Unit-2

Statistical method of analysis of Accident data

purpose - to find the possible causes of accident related to driver, vehicle, and
roadway.

to develop information such as:

Driver and Pedestrian - Accident occurrence by age groups and relationships of

accidents to physical capacities and to psychological test results.

Vehicle - characteristic of vehicle, severity, location and extent of damage etc.

Roadway conditions - characteristics of the roadway and roadway condition etc.

CAUSES OF ROAD ACCIDENTS

• Some of the common errors due to human beings resulting in road

accidents are as follows

– Over speeding, rash driving

– Drunk driving

– Distracted driver

– Jumping red signal

– Avoiding safety gear like helmet and seat belt

– Violation of rules

– Failure to understand signs

– Fatigue

– Pedestrians contribute to road accidents by

• Carelessness
• Illiteracy

• Crossing at wrong places

• Moving on the carriageway

• Jaywalking

• Passengers of vehicles cause accidents by

– Projecting their body outside the vehicle

– Talking to drivers

– Alighting and boarding vehicle from the wrong side

– Travelling on foot boards

– Catching a running bus, etc

• Vehicles

– Failure of brakes or steering

– Tyre burst

– Insufficient headlights

– Overloading

– Projecting loads

• Road conditions

– Potholes

– Damaged road

– Eroded road

– Merging of rural roads with highways

– Diversions

– Illegal speed breakers

– Weather conditions
• Fog

• Snow

• Heavy rainfall

• Wind storms

• Hail storms

• Direct consequences of accidents

– Death

– Injury

– Property damage

WHAT IS ACCIDENT RECONSTRUCTION?

• The forensic consulting firm Fire & Accident Causation Technical Services
defines accident reconstruction as “a branch of causation

forensics which involves determining how and

why an accident happened – accomplished

first by correctly interpreting the clues left by

the remaining physical evidence of the

accident, then by reconstructing and studying

the events preceding, during, and following

the accident.”

• In effect, accident reconstructionists work in reverse,

documenting and studying evidence at the scene to

develop conclusions about the cause of the accident and

how it unfolded. Reconstruction may reveal a host of

factors that led to the accident, including:

• Speeding
• Running stop signs and red lights

• Errors in turning and lane changes

• Loss of driver control due to the failure of a car part or a

vehicle defect

• Dangerous road conditions

• Visibility issues

• Accident reconstruction is a valuable

procedure in discovering what you, your

lawyer, and a jury would need to know about

an accident. Since accident reconstruction

takes a scientific approach, it is a pretty

reliable source of data.”

WHAT DO ACCIDENT RECONSTRUCTIONISTS DO?

• Reconstruction experts employ a number of sophisticated

methodologies to figure out what elements played a part in

the origin and seriousness of an accident. Key aspects of

reconstructing an accident may include:

• Thorough inspection of the vehicle or vehicles involved in

the accident

• Analysis of vehicle and crash site images

• Review of the traffic collision report, deposition transcripts,

witness statements, crash test reports, published studies,

and other documents

• Evaluation of victims’ medical records to determine the

consistency of injuries with the available evidence

• If applicable, accident reconstructionists may

also review information captured by the

vehicle’s event data recorder (also known as

the “black box”) to assess the events leading

up to and during the crash. Black box data is a

fixture of investigating aviation accidents, but

airplanes and helicopters are not the only

kinds of vehicles with onboard computers.

Electronic data may also be crucial in truck

accident claims and other types of collisions.

Computer Analysis of Accident Data

• Data collected from accident sites covers several aspects and is subjective to
the person collecting

the data.

• Identifying the cause of road accidents is the aim behind accident data

collection and reconstruction of the event with the main aim being reduction
damages caused by

traffic accidents.

• Because of exponential growth in population leading to increased number of

vehicles on the road

and consequently increasing accidents, the volume of data from accidents has
reached explosive

proportions.

• In order to manage this humongous data and analyse it to make sense to policy
planners, data
mining technologies are used

• 'WEKA' is a popular data mining program that can handle huge sets of data
efficiently

• The results of data mining will help organizations such as transportation, to

explore the accident

data recorded by the police information system, discover patterns to predict

future behaviors

and effective decisions to be taken to reduce accidents.

• Road accidents are predicted through machine learning algorithms and

advanced techniques for

analyzing information, such as convolutional neural networks and long short-

term memory

networks, among other deep learning architectures.

