ABSTRACT

Accident black spots are usually defined as road locations with high accident potentials. In
order to detect such hazardous locations, we have to know the probability of an accident for a
traffic situation of some kind, or the mean number of accidents for some unit of time. In
almost all procedures known to us, the various road locations are treated as isolated spots.
With small accident figures it is difficult to detect such places in the known procedures. Now
a day, road safety has become a major concern throughout the world. Road accident is a
pressing problem leading to live loss, property loss and severely impacting the society. Based
on the recent statistics, more than one million people were died due to road accident, and
approximately twenty to fifty million people were physically disabled as a result of Road
accident for the past few years. As Transportation increases, on the other hand accident rate
also increased steadily. The main cause of road accidents deals with various parameters such
as road type, vehicle fault, drunken drive etc. Beside all these reasons the lack of proper road
side sign boards play a vital role in accident count. The road side sign boards indicating the
accident spots were placed only at the exact spot, so the drivers were not aware of the black
spot areas on their way. Road accident cannot be totally avoided but by using suitable traffic
engineering safety plan and management measures, the accident rate can be reduced. The
algorithm to filter out black spot region from the large accident Dataset will be obtained by
using Accident severity index and Accident density method. The purpose of identifying
accident hotspots is to achieve high-priority locations in order to effectively allocate the
safety budgets as well as to promote more efficient and faster safety at the road network
level. As the volume of the collected data increases, Machine Learning (ML) techniques are
applied to further enhance the intelligence and the capabilities of an application.
 INTRODUCTION

Road network of a country is one of the most important factors responsible for the economic
and social development of that country. India has a high population and requires a large
amount of transportation services like air, land and water transportation. Road network is the
only means of transportation which has deep penetration in all areas and responsible for door
to door service. Hence it is very important to increase and maintain the road network of our
country.
Tamilnadu is one of the fastest growing states in India. The main reason for its development
is its wide road network which facilitates a better and faster transportation which helps in its
overall development. With increase in population the number of vehicles is also increasing
which are responsible for occurrence of a greater number of accidents. This causes an
obstruction is the economic and social development. To avoid this the accident-prone zones
on the highways must be studied, identified and rectified to reduce the accidents. An
accidental black spot is a term used in road safety management to denote a place where road
traffic accidents have historically been concentrated. It has been observed that almost 13
people die in road accidents all around the world every hour. According to World Health
Organization (WHO) road accidents are the leading cause of death amongst people aged
between 15-29. At the time of designing of national highway, vision is to construct accident
free highway for that purpose normal causes of accidents are taken into consideration. For
present study accidental data collected from National Highway Authority of India NHAI is
analysed by Ranking Method and black spot on national highway was found out.

Accident
Accident is defined as an error in driver-vehicle-roadway system and it must be recognized
that different types of accidents are caused due to different at any given location namely,
rear-end, side-swipes, head-on, night-time, bad-weather, etc. for instance, predominance of
rear-end accidents will indicate slippery pavement whereby the drivers have difficulty in
stopping in time. Side-swipe accidents will indicate ambiguous traffic control devices,
causing confusion among the drivers regarding right-of-way. Head-on collisions signify lack
of adequate sight distances at the location. Predominance of night-time accidents at the
location will indicate serious problems with night time visibility. Bad weather accidents can
result due to a road pavement which becomes dangerously slippery when wet or it may be
due to inadequate signs for inclement weather. Similarly, there are numerous other types of
accidents which occur due to a variety of reasons. The job of the accident’s analyst is,
therefore, to relate the accidents experience at any location to one or more causes. The state
of the art permits such treatments.
Black spots (BS)
According to previous studies, black spot was originally defined as “a road location of
limited are with a high concentration of accidents”. The term “Black spots” is said to derive
from the method that was originally used to identify hazardous sites. Accidents were
pinpointed on a map, using coloured pins to represent the trauma severity of each of these
events. Black was reserved for accidents having caused property damage only and the
significant proportion of these accidents created black dots at concentration points. There is
no universally accepted definition of a Black spot to the best knowledge of the author. The
terms “hazardous location” and “high accident locations” often used as synonym. This
definition has progressively evolved as several researchers now recommend including the
concept of “Potential for Improvement (PI)”.

