IRJET- Offline Location Detection and Accident Indication using Mobile Sensors

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 05 Issue: 03 | Mar-2018 www.irjet.net p-ISSN: 2395-0072
© 2018, IRJET | Impact Factor value: 6.171 | ISO 9001:2008 Certified Journal | Page 3537
OFFLINE LOCATION DETECTION AND ACCIDENT INDICATION USING
MOBILE SENSORS
Mrs S.T.SANTHANALAKSHMI1, R.SAMPADA2, C.S.MAHASHRI3, NANDHINI BASKARAN4
1ASST PROFESSOR, DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING, PANIMALAR
ENGINEERING COLLEGE, TAMIL NADU, INDIA
2,3,4 STUDENT, DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING, PANIMALAR
ENGINEERING COLLEGE, TAMIL NADU, INDIA
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - The usage of technology has ended up being a
value asset. Nowadays, from PCs to mobile phones,
advancement in the society is large . Because of these ideal
circumstances, new research has to make structures and
applications to help with people's prosperity, for instance,
recognizing accident with the usage of mobile phones. The
system is made out of three kinds of fragments: data
gathering, range decision, and Spot ID. It utilizes the wireless'
intrinsic sensors (accelerometer) to recognizetheregionofthe
mobile phone and once a zone is perceived, the accident
distinguishing proof portion happens. A general depiction on
fall area systems is given, including the differing sorts of
sensors used nowadays. The proposed course of action is
presented and depicted in wonderful unobtrusive component.
The accident detection results can be used as important cues
to assist many other human oriented tasks, for instance,
people tracking and human gait recognition.Thesedevicescan
be handy and it is comfortable to use.
Key Words: Accident detection,Offline tracker,
Mobile sensors,Location
1.INTRODUCTION
Accidents have been the major cause of injury in recent
years. To protect the people from the injury of accidents or
to give immediate assistance after the occurrence of an
accident , many researches have been devoted to the design
of a accident detection algorithm and system . Among all the
currently proposed algorithms, the system can be roughly
divided into two categories , namely, environmental
monitoring based , and wearable sensor-based systems.
Digital Object Identifier, pressure sensors , or accelerometer
for vibration detection are placed in a predefined space or
environment to monitor the activities of the people as well
as the occurrence of a accident event. Compared to the type
of wearable sensor-based system, the environmental
monitoring-based system ismore comfortable since thereis
no need of wearing any module. However,theenvironmental
monitoring-based system can only function in a predefined
environment where it is installed. Moreover, the protection
of the private matter is another problem and contention is
usually discussed with the environmental monitoring-based
system .
1.1 EXISTING SYSTEM
To design and develop a prototype of an electronic gadget
which is used to detect fall among elderly and the patients
who are prone to it. In this article, the body posture is
derived from change of acceleration in three axes, which is
measured using triaxial accelerometer.Toprotecttheelderly
from the injury of fall accident events or to give an
immediate assistance to the elderly after the occurrence ofa
fall accident event, many researches have been devoted to
the design of a fall detection algorithm and system . Among
all the currently proposed algorithms, the fall detection
system can be roughly divided into two categories, namely,
environmental monitoring based , and wearable sensor-
based systems. Pressure sensors or accelerometer for
vibration detection are placed in a predefined space or
environment to monitor the activities of the elderly as well
as the occurrence of a fall accident event.
1.2 PROPOSED SYSTEM
To design and develop a prototype where we can detect any
accident even in rural areas and find the exact location with
great accuracy with the help of our smart phones. This
system uses three intrinsic sensorswhichareaccelerometer,
gyroscope and magnetometer. These sensors help in
identifying the movement ,velocity of the smart phone and
calculate their values. The main advantage of this system is
that it works even offline. This system gets the location of
the smart phone from the satellite at regular intervals .
Initially the user is required to enter the emergency contact
number to which the alert message along with thelocationis
to be sent and has to set the base range value for all thethree
sensors. Whenever there is an abnormal movement in the
smart phone then the values of the three sensors varies and
if it exceeds the particular base value then the alert message
is automatically sent to the emergency contact along with
the location.
1.3 PROBLEM STATEMENT
Usually when an accidents occur ,the location of the phone
and where the phone was last active is tracked by the
police.The radius obtained is very large.This makes it even
harder to find the injured person .In this system,we can
obtain the location using satellite even when the user is

