See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/368289020

Fall detection system for the elderly or disabled people

Technical Report · February 2023

DOI: 10.13140/RG.2.2.25300.07045

CITATIONS READS
0 310

4 authors, including:

Radovan Stojanovic
University of Montenegro
183 PUBLICATIONS 1,146 CITATIONS

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

SMART4ALL https://smart4all-project.eu/ View project

Technologijom do boljeg zdravlja, By technology to better health - TeleCare.me View project

All content following this page was uploaded by Radovan Stojanovic on 05 February 2023.

The user has requested enhancement of the downloaded file.

 SEMINARY WORK
Topic: Fall detection system

Professor: Students:

Prof. dr Radovan Stojanović Šofranac Ivan

Ljucović Nikola
Radulović Ivana
Table of contents

1. Summary of the project ........................................................................................................................ 3

2. Introduction .............................................................................................................................................. 5
3. Objectives and benefits of the project ..................................................................................................... 6
4.Internet of Things (IoT) .............................................................................................................................. 7
4.1 IoT - Key features ................................................................................................................................ 7
4.2 IoT Advantages .................................................................................................................................. 8
4.3 Data Collection .................................................................................................................................... 9
4.4 Device integration ............................................................................................................................. 10
4.5 Real-Time Analytics ........................................................................................................................... 10
4.6 Application and Process Extension ................................................................................................... 10
4.7 NFC i RFID .......................................................................................................................................... 11
4.8 Low-Energy Bluetooth....................................................................................................................... 11
4.9 Low energy wireless .......................................................................................................................... 11
4.10 Radio Protocols ............................................................................................................................... 11
4.11 LTE-A ............................................................................................................................................... 12
4.12 WiFi-Direct ...................................................................................................................................... 12
5. Fall Risk Factors ....................................................................................................................................... 12
6.Fall Detection Algorithm .......................................................................................................................... 14
7. Components ............................................................................................................................................ 17
8. Photographs of the prototype ................................................................................................................ 19
9. Program code .......................................................................................................................................... 20
10. Results obtained ................................................................................................................................... 28
11. Final realization ..................................................................................................................................... 32
12.BLYNK Application .................................................................................................................................. 34
13. Conclusion ............................................................................................................................................. 37
14. References ............................................................................................................................................ 38
 1. Summary of the project
Human falls can occur at any age, caused by a loss of balance or an
inability to regain balance. Although human falls are common at a
young age, they can pose a significant health risk in advanced
years. Falls can lead to dependence, loss of autonomy, confusion,
immobilization and depression, which negatively affects a person's
daily life and usual activities. Falls can be classified according to their
cause as accidental falls, unpredictable physiological falls, and
predictable physiological falls. Accidental falls are unpredictable falls
that result from external factors that affect people without falling
risk. Unpredictable physiological falls account for about 8% of falls and
affect people without a risk of falling, but are the result of physiological
factors, such as pathological fractures or seizures.
To reduce the negative impact of human falls, it is important to act
quickly when a fall occurs and provide appropriate warning to health
support services. Several technologies have been developed that use
webcams to monitor the activities of the elderly. However, the
operation and installation costs are expensive and applicable only for
indoor spaces... The use of IoT-based devices can provide significant
relief when it comes to fall detection by enabling continuous and
remote monitoring of a person's environment.. A wearable IoT device
can be worn by the elderly with itself, thus creating a walking profile
and based on this, it is easy to detect or detect a fall in real time. In our
paper, we will explain an IoT-based solution for fall detection, using
wearable and adaptive devices and a layered architecture for real-time
data processing. This project proposes a cost-effective and reliable fall
detection system to detect falls and alert relatives or caregivers for help
and support. An accelerometer and a gyroscope were used to detect
the fall, which measure the acceleration and the angle of inclination of
the falling body, respectively. By connecting the accelerometer to the
gyroscope, the accuracy of the system is improved due to the reduction
of false positive and true negative fall detections. The MPU6050 sensor
module has a built-in gyroscope and accelerometer sensor. The
gyroscope is used to determine the orientation and the accelerometer
provides angular parameter information such as ox, yiz axis data. We
connect this sensor to the ESP 32 microcontroller and maintain
different acceleration thresholds to check if any false triggering is
happening or if the user has actually fallen. If the values exceed the
thresholds, we receive a notification on our Android device via the Blink
application or push notification. The warning system in the form of
short message service (SMS) is suitable for quickly and easily informing
someone and calling for help. Moreover, this wearable device requires
less implementation costs and provides fast response. As a result, this
fall detection and warning system has a sensitivity and specificity of
95% and 90% respectively. The warning system in the form of short
message service (SMS) is suitable for quickly and easily informing
someone and calling for help. Moreover, this wearable device requires
less implementation costs and provides fast response. As a result, this
fall detection and warning system has a sensitivity and specificity of
95% and 90% respectively. The warning system in the form of short
message service (SMS) is suitable for quickly and easily informing
someone and calling for help. Moreover, this wearable device requires
less implementation costs and provides fast response. As a result, this
fall detection and warning system has a sensitivity and specificity of
95% and 90% respectively.

