Master of Science / Department of Civil Engineering / Sunanda Dissanayake / The percentage of the U.S. population aged 65 years or older is increasing rapidly. Statistics also show this age group was 14.9 percent of the population in 2015 and is expected to be 20.7 to 21.4 percent for the years 2030–2050. Kansas has similar statewide trends with its aging population. Therefore, identifying issues, concerns, and factors associated with severity of older-driver crashes in Kansas is necessary. The Kansas Crash Analysis and Reporting System (KCARS) database maintained by Kansas Department of Transportation was used in this study to identify older-driver crash characteristics, compare older drivers with all drivers, and develop crash severity models. According to KCARS data, older drivers were involved in more than one in five fatal injuries out of all drivers in Kansas from 2010 to 2014. When compared with all drivers, older drivers were overly represented in fatal and incapacitating injuries. The percentage of older-driver fatal injuries was more than the twice that of all drivers. When compared with all drivers, older drivers were involved more often in crashes at four-way intersections, on straight and level roads, in daylight hours, and at a stop or yield signs. An in-depth crash severity analysis was carried out for the older drivers involved in crashes. Three separate binary logistic regression models were developed for single-vehicle crashes where only the older driver was present (Model A), single-vehicle crashes involving an older driver with at least one passenger (Model B), and multi-vehicle crashes involving at least one older driver (Model C). From the crash severity analysis, it was found that left turns were significant in changing the crash severity for Model A, but it was not significant in model B, meaning that older drivers may be safer with passengers. For Model B, none of the passenger attributes were significant, though it was originally developed to identify passenger attributes. Gender of the older driver was not significant in any model. For all models, variables such as safety equipment use, crash location, weather conditions, driver ejected or trapped, and light conditions distinguished crash severity. Furthermore, for Model A, variables such as day of the week, speed, accident class, and maneuver, distinguished crash severity. Moreover, accident class, surface type, and vehicle type changed crash severity in Model B. Number of vehicles, speed, collision type, maneuver, and two-lane roads were significant in Model C. A road-user survey was also conducted to identify habits, needs, and concerns of Kansas' aging road users since it was not advisable to conclude safety factors solely on crash data. The probability of occurrence was calculated by taking the weighted average of answers to a question. Then a contingency table analysis was carried out to identify relationships among variables. For older drivers, seatbelt use as a driver had the highest probability of occurrence. Driving in heavy traffic, merging into traffic, moving away from traffic, and judging gaps were dependent on age group. Findings of this research gave an understanding of older-driver crashes and associated factors. Since more than 85 percent of crash contributory causes were related to drivers, driver awareness programs, driver licensing restrictions, providing public transportation, and law enforcement can be used as countermeasures. Accordingly, results of this study can be used to enhance older-driver safety and awareness programs.

The technology for driver safety has been developed in many fields such as airbag system, Anti-lock Braking System or ABS, ultrasonic warning system, and others. Recently, some of the automobile companies have introduced a new feature of driver safety systems. This new system is to make the car slower if it finds a driver’s drowsy eyes. For instance, Toyota Motor Corporation announced that it has given its pre-crash safety system the ability to determine whether a driver’s eyes are properly open with an eye monitor. This paper is focusing on finding a driver’s drowsy eyes by using face detection technology. The human face is a dynamic object and has a high degree of variability; that is why face detection is considered a difficult problem in computer vision. Even with the difficulty of this problem, scientists and computer programmers have developed and improved the face detection technologies. This paper also introduces some algorithms to find faces or eyes and compares algorithm’s characteristics. Once we find a face in a sequence of images, the matter is to find drowsy eyes in the driver safety system. This system can slow a car or alert the user not to sleep; that is the purpose of the pre-crash safety system. This paper introduces the VeriLook SDK, which is used for finding a driver’s face in the real time driver safety system. With several experiments, this paper also introduces a new way to find drowsy eyes by AOI,Area of Interest. This algorithm improves the speed of finding drowsy eyes and the consumption of memory use without using any object classification methods or matching eye templates. Moreover, this system has a higher accuracy of classification than others.

