ABSTRACT

Driver fatigue is a significant factor contributing to road accidents

worldwide. To address this issue, we present the design and implementation of an Anti-
Sleep Alarm System (ASAS) aimed at preventing accidents caused by drowsy driving. This
project introduces a novel approach that combines real-time monitoring of driver's
physiological signals with advanced signal processing techniques to detect signs of fatigue
and trigger timely alerts.

The ASAS utilizes non-intrusive sensors, such as electroencephalography

(EEG) and electrooculography (EOG), to continuously monitor the driver's brainwave
patterns and eye movements. These physiological signals are processed using machine
learning algorithms to identify patterns associated with drowsiness and microsleep
episodes. The system employs a wearable device integrated into a driver's headset, making
it comfortable and convenient for extended use.

Upon detecting signs of fatigue, the ASAS activates an alarm mechanism

that includes auditory alerts, seat vibrations, and visual notifications on the vehicle's
dashboard. This multi-modal alert system ensures that the driver is promptly notified,
allowing them to take appropriate actions to stay awake and alert. Furthermore, the system
can be customized to adapt its sensitivity based on individual driver characteristics and
preferences.

The hardware architecture incorporates low-power microcontrollers and

wireless communication modules, making the system energy-efficient and capable of real-
time data transmission to a companion mobile application. The mobile app provides
additional features such as real-time monitoring of the driver's physiological state,
historical data analysis, and personalized fatigue risk assessment.

vehicles, from personal cars to commercial transport, contributing to safer roads

and more vigilant drivers.

vi
 CONTENTS
PREFACE .................................................................................................................. iii

Acknowledgment .......................................................................................................... v

ABSTRACT ................................................................................................................. vi

1. Introduction ....................................................................................................... 1

1.1 Project DEFINITION .............................................................................1

1.2 OBJECTIVE OF THE PROJECT ..........................................................1

1.3 Scope and Applicability..........................................................................2

1.4 SURVEY OF TECHNOLOGIES ..........................................................3

1.5 REQUIREMENT AND ANALYSIS .....................................................4

1.6 Planning and Scheduling ........................................................................4

1.7 System Analysis: ....................................................................................5

1.8 Feasibility Study: ....................................................................................5

1.9 SCOPE FOR FUTURE WORK: .........................................................5

1.10 Preliminary Product Description: ...........................................................6

1.11 Advantages of Conceptual Models: ........................................................7

2. SYSTEM DESIGN ............................................................................................. 8

2.1 BASIC MODULES ................................................................................8

2.1.1 Flow Chart ....................................................................................................... 8

2.2 PROCEDURAL DESIGN ......................................................................9

2.3 DATA DESIGN .....................................................................................9

2.4 GANTT CHART ..................................................................................10

2.5 Sequence Diagram ................................................................................11

2.6 ER DIAGRAMS ...................................................................................12

2.7 Arduino Nano .......................................................................................12

vii
 2.8 IR sensors .............................................................................................13

3. IMPLEMENTATION APPROACHES .......................................................... 14

3.1 Detailed Life Cycle of the Project ........................................................14

3.2 Coding Details and Code Efficiency ....................................................15

4. Eye Blink Sensor .............................................................................................. 18

4.1 433 MHz RF Transceiver Module ........................................................19

4.2 RF Transmitter ......................................................................................19

4.3 RF Receiver ..........................................................................................20

4.4 TESTING APPROACH .......................................................................20

4.5 The Testing Process ..............................................................................20

4.6 MODIFICATIONS AND IMPROVEMENTS ....................................24

5. RESULTS AND DISCUSSION ....................................................................... 27

5.1 Result: ...................................................................................................27

5.2 The Methodology .................................................................................27

5.3 Discussion .............................................................................................27

6. CONCLUSIONS .............................................................................................. 30

References ........................................................................................................31

viii
 LIST OF FIGURES
Figure 1 .Anti Sleep Alarm System With Glasses For DriverError! Bookmark
not defined.

Figure 2 : Circuit Diagram ....................................................................................... 9

Figure 3 : Flowchart ............................................................................................... 10

Figure 4 : GANTT CHART ................................................................................... 13

Figure 5 : Control Signal........................................................................................ 13

Figure 6 : Arduino Nano ........................................................................................ 13

Figure 7 : IR Sensor ............................................................................................... 13

Figure 8 : Infrared Sensors ..................................................................................... 13

ix
 1. INTRODUCTION

1.1 PROJECT DEFINITION

Project motivation and purpose The goal of this project is to develop a

system that can accurately detect sleepy driving and make alarms accordingly, which aims
to prevent the drivers from drowsy driving and create a safer driving environment.
The project was accomplished by a Webcam that constantly takes image of driver,
a beagle board that implement image processing algorithm of sleepy detection, and a
feedback circuit that could generate alarm and a power supply system.