2. Introduction
Falling is the most significant cause of injury in the elderly. Most of the
elderly (over 75 years old) fell at least once a year, and 24% of them
have serious injuries. This is a serious public health problem with a
significant impact on health and health care costs. The cost and burden
of caring for older adults continues to rise. Among people affected by
Alzheimer's disease, the probability of falling increases by three times.
Elderly care can be improved by using sensors that monitor patients'
vital signs and activities, and remotely transmit this information to
loved ones and caregivers. The consequences of a fall can range from
scratches to fractures and in some cases lead to death. Even if there are
no immediate consequences, a long wait on the floor for help increases
the likelihood of death from an accident. For that reason, fall detection
is an active area of research. In recent years, passive monitoring
solutions have taken root in health monitoring systems in homes, living
environments and nursing homes. They ensure timely interventions in
emergencies. Most research on falls in which accelerometers are issued
focuses on determining the change in magnitude of acceleration. When
the acceleration value exceeds the critical threshold, a fall is detected.
The use of wearable and active sensors provides better tracking
capability. The contribution to such standardization is made by
collecting the most relevant parameters, data filtering techniques and
testing approaches from the studies done so far. State-of-the-art fall
detection techniques are examined, highlighting differences in their fall
detection effectiveness. A standard fall study database structure has
been created that highlights the most important elements of a fall
detection system that must be considered to design a robust system, as
well as to address limitations and challenges. However, focusing only
on high acceleration can lead to many false positives for fall-like
activities such as rapid descent and running.

3. Objectives and benefits of the

project
Develop an intelligent and effective fall detection and warning
system using a smartphone and wireless connection
Develop a reliable and cost-effective fall detection and warning
system
Develop a fall detection system that is easy to use and does not
cause interference in the daily life activities of elderly people
 4.Internet of Things (IoT)
IoT is an advanced automation and analysis system that uses
networking, sensing, big data and artificial intelligence technology to
deliver complete systems for a product or service. These systems
enable greater transparency, control and performance when applied
to any industry or system. IoT systems have applications in various
industries thanks to their unique flexibility and ability to be suitable in
any environment. They improve data collection, automation,
operations and more through smart devices and the powerful
technology to enable it. IoT systems allow users to achieve deeper
automation, analysis and integration within the system. They improve
the reach of these areas and their accuracy. IoT uses existing and new
technology to detect.

4.1 IoT - Key features

The most important features of IoT include artificial intelligence,
connectivity, sensors, active engagement, and small device use. A brief
review of these features is given below:

 AI– IoT essentially makes virtually anything “smart”, meaning it

enhances every aspect of life with the power of data collection,
artificial intelligence algorithms, and networks. This can mean
something as simple as enhancing your refrigerator and cabinets
to detect when milk and your favourite cereal run low, and to
then place an order with your preferred grocer.
 Connectivity – New enabling technologies for networking, and
specifically IoT networking,mean networks are no longer
 exclusively tied to major providers. Networks can exist on a much
smaller and cheaper scale while still being practical. IoT creates
these small networks between its system devices.

