International Journal of Scientific & Engineering Research Volume 9, Issue 7, July-2018 2033

ISSN 2229-5518

An Automated Fall Detection System Using

Accelerometer
Mohd Nadim,Aravindh S,Qayyum Khan,Rizwana

Abstract— The objective of this work is to provide brief review on the technologies proposed to predict the collision between vehicles, before the
collision happens itself and smart activation of safety systems like air bag deployment, seat belt tightening. This paper also cover the review on the acci-
dent notification schemes proposed once the accident is predicted. At the later part of this paper, an ideal model for the accident prediction and notifica-
tion system schematic is given. A prototype of fall detection system using accelerometer and piezoelectric sensors is presented in this paper. Accel-
erometer and piezoelectric sensors are embedded in this system to get the result of fall detection more accurately. This research also can distinguish
condition of people between falls and activity daily living.In the current system we have sensor to identify vehicle is met with an accident or not.

Index Terms— Accelerometer, ADXL335, Automated, Detecting System, Fall, GSM, Piezoelectric Sensors.

——————————  ——————————

1 INTRODUCTION
The growth of automotive vehicles has been increasing grad- By placing tri-axial accelerometers at precise body lo-
ually day to day, which in turn lead to the increased growth of cations, systems easily recognize these patterns and the mo-
road accidents. In the current situation because of human er- tions or transitions can be measured using both linear acceler-

IJSER
rors and judgment thousands of lives are lost and this world is
ation and angular velocity. Should someone fall who is being
plagued by accidents. When the proper mechanism of alerting
drivers are done this accidents can be avoided to certain ex- monitored, the goal would be to ascertain with certainty that it
tent. A person when travelling on vehicle has to take lot of was really a fall, and provide assistance as soon as possible.
security measures. In spite of taking security measures there Real-time detection of falls and their urgent communication to
are many situations where accidents occur. When accident a telecare center may enable the rapid medical assistance that
occurs we generally opt for emergency services. In the present
is needed. This article will examine all of the key design ele-
scenario when a person has met with an accident then the
people in the surrounding areas will call for the emergency ments of a human fall detection system.
services if not the person is left all alone in that drastic situa-
tion. If proper measures are taken before only then we can 3 DESIGNING STRATEGY
avoid such type of situations. Proper Monitoring techniques
are to be implemented to reduce accidents. . An efficient and Fall detection systems typically use one or more of the follow-
accurate automatic fall detection system would be significant ing methods:
and necessary in an intelligent surveillance system and could ● Analyzing acceleration to detect falls using a four-axis
improve their ability of independent living [1] accelerometer or tri-axial accelerometer, typically us-
ing measurements from the waist or hip. The down-
2 FALL DETECTION side is that false positives occur when a person either
For these fall detection applications, extremely precise gyro- jumps or sits down quickly.
scopes measure and maintain orientation, while accelerome- ● Using acceleration and body orientation data to detect
ters measure all acceleration, or the rate of change of the veloc- falls. Three sensors, a gyro sensor that monitors body
ity of the object relative to any inertial frame of reference, un- orientation, a piezoelectric accelerometer that moni-
less based on gravity. Common fall detection systems are tors vertical acceleration shock and a vibration sensor
based on a sensor detecting a strong vertical acceleration, monitor body movement. Accuracy is improved, but
launching an alarm when a fall event is recognized. [5] posture information is lacking, as only the trunk ori-
In the case of fall detection, the sensor measures weight entation is used.
per unit of mass, or specific or “g” force. Both single axis and ● Finally, there is a help-button based medical alert,
multi-axis accelerometers detect magnitude and direction of which works well when the person is conscious and
acceleration and can sense orientation. Not only can multi-axis able to touch the button – which is not always the
accelerometers be used, but multiple units or pairs can detect case.
the proper acceleration of a frame of references. All of the forementioned methods have strong and weak
. points, but the most typical complaint is that, since by its very
nature fall-detection technology must error on the side of cau-
tion, they are overly sensitive and can misinterpret normal
IJSER © 2018
http://www.ijser.org
International Journal of Scientific & Engineering Research Volume 9, Issue 7, July-2018 2034
ISSN 2229-5518
activities of daily living as a fall The process to detect a fall ADXL335 is a triple axis accelerometer with extremely low
situation followed by sending notification to colleagues can be noise and power consumption – only 320 µ A.
done in real-time manners while still maintain high accuracy
for certain fall situations.[6]