Functions and Features :- This system has many features that make it unique and
functional. These features include:
1.Eye extraction, use open and close to determine sleepiness
2. Daytime and night detection
3. Real time image processing and detection
4. Sound and flashing LED warning system to redraw driver’s attention
5. Little inference and potential hazard to driver’s normal driving Objective

1.2 OBJECTIVE OF THE PROJECT

Detect Sleepiness: Create a smart system that can tell if a driver is getting too tired or not
paying attention.

Real-time Monitoring: Make sure the system keeps watching the driver all the time while
driving.

Wake-Up Alerts: Design alarms that wake up the driver gently if they start getting too
sleepy.

Adapt to Situations: Teach the system to work differently depending on the time of day
or road conditions.

Emergency Help: Connect the system to the car's emergency features, like hazard lights,
to help in case of a problem.

1
Learn and Improve: Use information from past situations to get better at telling when a
driver is really tired.

Learn from Driving Habits: Help drivers see their own driving habits to make safer
choices.

Figure 1 .Anti Sleep Alarm System With Glasses For Driver

1.3 SCOPE AND APPLICABILITY

Scope

This glasses alerts the driver whenever he is getting into sleep while driving the
vehicle. since sleeping on wheels is dangerous sometimes it may converts into fettle
accidents can leads to death. so to prevent such consequences of accident we can use this
gadget to alert the driver when he feels drowsiness.

2
Applicability

This system alerts the user if he/she falls asleep at the wheel thereby, avoiding
accidents and saving lives. This system is useful especially for people who travel long
distances and people who are driving late at night.

1.4 SURVEY OF TECHNOLOGIES

In modern-times, owing to hectic schedules it becomes very difficult to remain

active all the time. Imagine a situation where a person is driving home from work, dead
tired after facing all the challenges of the day. His hands are on the wheel and foot on the
pedal but suddenly he starts feeling drowsy, his eyes start shutting and his vision blurs and
before he knows it, he’s asleep. Falling asleep on the wheel can lead to serious
consequences, there may be accidents and people may even lose their lives. This situation
is much more common then we notice and hence, it is very important to counter this
problem. So to address this issue, we have come up with a Driver Anti-sleep Device. This
system alerts the user if he/she falls asleep at the wheel thereby, avoiding accidents and
saving lives. This system is useful especially for people who travel long distances and
people who are driving late at night. The circuit is built around Schmitt trigger, timer IC,
transistor, a relay and a logic gate. Around half an hour after the reset of timer IC, transistors
rive the buzzer to sound an intermediate beep. If timer IC is not reset at that time, around
one minute later the output of gate conducts. Due to this the clock stops counting further
and relay energizes to deactivate the load. This state changes only reset switch is pressed.
As a result of pressing the reset switch a next timer is set which will trigger the same events
after half an hour.

Existing System

This system alerts the user if he/she falls asleep at the wheel thereby, avoiding
accidents and saving lives. This system is useful especially for people who travel long
distances and people who are driving late at night. The circuit is built around Schmitt
trigger, timer IC, transistor, a relay and a logic gate.

Proposed System

This system alerts the user if he/she falls asleep at the wheel thereby, avoiding
accidents and saving lives. This system is useful especially for people who travel long
3
distances and people who are driving late at night. The circuit is built around Schmitt
trigger, timer IC, transistor, a relay and a logic gate.

1.5 REQUIREMENT AND ANALYSIS

Problem Definition

Anti-sleep alarm is an application to keep car drivers awake. Although it was

designed for car drivers, it can also be used in any other situation where you need to stay
awake. The way the app works is very simple.

Requirements Specification

Arduino Nano, 5Volt Buzzer, Battery.3.7V, Glasses Frame, Resistors.4.7k, Transistor

BC547, IR Sensor

1.6 PLANNING AND SCHEDULING

In planning phase, plan is made and strategies are set, taking into consideration the
user requirement. Planning provides direction, unifying frame work, performance
standards, and helps to reveal future opportunities. In Planning, the following steps are
followed.

• The Objectives of the projects in definite words

• Goals and stages intermediate to attain the final target
• Forecast and means of achieving goals i.e. Activities.

PROJECT SCHEDULING

• Scheduling is the allocation of resources

• Resources in conceptual sense are time & energy but in practical sense are the time,
manpower, equipment applied to material.

Scheduling is the process of formalizing the planned functions, assigning the starting and
completion dates to each activity which proceeds in a logical sequence and in an
orderly and systematic manner. This allows you to see at a glance:

• What the various activities are

4
 • When each activity begins and ends
• How long each activity is scheduled to last
• Where activities overlap with other activities, and by how much
• The start and end date of the whole project

1.7 SYSTEM ANALYSIS:

In System Analysis phase, the whole software development process, the overall
software structure and its outlay are defined. Analysis is very important in the whole
development cycle process. Any fault in the design phase could be very expensive to solve
in the software development process. In this phase, process, the software's overall
structure and its nuances are defined. This step refers to the gathering of system
requirements, with the goal of determining how these requirements will be accommodated
in the system.

