To see the other types of publications on this topic, follow the link: Driving Behavior.
Dissertations / Theses on the topic 'Driving Behavior'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Driving Behavior.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Toledo, Tomer 1969. "Integrating driving behavior modeling." Thesis, Massachusetts Institute of Technology, 2003. http://hdl.handle.net/1721.1/29285.
Full textAbstract:
Thesis (Ph. D .)--Massachusetts Institute of Technology, Dept. of Civil and Environmental Engineering, 2003.Includes bibliographical references (p. 192-197).
A framework for integrated driving behavior modeling, based on the concepts of short-term goal and short-term plan is proposed. Drivers are assumed to conceive and perform short-term plans in order to accomplish short-term goals. This behavioral framework captures drivers' planning capabilities and allows decisions to be based on anticipated future conditions. An integrated driving behavior model, which utilizes these concepts, is developed. This model captures both lane changing and acceleration behaviors. The driver's short-term goal is defined by the target lane. Drivers who wish to change lanes but cannot change lanes immediately, select a short-term plan to perform the desired lane change. Short-term plans are defined by the various gaps in traffic in the target lane. Drivers adapt their acceleration behavior to facilitate the lane change using the target gap. Hence, interdependencies between lane changing and acceleration behaviors are captured. The lane changing portion of the model integrates mandatory and discretionary lane changing considerations in a single model. Hence, allowing trade-offs between these considerations to be captured. Moreover, the integrated lane changing model overcomes the difficulty in defining conditions that trigger a mandatory lane changing situation. Model components that describe the choice of target gaps and acceleration behaviors to facilitate lane changing are introduced. The parameters of all components of the driving behavior model are estimated jointly using detailed vehicle trajectory data collected in a freeway in Arlington, VA. The result is a driving behavior model applicable to the behavior of all freeway traffic. Validation results of the proposed model using a microscopic traffic simulator are also presented.
by Tomer Toledo.
Ph.D .
2
Koutentakis, Dimitrios. "Modeling human driving behavior." Thesis, Massachusetts Institute of Technology, 2020. https://hdl.handle.net/1721.1/129895.
Full textAbstract:
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, February, 2020Cataloged from student-submitted PDF of thesis.
Includes bibliographical references (pages 81-84).
The goal of this thesis paper is to explore models that can predict and anticipate driver behaviors on the road and give probabilities on future actions of neighboring vehicles, while being lightweight enough to be formally verifiable. This thesis starts with looking into related work and doing a short literature review on previous work on driver models. We then talk about the available datasets used to perform such work, different models used (from classic regressions to neural networks) and finally present my approach and my results.
by Dimitrios Koutentakis.
M. Eng.
M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science
3
Golshani, Nima. "Analysis of aggressive driving behavior| A driving simulation study." Thesis, State University of New York at Buffalo, 2015. http://pqdtopen.proquest.com/#viewpdf?dispub=1600753.
Full textAbstract:
Aggressive driving behavior is the cause of a large percentage of accidents and fatalities, and it is growing every year. In several cases some drivers perceive their driving as non-aggressive when in fact they drive aggressively. To investigate factors affecting perceived (self-reported) and observed (based on the data from a driving simulation experiment) aggressive driving behavior, four fixed effect bivariate ordered probit models for three categories of aggressive driving behavior (i.e., observed and perceived non-aggressive, somewhat aggressive and very aggressive driving) are estimated. The models simultaneously account for panel data effects and cross equation error correlation. To further address unobserved heterogeneity, six grouped random parameter bivariate probit models for two outcomes (observed and perceived non-aggressive and aggressive driving) are estimated. Each model type is estimated using different barriers as driving behavior separators (either physical barriers in the distribution, or basic statistical measures). The results show that different socio-demographic characteristics, driving experience and exposure, and behavioral information of the participants affect the observed and the perceived aggressive driving behavior. The proposed approach, as a whole, provides an incremental step towards better understanding the different factors that affect the observed and the perceived aggressive driving behavior.
4
Ventaglio, Daniele. "Knowledge management driving customer behavior." Thesis, Pepperdine University, 2013. http://pqdtopen.proquest.com/#viewpdf?dispub=1541786.
Full textAbstract:
Addressing the needs and wants of the customers increases the intention of the customers to remain loyal to the company that satisfies their wants and needs. Knowledge Management (KM) and Customer Relationship Management (CRM) have both been shown to impact customer behavior. The purpose of this thesis was to explore and understand the impact of KM supported by a CRM on customer behaviors, specifically customer loyalty and customer perceived value. The results indicate that in order for KM and CRM to be effective in affecting positive changes in organizations, certain conditions need to be met. These include having employees perceive the importance of the implementation of KM and CRM approaches / processes through incorporating both KM and CRM in the business culture. All employees of all levels of the company need to have the same objective, scope and roles and responsibilities are clear defined and communicated. Both KM and CRM end-to-end processes need to be supported by one stable, easy to use, and easily accessible system with a high sophisticated search engine. The significance of this study is three-fold: for the academic community, for the companies that aim to attain competitive advantage over others, and for the customers of these companies.
5
Neuenburg, Jesko-Philipp. "Market-driving behavior in emerging firms /." Wiesbaden : Gabler, 2010. http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&doc_number=018694613&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA.
Full text
6
Olsson, Magnus. "Behavior Trees for decision-making in Autonomous Driving." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-183060.
Full textAbstract:
This degree project investigates the suitability of using Behavior Trees (BT) as an architecture for the behavioral layer in autonomous driving. BTs originate from video game development but have received attention in robotics research the past couple of years. This project also includes implementation of a simulated traffic environment using the Unity3D engine, where the use of BTs is evaluated and compared to an implementation using finite-state machines (FSM). After the initial implementation, the simulation along with the control architectures were extended with additional behaviors in four steps. The different versions were evaluated using software maintainability metrics (Cyclomatic complexity and Maintainability index) in order to extrapolate and reason about more complex implementations as would be required in a real autonomous vehicle. It is concluded that as the AI requirements scale and grow more complex, the BTs likely become substantially more maintainable than FSMs and hence may prove a viable alternative for autonomous driving.
7
Yanamanamanda, Srinivasa Rao. "Study of car-leading behavior in passing maneuvers on freeways /." free to MU campus, to others for purchase, 2003. http://wwwlib.umi.com/cr/mo/fullcit?p1418078.
Full text
8
Wei, Junqing. "Autonomous Vehicle Social Behavior for Highway Driving." Research Showcase @ CMU, 2017. http://repository.cmu.edu/dissertations/919.
