Road Accident Detection

CHAPTER 1
INTRODUCTION
1.1 GENERAL
With increase in number of individuals owning vehicle, road accidents are also increasing
correspondingly. Vehicles have become inevitable part of everyone’s life nowadays. With increasing
congestion, limited sense of traffic rules among citizens, and lack of enforcement of traffic rules,
causalities and death rates due to road accidents are enormous and among the highest of all deaths.
Most of the road casualties happen on highways where most of the vehicles are heavy and moving
with higher speeds. According to World Health Organization (WHO), it is reported that there were
1.25 million road traffic deaths in 2013 globally. It is also predicted that this number is likely to
increase in future. Low and middle income countries have higher road fatalities than higher income
countries due to lack of law enforcement and poor availability of emergency medication facilities.
Various social activists, researchers and concerned agencies have made several attempts and proposed
solutions in the direction to lessen road accidents and provide viable solutions or systems to mitigate
road accidents. For the fast relief operation initialization, some automated system deployment in the
vehicle itself shall be very beneficial. In the present work, crash detection system in vehicle that senses
accident and also raises emergency help is devised. Many times victim of road accidents die due to
delay in getting medical treatment. So, in case of accident, the proposed system can save many lives.
There have been a few methods proposed and implemented for accident detection system till date.
Different methods are briefly discussed here. In all these cases different methods are used to detect
accident, however GPS and GSM are common techniques used to locate the victim and inform
emergency services respectively, Vehicular AdHoc Networks (VANETs) based approach has been
used for accident detection system.
In this system, accident is detected by accelerometer and all the drivers within a certain range receives
an alert to inform them about the crash in nearby area and to stop further casualties. Message is
transmitted using 802.11g standards. In, GPS based method is used to detect accident. GPS measures

Muffakham Jah College of Engineering And Technology 1

 Road Accident Detection

speed of vehicle every second and compares it with the previous readings. The algorithm is so designed
that, it detects accident whenever the speed of the vehicle is below a certain level. Android app based
accident detection system using tilt of accelerometer is described in. But it detects accident only when
the vehicle is tilted with reference to the road, which is not the case every time.
In, accident is detected based on sensors system. The authors have gathered data from 400 sensors
and 72 accident incidents from recent past in Turkish highways. These are then preprocessed and
analyzed. Based on some features like velocity difference, occupancy difference, capacity usage
difference, weekend/weekday, rush hour - accident is detected. But the system applicability is limited
as malfunctioning of sensors raise false alarms which is a bottleneck in performance accuracy.
An accident detection unit with accelerometer using ARM7, which is equipped with gas and
alcohol sensors is described in. Accident detection using some machine learning techniques such as
Neural network, SVM, decision trees are described in. Machine learning is progressively making its
way in almost every area nowadays. Innovatively, the method of accident detection using image
classification with the use of machine learning is proposed in this paper. Transfer learning can be
applied on the already trained network of Google’s
Inception V3, which is Google’s image classifier on the top of tensor flow, which uses convolutional
neural networks to classify images among given classes.

Muffakham Jah College of Engineering And Technology 2

 Road Accident Detection

1.2 OBJECTIVE

In this section, we have tried to compare our work with other accident detection techniques. Most of the
studies in this field revolve around the enhancement of tangible infrastructure rather than on Intelligent
Transportation Systems (ITS) which include traffic congestion detection, accident detection, detecting the
occurrence of an event etc. Even the few existing studies in the domain lack implementation details and
are terrain specific i.e. there are constraints both in the geographical as well as demographic aspects.

Existing System:

In this section, we have tried to compare our work with other accident detection techniques. Most of
the studies in this field revolve around the enhancement of tangible infrastructure rather than on Intelligent
Transportation Systems (ITS) which include traffic congestion detection, accident detection, detecting the
occurrence of an event etc. Even the few existing studies in the domain lack implementation details and
are terrain specific i.e. there are constraints both in the geographical as well as demographic aspects. These
techniques have been discussed below: Lexus vehicles introduced in 2014 came with a feature called the
“Lexus Enform” wherein an impact sensor was placed at the rear end of the vehicle. In the occurrence of
an accident, the sensors would react and thus notify the user via the application. However, the
disadvantages of this system were plenty. Sensors were to be placed in every individual vehicle rendering
the concept expensive. Also, it requires physical entities like smartphones. An ancillary company of
General Motors called OnStar Corporation introduced an accident notification application called Chevy
star. It offered options like on-field assistance to victims as well as a self-regulated crash response.
However, this service was based on a subscription model rendering the service expensive. Also, reviews
suggested that the service lacked quality because of which the system itself was ineffective. SoSmart SpA
came up with a smartphone application called SOSmart which provided free assistance to the victim of
the accident at the time of occurrence. This facility was easy to use and you could avail help at the click
of a button. But the obvious flaw is that it is a manual reporting system.

Muffakham Jah College of Engineering And Technology 3

 Road Accident Detection

Disadvantages:

 This system were plenty.

 Sensors were to be placed in every individual vehicle rendering the concept expensive.

Muffakham Jah College of Engineering And Technology 4

 Road Accident Detection

LITERATURE SURVEY:
Title: A Critical Issue Requiring Government Attention.

Author: P. M. Vitousek, H. A. Mooney, J. Lubchenco, and J. M. Melillo.

Year: 2015.

