IOT based safety management for elderly people

A MiniProject report submitted in partial fulfillment of the

requirements for the award of the degree of
BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE AND ENGINEERING
Submitted by

Annam Navya Sree (19071A0503)

Sunayana Koora (19071A0531)

Sahithi Kuntala (19071A0533)

Jahnavi Neeradi (19071A0540)

Vardhan Nunemuntala (19071A0541)

Under the guidance of

Mrs Bhagya Rekha Konkepudi

(Assistant Professor, VNR VJIET)

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

VNR VIGNANA JYOTHI INSTITUTE OF ENGINEERING

&TECHNOLOGY
(An Autonomous Institute, NAAC Accredited With ‘A++’ Grade, NBA

Accredited, Approved by AICTE, New Delhi, Affiliated to JNTUH)

i
 VALLURUPALLI NAGESHWARA RAO VIGNANA JYOTHI
INSTITUTE OF ENGINEERING & TECHNOLOGY

(An Autonomous Institute)

Hyderabad – 500090

CERTIFICATE

This is to certify that Annam NavyaSree (19071A0503), Sunayana Koora

(19071A0531), SahithiKuntala (19071A0533) andJahnaviNeeradi (19071A0540),
Vardhan Nunemuntala (19071A0541)have successfully completed their mini
project work at Department of CSE, VNR VJIET,Hyderabadentitled“IOT BASED
SAFETY MANAGEMENT FOR ELDERLY
PEOPLE”inpartialfulfilmentoftherequirements
fortheawardofB.Techdegreeduringtheacademicyear2020-21.

Mrs K. Bhagya Rekha Mrs S. Nagini

Assistant Professor & InternalGuide Associate Professor &HOD
Department ofComputerScience Department of ComputerScience
VNRVJIET VNRVJIET

ii
 DECLARATION

We hereby declare that the mini project entitled “IOT based safety management

for elderly people” submitted in partial fulfilment of the requirements for award of
the degree of Bachelor of Technology in Computer Science and Engineering at VNR
Vignana Jyothi Institute of Engineering and Technology, affiliated to Jawaharlal
Nehru Technological University, Hyderabad, is a bonafide report of the work carried out
by us under the guidance and supervision of Mrs Bhagya Rekha Konkepudi(Assistant
Professor), Department of CSE, VNRVJIET. To the best of our knowledge, this report
has not been submitted in any form to any University/Institute for award of any degree or
diploma.

Annam Navya Sunayana Koora SahithiKuntala

Sree
(19071A0503) (19071A0531) (19071A0533)

IV B. Tech CSE IV B. Tech CSE IV B. Tech CSE

VNRVJIET VNRVJIET VNRVJIET

Neeradi Jahnavi Vardhan Nunemuntala

(19071A0540) (19071A0541)

IV B. Tech CSE IV B. Tech CSE

VNRVJIET VNRVJIET

iii
 ACKNOWLEDGEMENT

Behind every achievement lies an unfathomable sea of gratitude to those who

activated it, without which it would ever never have come into existence. To them we lay
the words of gratitude imprinting within us.

We are indebted to our venerable principal Dr. C. D. Naidu for this unflinching
devotion, which lead us to complete this project. The support, encouragement given by
him and his motivation lead us to complete this project. We are very much thankful to our
H.O.D., Mrs S. Naginimadam for extending her cooperation in doing this project.

We extend our heartfelt thanks to our guide, Mrs K. Bhagya Rekhama’am, for
her enthusiastic guidance throughout the course of our project. We also express our
sincere thanks to our Mini project co-ordinators Dr.RamaSatya and Mrs Hari
Priyawho extended their valuable support in helping us complete the project in a correct
way.

Last but not the least, our appreciable obligation also goes to all staff members of
Computer Science & Engineering Department and to our fellow classmates who directly
or indirectly helped us.

Annam NavyaSree (19071A0503)

Sunayana Koora (19071A0531)
Sahithi Kuntala (19071A0533)
JahnaviNeeradi (19071A0540)
Vardhan Nunemuntala (19071A0541)

iv
 ABSTRACT

Elderly people often stay at home alone and require attention when it comes to their
health. Small problems may lead to bigger health issues if left unnoticed. Safety is one
major concern in elderly people. There is no proper solution to solve the problem. Many
incidents are most damaging to elderly people in which falling is one major incident. To
avoid these kinds of incidents they need persistent assistance which may be not possible
at all times.

According to the World Health Organization (WHO), around 646 k fatal falls occur each
year in the world, the majority of whom are suffered by adults older than 65 years (WHO,
2018). This makes it the second reason for unintentional injury death, followed by road
traffic injuries. The age-adjusted fall death rate is 64 deaths per 100,000 older adults. Fall
death rates among adults age 65 and older increased about 30% from 2009 to 2018. The
increase was observed in 30 states and the District of Columbia. The fastest-growing rate
was among adults aged 85 and older (about 4% per year). In this regard, we are planning
to develop a wearable device that is capable to detect falls and provide quick assistance.

This project aims to develop smart wearable using various sensors that will help in
monitoring health and safety. The devices constructed using IOT help in detecting the fall
of any elderly people and send SMS/make calls for immediate aid. Moreover, the elderly
people's essentials such as heart rate and temperature are also monitored and warned
regarding abnormal health conditions.