Full textAbstract:
In recent years, autonomous driving has become an increasingly practical technology. With state-of-the-art computer and sensor engineering, autonomous vehicles may be produced and widely used for travel and logistics in the near future. They have great potential to reduce traffic accidents, improve transportation efficiency, and release people from driving tasks while commuting. Researchers have built autonomous vehicles that can drive on public roads and handle normal surrounding traffic and obstacles. However, in situations like lane changing and merging, the autonomous vehicle faces the challenge of performing smooth interaction with human-driven vehicles. To do this, autonomous vehicle intelligence still needs to be improved so that it can better understand and react to other human drivers on the road. In this thesis, we argue for the importance of implementing ”socially cooperative driving”, which is an integral part of everyday human driving, in autonomous vehicles. An intention-integrated Prediction- and Cost function-Based algorithm (iPCB) framework is proposed to enable an autonomous vehicles to perform cooperative social behaviors. We also propose a behavioral planning framework to enable the socially cooperative behaviors with the iPCB algorithm. The new architecture is implemented in an autonomous vehicle and can coordinate the existing Adaptive Cruise Control (ACC) and Lane Centering interface to perform socially cooperative behaviors. The algorithm has been tested in over 500 entrance ramp and lane change scenarios on public roads in multiple cities in the US and over 10; 000 in simulated case and statistical testing. Results show that the proposed algorithm and framework for autonomous vehicle improves the performance of autonomous lane change and entrance ramp handling. Compared with rule-based algorithms that were previously developed on an autonomous vehicle for these scenarios, over 95% of potentially unsafe situations are avoided.
9
VanValkenburg, MaryAnn E. "Alloy-Guided Verification of Cooperative Autonomous Driving Behavior." Digital WPI, 2020. https://digitalcommons.wpi.edu/etd-theses/1354.
Full textAbstract:
Alloy is a lightweight formal modeling tool that generates instances of a software specification to check properties of the design. This work demonstrates the use of Alloy for the rapid development of autonomous vehicle driving protocols. We contribute two driving protocols: a Normal protocol that represents the unpredictable yet safe driving behavior of typical human drivers, and a Connected protocol that employs connected technology for cooperative autonomous driving. Using five properties that define safe and productive driving actions, we analyze the performance of our protocols in mixed traffic. Lightweight formal modeling is a valuable way to reason about driving protocols early in the development process because it can automate the checking of safety and productivity properties and prevent costly design flaws.
10
Backman, Martin. "Driving skill : the role of car control behavior /." Turku : Turun yliopisto, 2001. http://catalogue.bnf.fr/ark:/12148/cb402215287.
Full text
11
Lea, Erin J. "Selection, Optimization, and Compensation in the Self-Regulatory Driving Behaviors of Older Adults." Cleveland, Ohio : Case Western Reserve University, 2010. http://rave.ohiolink.edu/etdc/view?acc_num=case1259949239.
Full textAbstract:
Thesis(M.A.)--Case Western Reserve University, 2010Title from PDF (viewed on 2010-01-28) Department of Psychology Includes abstract Includes bibliographical references and appendices Available online via the OhioLINK ETD Center
12
Aavik, Julie Jensen. "Drunk - Driving, Relapse Pattern and Risky Driving Behavior Among Participants in a DWI Prevention Programme." Thesis, Norges teknisk-naturvitenskapelige universitet, Fakultet for samfunnsvitenskap og teknologiledelse, 2010. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-11705.
Full textAbstract:
The overall aim of the study was to examine relapse among participants in the DWI Prevention Programme and those who get prison sentence after driving when influenced by alcohol and to examine the participants’ attitudes towards drunk – driving, risk behavior and traffic safety. A direct evaluation of the sentence and penal accomplishment is also examined. The sample of the survey study (see article 1) was 44 from the DWI – sample and 44 from the prison – sample that completed a questionnaire answering about their attitudes towards drunk – driving, risk behavior and traffic safety. The results presented in article 2 are based on transcripts of criminal convicts that participated in the DWI Prevention Programme during the period of 1998 – 2002 in the Salten District ( n = 68) and a sample of convicts to an unconditional sentence for drunk - driving in the same time periode (n = 112). The 1st analysis revealed that the DWI – sample had more ideal attitudes towards drunk – driving, risk behavior and traffic safety. There were also significant differences in how they evaluated their sentence and penal accomplishment. The DWI - sample were generally more satisfied with the penal accomplishment, the way they was treated and how the relationships around them were. They were also more satisfied with the contents of the penal accomplishment. Multivariate analysis, Kaplan – Meier and Cox regression was used in the 2nd analysis calculating if there were significant differences between the samples, survival time and to investigate effects of several variables upon the time a specified event takes to happen. In this study the relapse time was shorter for men than for women and the youngest age – groups had a shorter relapse time than the oldest age – groups. The Kaplan – Meier plot revealed that the prison – group have a shorter relapse time compared to the DWI – group. Based on the results of the two articles we can conclude that the DWI Prevention Programme had a very good effect on the participants compared to those who get traditional prison – sentence. The participants in the programme had the most ideal attitudes and the longest survival time after participating. When it comes to survival time among gender and age, women and the older age – groups had the longest survival time.
13
Neuenburg, Jesko-Philipp. "Market-driving behavior in emerging firms a study on market-driving behavior, its moderators and performance implications in German emerging technology ventures." Wiesbaden Gabler, 2009. http://d-nb.info/996954945/04.
Full text
14
Gurda, Ajla. "Evaluating the psychometric properties of the aggressive driving behavior questionnaire (ADBQ)." Honors in the Major Thesis, University of Central Florida, 2011. http://digital.library.ucf.edu/cdm/ref/collection/ETH/id/389.
Full textAbstract:
A principal axis factor analysis with promax rotation yielded four factors, or joint variations between the 20 items, that were inter-correlated with eigenvalues greater than 1. The ADBQ was also found to have high internal consistency (Cronbach's alpha = .86). The four factors were used to form four subscales of aggressive driving behavior that included anger/aggression, speeding/minor infractions, overt expression, and judgment of other drivers. The four subscales were found to correlate with self-reported biographical and driver history data, as well as, gender differences across scales. Additional analyses were conducted using data from the present sample from the University of Central Florida (N = 285) and the data from the previous study from Old Dominion University (N = 230) and Michigan Technological University (N = 265) for a combined sample of 780 undergraduate students. The findings in this present study provided additional support for the consistency, predictive validity, and factor structure of the ADBQ instrument. The Aggressive Driving Behavior Questionnaire proves to be a valuable measure in predicting the likelihood of a person engaging in aggressive driving behavior. The implications for driving behavior assessment, training, and instrument development are also discussed.; Over the past decade, aggressive driving behavior has become a topic of concern among the public, media, and researchers in the psychological community. Aggressive driving is a problematic pattern of social behavior that is not only a leading cause to motor vehicle accidents, but a serious threat to public safety. One instrument that has been developed to assess aggressive driving behavior is the Aggressive Driving Behavior Questionnaire (ADBQ). The ADBQ is a 20-item paper and pencil questionnaire intended to measure a driver's likelihood for engaging in aggressive driving behavior. The ADBQ was developed using a factor-analytic approach that combined five previously developed aggressive driving behavior scales (Brill, Mouloua & Shirkey, 2007). Of the 81 items of the five combined scales, nineteen latent variables were extracted and accounted for 67.4% of the explained variance for the observed responses. The final 20th item was developed by splitting one of the latent variables. A previous study, conducted at Old Dominion University (N = 230) and Michigan Technological University (N = 265), examined the ADBQ's factor structure and internal consistency, and found relatively high internal consistency (Cronbach's alpha = .77) and the identification of six factors using a principal axis factor analysis (Brill & Mouloua, 2011). The ADBQ was also tested in a controlled laboratory environment and found significant evidence that suggest the ADBQ is a valid predictor of aggressive driving behavior in a simulated environment (Brill, Mouloua & Shirkey 2009). The purpose of the present study was to further investigate the psychometric properties of the ADBQ. Based on a sample of 285 undergraduates (170 women and 115 men) from the University of Central Florida, the study examined the internal consistency, predictive and construct validity, and factor structure of the new questionnaire.B.S.