Description:

Human alteration of Earth is substantial and growing. Between one-third and one-half of the land surface
has been transformed by human action; the carbon dioxide concentration in the atmosphere has increased
by nearly 30 percent since the beginning of the Industrial Revolution; more atmospheric nitrogen is fixed
by humanity than by all natural terrestrial sources combined; more than half of all accessible surface fresh
water is put to use by humanity; and about one-quarter of the bird species on Earth have been driven to
extinction. By these and other standards, it is clear that we live on a human-dominated planet.

Muffakham Jah College of Engineering And Technology 5

Title:

Author:
Accelerometer Based Real-Time Remote Detection and Monitoring of Hand Motion.

An analysis of a large scale habitat monitoring application.

Year: 2011.

Description:

Habitat and environmental monitoring is a driving application for wireless sensor networks. We
present an analysis of data from a second generation sensor networks deployed during the summer
and autumn of 2003. During a 4 month deployment, these networks, consisting of 150 devices,
produced unique datasets for both systems and biological analysis. This paper focuses on nodal
and network performance, with an emphasis on lifetime, reliability, and the the static and dynamic
aspects of single and multi-hop networks. We compare the results collected to expectations set
during the design phase: we were able to accurately predict lifetime of the single-hop network, but
we underestimated the impact of multi-hop traffic overhearing and the nuances of power source
selection. While initial packet loss data was commensurate with lab experiments, over the duration
of the deployment, reliability of the backend infrastructure and the transit network had a dominant
impact on overall network performance. Finally, we evaluate the physical design of the sensor
node based on deployment experience and a <i>post mortem</i> analysis. The results shed light
on a number of design issues from network deployment, through selection of power sources to
optimizations of routing decisions.
Automatic road accident detection techniques.

Chen, X.; Zhou, G.; Chen, A.; Pu, L.; Chen, W.

Year: 2001.

Description:
Title:

Author:
Decision support tools used for vegetation management require accurate information on the spatial
array of different plant communities and an herbivore's grazing location. We tested the accuracy
and precision of locations derived using the satellite navigation global positioning system (GPS).
Before May 2000, the accuracy and precision of GPS-derived locations were degraded by a process
known as selective availability (SA); after May 2000, SA was disabled. In this study we
investigated how to handle and improve the quality of data generated both when SA was enabled
and when SA was disabled using relative GPS (rGPS). rGPS entails the post-processed correction
of the roving GPS module with simultaneously acquired positional errors recorded at a known
stationary reference location. With SA enabled, GPS data were obtained at a fixed known location
to obtain baseline information, and from a roving module that essentially mimicked surveying
techniques or the movement of a free-ranging animal. The mean accuracy of GPS with SA enabled
was 21 m for the fixed module and 25 m for the roving module. Use of rGPS and further
manipulation of the data improved the mean accuracy of the data to 7 m for the fixed module and
10 m for the roving module. With SA disabled, data were similarly recorded from the fixed known
location and resulted in a mean location accuracy of 5 m. The use of rGPS resulted in a significant
improvement of this value to 3�6 m and precision measured by the 95\% quantile was \<
10 m. For mapping and wildlife tracking, such quality in terms of location accuracy and precision
is unprecedented and demonstrates that rGPS may still be useful in many applications. GPS enables
the world-wide collection of accurate and precise location information at 1-second intervals.
Furthermore, by programming the GPS receiver to overdetermined location by using information
from all visible satellites, many of the limitations that arise in habitats or environments with a
limited view of the sky may be overcome. With SA now disabled, the potential use of GPS will
increase. With further miniaturization, surveying of remote featureless landscapes or the tracking
of crepuscular or far-ranging animals will become more accurate and more quantifiable than ever
before.
Smart vehicle accident detection and alarming system using a smartphone.

Muffakham Jah College of Engineering And Technology 7

Title:

Author:
R. Kays, S. Tilak, B. Kranstauber, P. A. Jansen, C. Carbone, M. J. Rowcliffe, T.
Fountain, J. Eggert, and Z. He,

Year: 2010.

Description:

Studying animal movement and distribution is of critical importance to addressing environmental

challenges including invasive species, infectious diseases, climate and land-use change. Motion
sensitive camera traps offer a visual sensor to record the presence of a broad range of species
providing location -specific information on movement and behavior. Modern digital camera traps
that record video present new analytical opportunities, but also new data management challenges.
This paper describes our experience with a terrestrial animal monitoring system at Barro Colorado
Island, Panama. Our camera network captured the spatio-temporal dynamics of terrestrial bird and
mammal activity at the site - data relevant to immediate science questions, and long-term
conservation issues. We believe that the experience gained and lessons learned during our yearlong
deployment and testing of the camera traps as well as the developed solutions are applicable to
broader sensor network applications and are valuable for the advancement of the sensor network
research. We suggest that the continued development of these hardware, software, and analytical
tools, in concert, offer an exciting sensor-network solution to monitoring of animal populations
which could realistically scale over larger areas and time spans.

Muffakham Jah College of Engineering And Technology 8

Title:

Wireless System for Vehicle Accident Detection and Reporting using Accelerometer and
GPS.

Author: Behera, S.K.; Rath, A.K.; Mahapatra, A.; Sethy, P.K.

Year: 2015.

