EVALUVATING and algorithms to find out the problems

EVALUVATING
ROAD TRAFFIC ACCIDENTS USING DATA

MINING
TECHNOLOGY

                                                                                            

ABSTRACT

Road
traffic safety is an important perturbation for government transport
authorities as well as common people. Road accidents are ambivalent and not
able to be predict the accidents and their survey requires the factors
affecting them. Road accidents cause difficulties which are higher at an
alarming rate. Controlling the traffic accidents on roads is a crucial task. To
give safe driving suggestions, clear and careful study of roadway traffic data
is critical. Increasing the number of vehicles from past few years has put lot
of pressure on the existing roads and ultimately resulting in increasing the
road accidents. A road traffic accident is any harm due to collision
originating from, terminating with or involving a vehicle partially or fully on
a public road.

1.                 
INTRODUCTION

            In modern life, accidents have
become daily happening. Every day we hear the news of theaccident on the
television, or through internet .During accident many people die at the spot, some
others may injured very severely. By witnessing an accident one can understand
the horror of it. There are several reasons for road accidents, some of them
are increasing the number of vehicles, careless driving, violating traffic
rules etc. Whenever a road accident occur there are various types of damage
takes place ,which could be in the form of human beings, infrastructure which
is damage to the government and many other administration damages . Poor
roadway maintenance also contributes accidents. But still many people continue
to neglect and ignore the danger involved in the accidents. In this paper we
are analyzing some methods and algorithms to find out the problems occur in
road accidents.

Section
2 elucidate literature survey, Section 3 elucidate conclusion.

2.      LITERATURE SURVEY                                                                               

The
paper 1 describes the association rule mining, its classifications and the
atmospheric components like roadway surface, climate, and light condition do
not strongly influence the fatal accident rate. But the human factors like
being alcoholic or not, and the impact have strongly affect on the fatal accident
rate. A common mechanism to recognize the relations between the data stored in
huge database and plays a very significant role in repeated object set mining
is association rule mining algorithm. A classical association rule mining
method is the Apriori algorithm whose main aim is to identify repeated object sets
to analyze the roadway traffic data. Classification in data mining methodology focus
atbuilding a classifier model from a training data set that is used to classify
records of unrevealed class labels. The Naïve Bayes technique is one of the probability
based methods for classification and is based on the Bayes’ hypothesis with the
probability of self rule between every set of variables.The author applies statistics
analysis and Fatal Accident Reporting System (FARS) tosolve this problem. From
the clustering result some regions have larger fatal rate but some others have
smaller. When driving within those risky or dangerous states,people take more
attention. When the task performed, data seems never to be sufficient to make a
strong choice. If non-fatal accident data, weather condition data, mileage
data, and so on are available, more test could be executed thus more advice
could be made from the data.

In paper 2, K-modes clustering techniqueis a framework
that is used as an initialwork for divisionof different road accidents on road network.
Then association rule mining are used to recognize the various situations that
are related with the occurrence of an accident for the entire data set (EDS)
and the clusters recognized by K-modes clustering algorithm. Six clusters (C1toC6)
are used based on properties accident type, road type, lightning on road and
road feature identified by K modes clustering method. On each cluster association
rule mining is applied as well as on EDS to create rules. Powerful methods with
higher raise values are taken for the inspection. Rules for various clusters
disclose the situations related with the accidents within that cluster. These
rules are compared with the rules created for the EDS and resemblance shows
that association rules for EDS does not disclose correct data that can be
related with an accident. If more feature are presented large information can
be identified that is associated with an accident. To buildup our methodology,
we also performed analysis of all clusters and EDS on monthly or hourly basis.
The results of analysis assist methodology that performing clustering prior to
analysis helps to identify better and useful results that cannot obtain without
using cluster analysis.

The paper 3 performsstatistical and empirical analysis
on State Highways and Ordinary District Roads accidental datasets.The need of
the study is to analyze the traffic accident data of SH’s and ODR’s to assign
the black spots and accidental elements, part to control the harm caused by the
accidents. The basic necessity of the analysis is to check the traffic
associated dataset through Exploratory Visualization Techniques, K-means and
KNN Algorithms using Rstudio.. The term accident black spot in management of
road traffic safety defines a place where accidents are been focus historically
and to analyze the accidental data using exploratory visualization techniques
and machine learning algorithms. These techniques and algorithms are used on
the traffic accidental dataset to get the desired output in order to reduce the
accident frequency.  Exploratory
Visualization Technique is a technique to anatomize and examine the sets of
data in order to abridge and encapsulate the important characteristics with
visual and pictorial method. Exploratory Visualization analysis can be
performed using scatter plot, correlation analysis, barplot, clustered barplot,
histogram, pie chart etc. Machine learning concentrates on algorithm designing
and makes predictions on sets of data. It includes Supervised (KNN Algorithm)
and Unsupervised learning (K-means Algorithm).This paper present result by
resembling the above  three mining
techniques and assigns the cause of accident, accident prone area, analyze the
time of accident, examine the cause of accident and scrutinize the litigators vehicle.