Bachelors
Sciences
Psychology
15
af, Wåhlberg Anders. "The Prediction of Traffic Accident Involvement from Driving Behavior." Doctoral thesis, Uppsala universitet, Institutionen för psykologi, 2006. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-6296.
Full textAbstract:
The aim of the studies was to predict individual traffic accident involvement by the quantification of driving style in terms of speed changes, using bus drivers as subjects. An accident database was constructed from the archives of the bus company whose drivers were used as subjects. The dependent variable was also discussed regarding whether responsibility for crashes should be included, and what time period to use for optimal prediction. A new theory was constructed about how accidents are caused by driver behavior, more specifically the control movements of the driver, i.e. all actions taken which influence the relative motion of the vehicle in a level plane when v>0. This theory states that all traffic safety related behavior can be measured as celerations (change of speed of the vehicle in any direction of a level plane) and summed. This theoretical total sum is a measure of a person's liability to cause accidents over the same time period within a homogenous traffic environment and a similarly homogenous driving population. Empirically, the theory predicts a positive correlation between mean driver celeration behavior and accident record. The theory was tested in three empirical studies. The first tested equipment and methods, the second studied the question whether driver celeration behavior is stable over time. Celeration behavior turned out to be rather variable between days, and repeated measurements were therefore needed to stabilize the measure. In the third study, a much larger amount of data brought out correlations of sizes sufficient to lend some credibility to the theory. However, the predictive power did not extend beyond two years of time. The reported results would seem to imply that the celeration variable can predict accident involvement (at least for bus drivers), and is practical to use, as it is easily and objectively measured and semi-stable over time.
16
af, Wåhlberg Anders. "The prediction of traffic accident Involvement from driving behavior /." Uppsala : Acta Universitatis Upsaliensis, 2006. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-6296.
Full text
17
Mürmann, Alexander, Alois Geyer, and Daniela Kremslehner. "Asymmetric Information in Automobile Insurance: Evidence from Driving Behavior." Wiley Periodicals, Inc, 2019. http://dx.doi.org/10.1111/jori.12279.
Full textAbstract:
Based on a unique data set of driving behavior we test whether private in-
formation in driving characteristics has significant effects on contract choice
and risk in automobile insurance. We define a driving factor based on over-
all distance driven, number of car rides, and speeding. Using local weather
conditions, we account for the endogeneity of the driving factor. While this
driving factor has an effect on risk, there is no significant evidence for se-
lection effects in the level of third-party liability and first-party insurance
coverage.
18
Wilhelmsson, Anna, and Sofia Bedoire. "Driving Behavior Prediction by Training a Hidden Markov Model." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-291656.
Full textAbstract:
Introducing automated vehicles in to traffic withhuman drivers, human behavior prediction is essential to obtainoperation safety. In this study, a human behavior estimationmodel has been developed. The estimations are based on aHidden Markov Model (HMM) using observations to determinethe driving style of surrounding vehicles. The model is trainedusing two different methods: Baum Welch training and Viterbitraining to improve the performance. Both training methods areevaluated by looking at time complexity and convergence. Themodel is implemented with and without training and tested fordifferent driving styles. Results show that training is essentialfor accurate human behavior prediction. Viterbi training is fasterbut more noise sensitive compared to Baum Welch training. Also,Viterbi training produces good results if training data reflects oncurrently observed driver, which is not always the case. BaumWelch training is more robust in such situations. Lastly, BaumWelch training is recommended to obtain operation safety whenintroducing automated vehicles into traffic.N ̈ar automatiserade fordon introduceras itrafiken och beh ̈over interagera med m ̈anskliga f ̈orare ̈ar det vik-tigt att kunna f ̈orutsp ̊a m ̈anskligt beteende. Detta f ̈or att kunnaerh ̊alla en s ̈akrare trafiksituation. I denna studie har en modellsom estimerar m ̈anskligt beteende utvecklats. Estimeringarna ̈ar baserade p ̊a en Hidden Markov Model d ̈ar observationeranv ̈ands f ̈or att best ̈amma k ̈orstil hos omgivande fordon itrafiken. Modellen tr ̈anas med tv ̊a olika metoder: Baum Welchtr ̈aning och Viterbi tr ̈aning f ̈or att f ̈orb ̈attra modellens prestanda.Tr ̈aningsmetoderna utv ̈arderas sedan genom att analysera derastidskomplexitet och konvergens. Modellen ̈ar implementerad medoch utan tr ̈aning och testad f ̈or olika k ̈orstilar. Erh ̊allna resultatvisar att tr ̈aning ̈ar viktigt f ̈or att kunna f ̈orutsp ̊a m ̈anskligtbeteende korrekt. Viterbi tr ̈aning ̈ar snabbare men mer k ̈ansligf ̈or brus i j ̈amf ̈orelse med Baum Welch tr ̈aning. Viterbi tr ̈aningger ̈aven en bra estimering i de fall d ̊a observerad tr ̈aningsdataavspeglar f ̈orarens k ̈orstil, vilket inte alltid ̈ar fallet. BaumWelch tr ̈aning ̈ar mer robust i s ̊adana situationer. Slutligenrekommenderas en estimeringsmodell implementerad med BaumWelch tr ̈aning f ̈or att erh ̊alla en s ̈aker k ̈orning d ̊a automatiseradefordon introduceras i trafiken
Kandidatexjobb i elektroteknik 2020, KTH, Stockholm
19
Boyle, Linda T. Ng. "Statistical analyses of traffic advisory systems on driving behavior /." Thesis, Connect to this title online; UW restricted, 1998. http://hdl.handle.net/1773/10174.
Full text
20
De, Jager Alexis Kate. "Delay Discounting and Campus Speeding Behavior." OpenSIUC, 2020. https://opensiuc.lib.siu.edu/theses/2656.
Full textAbstract:
TITLE: DELAY DISCOUNTING AND CAMPUS SPEEDING BEHAVIORMAJOR PROFESSOR: Dr. Ryan Redner Speeding, as defined by exceeding the speed limit posted in a designated area, is a problem that has a direct negative effect on a majority of America, college campuses not being exempt. A minimal amount of research has been conducted on specifically dangerous driving such as speeding on university campuses; this paper looks to expand upon the existing research. In addition, this study serves the purpose of attempting to correlate speeding and impulsivity. This was achieved by utilizing a survey in conjunction with delay discounting scenarios embedded within. Participants (n = 89) took a survey that involved questions about demographic information and past driving. The survey also included two hypothetical scenarios that encouraged participants to answer whether they would speed in the presented scenarios and at what point. To complete the survey the MCQ (Monetary Choice Questionnaire) was placed at the end. To assess the results the 89 participants were split into two groups two different times to be analyzed. One group was split into an impulsive group and non-impulsive group while the other group was split into speeders and non-speeders. As expected, both the impulsive and speeders were more likely to discount speed at a faster rate; this shown at higher rates in the penalty hypothetical scenario. The implications of this study include that those with that display higher impulsivity, shown through k-values, may have a higher tendency to engage in dangerous driving such as speeding, as well as understanding that penalty conditions, such as point loss, show a correlation with speeding.