1.8 FEASIBILITY STUDY:

This study will be bring the up the existing system and the drawbacks in
the existing one, after gathering the information a note of improvements should be done to
overcome in our system. The requirements are also considered in the study such as the
human effort, resources embedding in the application. In the system we going to propose
the resources will be the PDF (should be unique content), videos and PPT and many more.
Using drowsiness detection system, driver safety can be implemented in normal cars
also.

1.9 SCOPE FOR FUTURE WORK:

The future works may focus on the utilization of outer factors such as vehicle states,
sleeping hours, weather conditions, mechanical data etc for fatigue measurement. The
entire life cycle of the development process should be planned and kept on a track using a
development cycle to get the idea about the development and the progress we are making.
It includes the time planned for each module and its cost.

5
1.10 PRELIMINARY PRODUCT DESCRIPTION:

Benefit to organization

• The organization will obviously be able to gain benefits such as savingsthe

cost of the students by providing the academics need free of cost, reduction in
paperwork, having a core hub of knowledge along with its portability. The other benefits
are improved services and faster improvement of the students.

The initial cost

The initial cost of setting up the system will include the cost hardware
(server/clients, network adapter and related hardware), software (server OS, add-on
software utilities) and ((setup and maintenance). The same has to bear by the organization.

Running cost

Besides, the initial cost the short term cost will include the providing cost of the
system manually or through goggle services (Play Store), cost for update/renewal of
various related services.

Need for training

The user’s need a clear documentation of the services in the system and training to
the system handlers is also must.

Conceptual Model:

Books are very essential for each and every one of us in order to increase our
knowledge. It may be academic related books .Many of you have heard about the shopping
carts which have become a trend these days. The service providers make a lot of money
through the use of these shopping carts .Even the customer benefit a lot through
this since on time delivery is possible without any wastage of time, money, effort and
so on. The online second hand book selling is portal idea of is similar to the concept
of shopping carts. The updates of the books that are available can be mentioned
through this application.

6
1.11 ADVANTAGES OF CONCEPTUAL MODELS:

Establishes Entities:

By establishing and defining all the various entities and concepts that are likely to
come up throughout the course of a software development life cycle, a conceptual model
can help ensure that there are fewer surprises down the road, where entities or relationships
might otherwise have been neglected or forgotten.

Defines Project Scope:

A solid conceptual model can be used as a way to define project scope, which
assists with time management and scheduling.

Base Model for Other Models:

For most projects, additional, less abstract models will need to be generated beyond
the rough concepts defined in the conceptual model. Conceptual models serve as a
great jumping-off point from which more concrete models can be created, such as logical
data models and the like.

High-Level Understanding:

Conceptual models serve as a great tool by providing a high-level

understanding of a system throughout the software development life cycle. This can be
particularly beneficial for managers and executives.

7
 2. SYSTEM DESIGN

2.1 BASIC MODULES

2.1.1 Flow Chart

A flowchart is a type of diagram that represents a workflow or process. A flowchart

can also be defined as a diagrammatic representation of an algorithm, a step-by-step
approach to solving a task. The flowchart shows the steps as boxes of various kinds, and
their order by connecting the boxes with arrows. This diagrammatic representation
illustrates a solution model to a given problem. Flowcharts are used in analyzing,
designing, documenting or managing a process or program in various fields. Flowcharts
are used in designing and documenting simple processes or programs. Like other types of
diagrams, they help visualize what is going on and thereby help understand a process,
and perhaps also find less- obvious features within the process, like flaws and
bottlenecks. Every software development process are completely rely on different
development cycles which are selected accordingly, if the project is quite complex life
cycles like Spiral model, iterative model etc. System have different backend
functionalities and computations which are given using different diagrams like
ER,DFD,SDL ,WFD etc. Let’s discuss the diagram that will explain our system more
deeply:

• Flow Chart
• DFD (Data Flow Diagram)
• Class diagram
• Use Case Diagram

Sequence Diagram As our system is divided into two applications each diagram for
application must be given.

8
2.2 PROCEDURAL DESIGN

Figure 2 : Circuit Diagram

The flowchart is representing the flow of the system. The user is going
through the following flow, which are firstly the user is going to signup if he or she visited
for the first time .If the user have registered he or she logs in the application and visits the
dashboard .the dashboard will have a drawer that will be provide different section to
navigate on. After using all the services (view books, PDF downloading, books
buying, books inserting) the logout key will terminate the section between the
databases. The same process for admin but admin panel has features to add books,
subscription details, and manages order and payments.

2.3 DATA DESIGN

Data Flow Diagram

A data flow diagram (DFD) is a graphical representation of the "flow" of data

through an information system, modelling its process aspects. A DFD is often used as
a preliminary step to create an overview of the system without going into great detail,
which can later be elaborated. DFDs can also be used for the visualization of data
processing. A DFD shows what kind of information will be input to and output from the
system, how the data will advance through the system, and where the data will be stored. It

9
does not show information about process timing or whether processes will operate in
sequence or in parallel, unlike a traditional structured flowchart which focuses on control
flow, or a UML activity workflow diagram, which presents both control and data, flows
as a unified model.