 Sensors – IoT loses its distinction without sensors. They act as

defining instruments which transform IoT from a standard passive
network of devices into an active system capable of real-world
integration.
 Active Engagement – Much of today's interaction with connected
technology happens through passive engagement. IoT introduces
a new paradigm for active content, product, or service
engagement.
 Small Devices – Devices, as predicted, have become smaller,
cheaper, and more powerful over time. IoT exploits purpose-built
small devices to deliver its precision, scalability, and versatility.

4.2 IoT Advantages

The benefits of IoT span all areas of lifestyle and business. Here is
a list of some of the benefits IoT can offer:
• Improved customer engagement – Current analytics suffer from
blind spots and significant accuracy gaps; and as noted,
engagement remains passive.
• Technology Optimization – The same technologies and data that
improve user experience also improve device usability and help
drive more powerful technology improvements.
• Waste reduction – IoT makes areas of improvement clear.
Current analytics give us superficial insight, but IoT provides real-
 world information that leads to more efficient resource
management.
• Improved Data Collection – Modern data collection suffers from
its limitations and design for passive use. IoT takes it out of those
spaces and places it exactly where it's needed. It provides an
accurate picture of everything.

IoT software deals with its core areas of networking and acting through
platforms, embedded systems, partner systems, etc. These individual
and master applications are responsible for data collection, device
integration, real-time analytics, and the extension of applications and
processes within the IoT network. They leverage integration with
critical business systems (eg ordering systems, robotics, scheduling, and
more) to accomplish related tasks.

4.3 Data Collection

This software manages sensing, measurements, light data filtering, light
data security, and aggregation of data. It uses certain protocols to aid
sensors in connecting with real-time, machine-to-machine networks.
Then it collects data from multiple devices and distributes it in
accordance with settings. It also works in reverse by distributing data
over devices. The system eventually transmits allcollected data to a
central server.

4.4 Device integration

Software supporting integration binds (dependent relationships) all
system devices to create the body of the IoT system. It ensures the
necessary cooperation and stable networking between devices.These
applications are the defining software technology of the IoT network
because without them, it is not an IoT system. They manage the various
applications, protocols, and limitations of each device to allow
communication.

4.5 Real-Time Analytics

These applications take data or input from various devices and convert
it into viable actions or clear patterns for human analysis. They analyse
information based on various settings and designs in order to perform
automation-related tasks or provide the data required by industry.

4.6 Application and Process Extension

These applications extend the reach of existing systems and software to
enable a broader, more efficient system. They integrate predefined
devices for specific purposes, such as providing access to certain mobile
devices or engineering instruments. It supports improved productivity
and more accurate data collection.

The Internet of Things primarily uses standard protocols and network

technologies. However, the main enabling technologies and protocols
of IoT are RFID, NFC, low energy Bluetooth, low energy wireless, low
energy radio protocols, LTE-A and WiFi-Direct. These technologies
support the specific network functionality required in an IoT system as
opposed to a standard uniform network of shared systems.

4.7 NFC i RFID

 RFID (Radio-Frequency Identification) and NFC (Near Field
Communication) provide simple, low-energy and versatile options for
identity and access tokens, connection initiation and payments.

 RFID technology uses two-way radio transmitter-receivers to identify

and track tags associated with objects.

 NFC consists of communication protocols for electronic devices,

usually a mobile device and a standard device.

4.8 Low-Energy Bluetooth

This technology supports the low-power, long-use need of IoT function
while exploiting a standard technology with native support across
systems..

4.9 Low energy wireless

This technology replaces the most power hungry aspect of an IoT
system. Though sensors and other elements can power down over long
periods, communication links (i.e., wireless) must remain in listening
mode. Low-energy wireless not only reduces consumption, but also
extends the life of the device through less use.

4.10 Radio Protocols

ZigBee, Z-Wave and Thread are radio protocols for creating low-speed
private networks. These technologies are low power but offer high
throughput unlike many similar options. This increases the power of
small local area networks of devices without the typical overhead.

4.11 LTE-A
LTE-A, or LTE Advanced, brings an important upgrade to LTE technology
by increasing not only its coverage, but also reducing latency and
increasing bandwidth. This gives IoT tremendous power by expanding
its range, and its most significant applications are vehicles, UAVs and
similar communications.