WHAT IS BLACK SPOT

An accident black spot is a term used in road safety management to denote a place where
road traffic accidents have historically been concentrated. Black spot methods are designed to
identify the prone spots in particular stretch and reduce the crash risk in that area by
providing remedial measures. Identification of locations for safety improvement is the
starting point of all the processes. The process is sometimes known as black spot
identification or hazardous
identification location. Generally black spot is termed to define the location where many
accidents have occurred and risk (severe, major, and minor) is involved in that accident.

1.1. Causes of black spots and their remedial measures

Insufficient law enforcing agencies, improper road infrastructure, lack of proper warning
signs, inadequate illumination on footpaths and cycle tracks, poor emergency response
capability and injustice in the implementation of traffic laws are the main causes of road
accidents. Transporters do not care for the fitness of their vehicles and keep on modifying the
chassis/ frame of their vehicles without engineering specifications. They equip their vehicles
with illegal and inappropriate manner and engage such drivers who are alcoholics and drug
users on low wages. Lack of proper driving school also leads to accidents; While conducting
black spot study in an urban area, after collecting the accident’s information from respective
agencies, police stations, analysis of the location should be made using spot speed studies,
vehicles classification and driver studies, cost benefits and other relevant set of studies.
Further steps adopted for analysis of black spots are: recording the accidents and data
entering onto computer; finding sites with high number of accidents and commonly known as
black spots; weight sites for severity and exposure. Initial accident investigation and site
visits; rank sites for in depth investigation; collection of further data from accident forms/site
studies; analysis of data; more detective work; human factors; select and check packages of
counter measures; rank sites for treatment, implementation and construction; monitor
behaviour during first days and months; evaluate the effects on accidents and cost-benefit
analysis.

 Visibility effects

Poor visibilities, inadequate sight distance, braking distances especially on curves are the
major factors in the creation of black spots. At grade intersection, if links are not properly
designed, they may create visibility problem in the driver’s vision. Adequate sight distance as
provided by AASHTO; Green book helps drivers to safely negotiate the hazards while
travelling at design speed. If there is insufficient street lighting at night, or the sun is low on
the horizon, in mist, during rain, fires or storms, reduce the speed below the speed limit.
These conditions reduce vision and prevent a driver from reacting in time to hazardous
situations. If accident occurs on highways, it should be investigated on the basis of degree of
damage or severity of damage. According to AASHTO, if tyre braking impressions are
present on road, we can assume suitable data and work out the speed at which the vehicle hit
the object by using equation 1. Where in driver eye height and object height is assumed as 3.5
feet and 2 feet respectively.

With the help of this equation, it can clearly be estimated that vehicle was traveling with the
speed limits at the time of accidents or not. It gives us the real cause of accident in term of
over speeding, surface friction or unsafe sight distance.
  Geometric effects

Wrong and incompatible geometric designs may lead to sever accidents. Number of black
spots in the road length depends on many factors. In plan areas and straight alignment of the
road, design speed, visibility, width and number of lanes, shoulders width and conditions and
median types have great effects towards the safe movement of vehicles and its service
capacity. It further depends upon the type of roads on its functional classification. In rolling
and mountainous terrains, maximum and minimum grade, critical length of upgrade,
provision of climbing lanes, presence of hidden dips, roller coasters, sky line horizons,
selection of curve type, width and number of lanes are the major geometric parameters that
has mainly be concerned with the black spot identifications. Criteria defined by AASHTO for
maximum grade are based mainly on studies of the operating characteristics of typical heavy
trucks. Table 1 shows the maximum grades permitted for urban arterials.
Table 1: Maximum grades for urban Arterials.

For short length and one way down grades highways with less than 500ft tangent, maximum
grades may be 1% steeper than given in Table 6. One of the important aspects behind black
spots at curves is the attainment of super elevation through tangent run out and run off
distances. According to AASHTO, 66% super-elevation should be attained on tangent and
33% on curve length. It should be attained 100% on runoff if transition curve is provided.
Moreover, rate of transition of edge line from normal crown or cross slope to full super
elevation traditionally taken at 0.5%. Current recommendation varies from 0.35% at 80 mph
to 0.8% for 15 mph (with full adjustments for number of lanes). If super-elevation does not
attain according to the standard criteria as described by the agencies, curve area becomes
hazardous especially for high speed vehicles Maximum effort should be to avoid sharp
horizontal curvature to be introduced near bottom of steep grade near the low point of a
pronounced sag vertical curve.