Figure 3 : Flowchart

2.4 GANTT CHART

A Gantt chart is a horizontal bar chart developed as a production control tool in

1917 by Henry L. Gantt, an American engineer and social scientist.Frequently used
in project management, a Gantt chart provides a graphical illustration of a schedule
that helps to plan, coordinate, and track specific tasks in a project. Gantt charts give a
clear illustration of project status, but one problem with them is that they don't indicate task
dependencies - you cannot tell how one task falling behind schedule affects other tasks.
The PERT chart, another popular project management charting method, is designed to do
this. Automated Gantt charts store more information about tasks, such as the individuals
assigned to specific tasks, and notes about the procedures. They also offer the benefit of
being easy to change, which is helpful. Charts may be adjusted frequently to reflect the
actual status of project tasks as, almost inevitably; they diverge from the original plan.

10
 Figure 4 : GANTT CHART

Figure 5 : Control Signal

2.5 SEQUENCE DIAGRAM

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. Sequence
diagrams are typically associated with use case realizations in the Logical View of

11
the system under development. Sequence diagrams are sometimes called event diagrams
or event scenarios.

2.6 ER DIAGRAMS

The entity-relationship diagram is a data modelling technique that graphically

represents an information systems entity and the relationships between those entities.

An ER diagram is a conceptual and representational model of data which is used to

represent the system framework infrastructure. The ER diagram contains following
elements:

• Entities
• Relationships
• Attributes

In designing the ER diagram, we identify and define all the entities, determine
the interactions between the entities and determine the cardinality of the relationship. The
ER diagram for the movie rating system represents all the entities namely User,
Commenting, Rating and the relationship between these entities used in the system.
The User entity contains the attributes UID, Name, Tb name and Email ID where the
UID is its primary key.

2.7 ARDUINO NANO

The Arduino Nano is a small, complete, and breadboard-friendly board based on

the ATmega328 (Arduino Nano 3.x). It has more or less the same functionality of the
Arduino Due milanove, but in a different package. It lacks only a DC power jack, and works
with a Mini-B USB cable instead of a standard one.

12
 Figure 6 : Arduino Nano

2.8 IR SENSORS

IR sensors are now widely used in motion detectors, which are used in building
services to switch on lamps or in alarm systems to detect unwelcome guests. In a defined
angle range, the sensor elements detect the heat radiation (infrared radiation) that changes
over time and space due to the movement of people.

Figure 7 : IR Sensor

13
 3. IMPLEMENTATION APPROACHES

3.1 DETAILED LIFE CYCLE OF THE PROJECT

Road accidents became a matter of concern due to the huge increase in traffic. The
primary cause of accidents is due to the drowsiness of drivers in the nighttime. Fatigue
and drowsiness are some of the leading causes of major accidents on Highways. The
only solution to this problem is detecting the drowsiness and alerting the driver. So, in this
project, we have thought of building a Anti Sleep Glasses for Drivers using Arduino Nano,
Eye blink Sensor, and RF Transceiver module. The basic purpose of this system is to track
the driver’s eye movements using Eye blink Sensor and if the driver is feeling drowsy, then
the system will trigger a warning message using a loud buzzer alert.

Planning

Planning phase is used to gather the requirements which will be used to develop the
system, its need in the society and what the service the system is providing.

Defining

This phase will co relate the entire information and the resources which we have
collected and its uses in our development phase, where our system will use the
information based formats like PDF, videos and many more. Designing A prototype
of the system will be designed exactly similar to the real-time system we are going to
develop. Building The actual development (coding) according to the requirement is done

in this phase.

Testing

All the modules designed will be checked and tested to see if the desired output is

acquired from the built module.

Deployment

This is the last phase of the development in which the system is handover.

14
3.2 CODING DETAILS AND CODE EFFICIENCY

Coding Details:

Coding is the process by which an individual researcher takes a piece of information

from legislation, policy, or any other source and translates it into a set of characteristics
that can be quantitatively analysed. Coding is the process of using a programming
language to get a computer to behave how you want it to. Every line of code tells the
computer to do something, and a document full of lines of code is called a script.
Each script is designed to carry out a job. This job might be to take an image and change
its size.

Coding Efficiency:

Code efficiency is a broad term used to depict the reliability, speed and
programming methodology used in developing codes for an application. Code
efficiency is directly linked with algorithmic efficiency and the speed of runtime execution
for software. It is the key element in ensuring high performance. The goal of code
efficiency is to reduce resource consumption and completion time as much as possible with
minimum risk to the business or operating environment. The software product quality can
be accessed and evaluated with the help of the efficiency of the code used.

Code efficiency plays a significant role in applications in a high execution- speed

environment where performance and scalability are paramount.

One of the recommended best practices in coding is to ensure good code efficiency.
Well-developed programming codes should be able to handle complex algorithms.