4.12 WiFi-Direct
WiFi-Direct eliminates the need for an access point. It allows P2P (peer-
to-peer) connections with the speed of WiFi, but with lower latency.
WiFi-Direct eliminate an element of a network that often bogs it down,
and it does not compromise on speed or throughput.

5. Fall Risk Factors

A person can be more or less prone to fall, depending on a number of
risk factors and hence a classification based on only age as a parameter
is not enough. In fact, medical studies have determined a set of so
called risk factors:

Intrinsic:

1. Age(over 75 )

2. Chronic desease
3. Previous falls

4. Poor balance

5. Low mobility and bone fragility

6. Sight problems

7. Cognitive and dementia problems

8. Parkinson desease

9. Use of drugs that affect the mind

10. Incorrect lifestyle(inactivity,use of alcohol,obesity)

Internal Environment:

1. Need to reach high objects

2. Slipping floors

3. Stairs

4. Incorrect use of shoes and clothes

External Environment:

1. Damaged roads

2. Dangerous steps

3. Poor lighting

4. Crowded places
6.Fall Detection Algorithm
The total acceleration sum vector Acc, contains both dynamic and static
acceleration. The components are calculated from the sampled data as
indicated in the relation below:

where Ax, Ay, Az are the accelerations in the x, y, z axes.

Similar to acceleration, angular velocity is calculated from the sampled

data as indicated in the equation below.

Where Wx, Wy, Wz is the acceleration in the x, y, z axes, respectively.

At steady state, the acceleration magnitude, Acc, from the triaxial

accelerometer is constant, and the angular velocity is 0o/s. When a
person falls, the acceleration changes rapidly and the angular velocity
produces different signals along the direction of the fall. Because the
crash index (Acc) requires a high sampling frequency and rapid
acceleration changes, it will miss crashes that occur slowly. Thus, Acc is
not used unless we want to compare the performance of our systems
with previous studies that used the same positions but with different
speeds and accelerations. Lower and upper crash thresholds are set for
the acceleration and angular velocity used. To identify the fall they are
derived as follows:

1- Lower fall threshold (LFT):

Negative peaks for the resultant of each recorded activity are called
lower signal peak values (LPV). The LFT for the acceleration signals was
set to the level of the smallest lower peak drop (LFP) recorded.

2- Upper fall threshold (UFT):

The positive peaks for the recorded signals for each recorded activity
are called upper peak signal values (UPV). The UFTs for each of the
acceleration and angular velocity signals were set to the level of the
smallest recorded UPV magnitude. UFT refers to the peak impact force
experienced by a body segment during the impact phase of a fall.

Fall detection algorithms using thresholds are usually divided into two
groups, one based on LFT comparison and the other based on UFT
comparison of acceleration data. Although past research has achieved
some significant results, accuracy is still below desired levels.
Fall detection algorithm
7. Components

ESP 32 MPU 6050

Analyzing the severe fall consequences of the elderly, we used an

accelerometer and a gyroscope to analyze the user's body movements
and predict whether or not there was any sudden change in
acceleration that would give an indication of a likely fall.
The MPU6050 sensor module is a complete 6-axis (3-axis accelerometer
and 3-axis gyroscope) module. Micro-electro-mechanical systems
(MEMS) are used to measure acceleration, velocity, orientation,
displacement and many other motion-related parameters. Apart from
this, it also has an additional built-in temperature sensor. The MPU6050
module is small in size with lower power consumption. In addition, it
has high repetition, high impact tolerance and low user costs. Basically,
the MPU6050 comes with an I2C and auxiliary I2C interface.