This study aims to evaluate algorithms designed to detect distracted driving. This includes the comparison of how efficiently they detect the state of distraction and likelihood of a crash. Four algorithms that utilize measures of cumulative glance, past glance behavior, and glance eccentricity were used to understand the distracted state of the driver and were validated on two separate data sources (i.e., simulator and naturalistic data). Additionally, an independent method for distraction detection was designed using data mining methods. This approach utilized measures like steering degree, lane offset, lateral and longitudinal velocity, and acceleration. The results showed a higher likelihood of distracted events when cumulative glances were considered. However, the state of distraction was observed to be higher when glance eccentricity was added. Additionally, it was observed that glance behavior using the four legacy algorithms were better detectors of the state of distraction as compared to the data mining method that used vehicular measures. This research has implications in understanding the state of distraction, predicting the power of different methods, and comparing approaches in different contexts (naturalistic vs simulator). These findings provide the fundamental building blocks towards designing advanced mitigation systems that give drivers feedback in instances of high crash likelihood.

This thesis proposes a novel approach for efficiently estimating gaze points in dual camera transportation datasets. Traditional methods for gaze point estimation are dependent on large amounts of labeled data, which can be both expensive and time-consuming to collect. Additionally, alignment and calibration of the two camera views present significant challenges. To overcome these limitations, this thesis investigates the use of self-learning techniques such as semi-supervised learning and self-training, which can reduce the need for labeled data while maintaining high accuracy. The proposed method is evaluated on the DGAZE dataset and achieves a 57.2\% improvement in performance compared to the previous methods. This approach can prove to be a valuable tool for studying visual attention in transportation research, leading to more cost-effective and efficient research in this field. / Master of Science / This thesis presents a new method for efficiently estimating the gaze point of drivers while driving, which is crucial for understanding driver behavior and improving transportation safety. Traditional methods require a lot of labeled data, which can be time-consuming and expensive to obtain. This thesis proposes a self-learning approach that can learn from both labeled and unlabeled data, reducing the need for labeled data while maintaining high accuracy. By training the model on labeled data and using its own estimations on unlabeled data to improve its performance, the proposed approach can adapt to new scenarios and improve its accuracy over time. The proposed method is evaluated on the DGAZE dataset and achieves a 57.2\% improvement in performance compared to the previous methods. Overall, this approach offers a more efficient and cost-effective solution that can potentially help improve transportation safety by providing a better understanding of driver behavior. This approach can prove to be a valuable tool for studying visual attention in transportation research, leading to more cost-effective and efficient research in this field.

The integration of devices within cars is continuously evolving, enabling us to interact with them to an increasingly greater extent. This has transformed the way we drive, communicate and access information on the go. Despite this, there is a lack of research on how to guarantee driver safety while interacting with these systems, especially when looking at in-car systems used in professional settings as a work tool. This master's thesis was conducted in collaboration with NIRA Dynamics and aimed to investigate how the interface of in-car touch screen work tools can be designed to ensure usability and safety for the driver. The study included development of a prototype in the form of a new touch screen interface for a data acquisition system which was used by NIRAs test drivers for the purpose of testing their products. The prototype design was developed iteratively based on the test drivers' opinions as well as theory about important design aspects related to designing in-vehicle systems for high safety and usability. The resulting prototype was evaluated using the System Usability Scale in order to compare the prototype to the original system design and asses to what extent the new interface contributed to increased safety for the driver. The study revealed that some of the main issues that needed to be taken into account in the prototype design were prioritization of information, placement and gathering of elements and reduced amount clicks and scrolling. The final usability evaluation was conducted through user tests and the results indicated that the usability of the prototype was higher than for the original system design, thereby indicating an increased safety for the driver. Overall, this thesis contributes to the research on mitigating the risks of drivers related to interaction with in-car software systems.

In the human control of motor vehicles, there are situations regularly encountered wherein the vehicle operator becomes drowsy and fatigued due to the influence of long work days, long driving hours, or low amounts of sleep. Although various methods are currently proposed to detect drowsiness in the operator, they are either obtrusive, expensive, or otherwise impractical. The method of drowsy driving detection through the collection of Steering Wheel Movement (SWM) signals has become an important measure as it lends itself to accurate, effective, and cost-effective drowsiness detection. In this dissertation, novel technologies for drowsiness detection using Inertial Measurement Units (IMUs) are investigated and described. IMUs are an umbrella group of kinetic sensors (including accelerometers and gyroscopes) which transduce physical motions into data. Driving performances were recorded using IMUs as the primary sensors, and the resulting data were used by artificial intelligence algorithms, specifically Support Vector Machines (SVMs) to determine whether or not the individual was still fit to operate a motor vehicle. Results demonstrated high accuracy of the method in classifying drowsiness. It was also shown that the use of a smartphone-based approach to IMU monitoring of drowsiness will result in the initiation of feedback mechanisms upon a positive detection of drowsiness. These feedback mechanisms are intended to notify the driver of their drowsy state, and to dissuade further driving which could lead to crashes and/or fatalities. The novel methods not only demonstrated the ability to qualitatively determine a drivers drowsy state, but they were also low-cost, easy to implement, and unobtrusive to drivers. The efficacy, ease of use, and ease of access to these methods could potentially eliminate many barriers to the implementation of the technologies. Ultimately, it is hoped that these findings will help enhance traveler safety and prevent deaths and injuries to users.