Recommendations for code efficiency include:

• To remove unnecessary code or code that goes to redundant processing

• To make use of optimal memory and non-volatile storage.
• To ensure the best speed or run time for completing the algorithm.
• To make use of reusable components wherever possible.
• To make use of error and exception handling at all layers of software, such as the
user interface, logic and data flow.
• To create programming code that ensures data integrity and consistency.

15
 • To develop programming code that's compliant with the design logic and flow
To make use of coding practices applicable to the related software.

• To optimize the use of data access and data management practices.

• To use the best keywords, data types and variables, and other available programming

concepts to implement the related algorithm.

• Code efficiency is a broad term used to depict the reliability, speed and programming
methodology used in developing codes for an application.
• Code efficiency is directly linked with algorithmic efficiency and the speed of
runtime execution for software.
• It is the key element in ensuring high performance .
• The software product quality can be accessed and evaluated with the help of the
efficiency of the code used.

PROGRAMMING
// Define the sensor pin

#define SENSE A0

// Set up the initial configuration

void setup() {

pinMode(SENSE, INPUT); // Sensor pin as input

pinMode(2, OUTPUT); // Buzzer pin as output

pinMode(3, OUTPUT); // Motor pin as output

pinMode(LED_BUILTIN, OUTPUT); // Built-in LED pin as output

// Main loop

void loop() {

// Check if the sensor is activated

if (digitalRead(SENSE)) {

16
 digitalWrite(LED_BUILTIN, LOW); // Turn off the built-in LED

pinMode(2, LOW); // Turn off the buzzer

pinMode(3, HIGH); // Turn on the motor

} else {

digitalWrite(LED_BUILTIN, HIGH); // Turn on the built-in LED

pinMode(2, HIGH); // Turn on the buzzer

pinMode(3, LOW); // Turn off the motor

17
 4. EYE BLINK SENSOR

The eye blink sensor is used to detect the eye blinks and using which we can also
detect the activities like the Drowsiness of the driver while driving. It works based on the
technology of Infrared LED. It contains an Infrared transmitter and Receiver LED which is
used to detect the eye blink. The working of the simple IR sensor is shown as below:

Figure 8 : Infrared Sensors

As shown in the image above, infrared sensors consist of two elements:

infrared transmitter which acts as the source, and infrared receiver which acts as the
receiver. Infrared sources include an IR LED and Infrared detectors include photodiodes.
The energy emitted by the infrared source is reflected by an object and falls back on the
infrared detector. When the light emitted by the IR LED falls on the receiver, the
resistance of the photodiode falls down significantly. This photoreceiver is connected
with a potentiometer to form a voltage divider circuit, which gives a variable analog output
when blinking activity is detected.

Conditions

When the incident radiation is more on the photodiode, the voltage drop across the
series resistor/Potentiometer will be high. In the Comparator IC which is nothing but an

18
Operational Amplifiers, or Op-amps, both the reference analog voltage and the actual
output voltages are compared. If the voltage across the resistor series to photodiode
is greater than that of the reference voltage, the output of the comparator is high, else
Low. As the output of the comparator is connected to an LED, it glows when the sensor
detects some activity such as eye blinking. The threshold voltage can be adjusted by
adjusting the potentiometer depending on the environmental conditions..

• Technical Specifications of Eye Blink Sensor

• Working Voltage: 5V DC
• Output: TTL(5V/0V)
• Onboard 3 Pin Header for connections
• Infrared Technology

4.1 433 MHZ RF TRANSCEIVER MODULE

The RF stands for Radio Frequency. The corresponding frequency range varies
between 30 kHz & 300 GHz. Here we are using a 433 MHz RF Transceiver Module. This
RF module comprises a 433 MHz RF Transmitter and RF Receiver. The
transmitter/receiver (Tx/Rx) pair operates at a frequency of 433 MHz. An RF transmitter
receives serial data and transmits it wirelessly through RF through its antenna. The
transmitted data is received by an RF receiver operating at the same frequency as that of
the transmitter.

4.2 RF TRANSMITTER

The RF transmitter module uses Amplitude Shift Keying (ASK) and operates at
433MHz. The transmitter module takes serial data input and transmits that signal through
RF. The transmitted signals are then received by the receiver module wirelessly.

1. Ground: Transmitter ground. Connect to the ground plane

2. Data: Serial data input pin

3. VCC: Supply voltage; 5V

4. ANT: Antenna output pin

19
4.3 RF RECEIVER

The RF receiver module receives the data and sends it to the data OUTPUT pin. The output
data can be decoded by the Microcontroller for further action.