When the acceleration value is greater than the threshold, the

microcontroller will check the orientation of the user using the
gyroscope that came along with the MPU6050 accelerometer. There
are two possible outcomes from a gyroscope that is upright or lying
down. If the user is standing upright, the device will continue to track
acceleration. However, when a fall occurs and it is established that the
user is lying on the ground, a notification is sent via an application
(push notification) on the caregiver's mobile phone.
8. Photographs of the prototype
9. Program code

#include <Wire.h>

#include <WiFi.h>

#include <HTTPClient.h>

#include <stdio.h>

#include <string.h>

#include <stdlib.h>

#define BLYNK_PRINT Serial

#include <Blynk.h>

#include <BlynkSimpleEsp32.h>

char token[] = "k-e957855e4df2"; // mijenjati sa vašim API key-om

char notify[] = "true";

// Set web server port number to 80

WiFiServer server(80);

String header;

// Current time

unsigned long currentTime = millis();

// Previous time
unsigned long previousTime = 0;

char post[500];

String y = "";

const long timeoutTime = 2000;

String serverName = "";

const int MPU_addr = 0x68; // I2C address of the MPU-6050

int16_t AcX, AcY, AcZ, Tmp, GyX, GyY, GyZ;

float ax = 0, ay = 0, az = 0, gx = 0, gy = 0, gz = 0;

int minVal = 265;

int maxVal = 402;

double x;

double yy;

double z;

boolean fall = false; //stores if a fall has occurred

boolean trigger1 = false; //stores if first trigger (lower threshold) has occurred

boolean trigger2 = false; //stores if second trigger (upper threshold) has occurred

boolean trigger3 = false; //stores if third trigger (orientation change) has occurred

byte trigger1count = 0; //stores the counts past since trigger 1 was set true

byte trigger2count = 0; //stores the counts past since trigger 2 was set true

byte trigger3count = 0; //stores the counts past since trigger 3 was set true

int angleChange = 0;

char auth[] = "K3I30cefDjlK1lL6mV1_06DHNHs1Z9BS";

const char *ssid = ""; // Replace with your WIFI SSID

const char *pass = ""; // Replace with your WIFI PASSWORD

//char ssid[] = "";

//char pass[] = "";

void setup() {

Serial.begin(115200);

Wire.begin();

Wire.beginTransmission(MPU_addr);

Wire.write(0x6B); // PWR_MGMT_1 register

Wire.write(0); // set to zero (wakes up the MPU-6050)

Wire.endTransmission(true);

Blynk.begin(auth, ssid, pass);

WiFi.begin(ssid, pass);

while (WiFi.status() != WL_CONNECTED)

delay(300);

Serial.print(".");

Serial.println("");

Serial.println("WiFi connected");

server.begin();

}
void loop() {

Blynk.run();

mpu_read();

ax = (AcX - 2050) / 16384.00;

ay = (AcY - 77) / 16384.00;

az = (AcZ - 1947) / 16384.00;

gx = (GyX + 270) / 131.07;

gy = (GyY - 351) / 131.07;

gz = (GyZ + 136) / 131.07;

int xAng = map(AcX, minVal, maxVal, -90, 90);

int yAng = map(AcY, minVal, maxVal, -90, 90);

int zAng = map(AcZ, minVal, maxVal, -90, 90);

x = RAD_TO_DEG * (atan2(-yAng, -zAng) + PI);

yy = RAD_TO_DEG * (atan2(-xAng, -zAng) + PI);

z = RAD_TO_DEG * (atan2(-yAng, -xAng) + PI);

Blynk.virtualWrite(V4, x);

Blynk.virtualWrite(V5, yy);

Blynk.virtualWrite(V6, z);

// calculating Amplitute vactor for 3 axis

float raw_amplitude = pow(pow(ax, 2) + pow(ay, 2) + pow(az, 2), 0.5);

 int amplitude = raw_amplitude * 10; // Mulitiplied by 10 bcz values are between 0 to 1

Serial.println(amplitude);

if (amplitude <= 2 && trigger2 == false) { //if AM breaks lower threshold (0.4g)

trigger1 = true;

Serial.println("TRIGGER 1 ACTIVATED");

if (trigger1 == true) {

trigger1count++;

if (amplitude >= 12) { //if AM breaks upper threshold (3g)

trigger2 = true;

Serial.println("TRIGGER 2 ACTIVATED");

trigger1 = false; trigger1count = 0;

if (trigger2 == true) {

trigger2count++;

angleChange = pow(pow(gx, 2) + pow(gy, 2) + pow(gz, 2), 0.5);

Serial.println(angleChange);

if (angleChange >= 30 && angleChange <= 400) { //if orientation changes by between 80-100
degrees

trigger3 = true; trigger2 = false; trigger2count = 0;