 Over speeding and reckless driving

Speed is an important transportation consideration because it relates to safety, time, comfort,
convenience, and economics. On account of the measures, which have been taken, the citizen
has readily accepted the system of policing introduced on the motorway. In a little over three
years the Motorway Police has penalized 146,752 offenders mainly due to over speeding.
Only 470 contested police action and there have been no complaints with regards to their
conduct. The solution to over speeding and aggressive driving is to check the vehicle’s spot
speed on the roadway.

 Human errors

The key factor behind the human behaviour towards road accidents is the age, profession,
education and standard of living or the financial status. It has been observed that youngsters
tend to be fast drivers than aged persons. Although this trend exists for both men and women,
but women do not drive as fast as their male contemporaries and this habit pertains to an age
of about 40 years. According to National Research Centre Data Bank, human error was the
sole cause in 57% of all accidents and was a contributing factor in over 90%. In contrast, only
2.4% were due to mechanical fault and 4.7% by environmental factors. The reasons why
humans make so many driving mistakes are to be looked into the inherent limitations of
human information processing. Humans must rely on three fallible mental functions:
perception, attention and memory. The identification of the problems based on the above
stated facts which are related to drivers and vehicles can provide guidelines for future efforts
in the direction of crash and black spots avoidance.

 Vehicular conditions

Contribution of static and dynamic characteristics of vehicles cannot be denied in the analysis
of black spots. Static characteristics of vehicle affecting road design are the dimensions,
weight and height of driver’s seat, clearance and maximum turning angle of vehicle. Where
as dynamic characteristics of vehicles affecting road design are speed, acceleration, vehicle
stability, braking characteristics and some aspects of vehicle body design.

 Education factor
Recently as a pilot project, Govt. has employed a fleet of educated officers on highways to
control the accident ratio, in the absence of which, drivers endanger not only their lives but
also the lives of others. In order to effectively implement the road safety programme, it is
imperative to ensure that the key players possess the skills to accomplish what is required to
them. The drivers should be allowed on the roads only after assuring that they have achieved
an acceptable level of proficiency. The establishment and running of reputable Driver
Training Schools in all large cities is a fundamental requirement.

 Time of day

Early hours of the morning and the middle of the afternoon are the peak times for fatigue
accidents and long journeys on monotonous roads, particularly on motorways, and mostly
drivers fall in sleeps during that period of the day. There are difficulties in determining the
level of sleep related accidents because there is no simple and reliable way for an
investigating police officer to determine whether fatigue was a factor in an accident. This
result in varying estimates of the level of sleep related accidents. A study of road accidents
between 1987 and1992 found that sleep related accidents comprised 16% of all road
accidents and 23% of accidents on motorways.

 Excessive encroachments

Vehicular access for residential and commercial areas involves provision of frontage access
for the free flow of through traffic. The situation becomes more crucial when it is provided at
primary roads. People take advantage of direct access and establishment encroachments along
the access and even primary roads can often be seen. Most of the accidents occur due to land
occupied along the road and excessive pedestrian’s movements, parking, sellers, passenger’s
movements etc.

 Accident reporting centres

The planning and implementation of a comprehensive policy is a necessity in developing a

countrywide strategy related to traffic management. Planning for the future is necessary, and
in this context, it is strongly recommended to compile all relevant information about
accidents would be readily available for analysis and thereby assist in decision making. It is
therefore proposed, that Accident Reporting Centres (ARCs) should be established at major
cities to undertake this task.

 Provision of traffic calming devices

According to Montgomery County, Maryland department, Traffic calming can be defined as

a set of street designs and traffic rules that slow and reduce traffic while encouraging walkers
and bicyclists to share the street. Traffic calming has the objectives, including slowing traffic
speed, reducing cut-through traffic and increasing safety of pedestrians, bicyclists and
vehicles on streets, urban collectors and urban arterials. Selection and implementation of
specific traffic calming tool depends upon its appropriate application. In urban highways and
street of Pakistan, vertical deflection type traffic calming devices like speed humps, speed
cushion, and horizontal deflection type devices like roundabouts, prove to be more efficient
and economical. Speed humps are rounded raised areas placed across the road. Based on
driver’s psychology, current practice of speed hump is different in Pakistan as compared to
Institute of Transportation Engineers (ITE), India design. The speed humps are normally 6
feet long and 6 inches high than ITE design of 12 feet long and 3 to 4 inches high.