1. Ground: Receiver ground. Connect to the ground plane

2. Data: Serial data output pin

3. VCC: Supply voltage; 5V

4. ANT: Antenna output pin

4.4 TESTING APPROACH

Software Testing has a dual function; it is used to identify the defects in

program and it is used to help judge whether or not program is usable in practice. Thus
software testing is used for validation and verification, which ensure that software
conforms to its specification and meets need of the software customer. Developer
resorted Alpha testing, which usually comes in after the basic design of the program has
been completed. The project scientist will look over the program and give suggestions
and ideas to improve or correct the design. They also report and give ideas to get rid of
around any major problems. There is bound to be a number of bugs after a program have
been created. Tests are grouped together based on where they are added in SDLC or the
by the level of detailing they contain. In general, there are four levels of testing:
unit testing, integration testing, system testing, and acceptance testing. The purpose of
Levels of testing is to make software testing systematic and easily identify all possible
test cases at a particular level. There are many different testing levels which help to check
behaviour and performance for software testing. These testing levels are designed to
recognize missing areas and reconciliation between the development lifecycle states. In
SDLC models there are characterized phases such as requirement gathering, analysis,
design, coding or execution, testing, and deployment.

4.5 THE TESTING PROCESS

We test the software process activities such as Design, Implementation, and

Requirement Engineering. Because, design errors are very costly to repair once system has

20
been started to operate, it is quite obvious to repair them at early stage of the system. So
analysis is the most important process of any project.

Requirement Traceability
As most interested portion is whether the system is meeting its requirements or not,
for that testing should be planned so that all requirements are individually tested. We
checked the output of certain combination of inputs so that we can know whether it gives
desirable results or not. Strictly sticking to your requirements specifications, give you the
path to get desirable results from the system.

Testing Schedule

We have tested each procedure back-to-back so that errors and omissions can
be found as early as possible. Once the system has been developed fully we tested it on
other machines, which differs in configuration.

Testing strategy

There are types of testing that we implement. They are as follows:

• While deciding on the focus of testing activities, study project priorities. For
example for an on-line system, pay more attention to response time. Spend
more time on the features used frequently.

• Decide on the effort required for testing based on the usage of the system. If the
system is to be used by a large number of users, evaluate the impact on users due to
a system failure before deciding on the effort.

• A necessary part of the test case is a definition of the expected result.

• Write test cases for invalid and unexpected as well as valid and expected input
conditions.

• Thoroughly inspect the results of each test.

21
 Figure 9 : Testing Analysis

All these phases go through the process of software testing levels. There are mainly
four testing levels are:

1. Unit Testing

2. Integration Testing

3. System Testing

4. Acceptance Testing

Each of these testing levels has a specific purpose. These testing level provide value to the
software development lifecycle.

1) Unit testing:

A Unit is a smallest testable portion of system or application which can be compiled,

liked, loaded, and executed. This kind of testing helps to test each module separately. The

22
aim is to test each part of the software by separating it. It checks those components are
fulfilling functionalities or not. This kind of testing is performed by developers. Each
unit of the modules like the fetching data from the textboxes, cropping images,
retrieving images are tested number of times before building into module.

2) Integration testing:

Integration means combining. For Example, In this testing phase, different

software modules are combined and tested as a group to make sure that integrated system
is ready for system testing. Integrating testing checks the data flow from one module to
other modules. This kind of testing is performed by testers. Modules which work
dependently on each other like register module and login module are tested.

3) System testing:

System testing is performed on a complete, integrated system. It allows checking

system's compliance as per the requirements. It tests the overall interaction of components.
It involves load, performance, reliability and security testing. System testing most often
the final test to verify that the system meets the specification. It evaluates both
functional and non- functional need for the testing. The overall system has been checking
till date to find the efficiency as well as service problems.

4) Acceptance testing:

Acceptance testing is a test conducted to find if the requirements of a specification

or contract are met as per its delivery. Acceptance testing is basically done by the user
or customer. However, other stockholders can be involved in this process.

Other Types of Testing:

Regression Testing

Buddy Testing

Alpha Testing

Beta Testing

Beta Testing:

23
 Beta Testing is one of the Acceptance Testing types, which adds value to the
product as the end-user (intended real user) validates the product for functionality,
usability, reliability, and compatibility. Inputs provided by the end-users helps in
enhancing the quality of the product further and leads to its success. This also helps in
decision making to invest further in the future products or the same product for
improvisation. Since Beta Testing happens at the end user’s side, it cannot be the controlled
activity.

Beta Testing is one of the Customer Validation methodologies to evaluate the level
of customer satisfaction with the product by letting it to be validated by the end users,
who actually use it, for over a period of time. Product experiences gained by the end users
are asked for feedback on design, functionality, and usability and this helps in assessing the
quality of the product. Real People, Real Environment, Real Product are the three R’s of
Beta Testing and the question that arises here in Beta Testing is “Do Customers like the
Product?”

4.6 MODIFICATIONS AND IMPROVEMENTS

The previously proposed system had a few features and services as it just had
e-books to read from the database along with the low access speed which wastes
ample of user’s time. Along with iteration in the system new better efficiency
techniques were proposed into it, services like blogging, public chat, online video
lectures and many other improvements were brought into to the front end of this system
also had a rough look and needed better modification to the layouts and graphics.
Issues related the screen DPI of different smartphones was also recognized where
the layouts as well as its elements were not similar which was fixed later. Changes to
the splash screen and the inner activities like main dashboard were modified. Transparency
to the app drawer was included to bring better look and feel. Respects to database newer
nodes to its parents were added for better and efficient traversing. Uploading profile
photo with respect to each user was also added in later iterations and the main
modification yet to make is bringing both the systems services in a single application
which would be better for the user as well as for integrity of data. Giving this system a new
platform to serve i.e. iOS will also be referred in future.