Description:
How long does it take for the human visual system to process a complex natural image?
Subjectively, recognition of familiar objects and scenes appears to be virtually instantaneous, but
measuring this processing time experimentally has proved difficult. Behavioral measures such as
reaction times can be used1, but these include not only visual processing but also the time required
for response execution. However, event-related potentials (ERPs) can sometimes reveal signs of
neural processing well before the motor output2. Here we use a go/no-go categorization task in
which subjects have to decide whether a previously unseen photograph, flashed on for just 20 ms,
and contains an animal. ERP analysis revealed a frontal negativity specific to no-go trials that
develops roughly 150 ms after stimulus onset. We conclude that the visual processing needed to
perform this highly demanding task can be achieved in under 150 ms.
 Road Accident Detection

Proposed System
Convolutional neural network is the state-of-the-art tech-nique in image classification and
recognition. It has a stack of convolutional layers, ReLu layers and pooling layers. This is discussed
in detail in [10]. Convolutional layer is feature extraction layer which detects from general features
like edges to more specific features like objects and colors from the images. Pooling layer reduces
the dimensionality. It takes much time and computing power to train such a network and very large
image dataset is also required.

For example, Google’s inception-v3 image classifier is trained on the ImageNet dataset of 100000
images to classify among 1000 classes. It has 22 hidden layers and it took weeks to train it. Transfer
learning technique comes in handy to avoid such limitations. Transfer learning refers to using
learning from previous training session to a new training session.

ADVANTAGES
It is very efficient to train data.
It makes no assumptions about distributions of classes in feature space.
It is very fast at classifying unknown records.

Muffakham Jah College of Engineering And Technology 10

 Road Accident Detection

CHAPTER 2

PROJECT DESCRIPTION

2.1 METHODOLOGIES

2.1.1 MODULES NAME:

1. Uniform Aspect Ratio

2. Image-Scaling

3. Normalizing Image Inputs

1. Uniform Aspect Ratio

It is the first step that is followed in the pre-processing of the image data. By applying this
technique of unfirming all the images in the dataset, the model can be built seamlessly without any
problems. Here each image in the dataset is brought to an equal size and shape for better execution
of the model. All the images are brought into the same dimensions.

2. Image-Scaling

After unfirming all the image sizes in the dataset, by using the function image data generator from
Keras package, the image scaling technique is used. Images are either upscaled or downscaled
accordingly with the size fixed in the model.

3. Normalizing Image Inputs

This technique ensures the distribution of the data similarly according to the input parameters that
are set previously. It helps in faster training of the data. The normalization is performed by

Muffakham Jah College of Engineering And Technology 11

 Road Accident Detection

deducting the average from each one of the pixels and dividing the obtained result with standard
deviation.

CHAPTER 3
REQUIREMENTS ENGINEERING

3.1 GENERAL

We can see from the results that on each database, the error rates are very low due to the
discriminatory power of features and the regression capabilities of classifiers. Comparing the
highest accuracies (corresponding to the lowest error rates) to those of previous works, our results
are very competitive.

3.2 HARDWARE REQUIREMENTS

The hardware requirements may serve as the basis for a contract for the
implementation of the system and should therefore be a complete and consistent
specification of the whole system. They are used by software engineers as the
starting point for the system design. It should what the system do and not how it
should be implemented.

• PROCESSOR : DUAL CORE 2 DUOS.

• RAM : 4GB DD RAM
• HARD DISK : 250 GB

Muffakham Jah College of Engineering And Technology 12

 Road Accident Detection

3.3 SOFTWARE REQUIREMENTS

The software requirements document is the specification of the system. It should include both a
definition and a specification of requirements. It is a set of what the system should do rather than
how it should do it. The software requirements provide a basis for creating the software
requirements specification. It is useful in estimating cost, planning team activities, performing
tasks and tracking the teams and tracking the team’s progress throughout the development activity.

• Operating System : Windows 7/8/10

• Platform : Spyder3

• Programming Language : Python

• Front End : Spyder3

3.4 FUNCTIONAL REQUIREMENTS

A functional requirement defines a function of a software-system or its component. A function is
described as a set of inputs, the behavior, Firstly, the system is the first that achieves the standard
notion of semantic security for data confidentiality in attribute-based deduplication systems by
resorting to the hybrid cloud architecture.

3.5 NON-FUNCTIONAL REQUIREMENTS

EFFICIENCY

Our multi-modal event tracking and evolution framework is suitable for multimedia documents
from various social media platforms, which can not only effectively capture their multi-modal
topics, but also obtain the evolutionary trends of social events and generate effective event
summary details over time. Our proposed mmETM model can exploit the multi-modal property
of social event, which can effectively model social media documents including long text with
related images and learn the correlations between textual and visual modalities to separate the
visual-representative topics and non-visual-representative topics.

Muffakham Jah College of Engineering And Technology 13

 Road Accident Detection

CHAPTER 4

DESIGN ENGINEERING

4.1 GENERAL

Design Engineering deals with the various UML [Unified Modelling language] diagrams
for the implementation of project. Design is a meaningful engineering representation of a thing
that is to be built. Software design is a process through which the requirements are translated into
representation of the software. Design is the place where quality is rendered in software
engineering.

4.2 UML DIAGRAMS

4.2.1 USE CASE DIAGRAM

Muffakham Jah College of Engineering And Technology 14

 Road Accident Detection

Read Road Accident dataset

Pre-processing

Transfer Learning
Dataset Input User Input

Predictions

Road Accident Detection

EXPLANATION:
The main purpose of a use case diagram is to show what system functions are performed for which
actor. Roles of the actors in the system can be depicted. The above diagram consists of user as
actor. Each will play a certain role to achieve the concept.
4.2.2 CLASS DIAGRAM

Muffakham Jah College of Engineering And Technology 15

 Road Accident Detection

EXPLANATION

In this class diagram represents how the classes with attributes and methods are linked together to
perform the verification with security. From the above diagram shown the various classes involved
in our project.