The problem of deaths and injuries as a result of accidents is acknowledged to be a global

phenomenon and traffic safety has been a serious concern since the start of the automobile
age, almost one hundred years ago. It has been estimated that over 300,000 persons die and
10 to 15 million persons are injured every year in road accidents throughout the world.
Statistics have also shown that mortality in road accidents is very high among young adults
that constitute the major part of the work force. In order to combat this problem, various road
safety strategies, methods and counter measures have been proposed and used. These
methods mainly involve conscious planning, design and operations of roads. One important
feature of this method is the identification and treatment of accident-prone locations
commonly called black spots.
However, black spots are not the only causes of accidents on the highway. Regression
analysis is a common approach used in modelling highway geometrics, traffic
characterizations and accident frequencies in order to determine other causes of accidents.
Regression analysis highly depends on traffic flow data such as Average Daily Traffic
(ADT). It also requires the researcher to know exactly the dependent variables as well as the
independent variables. Sadly however, in Tamilnadu, data are often looked at from one
dimension. More often than not, the causes for road accidents in developing country like
India may have nothing to do with the highway geometry, or even traffic characterization.
Also, a large number of data mining algorithmic solution exist; but until now, little or no
empirical research has been done on comparing their efficiency especially on road accidents
data set. Therefore, this research work is useful to ascertain which of these Machine Learning
algorithmic solutions will scale better on road accident database.
What is Machine Learning?
Arthur Samuel, a pioneer in the field of artificial intelligence and computer gaming, coined
the term “Machine Learning”. He defined machine learning as – “Field of study that gives
computers the capability to learn without being explicitly programmed”.
In a very layman manner, Machine Learning (ML) can be explained as automating and
improving the learning process of computers based on their experiences without being
actually programmed i.e. without any human assistance. The process starts with feeding good
quality data and then training our machines(computers) by building machine learning models
using the data and different algorithms. The choice of algorithms depends on what type of
data do we have and what kind of task we are trying to automate.
Difference in ML and Traditional Programming

Traditional Programming: We feed in DATA (Input) + PROGRAM (logic), run it on

machine and get output.
Machine Learning: We feed in DATA(Input) + Output, run it on machine during training
and the machine creates its own program(logic), which can be evaluated while testing.