• Data sources for the road accident forecast is made.

• A classification is proposed according to its origin and characteristics, such as

open

data, measurement technologies, onboard equipment and social media data.

• Road accident forecasting and Traffic accident prediction are driven by traffic

engineering, data analysis and machine learning

• The main areas of interest of models obtained from computer analysis of

accident

data are

– detection of problematic areas for circulation

– real time detection of traffic incidents

– road accident forecasting and

– prediction of the severity of the consequences suffered by involved in a road

accident
• Therefore, the study of road accident prediction is a field of relevant and
current scientific knowledge, open to innovation in the research of algorithms
and data analysis techniques that respond to the challenge of generating a more
secure mobility environment, which considers the pecularities of each country
or region, i.e., traffic composition, weather conditions, roads conditions, and
demography.

• Data about accidents can be gathered by installing equipment on vehicles, for

example satellite positional systems (GPS, GLONASS, Galileo), cameras and

sensors, in order to gather data like acceleration, unexpected braking events,

sudden lane changes and information about the driver behavior and status

like drowsiness and level of stress

• Another emerging data source suitable for proposing models of road accident
prediction is social media

• Government data like police bodies, traffic police and road concessionaires
can be characterized as historical, since it contains data spanning several
decades, and can be considered as reliable, because it is supported by the
custody process of the entities responsible for the data.

• Open data can be defined, as the data that is produced and funded with public
money, that is made available and accessible without restriction to the public .

• Road traffic information is usually one of the most available data.

• Measurement technologies include all kind of equipment that is part of the

road infrastructure, such as radar, cameras, or equipment embedded on the road
itself.

• By using analytic methods, researchers seek to characterize the information

and variables of the road accident, in order to discover hidden patterns, profile
behaviors, generate rules and inferences.

• These patterns are useful to

– profile drivers or drivers’ behavior on the road

– limit unsafe areas for driving

– generate classification rules related to road accident data

– perform selection of variables to be fetched in real-time model of accidents

and

– select relevant variables to be used to train other methods, such as artificial

neural networks and deep learning algorithms.

• Clustering is a method of partitioning and grouping objects into groups

(clusters), so that objects grouped in each cluster share common characteristics,
while looking for them to be clearly different from other objects grouped in
other clusters.

• Common characteristics can be interpreted as the level of correlation of

objects according to the characteristics on which clustering techniques are
applied.

• Unlike classification methods, clustering does not require that the data be
previously marked with any particular category in order to distinguish different
groups within the data.

• The absence of these previous categories or classes indicates that the objective
of clustering is to find an underlying structure in the information and achieve a
more compact representation of it instead of discriminating future data into
categories.

• The main advantages of clustering algorithms are that they do not require prior
data processing, work well with large data sets, and their results can be
interpreted graphically.

• On the other hand, clustering algorithms are sensitive to the possibility of

finding a local maximum instead of a global maximum on their optimization
functions.

• Clustering algorithms use a distance function to calculate the similarity in

characteristics when they work with continuous elements and a measure of
similarity for data with qualitative elements.

• Among the techniques based on similarity functions we can include K-nearest

neighbor and Kmeans clustering
• Cluster techniques whose similarity function is based on distribution
probabilities, their operation is based on the premise that each cluster has an
underlying probability of distribution from which the data elements are
generated. An example of this type of algorithm is latent class clustering (LCC)

• For data sets with attributes both qualitative and quantitative, clustering
techniques such as twostep clustering

• Batch clustering, in combination with fuzzy C-means and real time clustering
is used to study abrupt braking events in real time

• Batch clustering results, correlations were obtained that indicate potentially

dangerous places for driving, according to the time of day.

• K-means clustering and association rules model in order to determinate the

variables that influence the event of road accidents, obtaining a 6-cluster model,
which was used as an input to a rules association model.

• It was found by computer analysis of accident data that accident severity, type
of road, lighting present in the road and the type of surrounding area were
important factors in any accident

• Real-traffic data is used in order to predict the number of accidents on any

road or intersection and to identify risk factors using clustering to group roads
and finding risk patterns.

• The quantity of clusters was evaluated and selected using the Bayesian

information criterion (BIC)

• A decision tree builds classification models in the form of trees or

dendrogram, each node represents one of the input variables, and each node

has several branches equal to the number of possible values of said input

variable.

• Decision trees are useful tools in pattern classification applications.