offline. When a user has met with an accident at a remote
location no one is aware of it this technique can will be
helpful.In this system when an accident occures the mobile
sensors trigger the satellite to send the location of the
person to any two selected contacts.
2. ARCHITECTURAL DESIGN
2.1 SYSTEM ARCHITECTURE
The first step is to login/register. In this modulewedesignto
develop login and signup screen. Android used xml to
develop classical screens in our application. The modules
describe signup page contains email id or user name,
password and confirm password those kindofdetailsshould
be stored in database. Login screen contains email id or
username and password when the user wants to login the
app, it should retrieve the data to the database and combine
based on user input. if it matchesuser name andpassword it
allows the user to enter into the app otherwise shows an
alert message to the user.
The next step is to create database. The user email idoruser
name and password have been stored after registration.
Android uses MYSQL Database for storing and fetching user
application details. Then we have to start the session. After
login, the Authenticated user go to Home screen to start the
session, where we have to add the emergency number and
the message that has to be sent. These data are added to the
Cloud application. In this module we can also update your
friend mobile number and Message options. The start
session button appears after this process.
FIG 1: architecture design
Next the mobile’s motion is checked. The body posture is
derived from change of acceleration in three axes, which is
measured using tri axial accelerometer. After the activity is
started, user can find motion variation from change of
acceleration in three axes , which is measured using tri axial
accelerometer. user can now view the accelerometer
changes. Finally, after calculating the variances in all the
three sensor valuesnow it gets the location fromthesatellite
and sends it to the favourite contacts. Thus the location is
sent successfully.
FIG 2: contectivity diagram
3. ALGORITHM
Deployment Algorithm Details The proposed deployment
algorithms are iterative, and in each iteration, the following
steps are carried out.
1) All sensors broadcast their sensing radii and positions.
Thus, based on the received information, every sensor
constructs its own region, given a guaranteed diagram.
2) Every sensor detects coverage holesin itsown region ina
distributed manner (i.e., independently).
3) After discovering the coverage holes, by using a specific
movement algorithm (which will be discussed in Section V-
B), the corresponding sensor calculates its new candidate
location.
4) Once the new location is calculated, the corresponding
coverage area is evaluated (based on the previously
constructed region) and compared with the current
coverage area. The sensor moves to the new location only if
the resulting coverage area isgreater than the presentvalue;
otherwise, it does not move in this iteration.
5) To have a termination criterion for the algorithm ,a
proper threshold δ is defined; the algorithm is terminated if
no sensor can improve itscoverage area by this thresholdor
a predefined number of iterations (Imax) has been
completed. δ and Imax are chosen based on which of the
coverage, energy consumption, or convergence time is the
main concern. For example, when the convergence time or
the energy consumption is the main concern, the operator
chooses a relatively small Imax and relatively large δ in the
beginning. On the other hand, when the coverage is the most
important concern, a relatively large Imax and a small