Serial.println(angleChange);

Serial.println("TRIGGER 3 ACTIVATED");

if (trigger3 == true) {
 trigger3count++;

if (trigger3count >= 10) {

angleChange = pow(pow(gx, 2) + pow(gy, 2) + pow(gz, 2), 0.5);

Serial.println(angleChange);

if ((angleChange >= 0) && (angleChange <= 10)) { //if orientation changes remains between 0-10
degrees

fall = true; trigger3 = false; trigger3count = 0;

Serial.println(angleChange);

else { //user regained normal orientation

trigger3 = false; trigger3count = 0;

Serial.println("TRIGGER 3 DEACTIVATED");

if (fall == true || z > 345) { //in event of a fall detection

Serial.println("FALL DETECTED");

serverName = "https://xdroid.net/api/message?k=k-e957855e4df2&t=Fall-
detection&c=HELP!&u=http://google.com";

sendCustom("true");

serverName = "";

delay(3000);

fall = false;

if (trigger2count >= 6) { //allow 0.5s for orientation change

 trigger2 = false; trigger2count = 0;

Serial.println("TRIGGER 2 DECACTIVATED");

if (trigger1count >= 6) { //allow 0.5s for AM to break upper threshold

trigger1 = false; trigger1count = 0;

Serial.println("TRIGGER 1 DECACTIVATED");

delay(100);

void mpu_read() {

Wire.beginTransmission(MPU_addr);

Wire.write(0x3B); // starting with register 0x3B (ACCEL_XOUT_H)

Wire.endTransmission(false);

Wire.requestFrom(MPU_addr, 14, true); // request a total of 14 registers

AcX = Wire.read() << 8 | Wire.read(); // 0x3B (ACCEL_XOUT_H) & 0x3C (ACCEL_XOUT_L)

AcY = Wire.read() << 8 | Wire.read(); // 0x3D (ACCEL_YOUT_H) & 0x3E (ACCEL_YOUT_L)

AcZ = Wire.read() << 8 | Wire.read(); // 0x3F (ACCEL_ZOUT_H) & 0x40 (ACCEL_ZOUT_L)

Tmp = Wire.read() << 8 | Wire.read(); // 0x41 (TEMP_OUT_H) & 0x42 (TEMP_OUT_L)

GyX = Wire.read() << 8 | Wire.read(); // 0x43 (GYRO_XOUT_H) & 0x44 (GYRO_XOUT_L)

GyY = Wire.read() << 8 | Wire.read(); // 0x45 (GYRO_YOUT_H) & 0x46 (GYRO_YOUT_L)

GyZ = Wire.read() << 8 | Wire.read(); // 0x47 (GYRO_ZOUT_H) & 0x48 (GYRO_ZOUT_L)

}
void sendCustom(char notify[]) {

if (WiFi.status() == WL_CONNECTED) {

// Preparing Data

// Combine Token For Header

char tok[500] = "Token ";

strcat(tok, token);

// Init Http Client

HTTPClient http;

// Your Domain name with URL path or IP address with path

http.begin(serverName);

// Specify content-type header

http.addHeader("Content-Type", "application/x-www-form-urlencoded");

// Token Header

http.addHeader("Authorization", tok);

// Post Data

strcat(post, "&BL_notify=");

strcat(post, notify);

// Send HTTP POST request

int httpResponseCode = http.POST(post);

Serial.print("HTTP Response code: ");

// Response 200 Means Notification Sent

Serial.println(httpResponseCode);

// Free resources
 http.end();

10. Results obtained

Some activities such as brisk walking also have a large vertical

acceleration. In the images below, we can see the differences when the
patient's movement changes, however, the difference between
accelerated movement when there was no fall and the last image when
a fall was actually detected is clearly visible.

Figure 1: Normal gait (walking)

Figure 2: Brisk walking (running)

Figure 3:Fall is detected

When a fall is detected, the caregiver receives this information in the
form of a message on the phone, on the basis of which he knows that
the patient needs help.

In the photo above, we have a display of such a notification.

