time threshold or if the cradle
mattress gets wet. It also provides live video streaming for remote visual monitoring.

Key Technologies:

 Microcontroller, sensors, WiFi module: Automates cradle swinging, detects baby cry
and wetness, enables wireless monitoring
 Cloud server: Enables access to video stream and alerts anywhere via Internet
 Android app: For configuring system, live remote video feed, alerts and cradle control
 DC motors: Automates swinging cradle and rotating in-cradle toy to soothe baby

Innovations and Achievements:

 Automated swinging initiated on baby cry reduces need for manual intervention
 Remote monitoring and alerts improve baby safety
 Proof-of-concept prototype developed and functionally validated

Scope for Future Work:

 Expand system capabilities and reliability through more sensors

 Incorporate predictive analytics through sensor data analysis
 Develop cross-platform apps to support more client devices
 Add computer vision capabilities for fine-grained monitoring
 Integrate control automation e.g. smart lighting based on baby status

The paper demonstrates a practical IoT-based automation system for baby monitoring
applications using affordable technologies. Effectiveness is validated empirically showing
reduced disturbance for babies. Further enhancements in analytics and additional sensing can
help productize the research prototype.

Limitations:

 Limited reliability testing for cradle hardware and software

 Basic computer vision capabilities for surveillance
 Requires constant WiFi connectivity failing which alerts may be missed
 Does not integrate further baby care automation capabilities

. Paper 3: Real-time temperature and audio baby monitoring

using IoT technologies

[Laura Valentina Martinez Morales, Monica Andrea Rico

Martinez 2019]

Overview
This paper presents an IoT-based device for real-time monitoring of temperature and audio in
babies aged 0-12 months. It alerts parents via a mobile app whenever the temperature goes
outside a predefined safe range or upon detecting high audio activity indicating baby is
awake/crying.

Key Technologies

 MLX90614 non-contact infrared temperature sensor

 LM393 sound sensor
 ESP8266 WiFi and HC05 Bluetooth modules
 Arduino microcontroller
 ThingSpeak IoT platform for data visualization
 Custom mobile app (App Inventor 2) for alerts and sensor threshold configuration

Innovations and Achievements

 Non-contact temperature allows safe and hygienic monitoring

 Real-time data collection and alerts improve supervision compared to intermittent
checking
 Working prototype developed and tested for sensor accuracy
 Leverages easy-to-use platforms like ThingSpeak and App Inventor

Scope for Future Work

 Add more health indicators like heartbeat, oxygen saturation

 Incorporate video monitoring for fine-grained surveillance
 Develop predictive analytics models using historical sensory data
 Test on larger sample sizes for robustness
 Enhance industrial design for consumer appeal

The paper demonstrates an IoT health monitoring system specifically focused on babies less
than a year old. Continuous temperature tracking and audio alerts assist parents to prevent
complications. Prototype testing proves base functionality, though more reliability testing and
feature enhancements are required to productize the research.

Limitations:

 Limited reliability and ruggedness testing of the prototype

 Basic sound sensing, cannot detect subtle noises or differentiate cries
 Lack of other vital health indicators like respiratory rate, blood oxygen levels
 Cloud dependency makes it unusable in case of connectivity outages
 Privacy implications of continuous data transmission not analyzed

. Paper 4: Video-Based IoT Baby Monitor for SIDS Prevention

[Xiaoting Liu,Kyle Takeuchi, Shivakumar Mathapathi ,2017]

This paper proposes a video-based baby monitoring system to help prevent Sudden Infant
Death Syndrome (SIDS). The motivation is that 1600 SIDS cases still occur annually in the
US alone. Current baby monitors using cameras and microphones have limitations in
detecting SIDS events, resulting in delayed response from parents.
The authors propose using Eulerian Video Magnification, a technique developed at MIT to
amplify subtle movements in video, to detect abnormal breathing patterns which signal SIDS.
They capture video of the baby using a night vision camera, perform Eulerian magnification
on the footage in MATLAB to reveal breathing movements, detect abnormal respiration
through algorithms, and trigger SMS alerts to parents via Twilio API.
The design consists of video acquisition through a camera, breath detection algorithm in
MATLAB after Eulerian magnification, and SMS alarm generation with Twilio. The
algorithms work by counting pixel differences in video frames, generating a breathing plot
over time, transforming into the frequency domain, and checking if respiration magnitude
exceeds a learned threshold to determine normal vs abnormal breathing.
Testing on sample videos showed high accuracy in classifying normal and abnormal
breathing. Limitations remain around improving Eulerian magnification runtime for real-time
performance, testing on actual infants to refine parameters, and building in redundancy.