Classification of Machine Learning

Machine learning implementations are classified into three major categories, depending on
the nature of the learning “signal” or “response” available to a learning system which are as
follows: -
Supervised learning: When an algorithm learns from example data and associated target
responses that can consist of numeric values or string labels, such as classes or tags, in order
to later predict the correct response when posed with new examples comes under the category
of Supervised learning. This approach is indeed similar to human learning under the
supervision of a teacher. The teacher provides good examples for the student to memorize,
and the student then derives general rules from these specific examples.
Unsupervised learning: Whereas when an algorithm learns from plain examples without
any associated response, leaving to the algorithm to determine the data patterns on its own.
This type of algorithm tends to restructure the data into something else, such as new features
that may represent a class or a new series of un-correlated values. They are quite useful in
providing humans with insights into the meaning of data and new useful inputs to supervised
machine learning algorithms.
As a kind of learning, it resembles the methods humans use to figure out that certain objects
or events are from the same class, such as by observing the degree of similarity between
objects. Some recommendation systems that you find on the web in the form of marketing
automation are based on this type of learning.
Reinforcement learning: When you present the algorithm with examples that lack labels, as
in unsupervised learning. However, you can accompany an example with positive or negative
feedback according to the solution the algorithm proposes comes under the category of
Reinforcement learning, which is connected to applications for which the algorithm must
make decisions (so the product is prescriptive, not just descriptive, as in unsupervised
learning), and the decisions bear consequences. In the human world, it is just like learning by
trial and error.
Errors help you learn because they have a penalty added (cost, loss of time, regret, pain, and
so on), teaching you that a certain course of action is less likely to succeed than others. An
interesting example of reinforcement learning occurs when computers learn to play video
games by themselves.
In this case, an application presents the algorithm with examples of specific situations, such
as having the gamer stuck in a maze while avoiding an enemy. The application lets the
algorithm know the outcome of actions it takes, and learning occurs while trying to avoid
what it discovers to be dangerous and to pursue survival. You can have a look at how the
company Google DeepMind has created a reinforcement learning program that plays old
Atari’s video games. When watching the video, notice how the program is initially clumsy
and unskilled but steadily improves with training until it becomes a champion.
Semi-supervised learning: where an incomplete training signal is given: a training set with
some (often many) of the target outputs missing. There is a special case of this principle
known as Transduction where the entire set of problem instances is known at learning time,
except that part of the targets are missing.
Applications of Machine Learning
Web Search Engine: One of the reasons why search engines like google, bing etc work so
well is because the system has learnt how to rank pages through a complex learning
algorithm.
Photo tagging Applications: Be it facebook or any other photo tagging application, the
ability to tag friends makes it even more happening. It is all possible because of a face
recognition algorithm that runs behind the application.
Spam Detector: Our mail agent like Gmail or Hotmail does a lot of hard work for us in
classifying the mails and moving the spam mails to spam folder. This is again achieved by a
spam classifier running in the back end of mail application.
Today, companies are using Machine Learning to improve business decisions, increase
productivity, detect disease, forecast weather, and do many more things. With the exponential
growth of technology, we not only need better tools to understand the data we currently have,
but we also need to prepare ourselves for the data we will have. To achieve this goal, we need
to build intelligent machines. We can write a program to do simple things. But for most of
times Hardwiring Intelligence in it is difficult. Best way to do it is to have some way for
machines to learn things themselves. A mechanism for learning – if a machine can learn from
input then it does the hard work for us. This is where Machine Learning comes in action.
Finally, the purpose of this project is to look at historical data of road accidents on one of the
Tamilnadu busiest roads on how can be more analysed in order to discover new knowledge
about road accidents in Tamilnadu and use this knowledge to reduce the carnage on our high
way.
Existing System
 J48. It is the implementation of ID3 algorithm developed by Weka project team and it
is used to generate univariate decision trees.
 Naive Bayes. It is a classifier which classifies based on applying Bayes' theorem with
strong (naive) independence assumptions between the features.
 SMO (Sequentially minimal optimization). It implements sequential minimal
algorithm for training a support vector classifier. It replaces all missing values and
transforms all nominal attribute into binary one.
 Multi-layer perceptron. It develops a network system, and it can be used for difficult
to complex problems. They are very good for approximation.
 Simple CART. This decision tree is normally applicable in data mining to produce a
frame work.
Disadvantages
 Inaccuracies: Mistakes in plotting the data points manually may lead to incorrect
interpretation of the pattern.
 Difficult to identify clusters in a location where accidents are very high
 Disregard for statistical and spatial analysis and a possibility of a personal bias
Proposed System
Roads in large- and medium-sized cities are becoming increasingly congested, which leads to
frequent traffic accidents. To enhance road traffic safety and reduce the traffic accident rate,
effectively identifying accident black spots is of great importance. In this project, the data
from traffic accidents on Tamilnadu, India were selected for the analytical dataset, and eight
impact factors (holiday, day of week, time, rush hour traffic, accident location type, accident
type, weather, responsibility and black spot) were set. The improved K-means clustering
algorithm was proposed to solve the shortcomings of the traditional algorithm, which is
susceptible to outliers and initial clustering centres. Through this algorithm, the traffic
accidents in the dataset were divided into two categories: black spots and non-black spots.
Then, using the updated dataset, we employed SVM to construct a black spot identification
model.

 K- means clustering
The K-means algorithm is a dynamic clustering algorithm based on partitioning. As a
commonly used data-identification approach, there is no particular limitation on the
clustering range, and as long as multiple datasets are independent of each other, they can be
run in parallel.
K-means clustering has been applied to determine the road traffic accident black spots.

 Correlation matrix
Correlation analysis model is introduced to find the key factors that have a strong correlation
with traffic accident black spots.

 SVM
SVM (support vector machine) is an algorithm for classifying linear and nonlinear data. Its
basic idea is to map spatially inseparable data through a kernel function to a high-dimensional
space. The SVM exhibits many unique advantages in solving small sample and high
dimensional pattern recognition problems.
The SVM classification algorithm is flexible in classifying accident datasets. It utilizes the
previous data information and adds the experience of the decision makers. Moreover, SVMs
can be used to study the relationships among variables to make predictions without any
presuppositions.
SVMs have been mostly used to classify and predict traffic accidents.