TEST CASES

24
 A test case is a set of conditions or variables and inputs that are developed
for a particular goal or objective to be achieved on a certain application to judge its
capabilities or features.

It might take more than one test case to determine the true functionality of the
application being tested. Every requirement or objective to be achieved needs at least
one test case. Some software development methodologies like Rational Unified Process
(RUP) recommend creating at least two test cases for each requirement or objective;
one for performing testing through positive perspective and the other through negative
perspective.

Test Case Structure

A formal written test case comprises of three parts - Information consists of general
information about the test case. Information incorporates Identifier, test case creator,
test case version, name of the test case, purpose or brief description and test case
dependencies. Activity consists of the actual test case activities. Activity contains
information about the test case environment, activities to be done at test case initialization,
activities to be done after test case is performed, and step by step actions to be done while
testing and the input data that is to be supplied for testing. Results are outcomes of a
performed test case. Results data consist of information about expected results and the
actual results.

Designing
Test Cases Test cases should be designed and written by someone who understands
the function or technology being tested. A test case should include the following
information

• Purpose of the test

• Software requirements and Hardware requirements (if any)
• Specific setup or configuration requirements
• Description on how to perform the test(s)
• Expected results or success criteria for the test

Designing test cases can be time consuming in a testing schedule, but they are worth
giving time because they can really avoid unnecessary retesting or debugging or at least

25
lower it. Organizations can take the test cases approach in their own context and according
to their own perspectives. Some follow a general step way approach while others may opt
for a more detailed and complex approach. It is very important for you to decide between
the two extremes and judge on what would work the best for you. Designing proper test
cases is very vital for your software testing plans as a lot of bugs, ambiguities,
inconsistencies and slip ups can be recovered in time as also it helps in saving your time on
continuous debugging and re-testing test cases.

26
 5. RESULTS AND DISCUSSION

5.1 RESULT:

The eye blink correlation classification matrices and corresponding linear

regression values based on alert and drowsy data illustrates very clear classification of alert
and drowsy conditions. The linear regression results indicated that the regression slopes
were quite low for the sleep deprivation participants and high for alert participants.

The driver performance data (deviation from centre line, reaction time, maximum
and average speed) showed very high correlation with eye blink data when the participants
were in sleep deprivation conditions.

5.2 THE METHODOLOGY

The method for monitoring eye blink duration and frequency is unique. The eye
blink capturing system described in this thesis measures the eye blink duration and
frequency. It is different from the more widely used infrared light (IR) reflection method
of (Johns et al., 2003). The new head mounted capturing system uses low emitting light
from green LEDs positioned to the side of the eye, housed in a frame such as would be used
for headphones; . The ‘headset’ weighs only 150 gm, which is similar to the weight of
normal spectacles. The video system is capable of capturing eye blink at a frequency of
about 30 Hz. The total light reflected back from the eye sclera region is detected by a CCD
camera sensor.

5.3 DISCUSSION

Driver drowsiness is a major, though elusive, cause of traffic crashes. Drowsy

drivers cause about 30% of all highway crashes, and this may be even higher for heavy
vehicles. Research has shown that drowsiness impairs a person’s abilities and awareness of
situations. This makes it difficult for drivers to assess their risk. Too often, a driver only
recognises drowsiness in hindsight. It requires only a few seconds in a drowsy state to veer
off the road and collide with a roadside object or another vehicle. Drowsy crashes are
serious in their consequences because they often occur at full speed, with no evasive action
being taken. “Think of it this way: Drivers often close their eyes for up to three seconds at

27
a time as drowsiness approaches. At 70 miles an hour, that’s like driving the length of a
football field with your eyes closed” . Driver state monitoring is an ongoing research topic
concerning the development of driver support systems to prevent car accidents resulting
from sleep. There are several criteria to predict driver drowsiness; most of them are related
to the eye blink behaviour of the driver that leads to prolonged eyelid closure. Research
and experimentation has shown that eye blink behaviour is an important factor in
identifying driver sleepiness. The development of a reliable method for detecting
drowsiness at the wheel is a major challenge in the field of accident avoidance systems.
Because of the hazard that drowsiness presents on the road, methods need to be developed
for counteracting its effects. Scientific support for the feasibility of this countermeasure
concept is provided by research showing that:

Drowsy drivers typically do not “drop off’ instantaneously. Instead, there is a

preceding period of measurable performance decrement with associated psycho
physiological signs.

Drowsiness can be detected with reasonable accuracy using driving performance

measures such as lane deviation, steering error and reaction time.