In paper 4, describes about a frame work that uses
K-mode clustering technique as aprimary task for dividing 11574 accidents on
road network of Dehradun (India) from 2009 to 2014. Then an association mining
rule are used to find out the various context associated with instance of an
accident for both the whole data set and clusters find out by K-modes
clustering algorithm. Then compare the findings from cluster based analysis and
entire data set. The results shows that the amalgamation of k mode clustering
and association mining rule is very encouraging, as it produces important facts
that would remain hidden if no segmentation has been performed prior to generate
association rules. Also a trend analysis has been performed on each clusters
and entire data set. By trendanalysis it shows that before analysis, prior
segmentation of data is very important. This paper put forward a frame work
based on cluster analysis using k-mode algorithm and association mining rule.
By using cluster analysis as a primary task can group the data into different
homogeneous parts. It is the first time that both association and clustering rule
are used together to analyze the data’s for road accidents. The output of the
study proves that by using cluster analysis as a primary task, it can help in
removing heterogeneity to some extent in the road accident data.) Based on
attributes accident type, road type, lightning on road and road feature, K -modes
clustering find six cluster (C1–C6). Association mining rule have been applied
on each cluster as well as on entire data set to generate rules. For this
analysis strong rules with high lift values are used.

        The
paper 5 describes purpose of data mining methods in the field of road
accident investigation. Association rules are used to identify the patterns and
rules that are subjected the cause the occurrence of road accidents. An
efficient method for updating the index year after year could be designed.
Additionally, further analysis of traffic safety data using data mining
techniques are allowed.Cluster
analysis evaluates data objects without consulting a common class label.
The objects are clustered or arranged on the basis of maximizing the intra
class similarity and minimizing the interclass similarity. Outlier analysis: A database having data
objects that do not satisfies the general behavior or model of the data. These
data objects are also called outliers.
Evolution analysis which defines and models consistencies or trends for
objects whose behavior changes over time.We are currently build up by
considering several issues, changes in clash occurrence may have some after effect
for traffic safety measures in certain countries. The determination of specific
precautionary measures to overcome clashes requires study of other factors such
as the identification of specific road sections that need work, etc..It
analyzed the traffic accident using data mining technique that could possibly
reduce the fatality rate. Using a road safety database enables to reduce the
fatality by implementing road safety programs at local and national levels.

            The
paper 6 describes data
mining techniques to analyze high-frequency accident locations and further identify
different factors that affect road accidents at specifying locations. We first
partitioned the accident locations into k groups
based on their accident frequency poll using k means clustering algorithm.
Association rule mining algorithm is used to reveal the correlation between
different elements in the accident data and understand the characteristics of
these locations. Hence, the major significance will be the evaluation of the
outcomes. Data
mining has been proven as a reliable technique to analyzing road accident data.
Several data mining techniques such as clustering, classification and
association rule mining are widely used in the literature to identify reasons
that affect the severity of road accidents. It is the first time that k-means algorithm
is used to identify high- and low-frequency accident locations based on
accident count as it provides some technical measures to divide the accident
locations based on threshold values.The road accident dataset and its analysis
using k-means clustering and association rule
mining algorithm shows that this approach can be reused on other accident data
with more attributes to identify various other factors associated with road
accidents.

In paper 7 describes the results from analysis of traffic accidents on
the Finnish roads by applying large scale data mining methods. The set of data
collected from road traffic accidents are vast, multidimensional and diverse.The
Finnish Road Administration between 2004 and 2008 data was collected for this
study. This set of data contains more than 83000 accidents and 1203 of which
are fatal. The main aim of this is to examine the usability of robust clustering,
association and frequent itemsets, and visualization methods to the roadtraffic
accident analysis. The output shows that the pick out data miningmethods are
able to produce intelligible patterns from the data, detectingmore information that
could be increased with more detailed and comprehensive data sets.Most of the fatal
accidents occur due to the condition of single roadway mainroads outside built-up
areas where the permitted speed varies typically between 80-100km/h. Aged and
young drivers have large contribution to the high risk accidents inhighways.
Most of the surveys reported that one of the major reasons for accidents among
young people are consumption of alcohol. From the analysis it is understand
that failure of roads and end user groups are responsible for accidents at
certain limit.