threshold δ are chosen by the operator such thatthecovered
area increases as much as possible.
The deployment algorithms are iterative, and in each
iteration, it is tried to improve the total coverage, at least as
much as a threshold δ>0. The algorithm is stopped if no
improvement is possible or a certain number of iterations
(Imax) have passed. Algorithm 1 briefly describes the
farthest point-based GAWVD (FPGAW) method. The
deployment algorithm for the other algorithms(i.e.,FPGMW
and MPGP) is exactly the same, except that the movement
algorithm changes accordingly.
Deployment Algorithm for the FPGAW
k ←0, iterations←0,D←1
whileD = 1 and iterations <Imax do
for i = 1 ton do
• construct Πi according to(9) and set Πk i ← Πi
• find πk i (the area of the ith region that is covered by si)
end for
• iterations←iterations + 1
• k ← k + 1
• C←0
for i = 1 ton do
• calculate a new location (pk i ) for si, based on the FPGAW
movement strategy
• evaluate πk i based on the new location for the current
region (Πk−1 i )
if πk i >π k−1 i + δ then
move si to pki
C←C+ 1
end if
end for
if C = 0 do
D = 0
end if
end while
4.CASE STUDY
We propose an optimization-based path-planning
framework for an aerial mobile sensornetwork.Thepurpose
of the path planning is to monitor a set of moving surface
objects. The algorithm providescollision-free mobilesensor
trajectories that are feasible with respect to user-defined
vehicle dynamics. The objective of the resulting optimal
control problem is to minimize the uncertainty of the
objects, represented as the trace of the augmented state and
parameter estimation error covariance. A Voronoi-based
strategy is proposed to maximize the sensing coverage in a
mobile sensor network. Each sensor is moved to a point
inside its Voronoi cell using a coverage improvement
scheme.To this end,a gradient-based nonlinearoptimization
approach is utilized to find a target point for each sensor
such that the local coverage increases asmuch as possible, if
the sensor moves to this point. The algorithm is
implemented in a distributed fashion usinglocalinformation
exchange among sensors. Analytical results are first
developed for the single sensor case,and are subsequently
extended to a network of mobile sensors, where it is
desirable to maximize network-wide coverage with fast
convergence. It is shown that under some mild conditions,
the positions of the sensorsconverge to a stationary pointof
the objective function, which is the overall weighted
coverage of the sensors. Simulations demonstrate the
effectiveness of the proposed strategy. Voronoi-based
mobile sensor deployment algorithms require the
knowledge of sensors’ locations to guarantee a simple
reliable coverage detection, and they miss the mark if the
location is inaccurate. However, in practice, it is often too
expensive to include a Global Positioning System (GPS)
receiver in each node, and location information isinaccurate
as sensors estimate locations from the messages they
receive. We study sensor deployment algorithms in the
presence of location estimation error for sensors with
nonidentical sensing ranges. We propose a set of Voronoi-
based diagrams, which are called guaranteed Voronoi
diagrams (VDs), that guarantee single-cell-based coverage
hole detection algorithms, provided that upper bounds on
localization errors are assumed.. Hence, even if the location
information is exactly known at each node, assuming some
error margins improvesthe network coverage if guaranteed
Voronoi diagrams are used.
Efficient deployment algorithmsare developed in thispaper
to increase the coverage area in a networkofwirelessmobile
sensors. The proposed strategies iteratively compute the
new candidate position of each sensor based on the existing
coverage holes. These holes are obtained using a Voronoi
diagram for the case of sensors with the same sensing
ranges,and a multiplicatively weighted Voronoi (MW-
Voronoi) diagram for the case of sensors with different
sensing ranges. Each sensor is driven by some virtual forces
which are applied to it from the vertices and boundaries of
itsVoronoi cell. These forces are obtained in such a way that
when the sensor is relocated, the covered area of the