11. Final realization

The positioning of the fall detection device plays an important role in

this project. Correct placement of the device will increase the reliability
of the fall detection system. Currently commercialized fall detection
systems are available in the form of pendants and bracelets. Both the
pendant and bracelet have a high false alarm rate due to movement
during activities of daily living even though they are easy to wear and
take off. Therefore, in this project, the proposed method that will be
used is a body belt, which would be used as in the picture below. The
advantage of this belt is that it can reduce the false alarm rate due to
less movement from the upper torso. In addition, it is easy to wear and
take off especially for the elderly and patients.

Way of using

We managed to adapt all the components for the realization of our

project to everyday use, so that it is easy for the patient to wear.
The way to realize this is in the photos below.
12.BLYNK Application
Blynk was designed for the Internet of Things. It can control hardware
remotely, it can display sensor data, it can store data, vizualize it and do
many other cool things.

There are three major components in the platform:

Blynk App - allows to you create amazing interfaces for your projects
using various widgets we provide.

Blynk Server - responsible for all the communications between the

Smartphone and hardware.

Blynk Libraries - for all the popular hardware platforms - enable

communication with the server and process all the incoming and out
coming commands.

Features:
Similar API & UI for all supported hardware & devices
Connection to the cloud using:
WiFi
Bluetooth and BLE
Ethernet
USB (Serial)
GSM
Set of easy-to-use Widgets
Direct pin manipulation with no code writing
Easy to integrate and add new functionality using virtual pins
History data monitoring via SuperChart widget
Device-to-Device communication using Bridge Widget
Sending emails, tweets, push notifications, etc.

Our Blynk application shows the movement of the patient along the
x,yiz axis. This is shown in Figure 3 pie charts for each of the axes. In
this way, the guardian receives information at any time, that is, he can
simply follow the movement and position of the patient.
 Figure 4:Blynk system

Video link: https://youtu.be/f6LqF-WPdzc

13. Conclusion
Several parameters for the fall characteristics of 6-axis acceleration are
introduced and applied according to the algorithm. Possible falls are
selected via a simple threshold and then applied to the MPU to address
issues such as deviation of interpersonal fall behavior patterns and
similar fall actions. Upper and lower acceleration and velocity
parameters are adjusted to give the best fall detection with sensitivity,
specificity and accuracy over 95%. This shows a reduction in
computational effort and resources, compared to using all applied
events. The algorithms are very simple because they depend on a
simple sensor (measure the angle) and the program calculates the
angular velocity and acceleration. They can be implemented in an
embedded system such as a microcontroller. Once the proposed
algorithms are implemented in the embedded system, its performance
will be tested in real time.
 14. References
1. Hwang, J.Y., Kang, J.M., Jang, Y.W., Kim, H.C.: Development of novel
algorithm and real time monitoring ambulatory system using Bluetooth
module for fall detection in the elderly. In: Engineering in Medicine and
Biology Society, IEMBS 2004, 26th Annual International Conference of the
IEEE, vol. 1, pp. 2204–2207, September 2004
2. B. Najafi, K. Aminian, F. Loew, Y. Blanc and P. A. Robert, "Measurement of
stand-sit and sit-and transitions using a miniature gyroscope and its
application in fall risk evaluation in the elderly", IEEE Trans. Biomed. Eng.,
vol. 49, no. 8, pp. 843-851, 2002.
3. M. Alwan, D. Mack, S. Dalal, S. Kell, B. Turner, and R. Felder, “Impact of
passive in-home health status monitoring technology in home health:
Outcome pilot,” in Distributed Diagnosis and Home Healthcare, 2006.D2H2.
1st Transdisciplinary Conference on, 2006, pp. 79 –82.
4. Kangas, M., Konttila, A., Lindgren, P., Winblad, I., Jämsä, T.: Comparison of
low-complexity fall detection algorithms for body attached accelerometers.
Gait Posture 28(2), 285–291 (2008)
5. M. Avvenuti, C. Baker, J. Light, D. Tulpan, and A. Vecchio, “Non-intrusive
patient monitoring of alzheimer’s disease subjects using wire-less sensor
networks,” Privacy, Security, Trust and the Management of e-Business,
World Congress on, vol. 0, pp. 161–165, 2009.

View publication stats