ITEC 810 Project Outline: Effects of Emotional States in Drivers

This project outline, submitted by Bhupinder Kaur for ITEC 810 at Macquarie University, explores methods for detecting driver drowsiness to mitigate road accidents. The research focuses on visual inputs like head and face movements, and physiological data such as heart rate variability obtained from wearable sensors and driving simulator experiments. The project reviews existing detection methods, including vehicle-based, behavioral, and physiological measures, while discussing the benefits and limitations of each. The study aims to evaluate the impact of road environment monotony on driver fatigue, and uses a driving simulator with steering wheel movement analysis and heart rate monitoring via Empatica E4 wristbands. The methodology involves data collection from heart rate monitors, accelerometers, and driving simulator experiments to identify and alert drivers experiencing drowsiness. The expected outcomes include the development of a reliable system to detect driver fatigue before accidents occur, utilizing techniques like EEG, ECG, and oculographical measurements, along with statistical analysis of crash data related to drowsiness. The project emphasizes the significance of early detection to prevent accidents and improve road safety.

1
“Effects of Emotional states in losing Alertness’’
Bhupinder kaur
Student id: 43993931
Supervisor: Professor. Dr. Manolya Kavakli Thorne
ITEC 810: Information Tecnology Project, Project Outline
For the degree of
Master of IT in Management at Department Computing,
Macquarie University
Sydney. Australia
8 May ,2018

2
Abstract :
This research outlines the methods or steps which are involved in designing and
implementing a driver drowsiness detection system based on visual inputs ( such as , driver
head and face movements and expresssions). It will demonstrates the report of how human
minds react and feel while driving , it will check and monitors each and every movements of
drivers such as their eye movement states, facial expressions, head movements etc in the
driver simulator experiment. Driver fatigue often becoming a direct cause of many road
accidents now a days. And in current years , it has been one of the major causes of crashes
and lead to severe significant economic losses. So to avoid these problems and reduces the
accidents on the roads , there is a need to develop the system which will detect and monitors
the movements of drivers and notify to him/her in their bad psychological conditions which
will help to reduce the number of fatigue car accidents. However, such systems encounters
some problems or difficulities as well but taking important meaures into consideration it can
be solved easily. Researchers have alredy designed or attempted various measures to
determine the driver drowsiness such as 1) vechicle- based measures, 2) behavioural
measures,3) and pysiological. In this report , we will review all these measures and discuss
the benefits adnd limitations of each. Also the others experiments and several ways will be
followed to manipulate the drowsiness experimentally. Then , successfully we can accurately
measures the actual reasons of driver drowsiness level and might be avoided the crashes and
accidents on the road. This report will discuss all about the diving drowsiness monotony
factors in the following parts.
Keywords: (Drowsiness, fatigue, detection measures, techniques, eyes and face
detection , alert.)

3
Table of contents:
Abstract ……………………………………………………………………………………..2
1.Introduction………………………………………………………………………………4
1.1 Background………………………………………………………………………………5
 Project description
 Aim of the project
1.2 research question and problem………………………………………………………….5
1.3 Significance………………………………………………………………………………
2) Literature:………………………………………………………………………………..5
3) Methodology………………………………………………………………………….6
 Approach
 Task plan.
4)Finding, Results and Evaluation……………………………………………………7
 Expected outcomes………………………………………………..
5)Conclusion…………………………………………………………………………10
6)References…………………………………………………………………………11
Introduction