The current program of research contributes to the World Health Organisation's (WHO, 2004) recent call to pool global resources in the attempt to uncover the most effective countermeasures and polices for the prevention of road trauma. Specifically, this program of research investigates the persuasive outcomes of different emotional health messages in an important applied context, road safety. In this context the use of negative, fear-based approaches has predominated with limited use of more positive-based approaches such as humorous- or pride-based emotional appeals. The overarching aim of the current research program was to examine the effectiveness (i.e., persuasiveness) of positive and negative emotional appeals and, specifically, the issue- or message-relevant affect that such appeals evoke. An additional aim was to ascertain the relative influence and effectiveness of positive and negative emotional appeals for specific target audiences. Particular attention was given to the effectiveness of such messages for males, a high risk road user group of particular concern. The research program also aimed to examine the relative roles and interplay of emotion and cognition in determining message effectiveness. The research focused upon the cognitive constructs of response efficacy (i.e., the extent to which a message incorporates coping strategies and information as well as the extent that individuals' perceive a message as incorporating such coping strategies and information) and involvement (i.e., the extent to which individuals perceive an issue or message as personally relevant and/or as being at risk of experiencing).----- The research program may be conceptualised as three stages, with each stage comprised of an empirical study and one or more manuscripts. The first stage of the research explored the roles and effectiveness of negative and positive emotional appeals. With a substantial body of literature available on the use of fear as a persuasive strategy, Paper One reviewed the theoretical and empirical evidence relating to the function and effectiveness of such appeals. This paper highlighted the mixed findings that have been reported and the controversy surrounding the nature of the fear-persuasion relationship. This paper also highlighted the importance of cognitive components of a message and, in particular, the need to incorporate high levels of response efficacy and to be cognisant of the issue of threat and message relevance.----- Paper Two was based on qualitative research derived from focus groups of licensed drivers (N = 16). The study investigated the roles and effectiveness of positive and negative emotional appeals in road safety advertisements addressing speeding and drink driving. The results suggested that positive and negative emotional appeals may serve different functions. Positive emotional appeals were regarded as a potentially efficacious means of promoting the message of prevention and to model safe behaviour and the rewards received whereas negative emotional appeals were regarded an important way to remind drivers of the dangers of driving.----- The second stage of the research program endeavoured to extend upon the findings reported in the first stage by providing an empirical comparison of positive, humorous appeals and negative, fear-based appeals on a range of outcome measures and over time. In Paper Three, the type of emotional appeal (positive/humorous, negative/fear), level of response efficacy (low, high), level of involvement (low, high), and gender were manipulated in a 2 x 2 x 2 x 2 mixed group design. Licensed drivers (N = 201) completed either a paper-and-pencil or internet-based version of a questionnaire. Prior to the anti-drink driving television advertisements being shown, pre-exposure were assessed. Attitudes and intentions were then assessed immediately after exposure and attitudes, intentions, and behaviour, 2 to 4 weeks later. The results provided evidence of the greater persuasiveness of negative appeals immediately after exposure and greater improvement of positive appeals over time. Also, the results highlighted the importance of high levels of response efficacy, irrespective of emotional appeal type. Paper Three also supported and extended upon earlier findings by examining third-person perceptions in relation to positive, humorous emotional appeals. The results revealed that males reported significantly greater overall influence both to themselves personally, as well as other drivers in general, than females for the humorous appeals. Further, consistent with the multiple roles of affect posited by Elaboration Likelihood Model, explanations were provided for the differential effectiveness of positive and negative affect.----- An additional aim of the second stage of the research program was to clarify an important methodological issue; the sampling adequacy of traditional university student samples versus internet-based samples for health message persuasion research. Fear appeal empirical literature has been criticised for its over-reliance upon student samples. Paper Four examined the extent that the internet may function as an efficacious means of accessing drivers for road safety advertising research. The sample characteristics and results obtained from student and internet samples of drivers were compared empirically. The results provided support for the greater diversity and representativeness of the internet sample and suggested that the two sampling approaches produce equivalent results. This paper served to inform the validity of prior research and informed the choice of sampling methodologies for the subsequent research stage reported in Paper Five.----- The third stage of the research built upon the preceding stages and, most notably, broadened the scope of emotional appeals examined by comparing a range of negative and positive emotional appeals addressing the issue of speeding. Drawing upon the Rossiter-Percy (1987, 1997) motivational model, Paper Five examined two different negative and two positive emotional appeals designed as audio messages. Specifically, the type of emotional appeal (Problem Avoidance/Fear based; Problem Removal/ Agitation or annoyance-based; Social Approval/ Pride-based; and Intellectual Mastery/ Humour-based), level of response efficacy (low, high), level of involvement (low, high), and gender were manipulated in a 2 x 2 x 2 x 2 fully between groups design. A range of persuasion outcome measures, including attitudes and intentions, were assessed immediately after exposure and 1 month later. Further, the study assessed adaptive (message acceptance) as well as maladaptive (message rejection) intentions. The results provided evidence of the effectiveness of humorous-based appeals for males and highlighted that appeals of the same valence (positive or negative) need not have the same persuasive effects. The results also supported the importance of response efficacy for all appeal types and highlighted that a message's overall effectiveness requires consideration of both message acceptance and rejection rates.----- Overall, the current research program, based upon a sound, multi-disciplinary theoretical framework, provided evidence for the need to broaden the scope of emotional appeals in the road safety advertising context and which may also be relevant within a wider health persuasion context. The results of the three studies have important theoretical and practical implications for future campaign development which are discussed.