Advantages
 Accident analysis and on-site visit
 Recommendation for action measures
 Writing of the accident analysis report
 Development of a rehabilitation concept
 Carrying out short- and long-term performance monitoring.
 Systematically eliminate accident black spots
 Receive indications about safety deficits, risks and accident conditions at accident
black spots
 Identify and implement effective and efficient action measures for accident black
spots
 Fulfil the mandate to eliminate accident black spots.
 The results are obtained very fast,
 Simple application,
 It is acceptable in conditions of poor available data, namely low-quality data on traffic
accidents,
 It stimulates co-ordination and co-operation in the work of different stakeholders in
traffic safety
Literature Survey
There are many studies on the Blackspot identification in past few years. Government of
India also focusing on the Blackspot identification, to reduce the accident rates. Previously it
has been observed that by identifying BlackSpots there is decrease in rate of accidents upto
28%. Following are some of research papers.

[1] “Identification of Blackspots and junction improvements in Vishakhapatnam city”,

studied about the city Vishakhapatnam in India in Andhra Pradesh. It is the second largest
city in Andhra Pradesh with an area of 550 km², it is primarily an industrial city, apart from
being a port city. The traffic volume of Visakhapatnam city is about 59% of the total traffic
volume of the district (Gopala raju, 2011). The term BlackSpot is used to describe locations
that have a higher average accident rate. The identification, analysis and treatment of road
crash black spots are widely regarded as one of the most effective approaches to road crash
prevention. Generally hazardous locations are selected on the basis of formal road safety
audits.

[2] “Identification of Accident Black Spots for National Highway Using GIS”, in this they
were studied about traffic in Muzaffarnagar and Meerut. Muzaffarnagar District is bounded
by Meerut District to the south and Haridwar District to the north. The data were collected
from police stations and survey of topographical map has been studied. After that the Ground
Control Points with the help of Global Position System has been found out & then the black
spots has been identified by using Critical Crash Rate Factor Method.

[3] “Black Spots Analysis on Pune - Bangalore National Highway”, identified accidental
Black Spots on a section (820 km-830 km) of NH-4 by studying the accidental data provided
by National Highway Authority of India (NHAI) during year 2014-2015. They used
Weighted Severity Index (WSI) and Accidental Density Method (ADM) for identification of
Black Spots. By considering all the parameters of Accidental Density Method (ADM) they
found black spots at chainage 821.2 km, 823 km, 824.1 km, 825.3 km and 829.1 km.

[4]. “Black spots identification through a Bayesian Networks quantification of accident risk
index” Traffic accidents constitute a major problem worldwide. One of the principal causes
of traffic accidents is adverse driving behaviour that is inherently influenced by traffic
conditions and infrastructure among other parameters. Probabilistic models for the
assessment of road accidents risk usually employs machine learning using historical data of
accident records. The main drawback of these approaches is limited coverage of traffic data.
This study illustrates a prototype approach that escapes from this problem, and highlights the
need to enhance historical accident records with traffic information for improved road safety
analysis. Traffic conditions estimation is achieved through Dynamic Traffic Assignment
(DTA) simulation that utilizes temporal aspects of a transportation system. Accident risk
quantification is achieved through a Bayesian Networks (BNs) model learned from the
method's enriched accidents dataset. The study illustrates the integration of BN with the
DTA-based simulator, Visual Interactive Systems for Transport Algorithms (VISTAs), for
the assessment of accident risk index (ARI), used to identify accident black spots on road
networks.

[5]” Identification of Accident Black Spots for National Highway Using GIS” In some
countries where the economies are weak, it becomes crucial for those concerned with
developmental policies to adopt approaches which will ensure that every single cent available
is used to develop the country. In those fields to facilitate a conductive environment for
economic development. Road traffic accidents have been recognized as one of those adverse
elements which contribute to the suffocation of economic growth in the developing countries,
due to the high cost related to them, hence causing social and economic concern. So, Traffic
safety is an important key and integral role in sustainable transportation development areas.
Now days, the main negative impact of modern road transportation systems are injuries and
deaths in road accidents. The success of traffic safety and highway improvement programs
hinges on the analysis of accurate and reliable traffic accident data. This study discusses the
present state of traffic accident information on NH-58 from Meerut to Muzaffarnagar in
Uttarakhand State. It shall also discuss the Identification of high rate accident Locations by
using GIS Software and safety deficient areas on the highway. So, implement the remedial
measures to those accidental locations (Black Spots) and provisions for traffic safety.