The use of direct, unobtrusive driver physiological monitoring (e.g., of eye blink)
could potentially enhance drowsiness detection significantly. This research study has
focused on reliable detection of driver drowsiness. A number of investigations were carried
out during the period of study. It should be remembered that all of the results obtained are
for research conducted in a virtual reality simulator using ordinary people in a state of
normal and sleep deprivation conditions. These results are believed to be indicative of
actual driving under similar on-the-road conditions. The aim of driver drowsiness warning
devices is to provide information to the driver that their alertness is below a level
compatible with safe operation of a vehicle. There is evidence that such warnings are useful
to drivers who may be aware that drowsiness is increasing, but not aware of the impact of
the drowsiness on their driving capacity. If the warning occurs early enough in the
development of drowsiness, such devices could enhance driver alertness sufficiently to
avoid a collision, although many of the devices currently under development, especially
the driver state measures, will be detecting later stage drowsiness, which is unlikely to be
overcome by a short period of stimulation such as a warning signal.

Driving performance measures

28
 Driving performance measures, such as lane-position measures (lane deviation,
standard deviation of the lane position, the mean square of lane deviation) and steering
wheel related measures are treated as drowsiness indicators in the literature. A drowsy
driver shows worse sensitivity to small movements and, as a result, the number of micro-
wheel adjustments decreases and lane keeping becomes poorer with increasing drowsiness.
This type of measure seems to be promising and should be further explored. It also has an
advantage in that it is possible to use existing sensors in the vehicle.

However, longitudinal velocity related measures, such as speed of vehicle, were not
found capable of detecting drowsiness.

29
 6. CONCLUSIONS

This system alerts the user if he/she falls asleep at the wheel thereby, avoiding
accidents and saving lives. This system is useful especially for people who travel long
distances and people who are driving late at night. The circuit is built around Schmitt
trigger, timer IC, transistor, a relay and a logic gate.

The main objective of designing the driving simulator for this research is to develop
reproducible and flexible methods for studying the relationships between physiological
driver states and driver performance in a virtual driving environment. Health and safety
issues were considered in the design of the laboratory based driving simulator. The Epworth
Sleepiness Scale (ESS) and the subjective sleepiness condition were included in the
questionnaire. This data helped categorize the participants’ results from their sleep
deprivation condition and quality of sleep before the simulator test. Initial experiments were
conducted with 18 healthy male and female participants aged 20 to 70 in carefully
controlled conditions. Five different performance measures were collected during a 40
minute simulator test. The reaction time measurements system is an additional feature that
added to the driving simulator to improve the quality of performance measures.

The results presented in the current research focused mainly on the comparison of
driving performance and physiological measures (blink duration and frequency). The
relationship between the NDS and driving performance, in terms of lane position and
reaction time was only investigated descriptively within the study. Complex time series
analysis and Fourier transformation methods could be used, however this would also need
to be analyzed separately for each participant and each session. However a successful
analysis of this type could lead to empirically derived NDS levels and correct time to warn
the driver before they get into danger level of drowsiness could be validated in future
research.

30
REFERENCES

[1] Ueno H., Kanda, M. and Tsukino, M. “Development of Drowsiness Detection

System”, IEEE Vehicle Navigation and Information Systems Conference
Proceedings,(1994), ppA1-3,15-20.

[2] Ishaq Azhar Mohammed, "ARTIFICIAL INTELLIGENCE: THE KEY TO

SELF-DRIVING IDENTITY GOVERNANCE", International Journal of Creative
Research Thoughts (IJCRT), ISSN:2320-2882, Volume.4, Issue 4, pp.664-667,
November 2016 .

[3] Sean Enright, Electronics Engineering Student, 506-650- 3611, May 26-2011, Alcohol
Gas Detector “Breathalyzer”.

[4] Weirwille, W.W. (1994). “Overview of Research on Driver Drowsiness Definition

and Driver Drowsiness Detection,” 14th International Technical Conference on
Enhanced Safety of Vehicles, pp23-26. '

[5] Arpit Agarwal, “Driver Drowsiness Detection System”, portfolio of projects on

human computer interaction,December,2010.

[6] Paul Stephen Rau, National Highway Traffic Safety Administration, United States,
Paper Number05-0192 Drowsy Driver Detection and Warning System for Commercial
Vehicle Drivers: Field Operational Warning System for Commercial Vehicle Drivers:
Field Operational Test Design, Data Analyses and progress.

[7] Weirwille, W.W. (1994). “Overview of Research on Driver Drowsiness Definition

and Driver Drowsiness Detection,” 14th International Technical Conference on
Enhanced Safety of Vehicles.

[8] Ishaq Azhar Mohammed, "HOW ARTIFICIAL INTELLIGENCE IS

CHANGING CYBER SECURITY LANDSCAPE AND PREVENTING CYBER
ATTACKS: A SYSTEMATIC REVIEW", International Journal of Creative Research
Thoughts (IJCRT), ISSN:2320-2882, Volume.4, Issue 2, pp.659-663, June 2016.

31