No description available.

The objective of this dissertation is to develop a Multi-Camera Lane Departure Warning (MCLDW) system and a framework to evaluate it. A Lane Departure Warning (LDW) system is a safety feature that is included in a few luxury automobiles. Using a single camera, it performs the task of informing the driver if a lane change is imminent. The core component of an LDW system is a lane detector, whose objective is to find lane markers on the road. Therefore, we start this dissertation by explaining the requirements of an ideal lane detector, and then present several algorithmic implementations that meet these requirements. After selecting the best implementation, we present the MCLDW methodology. Using a multi-camera setup, MCLDW system combines the detected lane marker information from each camera's view to estimate the immediate distance between the vehicle and the lane marker, and signals a warning if this distance is under a certain threshold. Next, we introduce a procedure to create ground truth and a database of videos which serve as the framework for evaluation. Ground truth is created using an efficient procedure called Time-Slicing that allows the user to quickly annotate the true locations of the lane markers in each frame of the videos. Subsequently, we describe the details of a database of driving videos that has been put together to help establish a benchmark for evaluating existing lane detectors and LDW systems. Finally, we conclude the dissertation by citing the contributions of the research and discussing the avenues for future work.

Safety is an important aspect of ethical, socially responsible logistics. Current U.S. motor carrier (MC) safety research topical coverage includes the effects of individual and environmental influences, carrier safety management, and regulatory compliance on carrier safety and driver fatigue/safety performance. Interestingly, little research on the subject of truck drivers' safety attitudes and behaviors exists and the underlying decision-making processes that guide drivers' safety-related behaviors have received little attention. Furthermore, researchers have not provided an integrated framework that explains individual, organizational, and regulatory factors' impact on drivers' safety decision-making and performance. Truck drivers' safety judgments, decisions, and actions must adhere to societal safety norms. To that end, ethical decision-making theory that draws from the deontological and teleological traditions in moral philosophy provides a theoretical foundation and integrated framework necessary to better understand drivers' safety decision-making processes. The current research sought to determine how drivers rely on safety norms and perceived consequences in forming safety judgments and behavioral intentions. Furthermore, the study was designed to explore how various factors (i.e., individual, organizational, and regulatory) influence drivers' safety decision-making processes. Specifically, the study sought to answer the broad question, "How do commercial motor vehicle drivers make safety-related decisions, and how do individual, organizational, and regulatory factors influence drivers' safety decision-making processes?" An experimental two-factor design (2×2) was used to manipulate safety norms (i.e., "deontologically unsafe situation" and "deontologically safe situation") and consequences (i.e., "positive consequences" and "negative consequences"). Multivariate statistical analysis revealed that drivers primarily rely on deontological evaluations in forming safety judgments. Furthermore, drivers primarily relied on safety judgments when forming behavioral intentions. Drivers' attitudes toward unsafe actions and the effectiveness of driver-related safety regulations were also influential to drivers' judgments and intentions, respectively. The empirical findings demonstrate to managers that communication and education of safety norms may be highly effective to improve safety in unique occupational contexts where employees are given high levels of responsibility with little physical supervision, and where judgment errors can have devastating consequences for multiple stakeholders.