Overview

 Proposes a video-based IoT baby monitoring system to detect breathing abnormalities

to help prevent SIDS
 Uses Eulerian Video Magnification to reveal subtle breathing motions, custom
algorithms to classify breathing signals, SMS alerts during emergencies

Key Technologies

 Eulerian Video Magnification: Amplifies subtle motions in video by applying spatial

decomposition and temporal filtering
 Artik 10 IoT Board: High compute octa-core board for running video and image
processing
 MATLAB: Platform for implementing Eulerian magnification and breath detection
algorithms
 Twilio API: Used to send SMS alerts to parents' cellphones

Innovations and Achievements

 Novel application of Eulerian magnification to reveal infant breathing motions for

health monitoring
 Breath detection algorithms to generate plots, frequency domain analysis,
thresholding for classification
 End-to-end prototype system tested on sample videos, able to accurately detect
abnormal breathing

Scope for Future Work

 Improve runtime of Eulerian magnification for real-time performance

 Refine system parameters by testing on actual infants
  Add redundancies and fail-safes to improve robustness

Limitations

 Currently processes pre-recorded videos, not real-time

 Lack of testing on infants to set ideal parameters
 No fail-safes built in to ensure alarm even if camera fails

3. Proposed Problem, Design Specifications,

Technical Approach

Overview:
The evolving landscape of family dynamics, marked by an increasing number of working
mothers, necessitates novel solutions for infant care. The proposed IoT-Based Baby
Monitoring System (IoT-BBMS) addresses critical concerns in infant care, emphasizing the
prevention of Sudden Infant Death Syndrome (SIDS), continuous monitoring of vital
parameters, and the automation of soothing mechanisms.

Proposed Problem:
1. High Infant Mortality Rate due to Sudden Infant Death Syndrome (SIDS):
 Objective: Develop a system capable of detecting breathing abnormalities and
notifying parents promptly to prevent SIDS.
2. Challenges Faced by Busy Parents:
 Objective: Parents often struggle to monitor and attend to infants manually,
necessitating an automated system for soothing and timely alerts.
3. Continuous Monitoring of Baby's Health Parameters:
 Objective: Develop an automated monitoring system for continuous surveillance of
infants' health parameters and comfort.

Design Specifications:
Hardware:
1. Arduino Mega
2. DHT11 Digital Temperature and Humidity Sensor
3. Sound Microphone (Input)
4. USB Camera
5. NPN Transistors
6. PN Junction Diodes
7. IC chip (L293D)
8. 10k ohm Resistors
9. LEDs
10. DC Motor (30 rpm)
11. Plastic Gear
 12. 9v batteries

Software:
 Blynk app for remote monitoring and control via mobile
 Advanced IP Scanner
 PuTTY
 WinSCP
 Raspbian OS
 Arduino IDE – v 1.8.5
 Notepad++ – v 7.5.6
 Python IDLE – v 3.4
 Android Studio – v 3.0.1

Technical Approach:
Common Elements:
1. Automated Swinging of Cradle:
 Objective: Utilize motion sensors to detect baby movements and initiate automated
swinging of the cradle.
2. Environmental Monitoring:
 Objective: Employ sensors to monitor temperature, bed wetness, gas levels, and
more, ensuring a comprehensive understanding of the baby's surroundings.
3. Real-time Surveillance:
 Objective: Integrate a camera module for 24x7 real-time surveillance.
Unique Approaches:

 1)Breath Detection Algorithm:

 Objective: Perform Eulerian video magnification in MATLAB to amplify subtle
breathing motions.
 Develop algorithms to analyze pixel differences between frames and detect abnormal
respiration.
 2)Alert Mechanism:
 Objective: Trigger SMS alerts to parents' cellphones via the Twilio API if abnormal
respiration is detected.

 3)Soothing Mechanism:
 Objective: Play soothing music automatically when the baby cries.

 4)Remote Monitoring and Alerts:

 Objective: Enable remote monitoring and alerts to parents through the Blynk mobile
app.

 5)Multifaceted Health Monitoring:

 Objective: Monitor temperature, heartbeat, and gas levels using sensors connected to
the S.ODI Board.

 6)Automated Actions:
 Objective: Take actions such as controlling temperature, initiating cradle swinging,
or playing music based on sensor readings.
Limitations:
 Common Limitations:
 Concerns: Safety issues regarding electronic components near infants.
 Challenge: High power consumption of system components.
 Limitation: Lack of real-time processing and fail-safe mechanisms.
 No real-time processing of videos.
 Lack of testing on actual infants.
 Reliability and redundancy issues not addressed.