4
1.1 Background and project description:
Driver fatigue is a major cause or reason in road accidents. It can be comes and result from
sleepiness(drowsiness), Boredom and any mental or physical exhaustion. From all of these
casual reasons, drowsiness is considered the most relevent aspect of fatigue when it will
applied in the driving context. This report will demonstrates the multiple factors which
contribute to drowsiness, such as long working hours shifts, due to lack of sleep, and some
medical conditons. These all factores may include driving duration and monotony, such as
that experiences in highway driving. And several studies shown that drowsiness and
hypovigilance frequently occur during hihnway driving and they may have serious
implications in term of accident causation. This paper will focus on that factors which are
involved in the development of these phenomena.
A driving simulator study will be conducted in order to evaluate the impact of monotony of
roadside visual simulations using a steering wheel movements(SWM) analysis procedure.
However, this research is also focused on the drivers heart rate by using a heart rate sensor or
empatica e4 real watch. The E4 wristband is a wearable research equipment device that
provides the real time physiological data and software for in depth analysis and for
visualization as well. It is designed with different sensors and to collect or gather high quality
data. It will measure the blood volume pressure of drives while driving from which a heart
rate variability can be derived. Its capture moton based activit and measures the constantly
changing fluctution in electrical proprties of the skin. It has an internal memory that allows
you to record for up to 60 hours with synchronization resolution.
Keywords: (Monotony factors, hypovigilance, driving stimulator, emaptica E4,
heart rate, resolution.)

5
(Source from wearable-tech-fashion.com 1074 x 1088 png)
Aim of the project:
The main objective of this exploarorty study is to evaluate the impact of the monotony of
road environment on driver fatigue. The performanc of the driver on the driving stimulator
will be closely monitored and analyzed. An estimated 10-30 % of road accidents are directly
related to fatigue driving. A large number of research studies have been conducted to reduce
the risks of accidents while driving. And many of these researches are based on the detection
of biloogical signals by drowsiness/sleepiness.
Significance:
As it explained in the above drowsy and fatigue driving ia a major transportation safety
concern and it is a main reason for the thousands and number mortalities every year. Drowsy
driving crashes are usually of high severity due to the driver significant loss of control, and
no breaking response. So, therefore some reliable safety systems are needed to mitigate these
risks and crashes. The most important challenge is to detect the driver condition sufficciently

6
prior to the onset of sleep, and to avoid collisions. To mitigate the risk of drowsiness on
driving and piloting, some detection technologies and management programs are demanded.
It can be detected by using a variety of sensors, including electroencephalograph(EEG),
electrocardiogram(ECG), accelerator sensors and other oculographical measurements. Each
have their own advantages and disadvantages. In all of these, EEG is one of the most
predictive and reliable techniques for drowsiness direction.
Another biological measure that has been significantly related to drowsiness is heart rate
variability(HRV). It is used to estimate the autonomous nervous system activity. It is
evaluated in non-invasive manner and signal can be obtained from an ECG. So, this project
outline report will first reviews the statistical significance of the crash data due to drowsiness
and fatigue conditions. Then after, various detection methods will be discussed in the
following parts to avoid the number of road accidents which are happened in daily life.
Keyword:(Technology, Accelerator, oculographical measurements, HRV, ECG,
EEG, stastiscal significance )
Literature:
Drowsiness distrupts the work performance and increases the risk of accidents substaintially.
In each year, 100,000 crashes are directly caused by driver fatigue. Several studies have been
proposed to identify the effective ways to monitor sleepiness driving. The most commonly
used test is the EEG. In that study electrodes were used on the head to measure or detect the
level of drowsiness while drivinng, which is our main goal of the project. As in previous
report mentioned fatigue, sleepiness and drowsiness are often used synonymously. These
factors are responsible for the thousands of accidents, injuries and fatalities annually. So , this
review will only focus on the examining or evaluatong the effectiveness of driver fatigue
technologies in the context of these various cascul factors. Therefore, the present research
sought to develop a method for measuring the drowsiness factor in the drivers by using
several ways. For example, doing some real life driving stimulator experiments in the
laboetary environment, and give them wearable sensor devices to check each and every
movements of them while driving. In a literature search we found that researchers have tested
at alteast 50 to 87 different metrics of driving performance for their potential bebefits to
detect ing the driver drowsiness. So, with the help of this structured study we will be easily
able to find the various efficient method and techniques to avoid this problem,and helps to
reduced the number of road accidents effectively.
Methodology:
We are assuming that we could use data which is obtained from heart rate monitor(HRM) to
detect the changes in the nervous system and on the other hand, data obtained from the
accerlerometer, gyroscope and pedometer to identify physical activities, and decided to unify
all the data in order to detect the statess of drowsiness/sleepiness of the driver and then we