On wearing the equipment, the Heart beat sensor, temperature sensor, accelerometer, and
IR sensor start tracking the vitals. Once any abnormal health values are identified, an alert
message/call is sent. Similarly, if the axis values of the accelerometer sensor exceed the
normal threshold value the fall detection algorithm predicts the fall of an elderly person.

v
 INDEX

Contents Page. No

CHAPTER 1

1. INTRODUCTION 14

1.1 Introduction 14

1.1.1 Parameters 15

1.1.2Types of Fall 16

1.1.3 Statistical Information 16

1.2 Existing Systems 17

1.2.1 Drawbacks of Existing Systems 19

1.3 Proposed System 20

1.3.1 Advantages of proposed system 21

CHAPTER 2

2. FEASIBILITY STUDY
6

2.1 Technical Feasibility 6

2.2 Economic Feasibility 7

2.3 Legal Feasibility 7

2.4 Operational Feasibility 7

2.5 Scheduling Feasibility 7

vi
 CHAPTER 3

3. LITERATURE SURVEY 8

CHAPTER 4

4. SYSTEM ANALYSIS 23
4.1 System Requirements 23
4.1.1 Software Requirements 24
4.1.2 Hardware Requirements 25

CHAPTER 5

5. SYSTEM DESIGN 26
5.1 UML Diagrams Introduction 28
5.2 Activity Diagram 26
5.2.1 Definition 26
5.2.2 Activity Diagram for Sepsis detection 27
5.3 Class Diagram 27
5.3.1 Definition 27
5.3.2 Class Diagram for Sepsis detection 28
5.4 Use case Diagram 28
5.4.1 Definition 28
5.4.2 Use case Diagram for Sepsis detection 29
5.5 Sequence Diagram 30
5.5.1 Definition 30
5.5.2 Sequence Diagram for Sepsis detection 30

vii
 CHAPTER 6

6. EQUIPMENTS 31

CHAPTER 7

7. IMPLEMENTATION 35
7.1 Coding 35
8.1.1 Code for MLP Classifier Algorithm 33

CHAPTER 8

8. CONCLUSION AND FUTURE SCOPE 44

8.1 Conclusion 44
8.2 Future Scope 44

CHAPTER 9

9. REFERENCES 45

viii
 LIST OF FIGURES

Figure 1.1.1 Facts 1

Figure 1.3Proposed Technique- Block Diagram 5

Figure 3.2 Block Diagram of Machine Learning

11
Algorithm

Figure 4.1 Sepsis dataset before re-sampling 16

Figure 4.1.1(a) Vital signs in Dataset 17

Figure 4.1.1(b) Laboratory Values in Dataset 17

Figure 4.1.1(c) Demographics in Dataset 17

Figure 4.1.1(d) Outcome in Dataset 17

Figure 4.2 Sepsis database after re-sampling 18

Figure 4.3 Feature Importance Score using XGBoost 18

Figure 4.4(a) Algorithm 21

Figure 4.4(b) Confusion Matrix of MLP Classifier 21

ix
Figure 4.4(c) Results obtained using Multi-Layer
21
Perceptron

Figure 4.4(d) Results obtained using Adaptive Boosting 23

Figure 4.4(e) Results obtained using Gradient Boosting

23
Classifier

Figure 4.4(f) Results obtained using Gaussian Naive

23
Bayes

Figure 4.4(g) Results obtained using Linear Discriminant

23
Analysis

Figure 4.4(h) Results obtained using Quadratic

23
Discriminant Analysis

Figure 5.1.1 Jupyter Notebook Logo 25

Figure 5.1.2 Training and Testing data set 26

Figure 5.1.3 Visualization tree 26

Figure 6.2.2 Activity diagram for Sepsis detection using

28
machine learning algorithms

Figure 6.3.2 Class diagram for Sepsis detection using

29
machine learning algorithms

Figure 6.4.2 Use case diagram for Sepsis detection using

30
machine learning algorithms

Figure 6.5.2 Sequence diagram for Sepsis detection using

31
machine learning algorithms

Figure 7.1 Flow Chart of Implementation 32

x
Figure 7.1.1 MLP Classifier Algorithm Code 34

Figure 7.1.2 Screenshot of Output of MLP Classifier

35
Algorithm

Figure 8.2 Graph of Accuracy and Log Loss Classifier 43

xi
 1. INTRODUCTION
1.1 Introduction

Elderly people represent the fastest growing segment of the population, by the year
2035, one-third of the European population will be more than 65 years old.
30% of elderly people fall once a year at least, which represents 75% of the victims of
falls.
The fall event is responsible for 70% of accidental deaths in persons aged 75+, and for
increasing the person's level of fear, anxiety, or depression leading to the reduction of
the day-to-day activity.
These observations have encouraged the development of fall detection devices to
detect or even prevent a fall event and to ensure rapid and efficient help when such an
event has occurred.

But very few fall detection systems are yet commercially available today, due to lack
of reliability, lack of easiness of installation and use, or because people did not accept
a system found too intrusive or expensive for instance.

Figure 1.1.1 a Facts

12
 FIGURE 1.1.1 b Interest of fall detection over time, from January 2004 to
December 2019. The data is taken from Google Trends with the search topic “fall
detection.” The values are normalized with the maximum interest, such that the
highest interest has a value of 100.