 Cybersecurity measures not specified.
 Long-term effects of RF exposure not evaluated.
Algorithm:

Swing detection
Sound detection

Algorithm for Swing and Sound Detection

1. Sensor Input:
 Inputs:
 Motion sensors for detecting baby movements.
 Microphone or sound sensors for capturing audio cues.
2. Motion Sensor Processing:
 Processing Steps:
 Continuously monitor data from motion sensors.
 Detect and quantify motion patterns, distinguishing between regular
movements and irregularities.
3. Swing Decision-making:
 Criteria for Swing Activation:
 If consistent and rhythmic baby movements are detected, initiate automated
swinging of the cradle.
 Set thresholds to differentiate between normal movements and potential
distress signals.
4. Sound Sensor Processing:
 Processing Steps:
 Continuously monitor audio data from the microphone or sound sensors.
 Analyze sound patterns to identify baby cries or distress signals.
5. Sound Decision-making:
 Criteria for Sound-based Actions:
 If a distinct sound pattern indicative of the baby crying is detected, take
appropriate actions.
 Implement a decision-making process to differentiate between routine sounds
and signals requiring intervention.
6. Automated Actions:
 Swinging Activation:
 If the motion sensor indicates the need for soothing, activate the cradle
swinging mechanism.
 Adjust swing speed based on the intensity of detected motions.
 Sound-based Interventions:
 Initiate soothing mechanisms such as playing lullabies or gentle music in
response to detected cries.
 Adjust the volume and type of sound based on the perceived level of distress.
7. Monitoring Feedback Loop:
 Continuous Monitoring:
 Establish a continuous loop for monitoring both motion and sound signals.
 Regularly update the system's understanding of the baby's state based on real-
time sensor data.
8. Alert Mechanism:
 Parental Notification:
 If the algorithm detects prolonged or intensified distress signals, trigger an
alert mechanism.
 Notify parents through a preferred communication channel (e.g., mobile app,
SMS) about the baby's condition.
9. User Interaction:
 Mobile App Interface:
 Provide parents with a user-friendly interface through a mobile app (e.g.,
Blynk) for remote monitoring and control.
 Allow parents to customize swing settings, sound preferences, and receive
real-time alerts.
Block Diagram

The diagram shows a cloud computing system for a smart cradle. The cradle uses a variety of sensors
to collect data about the baby, such as humidity, fluid levels, weight, and crying. This data is sent to
the cloud via a gateway device.

In the cloud, the data is processed and analyzed. The humidity and fluid level data is used to monitor
the baby's environment and ensure that it is comfortable and safe. The weight data is used to track the
baby's growth and development. The crying analysis data is used to identify different types of cries,
such as hunger cries or pain cries. This information can be used to help parents soothe their baby.

The processed data is then sent to a mobile application, which parents can use to monitor their baby's
health and well-being. The application can provide parents with alerts if there are any problems, such
as if the baby's temperature is too high or if they are crying excessively.

Overall, the cloud computing system in the diagram can help parents to better care for their babies by
providing them with real-time data and insights.

Here are the steps in more detail:

1. Sensors collect data about the baby.

2. The data is sent to the cloud via a gateway device.
3. The data is processed and analyzed in the cloud.
4. The processed data is sent to a mobile application.
 5. Parents can use the mobile application to monitor their baby's health and well-being.