            This paper 8 is to represent a
Traffic Accident Report and Analysis System (TARAS) through data mining using
Clustering technique. Detect the causes of accidents is the main aim of this
paper. The transport department of government of India produced the dataset for
the study contains traffic accident records of the yearand look into the
performance of J48. The classification accuracy on the test result discloses
the three cases such as accident, vehicle and casualty. Genetic Algorithms is
used for the future selection to lower the measurements of the dataset..More
detailed area specific information from accident locations and circumstances
are needed. With the help of this paper, the analysis can be done and therefore
preventive measures can be taken. It can help the government to keep track of
records of the accidents, causes of accident, vehicle number, vehicle owner’s
name and address.. With the current data it is possible to identify the risky
road segments and the road user groups responsible for accidents in certain environments.
The viewer or user can also make their own account for viewing the site .you
can view the data about causality .Our system will provide the graphical view
of the accidents with respect to the data entered into the system according to
the period .This system will provide the solutions as accidents causes. So that
with the help of thissystem government can take the necessary actions
accordingaccidents cases.

1) Accurate Location of
accident

2) GPS integration

3) Government ID Authentication
for user Data

4) Advanced Filter
technique Accident Solutionprediction.

The paper
9 describes application of data mining techniques on road accidents by using
machine learning algorithms that determines accident rate in the future to
decrease clash deaths and wounds.The accident dataset contains traffic accident
report of various cities examined by using machine learningalgorithms to
predict the accident rate.It implemented hybrid approach that performed with
higheraccuracy rate as compared to other methods to be described. The machine
learning techniques is used for to reduce accidents and saves life.We have to
expand the classification accuracy of road traffic accidents types, data
quality has to be added.

In paper 10
describes about a method called Innovators Marketplace on Data Jackets.
Innovators Marketplace on Data Jackets used to externalize the value of data
through ally. For analyzing the rate of traffic accidents on urban area   methods such as factor analysis, structure
equation modeling and data mining are used here. To construct traffic accident
risk evaluation model different indexes such as total number of accidents
reported, fatality rate injury rate   are
combined. To identify the connection between different factors population structure
information, vehicle information, road characters are used. In here we focused
on urban data, applied structural equation modeling to find out theimportant
factors associated with traffic accident. 
Important   factors are   population structure, vehicle information,
structure of road etc. This paper describes six factors by constructing an
accident risk causal framework based on urban data and thecomponent factor sets
of each feature and influence on traffic accident.

3.     
CONCLUSION

In this paper,
we have collected different researchers works together in one document as
analysis and examined about the contribution towards the effects of road and
traffic accident on human life and society. This survey focused the number of
approaches used to avoid the accident happened in various cities and countries.
The study on road traffic accident is to identify the key element quickly and
efficiently to provide instructional methods to prevent or to reduce the road
traffic accidents. Meanwhile, it would be helpful for improving the efficiency
and security service level of the road transportation system. The paper also
discussing about various data mining techniques which is proved supporting to
resolve traffic accident severity problem and conclude which one could be
optimal technique in road traffic accident scenario.  From our study, we conclude that Association
rule is an important method to analyze road traffic accidents. The brief survey
will also help us to find better mining technique in this kind of problem.

REFERENCE

1 “Analysis of Road Traffic Fatal Accidents
Using Data Mining Techniques”

       Liling
Li, Sharad Shrestha, Gongzhu Hu

2 “Analyzing road accident data using association
rule mining”

          Sachin Kumar; DurgaToshniwa

3 “Black Spot and Accidental Attributes
Identification on State Highways and Ordinary District           Roads Using Data Mining Techniques”.

    Gagandeep Kaur

4
“A data mining framework to analyze road accident data”

       Sachin Kumar, Durga Toshniwal

5
“An overview of data mining in road traffic and accident analysis”.

        K.
Jayasudha, Dr. C. Chandrasekar

6
” A data mining approach to characterize road accident locations”.

       Sachin KumarEmail author,
Durga Toshniwal

7″Mining
road traffic accidents”.

      Sami Ayramo,Pasi Pirtala,Janne Kauttonen,Kashif
Naveed,Tommi Karkk ainen

8 “Traffic Accident Report Analysis using Data
Mining Techniques”.

           Mrs.
Kanchan Gawande1 Ambikesh Pandey

9″ A Radical Approach to Forecast the Road
Accident Using Data Mining Technique”.                     AnupamaMakkar, Harpreet Singh Gill

10      Evaluating model of
traffic accident rate on urban data

Jianshi Wang,Yukio Ohsawa