4.2.3 OBJECT DIAGRAM

Muffakham Jah College of Engineering And Technology 16

 Road Accident Detection

Dataset Input Read Road Accident dataset Pre-processing

Predictions Transfer Learning

User Input

Road Accident Detection Results

EXPLANATION:

In the above digram tells about the flow of objects between the classes. It is a diagram that shows
a complete or partial view of the structure of a modeled system. In this object diagram represents
how the classes with attributes and methods are linked together to perform the verification with
security.

4.2.8 STATE DIAGRAM

Muffakham Jah College of Engineering And Technology 17

 Road Accident Detection

Dataset Input

Read Road Accident dataset

Pre-processing

Transfer Learning

User Input

Predictions

Road Accident Detection Results

EXPLANATION:

State diagram are a loosely defined diagram to show workflows of stepwise activities and
actions, with support for choice, iteration and concurrency. State diagrams require that the system
described is composed of a finite number of states; sometimes, this is indeed the case, while at
other times this is a reasonable abstraction. Many forms of state diagrams exist, which differ
slightly and have different semantics.

Muffakham Jah College of Engineering And Technology 18

 Road Accident Detection

4.2.9 ACTIVITY DIAGRAM

Dataset Input

Read Road Accident dataset

Pre-processings

Transfer Learning

User Input

Predictions

Road Accident Detection Results

EXPLANATION:
Activity diagrams are graphical representations of workflows of stepwise activities and
actions with support for choice, iteration and concurrency. In the Unified Modeling Language,
activity diagrams can be used to describe the business and operational step-by-step workflows of
components in a system. An activity diagram shows the overall flow of control.

Muffakham Jah College of Engineering And Technology 19

 Road Accident Detection

4.2.6 SEQUENCE DIAGRAM

Dataset Read Pre-processing Transfer User Road Accident

Input Images Learning Input Detection

Define path & select Road Accident dataset

used to read Road Accident dataset

used to convert data into array format

classification, train & extract features

user Road Accident image input

predict user image from train model

Display Road Accident Detection Results

EXPLANATION:

A sequence diagram in Unified Modeling Language (UML) is a kind of interaction diagram

that shows how processes operate with one another and in what order. It is a construct of a Message
Sequence Chart. A sequence diagram shows object interactions arranged in time sequence. It
depicts the objects and classes involved in the scenario and the sequence of messages exchanged
between the objects needed to carry out the functionality of the scenario.

Muffakham Jah College of Engineering And Technology 20

 Road Accident Detection

4.2.7 COLLABORATION DIAGRAM

0: Define path & select Brain Tumor dataset 2: used to read Road Accident dataset

Dataset Input Read Pre-processing

Images

0: Display Brain Tumor Detection

3: used to convert data into array format
Transfer
Learning
4: classification, train & extract features

0: user Brain MRI image input

0: display data to admin

Road Accident User Input

Detection

6: predict user image from train model

EXPLANATION:
A collaboration diagram, also called a communication diagram or interaction diagram, is
an illustration of the relationships and interactions among software objects in the Unified Modeling
Language (UML). The concept is more than a decade old although it has been refined as modeling
paradigms have evolved.

Muffakham Jah College of Engineering And Technology 21

 Road Accident Detection

4.2.4 COMPONENT DIAGRAM

Dataset Read Road

Input Accident dataset

Pre-processing
User
Input

Road
Accident

Detection
Results Predictions
Transfer
Learning

EXPLANATION

In the Unified Modeling Language, a component diagram depicts how components are wired
together to form larger components and or software systems. They are used to illustrate the
structure of arbitrarily complex systems. User gives main query and it converted into sub queries
and sends through data dissemination to data aggregators. Results are to be showed to user by data
aggregators. All boxes are components and arrow indicates dependencies.

4.2.5 DEPLOYMENT DIAGRAM

Muffakham Jah College of Engineering And Technology 22

 Road Accident Detection

Read Road Accident Pre-processing

Dataset Input
dataset

Transfer Learning
User Input

Road Accident Detection

Predictions
Results

EXPLANATION:

Deployment Diagram is a type of diagram that specifies the physical hardware on which the
software system will execute. It also determines how the software is deployed on the underlying
hardware. It maps software pieces of a system to the device that are going to execute it.

Data Flow Diagram

Level-0:

Muffakham Jah College of Engineering And Technology 23

 Road Accident Detection

User
Dataset input

Read Road Accident

dataset

Pre-Processing

Level-1

Muffakham Jah College of Engineering And Technology 24

 Road Accident Detection

Splitting

Transfer Learning

User Input

System Prediction

Road Accident Detection

Results

Muffakham Jah College of Engineering And Technology 25

 Road Accident Detection

System Architecture

Fig 4.12: System Architecture

Muffakham Jah College of Engineering And Technology 26

 Road Accident Detection

CHAPTER 5

DEVELOPMENT TOOLS

5.1 Python

Python is a high-level, interpreted, interactive and object-oriented scripting language. Python is

designed to be highly readable. It uses English keywords frequently where as other languages use
punctuation, and it has fewer syntactical constructions than other languages.

5.2 History of Python

Python was developed by Guido van Rossum in the late eighties and early nineties at the National
Research Institute for Mathematics and Computer Science in the Netherlands.

Python is derived from many other languages, including ABC, Modula-3, C, C++, Algol-68,
SmallTalk, and Unix shell and other scripting languages.