[6]” The Analysis of Causes of Highway Traffic Black-Spot Based on Rough Set and Fuzzy
Set Theory” Accident” black-spots” is the space that often have the event of accidents, that is,
it is usually accident-prone location and dangerous place. For a single road traffic accident,
its occurrence has a great chance, although we can find the most direct incentive, it is often
lead by the combination of many factors come from drivers, vehicles and roads. Although we
cannot say the accident is caused by road conditions through the sporadic traffic accidents,
however, if car accidents focus on some points in the road, we can determine that there is
relation between these incidents and road traffic environment. Road traffic accidents are
closely related with these factors such as road linear, intersection design, traffic safety
facilities and roads surrounding environment, and the impact of these factors is uncertain, it is
difficult to determine what mainly factors caused the accident-prone location. How to
determine the degree of influence from many uncertain factors on accident black spots, and
then take measures to effectively control and prevent traffic accidents according to the impact
of traffic safety are important subjects we currently faced. Rough set theory is a mathematical
tool to deal with imprecise, incomplete and inconsistent data. After more than twenty years of
pursuing rough set theory and its application, this theory has reached a certain degree of
maturity. In recent years we have witnessed a rapid growth of interest in rough set theory and
its application worldwide, e.g., data mining, machine learning, finance, industry, multimedia,
medicine, control theory, pattern recognition, and most recently bioinformatics. rough set
theory has a greatest merit that it does not need any additional information about data. This
theory can analysis data effective and objective. It can process imprecise, uncertain and
incomplete data, and discovered hidden and potential knowledge from data. On the basis of
statistical data of the causes of the accident black spots, we can analysis the degree of impact
from various factors of the accident black spots use rough set theory.
Architecture Diagram
 Blackspot Server

Classified File

Classification

Feature Extraction BS Notification System

Login
By Place
Clustering Prediction
Source to Destination
Preprocessing
Visualization

Cloud Server Admin Driver/User

Modules
 1. Blackspot Server Web App
2. Admin Interface
2.1. Accident Dataset/ Add Accident GUI
2.2. Pre-processing
2.3. Clustering
2.4. Feature Extraction
2.5. Classification
3. User Interface
3.1. Register
3.2. Login
3.3. Search
3.4. Notification
4. Visualization
5. Performance Evaluation

Points to remember.
We can apply the neural networks clustering algorithm like K-means etc. for
finding the efficient Accident-prone area.
We can also increase the efficiency for finding the accident-prone area by dividing the google
maps into blocks and find the accident-prone areas of only one block in which user is present.
We also take an input of time, date, severity, number of vehicles involved, So we can run the
important queries like in which particular time the most of the accident occurs, average
severity of accidents in one month etc.
We can also take the reasons of accident from users to deduce the reason for that area to be
accident prone and we can also inform the respective authorities so that necessary steps
should be taken.
We can provide the feature in which a user enters the starting point and destination point and
application shows the different paths with the number of accidents occurred in each path.

References
1) Snehal Bobade-Sorate, Anuj U.Manerikar, Devika J.Buttepatil, Prem M.Rathod (April
2016), “Black Spots Analysis on Pune - Bangalore National Highway”, International
Research Journal of Engineering and Technology (IRJET), Volume: 03 Issue: 04, pp. 1157-
1160
2) R.R.Sorate, R.P. Kulkarni, S.U. Bobade, M.S. Patil, A.M. Talathi, I.Y. Sayyad, S.V.Apte
(June 2015), “ Identification of Accident Black Spots On National Highway 4 (New Katraj
Tunnel To Chandani Chowk)”, Journal of Mechanical and Civil Engineering (IOSR-JMCE),
Volume 12, Issue 3 Ver. I, PP 61-67.
3) Snehal U Bobade, Jalindar R Patil, Raviraj R Sorate (Feb 2015), “Identification of
Accidental Black spots on National Highways and Expressways”, International Journal of
Research in Advent Technology, pp 82-85.