4.1.1 Theory of Operation

4 DESCRIPTION OF HARDWARE
4.1 Accelerometer The ADXL335 is a complete 3-axis acceleration measurement
An accelerometer is an electromechanical device used to system. The ADXL335 has a measurement range of ±3 g min-
measure acceleration forces. Such forces may be static, like the imum. The output signals are analog voltages that are propor-
continuous force of gravity or, as is the case with many mobile tional to acceleration.
devices, dynamic to sense movement or vibrations. An accel-
erometer measures proper acceleration, which is the accelera- The accelerometer can measure the static acceleration of gravi-
tion it experiences relative to freefall and is the acceleration ty in tilt-sensing applications as well as dynamic acceleration
felt by people and objects. Accelerometers are generally low- resulting from motion, shock, or vibration. Acceleration de-
power devices. F=ma, this equation is the theory behind accel- flects the moving mass and unbalanced the differential capaci-
erometers: they measure acceleration not by calculating how tor resulting in a sensor output whose amplitude is propor-
speed changes over time but by measuring force. tional to acceleration. Phase-sensitive demodulation tech-
niques are then used to determine the magnitude and direc-
TRI-AXIS ACCELEROMETER WITH REGULATOR- tion of the acceleration. When using accelerometer, which is
ADXL335 composed of measure of acceleration of the body or parts of

IJSER
This Accelerometer module is based on the popular ADXL335
the body, it is one of the most extensively-used methods im-
three-axis analog accelerometer IC, which reads off the X, Y
plemented for measuring physical activities to monitor activi-
and Z acceleration as analog voltages. By measuring the
ty patterns [4]
amount of acceleration due to gravity, an accelerometer can
figure out the angle it is tilted at with respect to the earth. By
sensing the amount of dynamic acceleration, the accelerometer
can find out how fast and in what direction the device is mov-
ing. The accelerometer is very easy interface to an Arduino
Micro-controller using 3 analog input pins, and can be used
with most other micro controllers, such as the PIC or AVR.
Accelerometers with an analog interface show accelerations
through varying voltage levels. These values generally fluctu-
ate between ground and the supply voltage level. An ADC on
a microcontroller can then be used to read this value. These
are generally less expensive than digital accelerometers.

ADXL335 is 3 axis accelerometer with on board volt-

age regulator IC and signal conditioned Analog voltage out-
put. .For detecting a fall using accelerometers, currently there
are two categories of detection methods: analytical methods Fig. 1. Structure of ADXL335
and machine learning methods [2].The module is made up of
ADXL335 from Analog Devices. The product measures accel- 4.2 Piezoelectric Sensors
eration with a minimum full-scale range of ±3 g. It can meas- A piezoelectric sensor is a device that uses the piezoelectric
ure the static acceleration of gravity in tilt-sensing applica- effect, to measure changes in pressure, acceleration, tempera-
tions, as well as dynamic acceleration resulting from motion, ture, strain, or force by converting them to an electrical charge.
shock, or vibration. Bandwidths can be selected to suit the
application, with a range of 0.5 Hz to 1600 Hz for the X and Y 4.2.1 Sensor Design
axis, and a range of 0.5 Hz to 550 Hz for the Z axis. Accel- Based on piezoelectric technology various physical quantities
erometers are generally low-power devices.The required cur- can be measured; the most common are pressure and accelera-
rent typically falls in the micro (µ) or milli-amp range.The tion. When the accelerometer experiences a motion, the invari-

IJSER © 2018
http://www.ijser.org
International Journal of Scientific & Engineering Research Volume 9, Issue 7, July-2018 2035
ISSN 2229-5518
ant seismic mass loads the elements according to Newton's ● Low power consumption
second law of motion {display style F=ma}.The main differ- ● Operating temperature range: -40 ° C ~ + 85 ° C
ence in working principle between these two cases is the way ● Supply voltage range: 9V to 12V
they apply forces to the sensing elements. In a pressure sensor, ● Switching Regulator Based Power Supply
a thin membrane transfers the force to the elements, while in ● Operating temperature: -40C to +85C
accelerometers an attached seismic mass applies the forces. ● One SIM card interface.
● Audio channels which include a microphone input
Sensors often tend to be sensitive to more than one
and a receiver output
physical quantity. Pressure sensors show false signal when
they are exposed to vibrations. Sophisticated pressure sensors
therefore use acceleration compensation elements in addition
to the pressure sensing elements. By carefully matching those 5 CIRCUIT DIAGRAM
elements, the acceleration signal (released from the compensa-
tion element) is subtracted from the combined signal of pres-
sure and acceleration to derive the true pressure information.
Vibration sensors can also harvest otherwise wasted energy
from mechanical vibrations. This is accomplished by using
piezoelectric materials to convert mechanical strain into usable
electrical energy