21
Kondaveeti, Srinivasa Kiran, and Andreas Kostoulas. "Successful Organizational Innovation and Key Driving Factors." Thesis, Blekinge Tekniska Högskola, Institutionen för industriell ekonomi, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-17295.
Full textAbstract:
The aim of the thesis is to discuss the key driving factors influencing the success of innovation in high-tech firms based in Sweden. The thesis will discuss key determinant factors and how those factors are connecting with each other. Organizational innovation and Organizational culture relationship have been under research for many years. The success of organizational innovation can be captured by various factors. Similarly, the organizational culture can be captured by different factors. During the research process, we came across various theories and this thesis is based on Rao and Weintraub (2013) developed model. The model provides six building blocks with determinant factors as a foundation for the successful innovative organizational culture. The six major building blocks or factors are Values, Behaviours, Climate, Resources, Processes, and Success (Rao & Weintraub, 2013). The purpose of the study is to define the hypothetical relationship between some of the six major factors which drives the successful innovation in the organization. The authors have developed a model for successful organizational innovation based on their hypotheses. It will be a matter of great interest to reflect upon the employee's feedback regarding those factors that influence firm’s organizational culture and successful innovation. The model was analyzed using the results of the survey in which 230 employees participated from Swedish based high-tech firms, using Structural Equation Modelling (Hair et al, 2010). The research results reveal some of the key contributors towards the successful organizational innovation and the relation between the factors for the successful organizational innovation. The factor successful innovation is strongly dependent on the innovation processes factor and this is followed by some more relatively moderate contributing factors such as the leaders’ behaviours, and the organizational resources. The study reveals that there is a strong relation between the innovation success and the innovation processes. The innovation processes factor is positively connected to the organization values, the leaders’ behaviours, and the organization resources. The organization climate is weakly connected to the innovation processes as represented by the data sample collected which needs to be further investigated. The model identified in the thesis gives an understanding of how the six factors are connected to drive the successful organizational innovation.
22
Jun, Jungwook. "Potential Crash Measures Based on GPS-Observed Driving Behavior Activity Metrics." Diss., Georgia Institute of Technology, 2006. http://hdl.handle.net/1853/19832.
Full textAbstract:
Identifying and understanding the relationships between observed driving behavior over long-term periods and corresponding crash involvement rates is paramount to enhancing safety improvement programs and providing useful insights for transportation safety engineers, policy markers, insurance industries, and the public. Unlike previous data collection methods, recent advancement in mobile computing and accuracy of global positioning systems (GPS) allow researchers to monitor driving activities of large fleets of vehicles, for long-time study periods, at great detail.
This study investigates the driving patterns of drivers who have and who have not experienced crashes during a 14-month study period using the longitudinally collected GPS data during a six-month Commute Atlanta study. This investigation allows an empirical investigation to assess whether drivers with recent crash experiences exhibit different driving or activity patterns (travel mileage, travel duration, speed, acceleration, speed stability duration, frequency of unfamiliar roadway activities, frequency of turn movement activities, and previous crash location exposures). This study also discusses various techniques of implementing GPS data streams in safety analyses. Finally, this study provides useful guidance for researchers who plan to evaluate the relationships between driver driving behavior and crash risk with large sample data and proposes driving behavior activity exposure metrics of individual drivers for possible safety surrogate measures as well as for driver re-training and education programs.
23
Emanuelsson, Kajsa. "Examining factors for low use behavior of Advanced Driving Assistance Systems." Thesis, Linköpings universitet, Institutionen för datavetenskap, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-166400.
Full textAbstract:
Advanced Driving Assistance Systems (ADAS) has the potential to decrease the number of fatal accidents in traffic. However, in some cases, drivers with the systems in their car are resistant against using them. Exploring the underlying reasons and factors of the low-usage of ADAS was the purpose of this thesis. The thesis consists of Study I, an exploratory interview study with ten drivers who had cars with ADAS. The goal of Study I was to highlight the possible reasons behind the low usage of ADAS. The results of Study I were used to design Study II, which consisted of a survey targeted to drivers who had access to the ADAS adaptive cruise control and lane keep assist (N = 49). The results indicate that the factors or circumstances that affect usage depend on the ADAS and the user groups. Some identified underlying factors for low usage behavior of ADAS are the need to monitor the vehicle more when ADAS is activated and lack of trust in own ability when using ADAS compared to the high usage group.Advanced Driving Assistance Systems (ADAS) har potential att förhindra antalet dödsfall i trafiken. Det förekommer att förare som har systemen i sin bil, väljer bort att använda dem. Syftet med den här uppsatsen var att undersöka underliggande orsaker och faktorer till låg användningsgrad av ADAS. Uppsatsen består av två studier. Studie I är en explorativ intervjustudie med tio förare som hade bilar med ADAS. Målet med Studie I var att ringa in de möjliga bakomliggande faktorerna för låg användningsgrad av ADAS. Resultaten från Studie I användes för att utforma en enkätstudie till Studie II som var riktad till förare som hade bilar med förarstödsystemen adaptiv farthållare och körfältsassistans (N = 49). Resultaten pekar på att de underliggande orsakerna och faktorerna beror på vilken ADAS som avses samt vilket användargrupp föraren tillhör. Några underliggande faktorer för låg användingsgruppen tycks vara känsla av att behöva övervaka fordonet samt lägre grad av tilltro till den egna förmågan än vad höganvändingsgrupper rapporterade.
24
Mekki, Fatma. "Psychoanalytic maps of driving behavior inspired from Zizekian psychoanalysis : Tunisian context." Thesis, Lille 1, 2016. http://www.theses.fr/2016LIL12006.
Full textAbstract:
L’insécurité routière est un problème de santé publique. Il n' y a pas de recherche qui a exploré la psychanalyse de Zizek pour comprendre le comportement du conducteur. Cette recherche est basée sur l'approche interdisciplinaire dans le cadre du mouvement "Transformative Social Marketing". La contribution théorique présente une nouvelle vision du comportement basée sur des concepts psychanalytiques de Slavoj Zizek pour comprendre le comportement du conducteur, comme une première en Théorie marketing. Elle présente trois groupes basés sur la triade Réel-Symbolique-Imaginaire qui oriente le comportement vers le respect/non respect du code de la route. La contribution méthodologique est "la carte psychanalytique" qui tient compte de la complexité du comportement. La contribution pratique est l'acte authentique, provenant du conducteur pour personnaliser le message adéquat dans sa voiture ainsi que le changer en utilisant la technologie "VANet" en tenant en compte de l'aspect routinier de l'acte de conduireThe disobedience of traffic rules is a public health problem. There is an absence of understanding driving behavior from Zizekian psychoanalysis. The general scope of this research is based on the interdisciplinary approach in a Transformative Social Marketing. The theoretical implication presents a new view of human behavior inspired from Zizekian psychoanalysis (based on "conscious/unconscious" in a continuous process, Real-Symbolic-Imaginary Triad, Reflexivity, Interpassivity, authentic act). Three groups (Pleasing, Care, Refuge) emerge from the Real-Symbolic-Imaginary Triad that orients behaviors to obey or disobey traffic rules. The methodological implication is the "psychoanalytic map" as a new methodological tool for more understanding the complexity of driving behavior. The practical implication is an authentic act, emerged from the driver, to choose a personalized message which changes after a period using VANet technology
25
Versuk, Karen Anne. "The Influence of Public Policy Interventions on Millennial Distracted Driving Behavior." ScholarWorks, 2016. https://scholarworks.waldenu.edu/dissertations/2242.