corresponding cell increases.Simulationresultsdemonstrate
the efficacy of the proposed strategies, and their superiority
to existing algorithms. HazeEst—a machine learning model
that combines sparse fixed station data with dense mobile
sensor data to estimate the air pollution surface for any
given hour on any given day in Sydney. We assess our
system using seven regression models and tenfold cross
validation. The results show that estimation accuracy of
support vector regression (SVR) is similar to decision tree
regression and random forest regression, and higher than
extreme gradient boosting, multi-layer perceptrons, linear
regression, and adaptive boostingregression.Ourresultscan
be visualized using a Web-based application customized for
metropolitan Sydney. We believe that the continuous
estimates provided by our system can better inform air
pollution exposure and its impact on human health.We
consider the design of a pair of moving sensors trajectories
for the purpose of optimally localizing a stationary emitter
based on time-difference-of-arrival measurements.The
localization error covariance matrix is predicted by the
Cramér–Rao bound.
5. CONCLUSION
We propose in this paper a smart phone-based pocket fall
accident detection system. The fall detection algorithm is
realized with the proposed state machine that investigates
the features in a sequential manner. Once the corresponding
feature is verified by the current state, it can proceed to next
state; otherwise, the system resets to the initial state and
waiting for the appearance of another feature sequence. To
speed up the efficiency of classification process, the early
states are composed of simple and important features that
allow a large number of negative samples to be quickly
excluded from being regarded asa fall event. Those complex
features are then placed in later states. With the proposed
algorithm, the computational and power consumption
burden of the system can be alleviated. Moreover, a
distinguished performance up to 92%on the sensitivity and
99.75% on the specificity can be obtained when a set of 450
test activities in nine different kinds of activities are
estimated by using the proposed cascaded classifier with
SVM, which demonstrates the superiority of the proposed
approach
REFERENCES:
[1] G. Acampora, D. J. Cook, P. Rashidi, and A. V. Vasilakos, “A
Survey on ambient intelligence in healthcare,” Proc. IEEE,
vol. 101, no. 12, pp. 2470–2494, Dec. 2013.
[2] P. Rashidi and A. Mihailidis, “A survey on ambient-
assisted living tools for older adults,” IEEE J. Biomed. Health
Informat., vol. 17, no. 3, pp. 579–590, May 2013.
[3] M. Mubashir, L. Shao, and L. Seed “A survey on fall
detection:Principles and approaches,” Neurocomputing,vol.
100, no. 16, pp. 144–152, 2013.
[4] T. Shany, S. J. Redmond, M. R. Narayanan, and N. H.Lovell,
“Sensors- Based wearable systemsfor monitoring of human
movement and falls,” IEEE Sensors J., vol. 12, no. 3, pp. 658–
670, Mar. 2012.
[5] B.Mirmahboub, S. Samavi,N.Karimi, and S. Shirani,
“Automatic monocular system forhumanfalldetectionbased
on variations in silhouette area,” IEEE Trans. Biomed. Eng.,
vol. 60, no. 2, pp. 427–436, Feb. 2013.
[6] M. Yu, Y. Yu, A. Rhuma, S. M. R. Naqvi, L. Wang, and J. A.
Chambers, “An online one class support vector machine-
based person-specific fall detectionsystemformonitoringan
elderly individual in a room environment,” IEEE J. Biomed.
Health Informatics, vol. 17, no. 6, pp. 1002–1014, Nov. 2013.
[7] M. Yu, A. Rhuma, S. M. Naqvi, L. Wang, and J. Chambers,“A
posture recognition-based fall detection system for
monitoring an elderly person in a smarthomeenvironment,”
IEEE Trans. Inf. Technol. Biomed., vol. 16, no. 6, pp. 1274–
1286, Nov. 2012.
[8] E.Auvinet, F. Multon, A. Saint-Arnaud, J. Rousseau, and J.
Meunier, “Fall detection with multiple cameras: An
occlusion-resistant method based on 3-D silhouette vertical
distribution,” IEEE Trans. Inf. Technol. Biomed.,vol.15,no.2,
pp. 290–300, Mar. 2011.
[9] C. Rougier, J. Meunier, A. St-Arnaud, and J. Rousseau,
“Robust video surveillance for fall detectionbasedonhuman
shape deformation,” IEEE Trans. Circuits Syst. Video
Technol., vol. 21, no. 5, pp. 611–622, May 2011.
[10] Y. Li, K. C. Ho, and M. Popescu, “A microphone array
system for automatic fall detection,” IEEE Trans. Biomed
[11] A. Ariani, S. J. Redmond, D. Chang, and N. H. Lovell,
“Simulated unobtrusive falls detection with multiple
persons,” IEEE Trans. Biomed. Eng., vol. 59, no.11,pp.3185–
3196, Nov. 2012.
[12] M. Mercuri, P. J. Soh, G. Pandey, P. Karsmakers, G. A. E.
Vandenbosch, P. Leroux, andD. Schreurs, “Analysis of an
indoor biomedical radar-based system for health
monitoring,” IEEE Trans.Microw. Theory Tech., vol.61,no.5,
pp. 2061–2068, May 2013.
[13] H. Rimminen, J. Lindström, M. Linnavuo, and R.
Sepponen, “Detection of falls among the elderly by a floor
sensor using the electric near field,” IEEE Trans.Inf.Technol.
Biomed., vol. 14, no. 6, pp. 1475–1476, Nov. 2010.
[14] Y. Zigel, D. Litvak, and I. Gannot, “A method for
automatic fall detection of elderly people using floor
vibrations and sound-proof of concept on human mimicking
doll falls,” IEEE Trans. Biomed. Eng., vol. 56, no. 12, pp.
2858–2867, Dec. 2009.

[15] L. Tong, Q. Song, Y. Ge, and M. Liu, “HMM-Based human
fall detection and prediction method using tri-axial
accelerometer,” IEEE Sensors J., vol. 13, no. 5, pp. 1849–
1856, May 2013.
[16] W.-C. Cheng and D.-M. Jhan, “Triaxial accelerometer-
based fall detectionmethod using a self-constructing
Cascade-AdaBoost-SVM classifier,” IEEE J. Biomed. Health
Informatics, vol. 17, no. 2, pp. 411–419, Mar. 2013.
[17] D. Naranjo-Hernandez, L. M. Roa, J. Reina-Tosina,andM.
A. Estudillo- Valderrama, “Personalization andadaptationto
the medium and context in a fall detection system,” IEEE
Trans. Inf. Technol. Biomed., vol. 16, no. 2, pp. 264–271,Mar.
2012.

IRJET- Offline Location Detection and Accident Indication using Mobile Sensors

More Related Content

What's hot (20)

Similar to IRJET- Offline Location Detection and Accident Indication using Mobile Sensors (20)

More from IRJET Journal (20)

Recently uploaded (20)

IRJET- Offline Location Detection and Accident Indication using Mobile Sensors