1.1.1 Parameters

The parameters for detecting fall include:

Humidity: It is calculated based on the surroundings temperature.

Temperature: the normal body temperature for a person ranges from 36- 39 degree
Celsius.

Heart Beat: The average heart rate that a person should have per minute under
normal condition is 60 to 100 beats per minute.

13
1.1.2 Types of Fall

The impact and consequences of a fall can vary drastically depending upon
various factors. For instance, falling whilst either walking, standing, sleeping
or sitting on a chair, share some characteristics in common but also have
significant differences between them.

In El-Bendary et al. (2013), the authors group the types of falls in three basic
categories, namely forward, lateral, and backward. Putra et al. (2017)
divided falls into a broader set of categories, namely forward, backward, left-
side, right-side, blinded-forward, and blinded-backward, and in the study by
Chen et al. (2018) falls are grouped in more specific categories including fall
lateral left lie on the floor, fall lateral left and sit up from floor, fall lateral
right and lie on the floor, fall lateral and left sit up from the floor, fall
forward and lie on the floor, and fall backward and lie on the floor.

Besides the direction one takes whilst falling another important aspect is the
duration of the fall, which may be influenced by age, health and physical
condition, along with any consequences of activities that the individual was
undertaking. Elderly people may suffer from longer duration of falls,
because of motion with low speed in the activity of daily living. For
instance, in fainting or chest pain related episodes an elderly person might
try to rest by a wall before lying on the floor. In other situations, such as
injuries due to obstacles or dangerous settings (e.g., slanting or uneven
pavement or surfaces), an elderly person might fall abruptly. The age and
gender of the subject also play a role in the kinematics of falls.

The characteristics of different types of falls are not taken into consideration
in most of the work on fall detection surveyed. In most of the papers to date,
data sets typically contain falls that are simulated by young and healthy
volunteers and do not cover all types of falls mentioned above. The resulting

14
 models from such studies, therefore, do not lead to models that generalize
well enough in practical settings.

1.1.3 Statistical Information

More than nine percent of the population of China was aged 65 or older in 2015
and within 20 years (2017–2037) it is expected to reach 20%1. According to the World
Health Organization (WHO), around 646 k fatal falls occur each year in the world, the
majority of whom are suffered by adults older than 65 years (WHO, 2018). This makes it
the second reason for unintentional injury death, followed by road traffic injuries.
Globally, falls are a major public health problem for the elderly. Needless to say, the
injuries caused by falls that elderly people experience have many consequences to their
families, but also to the healthcare systems and to the society at large.

FIGURE 1.1.5 (A) A map and (B) a histogram of publications on fall detection by
countries and regions from 1945 to 2020.

1.2 Existing Systems

Wearable devices

They can be defined as miniature electronic sensor-based devices that are worn by the
bearer under, with or on top of clothing . The vast majority of wearable fall detectors are
15
in the form of accelerometer devices (186 out of 197). Some of them also incorporate
other sensors such as gyroscopes to obtain information about the patient’s position. The
use of applications based on accelerometers and gyroscopes in gait and balance
evaluation, fall risk assessment and mobility monitoring has been actively explored. This
trend has increased over the last years due to the availability of cheap embedded sensors
included in smartphones. In this paper, we classify the different studies using wearable
devices according to whether or not sensors are built into smartphones, 30 and 156 papers
respectively. The next two sections provide more details about these subgroups.

Accelerometer attached to the body

Acceleration data are collected during falls using independent tri-axial accelerometers
attached to different parts of the body. A review of several research studies was
conducted. For the purpose of comparison, Table 3 examines the most relevant works.
The fields are the same as in section Context-aware systems, including a new item with
the accelerometer placement on the body. Since Table 3 is only focused on acceleration-
based systems, the possible techniques for fall detection are reduced to just two: i)
threshold-based methods, TBM, in which a fall is reported when the acceleration peaks,
valleys or other shape features reach predefined thresholds; ii) machine learning methods,
MLM. The aim is to visualize progress in research over the last years.

Smartphone built-in accelerometer

Today’s smartphones come with a rich set of embedded sensors, such as an

accelerometer, digital compass, gyroscope, GPS, microphone, and camera . Several
researchers are currently taking advantage of this fact to develop smartphone based fall
detectors. Low-complexity algorithms based on thresholding are used in most of the
studies, and only few go further and adopt machine learning strategies . They use Support
Vector Machines, Sparse Multinomial Logistic Regression, Naïve Bayes, K-Nearest
Neighbors, Decision Trees and Multi-layer Neural Networks .
16
The types of falls considered and the number of subjects involved in the studies are
similar to those of the previous section. Regarding the position of the phone, the waist is
still the preferred part of the body, although there is an emerging trend towards the thigh,
coinciding with the location of the pocket.

Some of these studieshave resulted in real fall detection applications that are available for
download in Google Play . This site offers another source of information. Thus, a search
has been conducted in this repository including either “fall detector” or “fall detection” as
the keywords. As a result, a total of 9 applications were obtained, of which 7 were for
seniors. To quote some statistics, 3 of them reported between 1000 and 5000 downloads,
while the rest had less than 500. Although these numbers indicate a certain level of
interest, they are still far from the number of potential users. Focusing on the app rating,
we found that an average of only 6 people have given their opinions on them. This is a
symptom that people using these apps do not seem to be enthusiastic about them.