Full textAbstract:
Despite recent public policy initiatives limiting or banning forms of distracted driving resultant from cellular phone use, crashes remain on the rise. Individuals from the millennial generation, ages 16 to 35, appear to be most susceptible to distracted driving. Understanding the behaviors, attitudes, and habits of millennials is critical to developing effective policy for behavior change. A dual task ethnographic study framed by Skinner's theory of behavior modification and Maslow's hierarchy of needs motivational model, was used to investigate to what extent millennials feel public policy has influenced their driving, and if additional policy initiatives are required to deter distracted driving behavior. Two phases of inquiry, first, naturalistic observation, and then focus group were conducted at a commuter university. Distracted driving behaviors including hand held cellular phone use, eating, drinking, and passenger interaction of 100 drivers entering or exiting campus were observed, tracked, and analyzed using a researcher-developed tracking form. Eighty-four percent exhibited at least one distracted driving behavior. After which, 12 enrolled and licensed students, aged 18-35, were recruited via social media for two focus group discussions. Focus group data were inductively coded and analyzed using semantical attribution analysis. The students revealed that millennial drivers felt distracted driving policy did not address behaviors they see as worthy of intervention, they did not perceive that cellular phone use while driving posed a significant threat, and they felt current law was difficult to enforce with penalties they regarded as non-prohibitive. Social change implications include improved distracted driving public policy, which may result in driving behavior changes and a potential reduction of death, injury, and property loss.
26
Fox, Russell Thomas. "Examining Attention, Impulsiveness, and Cognitive Failures in Driving Behaviors." Digital Commons @ East Tennessee State University, 2012. https://dc.etsu.edu/etd/1465.
Full textAbstract:
Dangerous driving behaviors are influenced by multiple factors including cognitive processes such as impulse inhibition and attentiveness. Impulsiveness, inattention, and cognitive failures have been linked to other risky behaviors, but a comprehensive evaluation using multiple methods of measurement of these has never been conducted to analyze their impact on dangerous driving. The purpose of this study was to examine influences of attentional abilities, impulsiveness, and cognitive failures on reported and demonstrated dangerous driving behaviors. Seventy-five participants completed a self-report dangerous driving measure, a self-report ADHD measure, a self-report impulsiveness measure, a continuous performance task to measure behavioral impulsivity and inattention, a measure of cognitive failures, and a driving simulator task. Two hierarchical linear regressions with simultaneous entry into blocks were used to analyze contributions of impulsiveness, inattention, and cognitive failures assessments in predicting dangerous driving behavior. Results indicated these assessments accounted for a significant proportion of the variance in Dula Dangerous Driving Index (3DI) scores above and beyond the effects of age and sex, Adjusted R▓ = .20, F(6, 59) = 2.51, p < .05, but no significant individual predictors emerged. Scores on these measures were also found to account for a significant amount of the variance in risky driving as measured by the driving simulator, above and beyond the effects of age and sex, Adjusted R▓ = .15, F(6, 60) = 2.91, p < .05, and identified BIS-11 scores and ADHD-RS impulsiveness scores as significant individual predictors. It seems that despite multiple methods of assessment, it is still difficult to capture the assumed relationships between each of these factors and driving. Though each assessment measures different aspects of constructs related to dangerous driving, the lack of relationships and predictive abilities may indicate that impulsiveness, inattention, cognitive failures, and dangerous driving may be more complex and multifaceted than previously understood.
27
Van, Dyke Nicholas A. "ALCOHOL-INDUCED IMPAIRMENT OF SIMULATED DRIVING PERFORMANCE AND BEHAVIORAL IMPULSIVITY IN DUI OFFENDERS." UKnowledge, 2018. https://uknowledge.uky.edu/psychology_etds/141.
Full textAbstract:
Licensed drivers arrested for driving under the influence (DUI) of alcohol have increased rates of vehicle crashes, moving violations, traffic tickets, and contribute to an estimated 120 million occurrences of impaired driving per year (Evans, 2004; Jewett et al., 2015). Survey research on DUI offenders indicates traits of impulsivity (e.g., sensation seeking). Together, these pieces of evidence suggest that DUI offenders display patterns of impulsive action and risk-taking while driving. However, to-date DUI offenders are rarely studied in a laboratory setting, and not much is known about how they respond to a dose of alcohol. The present study examined the degree to which DUI offenders display an increased sensitivity to the acute impairing effects of alcohol on mechanisms of behavioral impulsivity, skill and risk-based driving simulations, and subjective evaluations of driving fitness and perceived intoxication following alcohol consumption. A sample of 20 DUI offenders were compared to a demographically-matched sample of 20 control drivers. All participants attended two dose sessions in which they received either a 0.65 g/kg dose of alcohol or a placebo dose, counterbalanced, on separate days. Results indicated that alcohol affected all of the behavioral outcome measures. More specifically, alcohol increased impulsive choice responses and decreased response inhibition on the behavioral impulsivity tasks. Alcohol also increased risky driving behaviors and decreased driving-related skills. Furthermore, alcohol generally decreased participants’ self-reported willingness and ability to drive a motor vehicle, and increased levels of intoxication and BAC estimations relative to placebo. With regard to group differences, DUI offenders showed an increased sensitivity to the disrupting effects of alcohol on impulsive choices, such that DUI offenders showed a significantly greater preference for impulsive choices under alcohol relative to placebo than controls. Taken together, these findings provide some of the first pieces of evidence that compared to controls, DUI offenders display an increased tendency for impulsive decisions under alcohol, which likely contributes to risky decisions to drive after drinking, despite clear evidence for their behavioral impairment. These findings could have important implications for understanding the mechanisms underlying maladaptive behaviors in this high-risk population, and sheds light on possible targets for intervention to reduce DUI recidivism.
28
Kim, Taehyung. "Analysis of variability in car-following behavior over long-term driving maneuvers." College Park, Md. : University of Maryland, 2005. http://hdl.handle.net/1903/3048.
Full textAbstract:
Thesis (Ph. D.) -- University of Maryland, College Park, 2005.Thesis research directed by: Civil Engineering. Title from t.p. of PDF. Includes bibliographical references. Published by UMI Dissertation Services, Ann Arbor, Mich. Also available in paper.
29
Miyajima, Chiyomi, Yoshihiro Nishiwaki, Koji Ozawa, Toshihiro Wakita, Katsunobu Itou, Kazuya Takeda, and Fumitada Itakura. "Driver Modeling Based on Driving Behavior and Its Evaluation in Driver Identification." IEEE, 2007. http://hdl.handle.net/2237/9623.
Full text
30
Platten, Frederik. "Analysis of Mental Workload and Operating Behavior in Secondary Tasks while Driving." Doctoral thesis, Universitätsbibliothek Chemnitz, 2013. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-qucosa-105221.