7
can alert the drivers immediately or advising them to stop driving when all these symptoms
ocuurs.
For this experiment, we needed to find a device that includes all the necessary sensors and it
will not harm or threat to user when driving. For this, technology currently provides, a single
device, a smart watch which will gives the information about heart rate and with the help of
sensors its detect as accurately as possible states or levels of drowsiness during driving. Other
technique that we could use is driving simulator experiment. In this practical,test a driver will
ask to driving in a simulator for 30 minutes, as same as he drives on highway. This scenarios
may not be exactly like a real driving situation, but use of simulation is very close to reality
and it did not pose any risks to drivers. After completing this, a driver will ask to complete or
filled out a form with the actions that he had performed in the experiment, such as which
routes he had taken and does he feel any physical states while driving ( either, tiredness,
fatigued, some drowsiness, stressed, etc). so, to performed this , we have to collect or analyse
the samples and have to arranged the simultion test for the participants to analyze the data for
the unambiguous detection of the different states.
Results, findings and expected outcomes:
The following techniques or measures have been developed and used widely to monitor the
level of drowsiness of the driver, which are as follow:
1) Vehicle-based measures
2) Behavioral measures
3) Physiological measures
1. Vehicle-based: one of the most important challenges in developing an efficient
drowsiness detection system is how to obtain the proper drowsiness data. Due to
safety reasons, it cannot be manipulated in a real environment, thus this detection
system has to be developed and tested in a laboratory setting. So , it is a fixed-based
driving stimulator which is composed of a complete automobile, fully functional
pedals and dashboard,and a large projector screen which is showing the highway
images projected by an RGB projector. Room temparature is controlled, a
potentiometer attached to the steering column for detailed recording of the steering
wheel movements.

8
(source from 350*253 px newsroom.mq.edu.au)
In this experiment, 10 to 12 student as a volunteer ask to participate in to detect the states of
drowsiness. The time duration of this experiment is around 30 to 40 minutes. All road driving
tests carried out in April with in one week, and all test started in the late afternoon
Participants arrived at the laboratory at 1pm or 1.30 pm , and we drove them for a 5-min

9
period in order to familiarize themselves to the simulator. One likert scale was created to
measure the subjective level of alertness(SA). Then the participants were asked to tested for
SA and ask to complete a first 40 minutes driving period. After that, they were given a 15
minutes break for the outdoor walk. They were tested again. Three different road scenarios
were used in the experiment. When they completed the driving test then questionnarie
document given them to give their feedback about the simulator. Such as, how they feel when
they were driving , did they feel any physical states like fatigue, boredom or drowsy or
sleepiness while driving. So , with the help of this we could know that the driver is feeling
drowsy and then alert is sent to driver to save his life and avoid the crashes on the road.
2) Behavioural measures: in this technique, we detect the facial movements of the
driver, including yawning, eye closure, eye blinking, and head position. These all factros are
monitored by using a camera and driver is alerted if any of these symtoms are detected or
noticed.
Because, when driver felt sleepy at that time his eyes blinking and gaze between eyelids are
different from natural situations so they easily detect drowsines by placing remote camera in
the car which acquire video and sequentially loacalize face expressions, eyes positons to
measure ration of closure. As, driver face is continuously detected or captured by using a
video camera so with the help of it we can easily detect or track the location of the mouth as
well. After doing this, the yawning state is measured and detected. Similarly in this way,we
can figure out the head positions of the drivers also. When the head position goes wrong and
beyond a certain angle, then an auto alarm is transmitted in the drivers air. so, all these
factores are really helpful to measures the behavioural detection in more effective ways.
(source from 394*340 www.advanced sourcecode)