• Decision tree method of analysis is exploratory and not inferential.

• Rule learners and classifiers do not require prior data processing and work
well with large data sets and rule learners and classifiers can be interpreted
graphically; however, their results are not as accurate

• Road Accident Data Management System (RADMS) is a Geographic

Information System (GIS) based software that is funded by world bank used for
collecting, comparing and analyzing road accident data.Currently, it is being
used by the government of Tamil Nadu.

• RADMS is a comprehensive traffic-management system which helps to study

and analyse traffic accidents in a scientific manner.

• The various components of RADMS are:

– Creation of GIS database

– Web based access and data flow

– Report generation and plotting results on maps

– Analysis and identification of black-spots for police and transport departments

to take-up necessary measures

– RADMS generates the following twelve types of reports for analysis and
suggestion of remedial measures

• Driver report

• Vehicle report

• Road report

• Yearly report

• Enforcement

• Collision type

• Time period report

• Alcohol usage report

• Person report

• Landmark report
• Weather report

• General report

• RADaR is a robust road crash database in order to reduce road accidents.

RADaR is Road Accident Data Recorder

• RADaR is an end-to-end solution for road accident data recording and

reporting as it helps identify the factors contributing to road accidents

• RADaR is designed as a n application for android tablet with connectivity to

web-based database server.

• It used GPS/GPRS to record exact accident location in global coordinate

system and transmits data to web-based central server

• It also provides a facility to take photographs of the accident scene and upload
it to the network

• It features a pictorial menu-driven recording of road layout of crash site and

collision diagram plotted on layout for scientific investigation

• RADaR can draw data for vehicle registration and driver license information
from national databases

• The pilot studies for RADaR was carried out in New Delhi (India) and Addis
Ababa (Ethiopia)

• AI machine-learning method is used to create decision trees distinguishing the

characteristics of accidents

• In order to identify factors causing accidents, Data Mining (DM) techniques

such as Decision Trees (DTs) that are used as they allow certain decision rules
to be extracted. These rules could be used in future road safety campaigns
thereby enabling managers to implement priority actions.

• Artificial Neural Network (ANN) models are used for the analysis and

prediction of accidents. In this technique, the number of vehicles,

accidents, and population are selected and used as model parameters.

The sigmoid and linear functions are used as activation functions with the

feed forward-back propagation algorithm.

• The ANN model has demonstrated to be better than statistical methods in

use.

• Since the data collected from accident sites is huge, it falls under the

domain of 'BIG DATA'.

• Traffic on highways is monitored and lots of data is processed daily to

predict probability of accidents based on highway conditions like road

surface, light on highway, turns etc.

• Accident prediction is based on different queries and in order to process

this big data, Hadoop has been used.

• Execution time is very less on Hadoop as compared to other sequential

techniques.

Recording of crash data

Recording crash data is essential for understanding the causes and consequences
of road traffic accidents, identifying trends, and informing road safety
interventions and vehicle design improvements. Here's how crash data is
typically recorded:

1. Crash Reporting Systems:

Police Reports: Law enforcement agencies often respond to and investigate road
traffic accidents. They compile reports detailing the circumstances of the crash,
including factors such as location, time, weather conditions, vehicle types
involved, and severity of injuries.

Crash Forms: Standardized crash report forms, such as those based on the
Traffic Collision Investigation Manual (TCIM) or similar guidelines, are used
by police officers to document relevant information at the scene of the accident.

2. Crash Data Collection:

On-Scene Data Collection: Police officers gather information directly from

involved parties, witnesses, and physical evidence at the crash site.
Interviews and Statements: Officers may interview drivers, passengers, and
witnesses to obtain firsthand accounts of the events leading up to the crash.

Photographic Evidence: Photographs of the crash scene, vehicle damage, and

road conditions are often taken to document evidence and aid in reconstruction
efforts.

3. Crash Data Elements:

Vehicle Information: Details about the vehicles involved, including make,

model, year, registration, and insurance information.

Driver Information: Personal details of drivers, including license information,

age, gender, and potential impairments (e.g., alcohol or drug use).

Crash Characteristics: Factors such as crash type (e.g., rear-end collision, side
impact), contributing factors (e.g., speeding, distracted driving), and road
conditions.

Injury Severity: Recording the severity of injuries sustained by involved parties,

ranging from minor cuts and bruises to fatalities.