The number of published studies based on smartphones is still low in comparison with the
previous categories, and none of them involve older people to evaluate the detector.
Therefore, studies still need to incorporate a more exhaustive evaluation. These are signs
that we are facing an emerging field.

1.2.1 Drawbacks of ExistingSystems

Performance under real-life conditions

Fall detectors need to be as accurate and reliable as possible. A robust fall detection
system should exhibit both high sensitivity and specificity. This is sometimes reached in
experimental environments, but when applied to a real situation, the detection rate
decreases . These devices are designed and tested under controlled conditions, for
example they use data from falls and ADL of young people simulated at the discretion of
each author due to the lack of a standardized procedure or a public database for
comparison. Furthermore, it is worth pointing out that fall detectors are aimed at older

17
people, so they should also be involved in their development. Only few studies
incorporate data from older people , although their participation is limited to perform a set
of simulated activities of daily living for a few minutes or hours. That is not enough to
assess the system performance in a real situation. Users should wear the devices for
longer periods (at least months). Some studies have worked in this direction , resulting in
a significant number of false activations, among other concerns.

Usability

Smartphone-based fall detectors are attractive because of the widespread use of phones,
even among the older population. However, the majority of the studies referenced in This
allowed highly stereotypical measurements that aided accuracy ratings but made the
results less applicable to the way people carry their smartphones every day (for example:
in pockets or handbags). Future smartphone-based detectors should not limit the
placement of the device to a single part of the body (waist, wrist, chest, etc.).
Smartphones should be used in a normal way, with no restrictions regarding their position
or functionalities. This may lead to lower detection rates.

Acceptance

Little is published about the practicality and acceptability of the technology. Elders’
acceptance poses a major problem since they may not be familiar with electronic devices.
To overcome this challenge, the way the system operates is essential . The detector should
activate and operate automatically, without user intervention. Vision systems, like other
non intrusive methods, are very good in this sense. However, some wearable devices like
smartphones have other advantages that can help to improve the acceptance of fall
detectors. They can operate both indoors and outdoors and integrate not only fall
detection but also other healthcare applications in the same device. In this way, the
traditional reluctance to carry different devices, each one targeting a specific function,
would be overcome. However, the use of smartphones by older people is not without
difficulty: these devices, as they were conceived, represent a major usability barrier for
them. Proof of this is the absence of rating in the existing fall detection applications,

18
 which is a symptom of little real use. In this sense, potential solutions to improve the
usability and accessibility of smartphones are needed. Nevertheless, as a result of a study
still in progress we have found that fall detectors were highly valued by the elderly, who
showed a positive attitude towards smartphone-based solutions after carrying out a
practical demonstration of several assistive technologies. This conclusion agrees with the
work of Plaza et al. [60], who reviewed mobile applications for older people and found
that they are most frequently related to two domains: “Health – wellness – home care”
and “Safety – security – mobility”.

1.3 ProposedSystem

The first step is to initialize and activate the sensors in the devices. Then a connection is
established between the mobile and the devices by inserting a sim card. On wearing the
equipment’s, the Heart beat sensor, temperature sensor, accelerometer and IR sensor start
tracking the vitals. Once any abnormal health values are identified, an alert call is sent to
the corresponding person through the GSM Module. Similarly, if the axis values of the
accelerometer sensor exceed the normal threshold value the fall detection algorithm
predicts the fall of elderly person.

19
 Fig 1.3 System Architechture - Block diagram

1.3.1 Advantages of ProposedSystem

The advantages of the Proposed System include thefollowing:

 The proposed system ensures the good fall detection to provide safety for the
elderly people and to monitor their health.

 The system monitors both health and safety of elderly people using heartbeat,
temperature, humidity, accelerometer and gsm module for making calls.

 The system will detect the fall efficiently and alert the responsible person to
provide medical attention.

20
 2. FEASIBILITYSTUDY

A feasibility have a look at is accomplished on a software program mission to apprehend

the viability of the product. Information a venture’s feasibility has lots to do with how it's
going to carry out inside the marketplace, what will paintings, what competition have
created and how will this product live to tell the tale. It's far part of the initial layout level
of any proposed venture/plan. It's miles finished to assess the feasibility of a proposed
venture or an current software program used by the business. It can assist in identifying
and assessing the possibilities and threats gift in the natural environment, the resources
needed for the venture, and the possibilities of success.

2.1 Technical Feasibility

Technical feasibility inspects whether or not software program may be built in any
respect with to be had equipment and experts.

In this project, an Arduino UNO is used to read inputs from sensors (IR sensor, DHT11,
Heartbeat sensor) and turn it into an output-activating or publishing something online
(call alert).

21
2.2 Economic Feasibility

Economic feasibility examines the costs and economic advantages of the project. To
decide economic feasibility, a difficult order of magnitude (ROM) estimate is usually
finished.

In this project, the investment was done on sensors and arduino uno and devices were
chosen cost efficiently.

2.3 Legal Feasibility

Legal feasibility makes sure that your product complies with all rules and doesn’t break
any law. Besides that, you need to discover what legal risks there are and the way they
are able to impact your task.

This project does not violate any legal requirements like data privacy . It ensures legal
statistics access and offers prominence to records safety

2.4 Operational Feasibility

Operational feasibility explores how a new project will effect day by day approaches to
your company, what processes have to be implemented, and what efforts ought to be
taken to preserve it.