10
Physiological meaures: various techniques and types of methods are used to detect
the phsiological measure such as EEG, ECG HRV and so on. The heart rate also varies
significantly between the different stages of the drowsiness and such as alertness or fatigue.
So, for this experiment we used a device that contains all the necessary sensors and did not
pose any risk or threat to drivers while driving. This is a called as smartwatch like empatica
e4. Which is worn on the hand and it contains sensors and has many benefits in one device.
So with the help of this we can easily measure the heart rate variablity, and any physical
acions such as anger, frustration , sadness which effects the mood of the drivers and raise his
blood pressure volume high and put impact on his driving. It is very easy to carry and also
helps to detect the lack of physical activity while driving. Its worked well and easily detect
the heart movements of drivers efficientl and mitigate the risks of accident.
 Empatica: its measuring blood volume, heart rate variability, accerlerometer and
temperature.
 Activity bracelet: it is alsp measured HRV
 Brain activity: its measure EEG, relaxation and stress level, interest etc.
Conclusion:
As a conclusion, we have reviewed the various techniques and methods available to
determine the drowsiness state of the driver. However, there is no universally accepted
definition for drowsiness,but in this research various definitions and the reasons behind them
were explained ir discussed. This researh also discusses the previous researches that were
done in many types of sensors in detecting drowsy driver by using smart wearable devices
and by fdriving stimulator environment. In the end, the main purpose of this project is to
design a system that can alert the driver by detecting his heartbeat, by checking his facial
expressions ad his way of driving by conductin the simulator experiment. So, in this way
number of road accidents could be avoided if an alert or alarm sign is sent to drowsy driver.

11
References :
Morsi, I. and Y.Z. Abd El Gawad. 2013. Fuzzy Logic in Heart Rate and Blood Pressure Measuring
System. In Sensors Applications Symposium (SAS), 2013 IEEE.
Drivers Beware Getting Enough Sleep Can Save Your Life This Memorial Day; National Sleep
Foundation (NSF): Arlington, VA, USA, 2010.
Husar, P. Eyetracker Warns against Momentary Driver Drowsiness. Available online:
http://www.fraunhofer.de/en/press/research-news/2010/10/eye-tracker-driver-drowsiness.html
(accessed on 27 July 2012).
McBain, W., 1970. Arousal, monotony, and accidents in line driving. J. Appl. Psychol. 54, 509–519.
McCartt, A.T., Ribner, S.A., Pack, A.I., Hammer, M.C., 1996. The scope and nature of the
drowsy driving problem in the New York state. Accident Anal. Prevention 28, 511–517
Xiao, F.; Bao, C.Y.; Yan, F.S. Yawning detection based on gabor wavelets and LDA. J. Beijing
Univ. Technol. 2009, 35, 409–413.
Kokonozi, A.K.; Michail, E.M.; Chouvarda, I.C.; Maglaveras, N.M. A Study of Heart Rate and Brain
System Complexity and Their Interaction in Sleep-Deprived Subjects. In Proceedings of the
Conference Computers in Cardiology, Bologna, Italy, 14–17 September 2008; pp. 969–971
F. Jurysta, P. van de Borne, P. F. Migeotte, M. Dumont, J. P. Lanquart, J. P. Degaute, and P.
Linkowski, “A study of the dynamic interactions between sleep EEG and heart rate
variability in healthy young men,” Clinical Neurophysiology, vol. 114, pp. 2146-2155, 2003.
Hu, S., et al. 2009. Pulse Wave Sensor for Non-intrusive Driver's Drowsiness Detection. In
Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International
Conference of the IEEE.
Mayhew, D.R.; Simpson, H.M.; Wood, K.M.; Lonero, L.; Clinton, K.M.; Johnson, A.G. On-road and
simulated driving: Concurrent and discriminant validation. J. Safety Res. 2011, 42, 267–275.
Liu, N., Zhang, K., & Sun, X. (2007). The Measurement of Driver's Mental Workload: A
Simulation-based Study. In Q. Peng, K. Wang, Y. Qui, Y. Pu, X. Luo & B. Shuai (Eds.),
International Conference on Transportation Engineering 2007 (ICTE 2007). Chengdu, China:
ASCE.
R. G. SMART, G. STODUTO, R. E. MANN, and E. M. ADLAF. Road rage experience and
behavior: Vehicle, exposure, and driver factors. Tra c Injury Prevention, 5(4):343–348,ffi
2004. PMID: 15545072
Liu, Y. C., & Wu, T. J. (2009). Fatigued drivers’ driving behavior and cognitive task performance:
Effects of road environments and road environment changes. Safety Science, 47, 1083–1089.

12