Full textAbstract:
In this thesis, situations were analyzed in which drivers operate infotainment systems (IVIS) while driving. In this, the focus lay on such situations in which drivers operated these secondary tasks successfully. Following that, a resource orientated approach was chosen in contrast to the focus of many other studies. Demonstrating the negative effects of secondary tasks while driving was less central in this thesis. Rather, everyday behavior adaptations were analyzed that enabled drivers to operate secondary tasks successfully while driving. Therefore these adaptations were measured with regards to the following three factors: driving task, secondary task and mental workload. Additionally the influence of several secondary task attributes was analyzed. Thereby especially the perceived interruptibility was researched in detail. The thesis contains 3 different parts: 1. Introduction to research field, 2. Empiric part and 3. Overall discussion. In the first part an introduction and an overview of the current research concerning secondary task operation while driving is presented. The second part contains 3 studies, each presented in manuscript form. The goal of the first study was to show basic behavior adaptations in a driving simulator study that enables drivers to operate secondary tasks while driving. Thereby it became obvious that drivers adapted their driving behavior as well as their activity in the secondary task dynamically to the specific situation. The driving task was prioritized thereby. The adaptations were dependent on the current as well as the anticipated development of the situations and correspondingly sensitive to the variation of a cue to a hazardous driving situation. If drivers were warned (and thereby an anticipation was possible), they reduced especially their activity in the secondary task. In the second study the influence of mental workload and the attributes of a secondary task were analyzed in-depth. Drivers were informed by a noise signal either about an upcoming unknown driving situation or about an upcoming speed reduction situation in this study. It could be shown that if a secondary task can be interrupted without a perceived decline in performance, it is interrupted in demanding driving situations. If an interruption causes a perceived performance loss, the task is interrupted less often, and so the workload is increased (measured with a physiological measurement). Thus, drivers compensate their current demands by behavior adaptations in different factors, depending on the characteristics of a secondary task. The interaction between driving task, secondary task and workload could be proven by this research. Only if a secondary task could be interrupted without a perceived loss of performance drivers interrupted the task before a hazardous situation was reached. In line with the findings from the studies above a setting was developed for the third study that is less bound to the simulation of complex driving situations and thereby independent from specific driving simulator settings. Nevertheless the anticipation of further driving situations and the option to adapt behavior was given to the drivers by the setting to measure the effects described above. Additionally secondary tasks were analyzed that have a high comparability to common IVIS. Thus, a focus was on the influence of tasks that require time critical inputs. As expected, in tasks with time critical inputs the activity was less often reduced, even if a demanding driving situation was announced. Thereby another influencing factor to the perceived interruptibility of secondary tasks could be analyzed. In the presented studies it was shown that drivers anticipate the further development of a situation and adapt their activity in the secondary task dynamically due to several characteristics of this task. For the future evaluation of IVIS, methodological requirements were deduced from the presented studies and a possible setting for further research was discussedIn dieser Dissertation werden Situationen untersucht, in denen Fahrer während der Fahrt Infotainmentsysteme (In- Vehicle Infotainment Systeme, kurz IVIS) bedienen. Hierbei wird der Fokus auf Situationen gelegt, in denen Fahrer erfolgreich Nebenaufgaben bearbeiten. Im Gegensatz zu einer Vielzahl von anderen Studien wird hier ein ressourcenorientierter Ansatz gewählt. Im Mittelpunkt steht demnach weniger der Nachweis von Leistungseinbußen in der Fahraufgabe durch zusätzliche Aufgaben. Es wird im Gegensatz dazu herausgearbeitet, durch welche alltäglichen Verhaltensanpassungen Fahrer in der Lage sind, Aufgaben zusätzlich zur Fahraufgabe erfolgreich zu bearbeiten. Dazu werden diese Verhaltensanpassungen messbar gemacht. Ein Hauptaugenmerk wird dabei auf die Faktoren Fahraufgabe, Nebenaufgabe und die mentale Beanspruchung gelegt. Des Weiteren wird der Einfluss verschiedener Nebenaufgaben auf das Verhalten analysiert. Dabei wird insbesondere die wahrgenommene Unterbrechbarkeit der Nebenaufgaben detailliert untersucht. Die Arbeit besteht aus 3 Teilen: 1. Hintergrund des Forschungsfeldes, 2.Experimentalteil und 3. zusammenfassende Diskussion. Im ersten Teil der Arbeit wird zunächst eine Einführung in das Forschungsfeld gegeben und anschließend ein Überblick über den aktuellen Forschungsstand in Bezug auf Zweitaufgabenbearbeitung während der Fahrt. Im Experimentalteil werden 3 Studien präsentiert, die im Rahmen dieser Arbeit durchgeführt wurden (jeweils in Form einer Veröffentlichung). In der ersten Studie war das Ziel grundlegende Verhaltensanpassungen in einer Fahrsimulationsstudie nachzuweisen, die es Fahrern ermöglichen Nebenaufgaben erfolgreich während der Fahrt zu bearbeiten. Dabei wurde deutlich, dass Fahrer ihr Fahrverhalten und ihre Eingabeaktivität in einer Nebenaufgabe der jeweiligen Situation dynamisch anpassen. Die Fahraufgabe wurde dabei priorisiert. Die Verhaltensanpassungen waren sowohl abhängig von der aktuellen, als auch von der antizipierten Situation und zeigten sich demnach abhängig von der Variation eines Hinweisreizes auf eine kritische Verkehrssituation. Als die Fahrer vor einer möglichen Gefahr gewarnt wurden (sie diese also antizipieren konnten), wurde insbesondere die Aktivität in der Nebenaufgabe reduziert. In der daran anschließenden Studie wurde die Rolle der Beanspruchung im Zusammenhang mit den Eigenschaften der Nebenaufgabe näher untersucht. Probanden wurden mithilfe eines Tons entweder auf eine bevorstehende, unbekannte Fahrsituation oder auf eine bevorstehende Geschwindigkeitsreduktion hingewiesen. Es konnte gezeigt werden, dass Fahrer in Situationen, in denen sie den weiteren Fahrverlauf antizipieren und die Nebenaufgabe ohne wahrgenommenen Leistungsverlust unterbrechen konnten, signifikant weniger bedienten. Im Gegensatz dazu zeigte sich in Nebenaufgaben, deren Unterbrechung einen direkten Leistungsverlust nach sich zog, dass Fahrer auch in kritischen Situation gleich viel bedienten. Dieses Verhalten wurde durch eine höhere Anstrengung kompensiert (gemessen mit einem physiologischen Beanspruchungsmaß). Der Zusammenhang der drei Faktoren Fahraufgabe, Nebenaufgabe und Beanspruchung wurde hierbei deutlich. Des Weiteren konnte der Einfluss der Eigenschaften der Nebenaufgaben deutlich gemacht werden: Nur wenn die Unterbrechung der Nebenaufgabe keinen direkten Leistungsverlust zur Folge hatte, wurde diese bereits vor dem Auftreten einer kritischen Situation unterbrochen. Basierend auf den Ergebnissen der ersten beiden Studien wurde für die dritte Studie ein vereinfachtes Setting entwickelt, das weniger auf der Simulation komplexer Fahrsituationen basiert, mithilfe dessen jedoch dennoch die relevanten Effekte messbar sein sollen. Dadurch wird das Setting unabhängiger von einer bestimmten Simulationsumgebung. Dabei wurde den Probanden sowohl ermöglicht relevante Fahrsituationen zu antizipieren als auch ihr Verhalten daran anzupassen. Des Weiteren wurden Nebenaufgaben analysiert, die ähnliche Bedieneingaben erforderten wie gebräuchliche IVIS, und die zum Teil zeitkritische Eingaben erforderten. Wenn Eingaben zeitkritisch gemacht werden mussten, wurde die Nebenaufgabe erwartungsgemäß seltener unterbrochen, auch wenn eine kritische Fahrsituation angekündigt wurde. Dadurch wurde ein weiterer Einflussfaktor auf die wahrgenommene Unterbrechbarkeit von Aufgaben in Fahrsituationen untersucht. In den vorliegenden Studien konnte gezeigt werden, dass Fahrer den weiteren Verlauf von Fahrsituationen antizipieren und ihre Aktivität in einer Nebenaufgabe dynamisch und in Abhängigkeit zu bestimmten Eigenschaften der Nebenaufgabe anpassen. Für die zukünftige Bewertung von IVIS wurden dabei relevante methodische Rahmenbedingungen herausgearbeitet und ein mögliches Setting vorgestellt
31
Amata, Hideomi, Chiyomi Miyajima, Takanori Nishino, Norihide Kitaoka, and Kazuya Takeda. "Prediction model of driving behavior based on traffic conditions and driver types." IEEE, 2009. http://hdl.handle.net/2237/13899.