The proposed system overcomes the drawbacks of previous models by an improved alert
system and fall recognition.
2.5 Scheduling Feasibility

Scheduling feasibility offers you a belief of realistic closing dates and facilitates stick
with them.

22
This project is developed in a scheduled manner by allotting enough time for every task
and completing it by the time.

23
 3. LITERATURESURVEY

3.1 Intelligent Video Surveillance for Monitoring Fall Detection of Elderly in Home
Environments.

Detect various posture-based events in a typical elderly monitoring application in a

home surveillance scenario. Combination of best-fit approximated ellipse around
the human body provide a useful cue for detection of different behaviors.

It Detect type of fall incident (forward, backward or sideway)

Rate of experimental results (91.12%)

Most of current systems are unable to discriminate between real fall incident and an
event when person is lying or sitting down abruptly.

3.2 Monocular 3D Head Tracking to Detect Falls of Elderly People .

Approach is based on the 3D trajectory of the head, which allows us to distinguish

falls from normal activities using 3D velocities.

Audio information or using 3D trajectory and speed of head is stored for future

purpose.

The tracking sometimes loses the position of the head at the end of the fall. These

mechanisms tend to be more complex and need extra additional costs.

3.3 Camera-Based Fall Detection on Real World Data

Based on background subtraction and simple measures extracted from the dominant
foreground object such as aspect ratio, fall angle and head speed.

Dataset based on real life data, recorded at the place of residence of four older persons
over several months

24
 The higher false alarm rate can be explained by the challenging nature of the dataset.
Two out of the three undetected falls started and ended outside of the view of the
camera

3.4 Latest Research Trends in Fall Detection and Prevention Using Machine Learning:

A Systematic Review

Presents the latest research trends in fall detection and prevention systems using Machine
Learning (ML) algorithms. It uses recent studies and analyzes datasets, age groups, ML
algorithms, sensors, and location

1. Energy Efficiency

2. Datasets

3. Context Awareness

4. Sensor Fusion

5. Wearable Design.

It is difficult to select the correct machine learning algorithm and proper dataset which is
efficient and acceptable.

3.5 An IoT System for Remote Health Monitoring in Elderly Adults through a
Wearable Device and Mobile Application

Using a biometric bracelet connected to a mobile application, which allows real-

time visualization of all the information generated by the sensors (heart rate, body
temperature, and blood oxygenation) in the bracelet

Wearable ioT device with alert notifications, used to save medical history and easy
communication with family.

Not budget friendly,difficult to automate.

3.6 A Survey of IoT-Based Fall Detection for Aiding Elderly Care:

25
 Sensors, Methods, Challenges and Future Trends

To review recent research whose focus is to develop AI algorithms and methods of

fall detection systems (FDS) in the IoT environment. In addition, the usability of
different sensor types, such as gyroscopes and accelerometers in smartwatches

Device with alert notifications, used to save medical history and easy
communication with family.

It is difficult to select the correct machine learning algorithm and proper dataset
which is efficient and acceptable.

Choosing appropriate placement of sensors,Not budget friendly,difficult to

automate.

3.7 Analysis of Android Device-Based Solutions for Fall Detection.

Classifies and compares the proposals of the literature taking into account different
criteria such as the system architecture, the employed sensors, the detection algorithm or
the response in case of a fall alarms.

Analysis of the evaluation methods that are employed to assess the effectiveness of the
detection process. Reveals the complete lack of a reference framework to validate and
compare the proposals.

Shows that most research works do not evaluate the actual applicability of the Android
devices to

fall detection solutions.

Usability and Ergonomics should be carefully investigated. The opinion of older

users must be taken into account in the design of fall detectors.

3.8 Review of fall detection techniques: A data availability perspective

Taxonomy for the study of fall detection from the perspective of availability of fall data.
26
Comprehensive literature review within those categories and identify the approach of
treating a fall as an abnormal activity to be a plausible research direction

Independent of the type of sensors used and specific feature extraction/selection methods.

Identifies different categories of classification methods for the study of fall detection
based on the availability of the data during training the classifiers.

Data is difficult to collect or not readily available. Fails to represent characteristics of the
data and provide unfavourable accuracies when presented with imbalanced dataset, and
their

predictions may be dominated by the majority class.

3.9 A comprehensive study on the use of artificial neural networks in

wearable fall detection systems

Cross validating the detection methods with public benchmarking datasets.Analyzes those
papers in the literature that have proposed a FDS that is partly or entirely based on the use
of an ANN.

Discusses the most recent trends in the application of neural architectures to the problem
of automatic detection.Possibility of directly extracting and learning these features from
the raw input data collected by the inertial sensors. Computational costs of implementing
ANNs have to be carefully evaluated. Battery lifetime is another basic concern for any
transportable device that is also largely disregarded by the literature on wearable FDSs.

3.10 Approaches and principles of fall detection for elderly and patient

Categorized methods based on wearable, computer vision and ambient devices.

The principle of fall selection is that has a different pattern of motion from other activity

27
The wearable device approach has its advantages.First, except wearable garments other
wearable devices for fall detection are cheap.Second, wearable device for fall detection
are easy to be set up and operated.

3.11 Survey and evaluation of real-time fall detection approaches

Using techniques that measure only the acceleration or combined with gyroscope and
static orientation data for fall detection.