Environmental Factors: Noting weather conditions, lighting, road surface

conditions, and any other environmental factors that may have contributed to
the crash.

4. Data Storage and Management:

Centralized Databases: Crash data is typically stored in centralized databases

maintained by government agencies responsible for transportation or public
safety.

Data Analysis Tools: Specialized software and tools are used to analyze crash
data, identify patterns, and generate reports for further analysis.

Privacy and Security: Measures are in place to ensure the privacy and security
of crash data, including protocols for data encryption, access control, and
compliance with data protection regulations.

5. Utilization of Crash Data:

Policy Development: Government agencies use crash data to inform the
development of road safety policies, infrastructure improvements, and traffic
enforcement strategies.

Research and Analysis: Researchers and analysts use crash data to study trends,
identify risk factors, and evaluate the effectiveness of road safety interventions.

Vehicle Design and Safety: Automotive manufacturers utilize crash data to

improve vehicle safety features, enhance crashworthiness, and meet regulatory
requirements.

By systematically recording crash data and analyzing it effectively, stakeholders

can gain valuable insights into road traffic accidents and take proactive
measures to prevent future incidents and minimize their impact on road safety.

Black spot Identification and investigation

Identifying and investigating black spots, also known as high-risk or accident-

prone locations, is a critical aspect of road safety management. Here's a
systematic approach to black spot identification and investigation:

1. Data Collection and Analysis:

Crash Data Analysis: Analyze historical crash data to identify locations with a
higher frequency of accidents. Look for patterns in crash types, severity,
contributing factors, and time of occurrence.

Severity Assessment: Prioritize locations based on the severity of accidents,

considering factors such as the number of fatalities, injuries, and property
damage.

Traffic Volume and Characteristics: Consider traffic volume, vehicle speed,

road geometry, and environmental factors that may contribute to crash risk.

2. Site Inspection and Assessment:

On-Site Evaluation: Conduct field visits to identified black spots to assess road
conditions, signage, visibility, lighting, and other factors that may contribute to
accidents.
Road Safety Audit: Perform a comprehensive road safety audit to identify
deficiencies in road design, signage, markings, and traffic control devices.

Pedestrian and Cyclist Safety: Assess pedestrian crossings, sidewalks, and

cycling infrastructure to identify potential safety hazards for vulnerable road
users.

3. Stakeholder Engagement:

Local Authorities: Collaborate with local transportation authorities, law

enforcement agencies, and municipal bodies to gather information and
coordinate efforts in identifying and addressing black spots.

Community Input: Solicit feedback from local residents, businesses, and

community groups about their observations and concerns regarding road safety
issues in the area.

Public Awareness: Raise awareness among the public about the importance of
identifying black spots and encouraging reporting of hazardous road conditions
or near-miss incidents.

4. Crash Risk Factors Analysis:

Human Factors: Identify contributing factors such as speeding, distracted

driving, impaired driving, and failure to obey traffic laws that may increase
crash risk.

Infrastructure Deficiencies: Evaluate road design, intersection layout, signage,

and visibility issues that may contribute to accidents.

Environmental Conditions: Consider weather conditions, lighting, and road

surface conditions that may affect driver behavior and increase crash risk.

5. Countermeasure Development:

Engineering Solutions: Develop engineering countermeasures to address

identified deficiencies, such as improving road geometry, installing traffic
calming measures, upgrading signage and markings, and enhancing pedestrian
and cyclist facilities.

Enforcement Actions: Implement targeted enforcement efforts, such as

increased police presence, speed enforcement, and crackdowns on distracted or
impaired driving.
Education and Awareness: Conduct public awareness campaigns and
educational programs to promote safe driving behaviors, pedestrian safety, and
the importance of adhering to traffic laws.

Technology Solutions: Explore the use of technology solutions such as

intelligent transportation systems, automated enforcement, and vehicle safety
technologies to mitigate crash risk.

6. Monitoring and Evaluation:

Effectiveness Evaluation: Monitor the effectiveness of implemented

countermeasures through ongoing data collection and analysis of crash rates,
severity, and other relevant metrics.

Adjustment and Iteration: Continuously review and refine strategies based on

monitoring results and stakeholder feedback to ensure that interventions remain
effective and address evolving safety concerns.

By following these steps, transportation authorities and road safety

professionals can systematically identify, investigate, and address black spots to
improve road safety and reduce the incidence and severity of traffic accidents.