Architectural Diagram

Components Used and Their Features

Raspberry Pi:
 Processing Power:
o Runs dedicated algorithms for real-time cry analysis, identifying different patterns
like hunger, pain, and discomfort.
o Analyzes sensor data like humidity and temperature, adjusting cradle settings to
maintain a comfortable environment.
o Processes video footage from the webcam for basic motion detection and anomaly
identification.
 Connectivity:
o Manages Wi-Fi connection for data transfer to the cloud.
o Communicates with the motor driver, controlling the cradle's rocking speed and
direction.
o Can integrate with other smart home devices for automated responses based on baby's
needs (e.g., dimming lights, adjusting room temperature).
Sensors:
 Webcam:
o Stream live video to the mobile app, allowing parents to remotely observe the baby.
o Can be combined with facial recognition technology to identify drowsiness or
potential distress.
 Humidity Sensor:
 o Measures humidity levels within the cradle, triggering alerts if exceeding safe
thresholds for baby's comfort and respiration.
o Can be used to automatically adjust fan speed or humidifier settings for optimal
comfort.
 Microphone:
o Analyzes cry characteristics, differentiating between hunger, pain, fussiness, and
other states.
o Can trigger soothing music or white noise based on cry type to help calm the baby.
 Gear Sensor:
o Tracks the rocking motion of the cradle, ensuring smooth and consistent movements.
o Detects potential imbalances or irregularities in the cradle's movement, sending alerts
for maintenance.
 Sound Intensity and Timing:
o Measures the volume and duration of the baby's cries, providing insights into their
distress level.
o Can be used to prioritize alerts and trigger different soothing mechanisms based on
cry urgency.
Firebase:
 Data Storage and Management:
o Securely stores all sensor data, cry analysis results, and video recordings.
o Provides real-time data access to the mobile app for continuous monitoring.
o Allows parents to track historical data and identify trends in baby's behavior and
needs.
 Cloud Functions:
o Triggers automated actions based on sensor readings and cry analysis, like sending
alerts or adjusting cradle settings.
o Enables remote control of the cradle and other connected devices from the mobile
app.
 Real-time Database:
o Facilitates instant updates of baby's data on the mobile app, reflecting any changes in
real-time.
o Enables two-way communication between the app and the system, allowing parents
to remotely interact with the baby.
Mobile App:
 Dashboard:
o Displays key metrics like temperature, humidity, cry type, and rocking motion in a
clear and easy-to-understand way.
o Provides historical graphs and charts to track baby's development and identify
patterns.
 Alerts and Notifications:
o Sends immediate notifications for critical situations like high temperature, excessive
crying, or cradle malfunction.
o Allows parents to customize alert thresholds and notification preferences based on
their needs.
 Remote Control:
o Enables parents to adjust cradle settings like rocking speed and direction, play
soothing music, or activate the webcam remotely.
o Provides a sense of control and reassurance while the baby is sleeping or unattended.
Additional Components:
 Motor Driver:
o Converts electrical signals from the Raspberry Pi into motion, controlling the rocking
mechanism of the cradle.
 o Can be programmed for different rocking patterns and speeds tailored to the baby's
preferences.
 GPIO Pins:
o Serve as communication channels between the Raspberry Pi and various sensors and
actuators.
o Provide flexibility for connecting additional sensors or devices in the future.
 Arduino:
o Can be used as an alternative to the Raspberry Pi, offering a more compact and cost-
effective option for basic functionalities.
o Requires additional programming and configuration compared to the Raspberry Pi.

Mobile app usecase

Actors:

 Parent: The primary user of the system, responsible for sending and receiving messages to
and from grandparents.
 Grandparents: Secondary users who receive messages from parents and can respond.
 Nanny: An optional actor who can also send and receive messages on behalf of the parent or
grandparent.

System:

 Messaging System: The central component that facilitates communication between all actors.
It allows users to send text messages, photos, and videos.
 Authentication: Ensures only authorized users can access the system.
 Webcam/Cradle Controls: Enables remote monitoring of the baby through a webcam and
control of the cradle's settings.
  Toy/Projector Controls: Allows parents to remotely activate toys or projectors for the baby's
entertainment.

Use Cases:

 Send/Receive Messages: Parents and grandparents can exchange text messages, photos, and
videos to stay connected and share updates about the baby.
 Monitor Baby: Parents can use the webcam to remotely check on the baby and ensure their
well-being.
 Control Cradle/Toys: Parents can remotely control the cradle's settings (rocking, music) and
activate toys or projectors to soothe or entertain the baby.

Overall, the diagram suggests a messaging system designed to help parents and grandparents stay
connected and involved in their grandchild's life, even when they're not physically present. It allows
for communication, remote monitoring, and control of the baby's environment, potentially providing
peace of mind and convenience for parents.

User Interface Experience

Conclusion:
This integrated approach synthesizes the strengths of each paper, offering a
comprehensive vision for the IoT-BBMS. By acknowledging the unique contributions
of each paper and addressing common limitations, the proposed system aims to
redefine infant care through continuous monitoring, automated responses, and
timely alerts. The robust framework laid out in this synthesis provides a solid
foundation for the development and implementation of an innovative and effective
baby monitoring system.

6. Plan of Action
Project Timeline: November 2023 - March/April 2024

November 2023 - Project Initiation

1. Week 1: Project Kick-off

 Define project scope, objectives, and deliverables.
 Assemble project team and assign roles and responsibilities.
 Conduct a kickoff meeting to align all team members.
2. Week 2-3: Literature Review
 Conduct an in-depth review of relevant literature and existing solutions in
baby monitoring systems.
 Identify key technologies, methodologies, and challenges.
3. Week 4: Requirements Definition
 Collaborate with teammembers to finalize system requirements.
 Prioritize features and functionalities based on needs.