4.3 GSM Module

IJSER
Global System for Mobile Communications, is a standard de-
veloped by the European Telecommunications Standards In-
stitute (ETSI).It was created to describe the protocols for se-
cond-generation (2G) digital cellular networks used by mobile
phones and is now the default global standard for mobile
communications – with over 90% market share, operating in
over 219 countries and territories. Intimation about that trou-
ble is possible by sending SMS (Short message service) in GSM Fig. 3. The circuit diagram for fall detection system
(Global system for Mobile communication) based and GPS
(Global Positioning System) based mobiles even if the mobile
is not receiving network signal with the help of location based 4 FUTURE WORK AND CONCLUSION
services[7] In this project, a fall detection system prototype for accelerom-
eter was proposed. Real time detection and notification of the
of the fall have vital importance. The present study demon-
strated that fall could be detected using this module. The pro-
posed model is an inexpensive, highly reliable model for acci-
dent prediction and alert system. Extensive research work has
been carried in the field of object based system ranging from
GSM based location determination GPS based location deter-
mination.[3]

REFERENCES
[1] M. Eklund, T. Hansen, S. Sastry. “Information technology for assisted living at
home: Building a wireless infrastructure for assisted living,” in Proceedings of the
27th Annual International IEEE EMBS Conference, Shanghai, China, 17-18 Jan.
Fig. 2. GSM Module 2006. pp: 3931 - 3934. DOI: 10.1109/IEMBS.2005.1615321
[2]N.Noury, A.Fleury, P.Rumeau, A.K.Bourke, G.O. Laighin, V.Rialle, J.E.Lundy.
4.4 Specfications “Fall Detection-Principles and Methods,” in Proceedings of the 29th Annual Inter-
national IEEE EMBS Conference, Lyon, France, 23-26 August 2007. pp:1663-1666
[3] K. Jonah Ravi, R. China Appala Naidu, "An Advanced Automatic Prior
IJSER © 2018
http://www.ijser.org
International Journal of Scientific & Engineering Research Volume 9, Issue 7, July-2018 2036
ISSN 2229-5518
Notification of Locomotives and its Steering Conditions", International Journal of
Research in Engineering and Science(IJRES) ISSN(Online): 2320-9364, vol. 3, no. 5,
pp. 14-24, May 2015, ISSN 2320-9356.
[4] Yujia Ge, Bin Xu, "Detecting Falls Using Accelerometer by Adaptive
Thresholds in Mobile Devices", Journal of computers, 2014.
[5] Y. Li, G. Chen, Y. Shen, Y. Zhu and Z. Cheng“Accelerometer-based fall
detection sensor system for the elderly”pp. 1216-1220, 2012
[6] W. Wibisono, D. N. Arifin, B. A. Pratomo, T. Ahmad and R. M. Ijtihadie
“Falls Detection and Notification System Using Tri-axial Accelerometer and Gyro-
scope Sensors of a Smartphone” pp. 382-385, 2013
[7] K. Navatha, R. China Appala Naidu, K Naga Durga Saile, K. Meghana,
"Implementation of Trouble Intimation System in GSM & GPS Based Mo-
biles", International Journal of Advanced Research in Computer and Communication Engi-
neering ISSN(Online):2278-1021, vol. 4, no. 10, pp. 195-198, October 2015, ISSN 2319-
5940.

Authors:
1) Mr.Mohd Nadim
Galfar Engineering and Contracting SAOG,
Muscat, Oman.
Mail id: [email protected]

IJSER
2) Mr.S.Aravindh
Bannari Amman Institute of Technology,
Erode (Dt.), Tamil Nadu, and India.
Mail id: [email protected]
3) Mr.Qayyum Khan
Galfar Engineering and Contracting SAOG,
Muscat, Oman.
Mail id: [email protected]
4) Ms.Rizwana
Aligarh Muslim University,
Aligarh, Uttar Pradesh, India
Mail id: [email protected]

IJSER © 2018
http://www.ijser.org