The number of subjects involved in the tests is still low if compared to acceleration-
based, common to all of these works is the absence of older people during the test period.

3.12 Survey of fall detection and daily activity monitoring techniques

Categorized methods into vision based,ambient-sensor based,and kinematic-sensor based

approaches.

They start with an object detection that can be performed through a background
subtraction in the vision-based systems ,they have sufficient discriminative power to
identify the fall events.

3.13 A survey on fall detection:principles and approaches

Three main classes,namely wearable devices based,ambience device based and vision
based.

The detectors limit the placement of device to a single part of body,also vision-based
systems are much more prone to privacy concerns.Fake alerts are also a problem in these
systems.

3.14 Survey on fall dete ction and fall prevention using wearable and external sensors
28
Categorized methods into wearable devices and external sensors that includes vision
based and ambient sensors.

The principle of fall selection is that has a different pattern of motion from other activity

The wearable device approach has its advantages.First, except wearable garments other
wearable devices for fall detection are cheap.Second, wearable device for fall detection
are easy to be set up and operated.

3.15 A survey on vision-based fall detection

Utilizing vision-based methods with RGB and 3D depth cameras.

Based on the review provided, individual depth cameras and inertial sensors seem to be
the most significant approaches in vision and non-vision-based systems. The authors
concluded that fusion of both types of sensor resulted in a system that is more robust than
a system relying on one type of sensor.

4.SYSTEM ANALYSIS

4.1 SystemRequirements:

4.1.1 Software Requirements

ARDUINO 1.8.19 IDE

Windows 10 & above version

i5 Processor

29
4 GB RAM ( 8 GB RAM for higher Performance)

64 bit OS

Arduino Software

The open-source Arduino Software (IDE) makes it easy to write code and upload it to the
board.The Arduino Integrated Development Environment (IDE) is a cross-platform
application (for Windows, macOS, Linux) used to write and upload programs to Arduino
compatible boards, and can be used for other vendor development boards as well. It
includes a code editor, a compiler, and an uploader. Code libraries for using peripherals,
such as serial ports and various types of displays are also included. Arduino programs are
called “sketches,” which are written in a language very similar to C or C++.

Figure 5.1.1 Arduino Logo

4.1.2 Hardware Requirements

ARDUINO UNO

DHT11 (Digital Temperature and Humidity Sensor)

30
ACCELEROMETER ADXL 345

IR SENSOR

GSM MODULE

HEARTBEAT SENSOR

Jumper cables

Breadboard

5. SYSTEMDESIGN

6.1 UML DiagramsIntroduction:

UML isa standard language for specifying, visualizing, constructing, and documenting
the artefacts of software systems. UML can be described as a general-purpose visual
modelling language to visualize, specify, construct and document software system.
Although UML is generally used to model software systems, it is not limited within this
boundary. It is also used to model non-software systems as well like process flow in a
manufacturing unit etc. UML is not a programming language but tools can be used to
generate code in various languages using UML diagrams. UML has a direct relation with
object oriented analysis and design. The goal of UML can be defined as a simple
modelling mechanism to model all possible practical systems in today’s
complexenvironment.

6.2 ActivityDiagram:

31
6.2.1 Definition:

Activity diagrams are graphical representations of workflows of stepwise

activities and actions with support for choice, iteration and concurrency. In the
Unified Modelling Language, activity diagrams are intended to model both
computational and organizational processes. Activity diagrams show the
overall flow of control

32
 6.2.2 Activity Diagram for Sepsis detection

Figure 6.2.2 Activity diagram for fall detection

6.3 ClassDiagram:

6.3.1 Definition:

33
 A class diagram in the Unified Modelling Language (UML) is a type of static
structure diagram that describes the structure of a system by showing the system's
classes, their attributes, operations (or methods), and the relationships among objects.

6.3.2 Class Diagram for Sepsis detection

Figure 6.3.2 Class diagram for fall detection

6.4 Use caseDiagram:

6.4.1 Definition

34
 Use case diagrams are a way to capture the system's functionality and requirements
in UML diagrams. It captures the dynamic behaviour of a live system. A use case
diagram consists of a use case and an actor. A use case represents a distinct
functionality of a system, a component, a package, or a class.

6.4.2 Use case Diagram for Sepsis detection

Figure 6.4.2 Use case diagram for fall detection

6.5 SequenceDiagram:

35
 6.5.1 Definition:

A sequence diagram simply depicts interaction between objects in

a sequential order i.e. the order in which these interactions take place. We can also
use the terms event diagrams or event scenarios to refer to a sequence
diagram. Sequence diagrams describe how and in what order the objects in a system
function.

6.5.2 Sequence Diagram for Sepsis detection

Figure 6.5.2 Sequence diagram for Sepsis detection using machine learning algorithms

7.EQUIPMENTS

7.1 DHT11 Digital Temperature and Humidity Sensor

36
 Fig 2.2: DHT11 Sensor

DHT11 digital temperature and humidity sensor is a composite Sensor

contains a calibrated digital signal output of the temperature and humidity.
Application of a dedicated digital modules collection technology and the
temperature and humidity sensing technology, to ensure that the product has
high reliability and excellent long-term stability. The sensor includes a
resistive sense of wet components and an NTC temperature measurement
device, and connected with a high-performance 8-bit microcontroller.