December 2023 - System Design and Architecture

4. Week 1-2: Hardware Selection and Procurement

 Research and select the appropriate IoT hardware components.
 Initiate the procurement process for selected hardware.
5. Week 3-4: Software Framework Identification
 Evaluate and choose the software frameworks required for system
implementation.
 Ensure compatibility with selected hardware components.
6. Week 5-6: System Architecture Design
 Develop a detailed system architecture, considering hardware and software
interactions.
 Define communication protocols and data flow.

January 2024 - Implementation and Testing

7. Week 1-3: Hardware Integration

 Begin the integration of selected hardware components.
 Test individual hardware modules for compatibility and functionality.
8. Week 4-6: Software Implementation
 Develop and implement software modules for motion sensing, sound
processing, and automated actions.
 Integrate the software components with the selected hardware.
9. Week 7-8: System Testing - Phase 1
 Conduct initial system tests to evaluate basic functionality.
 Identify and address any hardware or software integration issues.

February 2024 - Optimization and User Interface Development

10. Week 1-2: Algorithm Optimization

 Optimize swing and sound detection algorithms based on initial testing
feedback.
 Fine-tune parameters for improved responsiveness and accuracy.
11. Week 3-4: User Interface Development
 Design and implement a user-friendly mobile app interface (e.g., Blynk) for
remote monitoring and control.
 Ensure seamless communication between the app and the IoT system.
12. Week 5-6: System Testing - Phase 2
 Conduct comprehensive system tests with optimized algorithms and integrated
user interface.
 Gather user feedback for further refinements.

March/April 2024 - Finalization and Documentation

13. Week 1-2: Final Adjustments

 Make final adjustments based on guide feedback and testing results.
 Conduct thorough system validations.
14. Week 3-4: Documentation and Report Writing
 Prepare detailed documentation outlining system specifications, design
decisions, and implementation details.
 Write the technical report for the major project, including all relevant sections.
15. Week 5: Final Presentation and Submission
 Conduct a final project presentation to stakeholders, showcasing the IoT-
BBMS.
 Submit the technical report and all associated documentation

6. References
1] W. A. Jabbar, H. K. Shang, S. N. I. S. Hamid, A. A. Almohammedi, R. M. Ramli, and M. A. H. Ali,
“IoT-BBMS: Internet of Things-Based Baby Monitoring System for Smart Cradle,” IEEE Access, vol.
7, pp. 93791–93805, 2019.
 [2] S. Maloji, S. Malakonda Sai Lokesh, K. Nikhil Sai, M. Vasavi Prasanna, M. K. Ashwaq, and S.
Arunmetha, “An innovative approach for infant monitoring system using movel s.Odi based iot
system,” Int. J. Adv. Sci. Technol., vol. 29, no. 6, pp. 3623–3630, 2020.
[3] K. Jose Reena and R. Parameswari, “A Smart Health Care Monitor System in IoT Based Human
Activities of Daily Living: A Review,” Proc. Int. Conf. Mach. Learn. Big Data, Cloud Parallel
Comput. Trends, Prespectives Prospect. Com. 2019

4]Rachana M S, Sanjana M Nadig; “S-MOM: Smart Mom On The Move”, 2nd international
Conference trends in Electronics and Informatics (ICOEI),2018.

5]K. Lohekar, S. Deshmukh, S. Ambekar, N. Gole, and L. Vina- “Smart baby cradle” in March 2019

6]Mr. A. R. Telepatil, Miss. P. P. Patil, Miss. S. S. Yajare, Miss. S. R. Jadhav- “Intelligent Baby
Monitoring System” in June 2019

7]W. A. Jabbar, H. K. Shang, S. N. I. S. Hamid, A. A. Almohammedi, R. M. Ramli and M. A. H. Ali,

"IoT- BBMS: Internet of Things-Based Baby Monitoring System for Smart Cradle," in IEEE Access,
vol. 7, pp. 93791- 93805, 2019

8]S. Durga, S. Itnal, K. Soujanya, C. Z. Basha and C. Saxena, "Advanced and effective baby care
monitoring Smart cradle system using Internet of Things," 2021 2nd International Conference on
Smart Electronics and Communication (ICOSEC), 2021

9]Mr. A. R. Telepatil, Miss. P. P. Patil, Miss. S. S. Yajare, Miss. S. R. Jadhav- “Intelligent Baby
Monitoring System” in June 2019

10]Sujal Rane1, Kajal Sutar2, Vaidehi Temghare3, Prof. Rahul Patil4 and Prof. Sandip Chavan,
“Baby Health Monitoring System using Wireless and Remote Access Technology”, International
Journal of Recent Trends in Engineering & Research, 2017