Python is copyrighted. Like Perl, Python source code is now available under the GNU General
Public License (GPL).

Python is now maintained by a core development team at the institute, although Guido van Rossum
still holds a vital role in directing its progress.

5.3 Importance of Python

• Python is Interpreted − Python is processed at runtime by the interpreter. You do not need
to compile your program before executing it. This is similar to PERL and PHP.

• Python is Interactive − You can actually sit at a Python prompt and interact with the
interpreter directly to write your programs.

• Python is Object-Oriented − Python supports Object-Oriented style or technique of

programming that encapsulates code within objects.

Muffakham Jah College of Engineering And Technology 27

 Road Accident Detection

• Python is a Beginner's Language − Python is a great language for the beginner-level

programmers and supports the development of a wide range of applications from simple
text processing to WWW browsers to games.

5.4 Features of Python

• Easy-to-learn − Python has few keywords, simple structure, and a clearly defined syntax.
This allows the student to pick up the language quickly.

• Easy-to-read − Python code is more clearly defined and visible to the eyes.

• Easy-to-maintain − Python's source code is fairly easy-to-maintain.

• A broad standard library − Python's bulk of the library is very portable and crossplatform
compatible on UNIX, Windows, and Macintosh.

• Interactive Mode − Python has support for an interactive mode which allows interactive
testing and debugging of snippets of code.

• Portable − Python can run on a wide variety of hardware platforms and has the same
interface on all platforms.

• Extendable − You can add low-level modules to the Python interpreter. These modules
enable programmers to add to or customize their tools to be more efficient.

• Databases − Python provides interfaces to all major commercial databases.

• GUI Programming − Python supports GUI applications that can be created and ported to
many system calls, libraries and windows systems, such as Windows MFC, Macintosh,
and the X Window system of Unix.

• Scalable − Python provides a better structure and support for large programs than shell
scripting.

Muffakham Jah College of Engineering And Technology 28

 Road Accident Detection

Apart from the above-mentioned features, Python has a big list of good features, few are listed
below −

• It supports functional and structured programming methods as well as OOP.

• It can be used as a scripting language or can be compiled to byte-code for building large
applications.

• It provides very high-level dynamic data types and supports dynamic type checking.

• IT supports automatic garbage collection.

• It can be easily integrated with C, C++, COM, ActiveX, CORBA, and Java.

5.5 Libraries used in python

• numpy - mainly useful for its N-dimensional array objects.

• pandas - Python data analysis library, including structures such as dataframes.
• matplotlib - 2D plotting library producing publication quality figures.
• scikit-learn - the machine learning algorithms used for data analysis and data mining tasks.

Figure : NumPy, Pandas, Matplotlib, Scikit-learn

Muffakham Jah College of Engineering And Technology 29

 Road Accident Detection

CHAPTER 6

IMPLEMENTATION

6.1 GENERAL Coding:

# Importing the libraries import numpy as np import matplotlib.pyplot

as plt import pandas as pd from sklearn.model_selection import

GridSearchCV from sklearn.tree import DecisionTreeClassifier from

sklearn.metrics import accuracy_score, roc_auc_score, roc_LANE

# Importing the dataset dataset =

pd.read_csv('../Dataset/diabetes.csv') X =

dataset.iloc[:, :-1].values y = dataset.iloc[:,

8].values

# Splitting the dataset into the Training set and Test set from

sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 42) #

Feature Scaling from sklearn.preprocessing import StandardScaler sc = StandardScaler()

X_train = sc.fit_transform(X_train)

Muffakham Jah College of Engineering And Technology 30

 Road Accident Detection

X_test = sc.transform(X_test) # Parameter

evaluation treeclf =

DecisionTreeClassifier(random_state=42)

parameters = {'max_depth': [6, 7, 8, 9],

'min_samples_split': [2, 3, 4, 5],

'max_features': [1, 2, 3, 4]

} gridsearch=GridSearchCV(treeclf, parameters, cv=100,

scoring='roc_auc') gridsearch.fit(X,y) print(gridsearch.best_params_)

print(gridsearch.best_score_) # Adjusting development threshold tree =

DecisionTreeClassifier(max_depth = 6, max_features = 4,

min_samples_split = 5,

random_state=42)

X_train,X_test,y_train,y_test =

train_test_split(X, y, random_state=42)

tree.fit(X_train, y_train) print("Accuracy on

training set: {:.3f}".format(tree.score(X_train,

y_train))) print("Accuracy on test set:

{:.3f}".format(tree.score(X_test, y_test)))

Muffakham Jah College of Engineering And Technology 31

 Road Accident Detection

# Predicting the Test set results y_pred = tree.predict(X_test) # Making the Confusion

Matrix from sklearn.metrics import classification_report, confusion_matrix cm =

confusion_matrix(y_test, y_pred) print('TP - True Negative {}'.format(cm[0,0])) print('FP -

False Positive {}'.format(cm[0,1])) print('FN - False Negative {}'.format(cm[1,0])) print('TP

- True Positive {}'.format(cm[1,1])) print('Accuracy Rate:

{}'.format(np.divide(np.sum([cm[0,0],cm[1,1]]),np.sum(cm)))) print('Misclassification

Rate: {}'.format(np.divide(np.sum([cm[0,1],cm[1,0]]),np.sum(cm))))

round(roc_auc_score(y_test,y_pred),5)