Full text
32
Kalila, Adham. "Big data fusion to estimate driving adoption behavior and urban fuel consumption." Thesis, Massachusetts Institute of Technology, 2018. http://hdl.handle.net/1721.1/119335.
Full textAbstract:
Thesis: S.M. in Transportation, Massachusetts Institute of Technology, Department of Civil and Environmental Engineering, 2018.Cataloged from PDF version of thesis.
Includes bibliographical references (pages 63-68).
Data from mobile phones is constantly increasing in accuracy, quantity, and ubiquity. Methods that utilize such data in the field of transportation demand forecasting have been proposed and represent a welcome addition. We propose a framework that uses the resulting travel demand and computes fuel consumption. The model is calibrated for application on any range of car fuel efficiency and combined with other sources of data to produce urban fuel consumption estimates for the city of Riyadh as an application. Targeted traffic congestion reduction strategies are compared to random traffic reduction and the results indicate a factor of 2 improvement on fuel savings. Moreover, an agent-based innovation adoption model is used with a network of women from Call Detail Records to simulate the time at which women may adopt driving after the ban on females driving is lifted in Saudi Arabia. The resulting adoption rates are combined with fuel costs from simulating empty driver trips to forecast the fuel savings potential of such a historic policy change.
by Adham Kalila.
S.M. in Transportation
33
Lin, Cheng-Yang, and 林正陽. "Feasibility Study of Simulated Driving Behavior Replacing Real Driving Behavior." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/ug4yzh.
Full textAbstract:
碩士國立中央大學
資訊工程學系
107
According to the World Health Organization (WHO). Road traffic accidents, the leading cause of death by injury and the tenth-leading cause of all deaths globally. An estimated 1.2 million people are killed in road crashes each year, and as many as 50 million are injured. At the same time, the economic costs derived from traffic accidents are quite high, also the gross domestic product (GDP) of the world is 3% lost due to traffic accidents each year. It is easily to tell that traffic accidents will not only bring the injured but also affect global economy. Risk driving behavior is easy to cause traffic accidents. In order to identify risk behaviors, it is necessary to construct a driving behavior model. In the past, many teams have already collected risk driving behaviors in a real driving environment and build risk driving behavior models for verification. Collecting risk driving behaviors in real environment cost extremely high, in maintenance, and we believe that there is still considerable risk in collecting risk driving behaviors at any locations. In the past research, a novel driver identity verification system based on Gaussian Mixture Model’s driving behavior was proposed. The system constructs a simulated driving environment which collects the driver's wrist behavior data from a smartwatch. Due to the smartwatch based, it has the advantages of constructing simulation environment with low cost and strong portability also lots of risk driving behaviors are directly related to the wrist movements. These factors make it more suitable for collecting risk driving behaviors in this environment. However, no research has clearly pointed out the feasibility of using the simulated driving behavior prediction model to identify real driving behavior at present. Moreover, there are no precedents for effectively utilizing the simulated dangerous driving behavior model. Therefore, we expect this study to achieve: In other applications such as driver identification, the simulated driving behavior model can completely replace the real driving behavior model. With this concept, for all driving behaviors that do not conform to the normal road driving principles, such as: fatigue driving, drunk driving and other dangerous driving behavior, we can collect these dangerous driving behavior data through the simulated environment and apply it to identify dangerous driving behaviors in the real environment, thus providing a safer and more reliable dangerous driving discriminating mechanism in the market.
34
Zhong, Zi-Ren, and 鍾子仁. "Motorcycle Driving Behavior Analysis." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/97414123704602085745.
Full textAbstract:
碩士國立中興大學
電機工程學系所
105
To get a motorcycle driver''s license, the steps generally includes a health checkup, a knowledge test, and a road test. The road test is to evaluate the drivers’ maneuver capability in a simulated yard but not on real road networks and it cannot be assessed whether the drivers obey traffic rules and have good driving behaviors after they got a license. Therefore, we propose a motorcycle driving behavior analysis system, which can evaluate driver behavior persistently and determine whether the driver has safe driver behaviors. To recognize different driving behaviors, the driving behavior analysis system includes an Arduino diagnosis scanner to sample ECU data including engine rpm, battery energy, throttle, and intake and so on. It is also equipped with a gyroscope and an accelerometer to capture motion data of a motorcycle. The Arduino diagnosis scanner sends data to a smart phone via Bluetooth and the Android App uploads the data to a server for further processing. Finally, the server aggregates data and per-forms RBM neural network to train classifiers for on-line driving behavior recognition and analysis. To validate our system, we collect data of different driving behaviors under different traffic conditions and conduct experiments to evaluate the classification performance. The experimental results show that the proposed system can effectively recognize different driving behaviors. The future works are to extend it for more complex driving behaviors and apply the system for driving assistant and monitoring.
35
Shuo-YuSun and 孫碩昱. "Train Drivers’ Driving Behavior Investigation." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/27976862723518493467.
Full textAbstract:
碩士國立成功大學
交通管理學系碩博士班
98
Rail safety is very important, because trains are heavy and fast. Their kinetic energy means that the consequences of an accident are severe. In past investigations, train driver was one of the important factors in rail safety, because many accidents were caused by human factors of the train driver. So, if we want to improve rail safety, we must begin from the train driver. Recently, many railway companies started to install the Automatic Train Protection (ATP) in the driving cabs in order to prevent train drivers’ lapses and correct some incorrect driving behaviors to avoid major accidents. But even if the rail system were under Automatic Train Protection’s protect, there were still some potential negative if we depended on the system too much. If the system failed and the train driver was doing an incorrect behavior, an accident might happen. So we use the ATP’s records to find out the near miss incidents, and then use Generalized Estimating Equations (GEE) to attribute possible reasons from engineer (driver), train, track and environment. The results shows the near miss incidents and those four factors were significant related. There are two kinds of near miss incidents: “Late Brake” and “Over Speed”. Drivers’ records were significant in both near miss incidents and if seniority rose up would cause less Late Brake and more Over Speed incidents. Furthermore, train types and environment factors like slope and rain would also cause near miss incidents.
