IRJET - Improving Road Travel with Route Suggestion using Decision Tree Algorithm

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 04 | Apr 2020 www.irjet.net p-ISSN: 2395-0072
© 2020, IRJET | Impact Factor value: 7.34 | ISO 9001:2008 Certified Journal | Page 498
Improving Road Travel with Route Suggestion using Decision Tree
Algorithm
Sheryl Francis1, Muskan Shaikh2, Nihal Lanjewar3, Shivani Waghmale4, Dr.Mrs. M.A. Potey5
1,2,3,4Student, Dept. of Information Technology, D. Y. Patil College of Engineering, Akurdi
5Professor, Dept. of Information Technology, D. Y. Patil College of Engineering, Akurdi
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Use of Smart phones is nowadays a necessity for
monitoring as well as identifying thedifferentroadconditions.
In the proposed system, accelerometer and gyroscope which
are inbuilt sensors in mobiles are used. The collected data is
processed using certain algorithms. Taking into account, data
from both accelerometer and gyroscope, helps in achieving
better estimation than the model that takes into account the
magnitude from the accelerometer and the average speed
alone. GPS system of the smart-phones will be used for
capturing the location.
Key Words: Classify collect data, Send collect data for
classification, Update for current location, Road
condition of current location, Accelerometer.
1. INTRODUCTION
Roads have been used as a mode of transport from ages. It is
considered as the most basic mode of transport which
connects places in urban cities as well as rural places to
some extinct. The United States have the largest road
network across the world, followed by India in second
position. The road network in India is around, 5,903293 km
(by 2017). This road network helps in transporting64.5%of
the all goods in the country, also 90% of citizens of India use
roads for their daily commutation. According totheMinistry
of Road Transport and Highways,India,1,46,000people had
died due to roadaccidentsin 2015.Soapproximately10-12%
of the fatalities occurring in road accidents have been
recorded in India. Deadly road accidents are witnessedquite
often in India due to the bad condition of roads as well as
reckless, negligent driving. Accordingtoanofficial report, on
an average 400 deaths take place every day in India due to
road accidents. The condition of roads changes rapidly due
to usage and natural calamities. It also usually requires a
huge investment of time to collectthedata ona regularbasis.
Obtaining such data is often a challenge thatthegovernment
is facing, especially in countries where budget is limited and
advance technology is still not affordable.Theroughnessofa
particular road surface is an important aspect while
analyzing the road conditions, because it affects various
factors such as vehicle maintenance costs,fuel consumption,
comfort, and safety of the passengers. The different
conditions of road are measured normally using one or a
combination of two main approaches, which include a
ratings based on personal opinions and experiences or a
visual inspection, an approach that is consumes a lot of time
and requires a lot of man power; and the use of the
sophisticated pro-filers, which are highly accuratebutcostly
to obtain, operate and maintain, requires skillful operators
as well as cumbersome calibration before deployment. Our
system works on providing a route to the user which is
comfortable to travel i.e. a road in good condition. This
system includes incorporation of mobile-based sensors
along with GPS to provide routes.
2. LITERATURE SURVEY
 In [1] the researchers explore a low cost and easier
way for continuous road condition monitoring by
obtaining road surface(roughness) and traffic
conditions using data collected by sensors from
smart phones under realistic settings in which the
smart phones are placed at more realistic locations
and under realistic manner inside a moving vehicle,
to evaluate its relationship with the actual road
pavement roughness.
 In [2] the researchers have identified bad road
conditions such as potholes, bump which helps
drivers as well as authorities to use and maintain
the roads. Use of mobile sensorsaremostimportant
part of the evolving technology; this is explained in
this paper. By supervising roads and using
algorithm to detect and store the data about
potholes this paper gives us all analogies. Different
mobile sensors such as gyroscope, magnetometer
and accelerometer are being usedtocreatevaluable
data which further is used for algorithms
 In [3] a vibration based approach has been
presented which automatically detects the pothole
and speed-breakers with their severity levels. This
paper discusses about the monitoring of road
condition using android's built in accelerometer
which records 3-axis acceleration. This is stored in
local database. Various technologieslikeP2(Pothole
Patrol) is discussed. Proposed approachcanbevery
easily deployed on any android basedsmart-phone.
 In [4], researchers have built a system which is
capable of collectingdata regardingroad'scondition
with the help of an accelerometer and helps
visualizing this data by integrating with GPS. Data
collected was processed which yielded almost
accurate results. As data collection through this
method needs more efforts, researches have