# Importing the libraries import numpy as np import matplotlib.pyplot

as plt import pandas as pd from sklearn.model_selection import

train_test_split, cross_val_score from sklearn.model_selection import

GridSearchCV from sklearn.metrics import accuracy_score,

roc_auc_score, roc_LANE from sklearn.neighbors import

KNeighborsClassifier

Muffakham Jah College of Engineering And Technology 32

 Road Accident Detection

# Importing the dataset dataset =

pd.read_csv('../Dataset/diabetes.csv') X =

dataset.iloc[:, :-1].values y = dataset.iloc[:,

8].values

# Splitting the dataset into the Training set and Test set from

sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y,

test_size = 0.25, random_state = 42) # Feature Scaling from

sklearn.preprocessing import StandardScaler sc = StandardScaler()

X_train = sc.fit_transform(X_train)

X_test = sc.transform(X_test) # Parameter evaluation knnclf =

KNeighborsClassifier() parameters={'n_neighbors': range(1, 20)}

gridsearch=GridSearchCV(knnclf, parameters, cv=100,

scoring='roc_auc') gridsearch.fit(X, y) print(gridsearch.best_params_)

print(gridsearch.best_score_) # Fitting K-NN to the Training set

knnClassifier = KNeighborsClassifier(n_neighbors = 18)

knnClassifier.fit(X_train, y_train)

Muffakham Jah College of Engineering And Technology 33

 Road Accident Detection

print('Accuracy of K-NN classifier on training set: {:.2f}'.format(knnClassifier.score(X_train,

y_train))) print('Accuracy of K-NN classifier on test set: {:.2f}'.format(knnClassifier.score(X_test,

y_test)))

# Predicting the Test set results y_pred =

knnClassifier.predict(X_test) # Making the Confusion Matrix from

sklearn.metrics import classification_report, confusion_matrix cm

= confusion_matrix(y_test, y_pred) print('TP - True Negative

{}'.format(cm[0,0])) print('FP - False Positive {}'.format(cm[0,1]))

print('FN - False Negative {}'.format(cm[1,0])) print('TP - True

Positive {}'.format(cm[1,1])) print('Accuracy Rate:

{}'.format(np.divide(np.sum([cm[0,0],cm[1,1]]),np.sum(cm))))

print('Misclassification Rate:

{}'.format(np.divide(np.sum([cm[0,1],cm[1,0]]),np.sum(cm))))

round(roc_auc_score(y_test,y_pred),5)

# Importing the libraries import pandas as pd import numpy as np from

sklearn.model_selection import train_test_split, cross_val_score from

Muffakham Jah College of Engineering And Technology 34

 Road Accident Detection

sklearn.model_selection import GridSearchCV from sklearn.metrics

import accuracy_score, roc_auc_score, roc_LANE from sklearn.svm

import SVC import matplotlib.pyplot as plt from sklearn.metrics import

classification_report

# Importing the dataset dataset =

pd.read_csv('../Dataset/diabetes.csv') X =

dataset.iloc[:, :-1].values y = dataset.iloc[:,

8].values

# Splitting the dataset into the Training set and Test set from

sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y,

test_size = 0.25, random_state = 42) # Feature Scaling from

sklearn.preprocessing import StandardScaler sc = StandardScaler()

X_train = sc.fit_transform(X_train)

X_test = sc.transform(X_test)

#svm with grid search svm =

SVC(random_state = 42)

parameters = {'kernel':('linear', 'rbf'), 'C':(1,0.25,0.5,0.75),

Muffakham Jah College of Engineering And Technology 35

 Road Accident Detection

'gamma': (1,2,3,'auto'),'decision_function_shape':('ovo','ovr'),

'shrinking':(True,False)}

scores = ['precision', 'recall'] for

score in scores:

print("# Tuning hyper-parameters for %s" % score)

print()

svm = GridSearchCV(SVC(), parameters, cv=5,

scoring='%s_macro' % score)

svm.fit(X_train, y_train) print("Best parameters set

found on development set:")

print()

print(svm.best_params_)

print() print("Grid scores on

development set:")

print()

Muffakham Jah College of Engineering And Technology 36

 Road Accident Detection

means = svm.cv_results_['mean_test_score'] stds =

svm.cv_results_['std_test_score'] for mean, std, params in

zip(means, stds, svm.cv_results_['params']):

print("%0.3f (+/-%0.03f) for %r"

% (mean, std * 2, params)) print()

print("Detailed classification report:") print()

print("The model is trained on the full development set.")

print("The scores are computed on the full evaluation set.")

print() y_true, y_pred = y_test,

svm.predict(X_test)

print(classification_report(y_true, y_pred))

print()

svm_model = SVC(kernel='rbf', C=100, gamma = 0.0001, random_state=42)

svm_model.fit(X_train, y_train) spred = svm_model.predict(X_test) print

('Accuracy with SVM {0}'.format(accuracy_score(spred, y_test) * 100))

# Making the Confusion Matrix from sklearn.metrics import

classification_report, confusion_matrix cm =

confusion_matrix(y_test, y_pred) print('TP - True Negative

Muffakham Jah College of Engineering And Technology 37

 Road Accident Detection

{}'.format(cm[0,0])) print('FP - False Positive {}'.format(cm[0,1]))

print('FN - False Negative {}'.format(cm[1,0])) print('TP - True

Positive {}'.format(cm[1,1]))

print('Accuracy Rate: {}'.format(np.divide(np.sum([cm[0,0],cm[1,1]]),np.sum(cm))))

print('Misclassification Rate: {}'.format(np.divide(np.sum([cm[0,1],cm[1,0]]),np.sum(cm))))

svm.fit(X_train, y_train) round(roc_auc_score(y_test,y_pred),5)

Muffakham Jah College of Engineering And Technology 38

 Road Accident Detection

CHAPTER 7 SNAPSHOTS

General:

This project is implements like application using python and the Server process is maintained
using the SOCKET & SERVERSOCKET and the Design part is played by Cascading Style Sheet.