Applications HVAC, dehumidifier, testing and inspection equipment,

consumer goods, automotive, automatic control, data loggers, weather
stations, home appliances, humidity regulator, medical and other humidity
measurement and control.

Features Low cost, long-term stability, relative humidity and temperature

measurement, excellent quality, fast response, strong anti-interference ability,
long distance signal transmission, digital signal output, and precise calibration.

7.2 ACCELEROMETER

37
 An accelerometer is a device that measures proper acceleration. Proper
acceleration, being the acceleration (or rate of change of velocity) of a
body in its own instantaneous rest frame,[2]is not the same as coordinate
acceleration, being the acceleration in a fixed coordinate system. For
example, an accelerometer at rest on the surface of the Earth will measure
an acceleration due toEarth's gravity, straight upwards (by definition) of g
≈ 9.81 m/s2. By contrast, accelerometers in freefall (falling toward the
center of the Earth at a rate of about 9.81 m/s2) will measure zero.

Accelerometers have multiple applications in industry and science. Highly

sensitive accelerometers are components of inertial navigation systems for
aircraft and missiles. Accelerometers are used to detect and monitor
vibration in rotating machinery. Accelerometers are used in tablet
computers and digital cameras so that images on screens are always
displayed upright. Accelerometers are used in drones for flight
stabilization. Coordinated accelerometers can be used to measure
differences in proper acceleration, particularly gravity, over their
separation in space; i.e., gradient of the gravitational field. This gravity
gradiometric is useful because absolute gravity is a weak effect and
depends on local density of the Earth which is quite variable.

Accelerometer Sensor

7.3 IR SENSOR
38
 Infrared technology addresses a wide variety of wireless applications. The
main areas are sensing and remote controls. In the electromagnetic
spectrum, the infrared portion is divided into three regions: near infrared
region, mid infrared region and far infrared region.

An infrared sensor emits and/or detects infrared radiation to sense its surroundings.

The working of any Infrared sensor is governed by three laws: Planck’s

Radiation law, Stephen – Boltzmann law and Wien’s Displacement law.

Planck’s law states that “every object emits radiation at a temperature not
equal to 00K”. Stephen – Boltzmann law states that “at all wavelengths, the
total energy emitted by a black body is proportional to the fourth power of the
absolute temperature”. According to Wien’s Displacement law, “the radiation
curve of a black body for different temperatures will reach its peak at a
wavelength inversely proportional to the temperature”.

IR Transmitter and Receiver

39
7.4 GSM MODULE:

GSM/GPRS module is used to establish communication between a

computer and a GSM- GPRS system. Global System for Mobile
communication (GSM) is an architecture used for mobile communication in
most of the countries. Global Packet Radio Service (GPRS) is an extension of
GSM that enables higher data transmission rate. GSM/GPRS module consists
of a GSM/GPRS modem assembled together with power supply circuit and
communication interfaces (like RS-232, USB, etc.) for computer. The
MODEM is the soul of such modules.

GSM/GPRS MODULE

7.5 HEARTBEAT SENSOR

Heartbeat Sensor is an electronic device that is used to measure the heart rate
i.e., speed of the heartbeat. Monitoring body temperature, heart rate and blood
pressure are the basic things that we do in order to keep us healthy. In order to
measure the body temperature, we use thermometers and a
sphygmomanometer to monitor the Arterial Pressure or Blood Pressure. Heart

40
Rate can be monitored in two ways: one way is to manually check the pulse
either at wrists or neck and the other way is to use a Heartbeat Sensor. In this
project, we have designed a Heart Rate Monitor System using Arduino and
Heartbeat Sensor. You can find the Principle of Heartbeat Sensor, working of
the Heartbeat Sensor and Arduino based Heart Rate Monitoring System using
a practical heartbeat Sensor.

Principle of Heartbeat Sensor

The principle behind the working of the Heartbeat Sensor is Photo

plethysmograph. According to this principle, the changes in the volume of
blood in an organ is measured by the changes in the intensity of the light
passing through that organ.

Usually, the source of light in a heartbeat sensor would be an IR LED and the
detector would be any Photo Detector like a Photo Diode, an LDR (Light
Dependent Resistor) or a Photo Transistor. With these two i.e., a light source
and a detector, we can arrange them in two ways: A Transmissive Sensor and
a Reflective Sensor.

41
 Heart Beat Sensor

7.5 AURDINO UNO

Arduino is an open-source electronics platform based on easy-to-use hardware and

software. Intrinsically, Arduino boards read inputs such as — light on a sensor, a
finger on a button, or a Twitter message and transform it into an output like —
activating a motor, turning on an LED, or publishing something online. Over the
years Arduino has been the brain of thousands of projects, from everyday objects to
complex scientific instruments. Arduino was born at the Ivrea Interaction Design
Institute as an easy tool for fast prototyping, aimed at students without a
background in electronics and programming. As soon as it reached a wider
community, the Arduino board started changing to adapt to new needs and
challenges, differentiating its offer from simple 8-bit boards to products for IoT
applications, wearable, 3D printing, and embedded environments.

The major components of Arduino UNO board are as follows:

● USB connector

● Power port
42
● Microcontroller

● Analog input pins

● Digital pins

● Reset switch

● Crystal oscillator

● USB interface chip

● TX RX LEDs

43
 8.IMPLEMENTATION

8.1.1 About IOT

Internet of Things, we find out that it is the concept of inter-networking of physical

devices, connected devices, smart devices, and other devices embedded with
electronics, software, sensors, actuators, and network connectivity that enable these
objects to collect and exchange data.