concluded that in future a system working with less
efforts can be developed.
 In [5], the researches have involved a machine
learning method which is supervised learning.Here
data regarding the road is collected by an
accelerometer of a smart phone. The end result
helped the researches to distinguish among the six
types of road conditions such as slope, stairs, rough
etc.
 In [11], data was collected from accelerometers as
well as gyroscope along with additional hardware
such as Raspberry Pi, all mounted on a test vehicle.
Then a genetic type algorithm like GALGO [12] is
used for processing this data.
 A sensor known as accelerometer is used here to
collect data. Also they have integrated with GPS for
collecting the data. An approach to monitor road
surface with accelerometer along with GPS is done
in [9]
3. LIMITATIONS OF EXISTING SYSTEMS
Existing systems provide only status of road and not any
other information like traffic update. The computations
involved are very complex and require a lot of calculations.
Most of the existing systems require external hardware
devices and sensors which increases the cost.
4. PROPOSED SYSTEM
Proposed system usessmart phones whichanalyzestheroad
condition and road surface. Sensors present in mobile such
as accelerometer and gyroscope are being used, along with
GPS in Google Maps. These conditions are saved in a
database. If the user is going to that destination for the very
first time, then system will show the shortest path or best
route as per the Google maps. Then Decision tree algorithm
is applied on the inputs taken inthedatabasedetected by the
sensors. Proposedsystemis havinga databasewhichcollects
data with the help of android smart phones present in the
vehicle. This data updates in real time periodically.
Application utilizes this data to inform other application
users about road condition. Proposed system doesn’t need
any extra hardware. This system utilizes sensors already
present in most of the smart phones today.
4.1 System Architecture
The user will place smart phone on dash board of a carandit
will start the application. The applicationwill startcollecting
data through the sensors. The collected data from the
application will be analyzed and classified into various
categories and then it will be uploaded on the server. Server
will store the data into the database. The application will
collect real time data about the road condition. The data
stored in the database will be updated into the database
frequently. If there is any other application user on same
location, then the system will inform that user about the
road condition and traffic status. The architecture is shown
in Figure 1.
Figure 1 System Architecture
4.2 Algorithm
To improve and yield better system result we use decision
tree algorithm. Decision tree is a type of supervised learning
algorithm. It is mostlyusedinmachinelearningclassification
problems in which predefined output is provided for
particular input. In this technique, the data is split into two
or more groups or sets based on certain logic or conditions
applied on the input variables. An example is shown in
Figure 2 for reference.

Figure 2 Decision Tree Algorithm
4.3 Implementation
System’s first requirement will be the GPS must be on for
user’s current location. So user has to enable GPS first. Then
system will start the service and will show initial values of
accelerometer and gyroscope in the form of X, Y and Z co-
ordinates (Figure 3). After that user needs to enter the
source and destination. As soon as user starts moving the
values of accelerometer and gyroscope start updating.In the
end if the average value of accelerometer and gyroscope is
beyond threshold value then that route will beconsideredas
bad route. If the value is below Threshold value, then it will
be considered as comfortable route. It measures the
vibration of motion of a structure. The force because of
vibration, an electrical charge is created t is proportional to
the force exerted upon it. Using this statistics accelerometer
generates the required value. Gyroscope works on the
rotational axis configured (Figure 4), according to the
movement of the mobile phone it gathers the calculated
values of movements. It identifies potholes and gives
notification to system. Along with this decision tree
algorithm is used.
Figure 3 Screenshot of Application
Figure 4 Gyroscope Axis
5. FUTURE SCOPE
This system application can be used by all the frequent road
travelers for safer and comfortable travelling. Various cab
providing services such as uber, ola etc. can use this
application for safer and comfortable customer experience.
Cab drivers can choose more comfortable routeaccording to
the customers’ comfort level. Various travel agencies as well
as public transport can make use of this application for
smooth functioning. This application can also prove to be
very beneficial in emergency cases such as providing route
to ambulances. If there is any bump or speed breaker on the
road the system application will immediatelydetectit.Inthis
way, it will provide safer environment for the patients in
critical condition. Various speed breakers, potholes, bumps