SNAPSHOTS

Muffakham Jah College of Engineering And Technology 39

 Road Accident Detection

CHAPTER 8 SOFTWARE TESTING

8.1 GENERAL
The purpose of testing is to discover errors. Testing is the process of trying to discover
every conceivable fault or weakness in a work product. It provides a way to check the functionality
of components, sub-assemblies, assemblies and/or a finished product It is the process of exercising
software with the intent of ensuring that the Software system meets its requirements and user
expectations and does not fail in an unacceptable manner. There are various types of test. Each test
type addresses a specific testing requirement.

8.2 DEVELOPING METHODOLOGIES

The test process is initiated by developing a comprehensive plan to test the general
functionality and special features on a variety of platform combinations. Strict quality control
procedures are used. The process verifies that the application meets the requirements specified in
the system requirements document and is bug free. The following are the considerations used to
develop the framework from developing the testing methodologies.

8.3Types of Tests

8.3.1 Unit testing

Unit testing involves the design of test cases that validate that the internal program logic is
functioning properly, and that program input produce valid outputs. All decision branches and
internal code flow should be validated. It is the testing of individual software units of the
application .it is done after the completion of an individual unit before integration. This is a
structural testing, that relies on knowledge of its construction and is invasive. Unit tests perform
basic tests at component level and test a specific business process, application, and/or system
configuration. Unit tests ensure that each unique path of a business process performs accurately to
the documented specifications and contains clearly defined inputs and expected results.

Muffakham Jah College of Engineering And Technology 40

 Road Accident Detection

8.3.2 Functional test

Functional tests provide systematic demonstrations that functions tested are available as specified
by the business and technical requirements, system documentation, and user manuals.
Functional testing is centered on the following items:
Valid Input : identified classes of valid input must be accepted.
Invalid Input : identified classes of invalid input must be rejected.
Functions : identified functions must be exercised.
Output : identified classes of application outputs must be exercised.
Systems/Procedures: interfacing systems or procedures must be invoked.

8.3.3 System Test

System testing ensures that the entire integrated software system meets requirements. It tests a
configuration to ensure known and predictable results. An example of system testing is the
configuration oriented system integration test. System testing is based on process descriptions and
flows, emphasizing pre-driven process links and integration points.

8.3.4 Performance Test

The Performance test ensures that the output be produced within the time limits,and the time taken
by the system for compiling, giving response to the users and request being send to the system for
to retrieve the results.

8.3.5 Integration Testing

Software integration testing is the incremental integration testing of two or more integrated
software components on a single platform to produce failures caused by interface defects. The
task of the integration test is to check that components or software applications, e.g. components
in a software system or – one step up – software applications at the company level – interact
without error.

Muffakham Jah College of Engineering And Technology 41

 Road Accident Detection

8.3.6 Acceptance Testing

User Acceptance Testing is a critical phase of any project and requires significant participation by
the end user. It also ensures that the system meets the functional requirements.

Acceptance testing for Data Synchronization:

 The Acknowledgements will be received by the Sender Node after the Packets are received
by the Destination Node.
 The Route add operation is done only when there is a Route request in need.
 The Status of Nodes information is done automatically in the Cache Updating process.

8.2.7 Build the test plan

Any project can be divided into units that can be further performed for detailed processing. Then
a testing strategy for each of this unit is carried out. Unit testing helps to identity the possible bugs
in the individual component, so the component that has bugs can be identified and can be rectified
from errors.

CHAPTER 9

FUTURE ENHANCEMENT

In the near future, we focus on developing a “hybrid” wild animal classification framework whose
automated module working as a recommendation system for the existing citizen science-based
Wildlife Spotter project.

Muffakham Jah College of Engineering And Technology 42

 Road Accident Detection

CHAPTER 10

CONCLUSION & REFERENCE

10.1 CONCLUSION

Efficient and reliable monitoring of wild animals in their natural habitats is essential to inform
conservation and management decisions. In this paper, using the Wildlife Spotter dataset, which

Muffakham Jah College of Engineering And Technology 43

 Road Accident Detection

contains a large number of images taken by trap cameras in South-central Victoria, Australia, we
proposed and demonstrated the feasibility of a deep learning approach towards constructing
scalable automated wildlife monitoring system. Our models achieved more than 96% in
recognizing images with animals and close to 90% in identifying three most common animals
(bird, rat and bandicoot). Furthermore, with different experimental settings for balanced and
imbalanced, the system has shown to be robust, stable and suitable for dealing with images
captured from the wild. We are working on alternative ways to improve the system’s performance
by enhancing the dataset, applying deeper CNN models and exploiting specific properties of
camera trap images. Towards a fully automated wild animal recognition system, we would
investigate transfer learning to deal with problem of highly imbalanced data. In the near future, we
focus on developing a “hybrid” wild animal classification framework whose automated module
working as a recommendation system for the existing citizen science-based Wildlife Spotter
project.

REFERENCES
1] WHO road traffic deaths http://www.who.int/gho/road safety/mortality/en/

[2] J.L. DSouza,Road Safety: A Critical Issue Requiring Government Attention. International
Journal of Education and Science Research review, Volume-2, Issue-2, April, 2015.