What it means, is that an object can be sensed or controlled remotely across the
existing network infrastructure that enables direct integration of the physical world
into computer-based systems, which, in turn, improves their efficiency and accuracy
and reduces human intervention.

8.1.2 Working of a IOT Model

44
Figure 3.2 Prototype

The system comprises of two primary components. One is the wearable

devices such as a smart band. And the other component is the cell phone. The
GSM module enables communication between the two components. On
wearing these devices, the health and safety of the elderly people is
continuously monitored and during any detection of abnormal health
conditions or activities such as fall or slip of the elderly people, abnormal
heart beat, abnormal temperature the respective caretaker is alerted in order to
provide immediate aid to the elderly people. In, addition to avoid confusion
on false alerts a button is provided, which he can click and stop the
notification from being sent if he is alright. These wearable devices along with
the application work together on complete monitoring of the elderly people
thus providing a safe and secure living environment to the elderly people.

45
8.2 Coding:

Flow Chart of Implementation

Figure 7.1 Flow Chart of Implementation

46
We can define the workflow in 5 stages.

1)The first step is to initialize and activate the sensors in the devices.

2) Then a connection is established between the mobile and the devices by inserting a sim
card.

3) On wearing the equipment’s, the Heart beat sensor, temperature sensor, accelerometer
and IR sensor start tracking the vitals.

4) Once any abnormal health values are identified, an alert call is sent to the
corresponding person through the GSM Module.

5)Similarly, if the axis values of the accelerometer sensor exceed the normal threshold
value the fall detection algorithm predicts the fall of elderly person.

8.2.1 Code

47
48
49
50
 Testing

CASE 1: Heart beat and temperature sensor

The heartbeat of a person fluctuates under various conditions. The average heart rate that
a person should have per minute under normal condition is 60 to 100 beats per minute.

Secondly, for the temperature sensor, as per medical knowledge, the normal body
temperature for a person ranges from 36- 39 degree Celsius. The surrounding temperature
will have effect on the sensor which may increase or decrease the data slightly.

Figure 7.1.2 a Screenshot of Testing

51
Case 2: Fall detection

For the Accelerometer sensor, the acceleration threshold value set up based on roll and
pitch values -50 to 50. The device was tested by giving a sudden jerk to the
accelerometer. This sudden movement triggered the threshold value to less than -50 or
greater than 50 and a notification(call) of fall detection was sent to the family member to
his phone requesting for immediate aid.

Figure 7.1.2 b Screenshot of Testing

52
 8 CONCLUSION AND FUTURESCOPE

9.1 Conclusion

The several fall-feature parameters of the 6-axes acceleration were introduced and applied
according thealgorithm. Possible falls were chosen through the simple threshold and then
applied to the MPU to solvethe problems such as deviation of interpersonal falling
behavioural patterns and similar fall actions. Thetest of the proposed device studied along
a different 350 case studies. The parameters of upper and lowerof acceleration and
velocity have adjusted to give best fall detection with sensitivity, specificity, andaccuracy
which were over than 95 %. These results demonstrate the reduction of the computing
effort andresources, compared to those of using all the events applied. Then the proposed
algorithms were verysimple because it dependson a simple sensor (measure the angle)
and the program calculates the angularvelocity and acceleration. The proposed system
ensures the good fall detection to provide safety for the elderly people and to monitor
their health. The system monitors both health and safety of elderly people using heartbeat,
temperature, humidity, accelerometer and gsm module for making calls.The system will
detect the fall efficiently and alert the responsible person to provide medical attention.

9.2 FutureScope

The system will be developed as a prototype now and in future it will be

made in a compact size to be embedded into the wearable gadgets. In the
future GPS system can also be integrated which can indicate the place of fall
and thus making the approach faster and better.The corresponding person
can divert the call to a nearby hospital in case of emergency.

53
 BIBILIOGRAPHY

References

 https://pimylifeup.com/arduino-accelerometer-adxl345/

 https://microcontrollerslab.com/gsm-module-interfacing-arduino-send-receive-
sms/

 https://www.electronicshub.org/heartbeat-sensor-using-arduino-heart-rate-
monitor/

 https://microcontrollerslab.com/dht11-interfacing-arduino-code/

 https://create.arduino.cc/projecthub/Raushancpr/arduino-with-ir-sensor-1579b6
 https://www.sciencedirect.com/science/article/pii/S1877050918304721
 https://iotdesignpro.com/projects/iot-based-fall-detection-system-using-nodemcu-
esp8266-and-accelerometer-mpu6050
 https://biomedical-engineering-online.biomedcentral.com/articles/10.1186/1475-
925X-12-66
 https://www.lively.com/health-and-aging/what-is-fall-detection/
 https://www.sciencedirect.com/topics/engineering/fall-detection
 https://www.frontiersin.org/files/Articles/520978/frobt-07-00071-HTML/
image_m/frobt-07-00071-g001.jpg
 https://www.researchgate.net/figure/Fall-detection-statistical-
result_tbl1_251875130
 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8347190/
 https://www.frontiersin.org/articles/10.3389/frobt.2020.00071/full

54