are not visible at night times. People who travel at night
times can use this application for a safer travel experience.
People who travel through village roads can use this
application for a safer travel experience as village roads are
full of potholes and not in proper condition. Dangerous road
accidents can be avoided by making use of this application.
6. CONCLUSION
We have used an accelerometer as well as gyroscope sensor
in the Proposed system which collects the data. Also GPS is
used for current location. Decision tree algorithm will be
implemented in this system, grouping of two sensors;
accelerometer and gyroscope will yield better results.
Hardware usability is reduced, due to this approach as this
includes the use of software. As smart phones are used by a
numerous amount of people and they also travel on a large
scale this will help in every aspect to provide more
comfortable travelling suggestions. Because of the smart
phones we need not to deploy special sensors in vehicle. As
number of smart phone users is increasing day by dayhence
using smart phones is a biggest advantage. Thus,thissystem
aims to provide its various users a better brief about the
routes of their transportation.
REFERENCES
[1] V. Douangphachanh and H. Oneyama, "Estimation of
road roughness condition from smartphones under
realistic settings," 2013 13th International Conference
on ITS Telecommunications (ITST), Tampere, 2013, pp.
433-439.
[2] G. A. Kumar, A. S. Kumar, A. A. Kumar and T.
Maharajothi, "Road quality management system using
mobile sensors," 2017 International Conference on
Innovations in Information, Embedded and
Communication Systems (ICIIECS), Coimbatore, 2017,
pp. 1-6.
[3] V. Rishiwal and H. Khan, "Automatic pothole and speed
breaker detection using android system," 2016 39th
International Convention on Information and
Communication Technology, Electronics and
Microelectronics (MIPRO),Opatija,2016,pp.1270-1273.
[4] S. B. Prapulla, S. N. Rao and V. A. Herur, "Road quality
analysis and mapping for faster and safer travel," 2017
International Conference on Energy, Communication,
Data Analytics and Soft Computing (ICECDS), Chennai,
2017, pp. 2487-2490.
[5] Y. Ikeda and M. Inoue, "An estimation of road surface
conditions using participatory sensing," 2018
International Conference on Electronics, Information,
and Communication (ICEIC), Honolulu,HI,2018,pp.1-3.
[6] K. Kojima, H. Taniue and J. Kaneko, "Mahalanobis
distance-based road condition estimationmethodusing
network-connected manual wheelchair," 2016 IEEE
International Conference on Consumer Electronics-
Taiwan (ICCE-TW), Nantou, 2016, pp. 1-2.
[7] T. Satoh, A. Hiromori, H. Yamaguchi and T. Higashino,"A
novel estimation method of road condition for
pedestrian navigation," 2015 IEEE International
Conference on Pervasive Computing and
Communication Workshops (PerCom Workshops), St.
Louis, MO, 2015, pp. 427-432.
[8] J. C. Tudón-Martínez, S. Fergani, O. Sename,J.J.Martinez,
R. Morales-Menendez and L. Dugard, "Adaptive Road
Profile Estimation in Semiactive Car Suspensions," in
IEEE Transactions on Control Systems Technology, vol.
23, no. 6, pp. 2293-2305, Nov. 2015.
[9] M. Strutu, G. Stamatescu and D. Popescu, "A mobile
sensor network based road surface monitoringsystem,"
2013 17th International Conference on System Theory,
Control and Computing (ICSTCC), Sinaia, 2013, pp. 630-
634.
[10] Kongyang Chen, Mingming Lu, Xiaopeng Fan, Mingming
Wei and Jinwu Wu, "Road condition monitoring using
on-board Three-axis Accelerometer and GPS Sensor,"
2011 6th International ICST Conference on
Communications andNetworkinginChina (CHINACOM),
Harbin, 2011, pp. 1032-1037.
[11] J. M. Celaya-Padilla, C. E. Galván-Tejada, F. López-
Monteagudo, O. Alonso-González, A. Moreno-Báez, A.
Martínez-Torteya, J. I. Galván-Tejada, J. G. Arceo-Olague,
H. Luna-García, and H. Gamboa-Rosales, "Speed bump
detection using accelerometric features: a genetic
algorithm approach," Sensors, vol. 18, p.443, 2018.
[12] Trevino, V.; Falciani, F. GALGO: An R package for
multivariate variable selectionusinggeneticalgorithms.
Bioinformatics 2006, 22, 1154–1156.]

IRJET - Improving Road Travel with Route Suggestion using Decision Tree Algorithm

Recommended

More Related Content

What's hot (20)

Similar to IRJET - Improving Road Travel with Route Suggestion using Decision Tree Algorithm (20)

More from IRJET Journal (20)

Recently uploaded (20)

IRJET - Improving Road Travel with Route Suggestion using Decision Tree Algorithm