Muffakham Jah College of Engineering And Technology 44

 Road Accident Detection

[3] J. Pang, I. Singh, Accelerometer Based Real-Time Remote Detection and Monitoring of Hand
Motion. Proceedings of the World Congress on Engineering and Computer Science 2011 Vol
II WCECS 2011, October 19-21, 2011, San Francisco, USA.

[4] Author: Scott J. Weiner, Feasibility of a 802.11 VANET Based Car Accident Alert System.

[5] halil, U., Javid, T., & Nasir, A. (2017). Automatic road accident detection techniques: A brief
survey. 2017 International Symposium on Wireless Systems and Networks (ISWSN).

[6] Faiz, A. B., Imteaj, A., & Chowdhury, M. (2015). Smart vehicle accident detection and
alarming system using a smartphone. 2015 International Conference on Computer and
Information Engineering (ICCIE).

[7] Ozbayoglu, M., Kucukayan, G., & Dogdu, E. (2016). A real-time autonomous highway
accident detection model based on big data processing and computational intelligence. 2016
IEEE International Conference on Big Data (Big Data).

[8] Shailesh Bhavthankar, Prof. H.G.Sayyed, Wireless System for Vehicle Accident Detection
and Reporting using Accelerometer and GPS. International Journal of Scientific &
Engineering Research, Volume 6, Issue 8, August-2015.

[9] Miao Chong, Ajith Abraham and Marcin Paprzycki, Traffic Accident Analysis Using
Machine Learning Paradigms. Informatica 29 (2005) 8998.

[10] Keiron OShea, Ryan Nash, An Introduction to Convolutional Neural Networks.

arXiv:1511.08458v2 [cs.NE] 2 Dec 2015.
[11] Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on
Knowledge and Data Engineering, 22(10), 13451359.

[12] Dogru, N., & Subasi, A. (2018). Traffic accident detection using random forest classifier.
2018 15th Learning and Technology Conference (L&T).

[13] Jayadeva, Khemchandani, R., & Chandra, S. (2007). Twin Support Vector Machines for

Muffakham Jah College of Engineering And Technology 45

 Road Accident Detection

Pattern Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(5),
905910.

[14] Ding, S., Yu, J., Qi, B., & Huang, H. (2012). An overview on twin support vector machines.
Artificial Intelligence Review, 42(2), 245252.

[15] Tanveer2015application, title=Application of smoothing techniques for linear programming

twin support vector machines, author=Tanveer, M, journal=Knowledge and Information
Systems, volume=45, number=1, pages=191–214, year=2015, publisher=Springer.

[16] Richhariya, B., & Tanveer, M. (2018). A robust fuzzy least squares twin support vector
machine for class imbalance learning. Applied Soft Computing, 71, 418432.

[17] Li, D., & Tian, Y. (2014). Twin Support Vector Machine in Linear Programs. Procedia
Computer Science, 29, 17701778.

[18] P.Kaliuga Lakshmi, C.Thangamani, AN EFFICIENT VEHICLE ACCIDENT DETECTION

USING SENSOR TECHNOLOGY. International Journal of Advanced Research in Computer
Engineering & Technology (IJARCET) Volume 5 Issue 3, March 2016.

[19] Peddi Anudeep, K. Hari Babu, Wireless Reporting System for Accident Detection at Higher
Speeds in Peddi Anudeep Int. Journal of Engineering Research and Applications.

[20] Marek Dbrowski, Tomasz Michalik, How effective is Transfer Learning method for image
classification. Position papers of the Federated Conference on Computer Science and
Information Systems, pp. 39.

[21] Xiaoling Xia, Cui Xu and Bing Nan, Inception-v3 for Flower Classification. 2017 2nd
International Conference on Image, Vision and Computing.
[22] Prajapati, S. A., Nagaraj, R., & Mitra, S. (2017). Classification of dental diseases using CNN
and transfer learning. 2017 5th International Symposium on Computational and Business
Intelligence (ISCBI).

Muffakham Jah College of Engineering And Technology 46

 Road Accident Detection

[23] Vaishnavi Ravindran, Lavanya Viswanathan and Dr. Shanta Rangaswamy, A Novel Approach
to Automatic Road-Accident Detection using Machine Vision Techniques. (IJACSA)
International Journal of Advanced Computer Science and Applications, Vol. 7, No. 11, 2016.

[24] Nejdet Dogru, Abdulhamit Subasi, Traffic Accident Detection By Using Machine Learning
Methods. Conference: International Symposium on Sustainable Development, At Bosnia and
Herzegovina, Volume: 2

[25] Namrata H. Sane, Damini S. Patil, Snehal D. Thakare and Aditi V. Rokade, Real Time Vehicle
Accident Detection and Tracking Using GPS and GSM. International Journal on Recent and
Innovation Trends in Computing and Communication ISSN: 2321-8169 Volume: 4 Issue: 4.
[26] N.Upendra Yadav, Smart Vehicle Monitoring System using IOT. IJDCST@March-
April2017,Issue-V-5,I-3,SW-31.

[27] P. Shruthi,V.T. Venkatesh, B. Viswakanth, C. Ramesh, P.L. Sujatha, I. R. Dominic, Analysis

of Fatal Road Traffic Accidents in a Metropolitan City of South India J Indian Acad Forensic
Med.
October-December 2013, Vol. 35, No. 4 ISSN 0971-0973.

Muffakham Jah College of Engineering And Technology 47