36
Yin, Wei-lung, and 尹維龍. "Application of Driving Behavior Questionnire to Investigate the Relationship of Aberrant Driving Behaviors and Accidents." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/86850516623359164364.
Full textAbstract:
碩士國立交通大學
運輸科技與管理學系
93
This study investigated the relationship of driver’s attribute, mood, pressure, driving experience and aberrant driving behavior with the quantitative method in hierarchical way. Influence of aberrant driving behavior on traffic accidents was also investigated with the same way. Research results have exhibited that the aberrant behaviors can be categorized into: violations, mistakes and lapses. Regression analysis showed that violations were positively correlated with mood, driving skill, but negatively with safety-motive, pressure, age. Mistakes were negatively correlated with driving skill, but positively correlated with mood. Males reported more violations and mistakes than females. Lapses were significantly correlated with pressure, driving skill and education. Consequently, violations and mistakes were proved to be stable predictors of accidents. When the structure equation method was applied, the results indicated the same with regression analysis. It showed safety-motive was not significantly correlated with mistakes, lapses; and emotion was not significantly correlated with lapses either.
37
Li, Shih-Hong, and 李世宏. "The Study of Cyclist Driving Behavior with Bike Driving Simulator." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/74745181110850875601.
Full textAbstract:
碩士國立中央大學
機械工程研究所
98
Leisure activities in recent years, the gradual rise of bicycle riding, but the Taiwan region is among the road planning design for the bike lane, most of the current bike lanes with motorcycles sharing. Plus the number of motorcycles in urban areas in Taiwan have already exceeded the original design of the road capacity, not only made the motorcycle lanes very crowded. Because of motorcycle and bicycle speed gap and prone to road congestion, and even cause traffic accidents. In this study Bike driving simulator simulates the real condition of road junctions. The subject will experience a number of different emergencies. It will see whether the driving behavior of motorcyclist affects cyclist. Analyzing data of cyclist identifies the most influential factors. Event type, velocity difference, reaction time, wearing helmets has a certain impact. Emergency braking Event is most threat to subjects. Velocity difference has little effect. The shorter reaction time, subjects were more dramatic changes in driving performance. In the condition of Wearing helmet subjects adopted a more dangerous driving behavior.
38
Yang, Shun-Tang, and 楊舜棠. "A Study on the Impacts of Driver Education upon Driving Behavior through Driving Behavior Questionnaire." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/39074420662597246928.
Full textAbstract:
碩士國立交通大學
運輸科技與管理學系
95
The death rate of traffic accidents in Taiwan is several times higher than in other developed countries. The phenomenon is not only resulted from backwardness of traffic engineering, performance of vehicles, and driving skills of drivers but also resulted from driving manners and driving attitudes. The Rasch model, in this study, is applied to build an inventory to measure driving behavior of drivers before and after they took driving education courses. The aim of the study is to observe driving behavior through driving attitudes and driving abilities. According to the results of practical studies, four phases are explored as follows. First, driving attitudes, persons who lack a few abilities in “Self-Control” and “Risk Perception” should be much well-educated. Learning sessions should be redesigned and planed in components of “Attitudes to Regulations” and “Interactions with Other Road Users”. Second, confidence in driving skills, persons who lack a few abilities in “Manipulating”, “Regulation Cognition”, and “Defensive Driving” should be much well-educated. Learning sessions should be redesigned and planed in components of “Accident Disposal”, “Emergency Reacting”, and “Vehicle Maintenance”. Third, aberrant driving behavior, those components for “Driving Violation”, “Driving Errors” and “Aggressive Driving Behavior” which would cause serious accidents should be well-noticed to decrease incidence. Finally, driving attitudes before and after driving education, the results from abilities of “Regulation Perception” and “Risk Perception” have relatively improved. According to its lack of abilities, the component of “Interactions with Other Road Users” is the first subject which should be enhanced. The result of the study not only upgrades qualities of driver education but also provides the reference to complete development of driver education in the future.
39
Chang, Kai-Ciao, and 張凱喬. "Applying the Theory of Hierarchical Driving Behavior to Explore the Driving Behavior of Motor Coach Drivers." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/e3qjbc.
Full textAbstract:
碩士國立交通大學
運輸與物流管理學系
103
Driver’s inappropriate behavior account for the traffic accidents mostly. In the past, researchers are thinking about what factor is behind the inappropriate driving behavior. According to the development of traffic psychology, it is clear that driving performance is not sufficient to explain driving behavior, and it’s necessary to take motivational and attitudinal factors into account. Keskinen(1996) propose a four-level hierarchical modal to describe driving behavior which raised a point that the goals and contents of the driver play an essential role affecting driving performance. Between different hierarchies, the modal connected driving performance to the goals and contents of trip, even to driver’s life and personal characteristics. The objective of this paper is to construct a measuring scale which content covers four hierarchy of driving behavior, and being able to verify the relations between different hierarchies to support the theory of hierarchical driving behavior. We construct the regression model that driving behavior is treated as dependent variable. The study results show that driving behavior have negative correlation with personal value, decision making and driving skills. The results can bring further insights that driving behavior is truly affected by many factors with hierarchical concept. Even more importantly, the guidance to design the curriculum of driver education should cover all levels in the hierarchy. The training process should start with the acquisition of the necessary basic technics, and then progress to the mastery of traffic situations with better trip planning.
40
Chia-JuLin and 林家如. "Driving Behavior Analysis on Freeway Weaving Sections: A Driving Simulator Approach." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/87794569362822176276.
Full textAbstract:
碩士國立成功大學
交通管理科學系
102
The discussion of the research is near-crash event on Freeway weaving sections. If there are high speed, complicated flow and short distance, it will become to crash easily take place where interchanges. Moreover, to verify In-vehicle Warning System is useful to assists driver changing multi-lanes. The approach uses Driving Simulation System to construct weaving section on freeway. The scene includes three kinds of change limited distance and three kinds of weaving volume ratio and two groups of In-vehicle Warning System. We recruit 18 examiners and employ 9 factors of interaction reach the experimental samples. Then we will adopt statistical method not only analyzing the data but also evaluating affection on driver’s behavior and reaction. Results are 400 m of limited distance and 〈25% of weaving volume ratio are safer than the other level, as well as In-vehicle Warning System will enhance double performance than none. This outcome of the research is able to apply on advanced driver assistance system widely. To change limited distance and weaving volume ratio will promote the traffic safety and avoid accident happening on freeway. Finally, the conclusions may sustain the policy when enforcement department implement and augment driving safety on freeway weaving section.
41
Miao, Shu-Han, and 苗書翰. "Driving Knowledge, Safety Attitudes and Driving Behavior among Motorcyclists in Taipei." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/90466535611988772440.
Full textAbstract:
碩士國立臺灣海洋大學
運輸與航海科學系
98
With economic development and technological advances, the amount of private transportation grows up very fast and this becomes a very important issue. Especially in recent years, we have confronted the global economic downturn and high oil prices. When choosing transportation with one of the key factors is high oil prices. On account of the importance and above information, issues about road safety of motorcycles will become more and more significant that we cannot ignore. This study mainly aims at examing the influence of the motorcyclists’ knowledge and riding attitudes on the riding behavior by means of the measuring instruments, examining sheets regarding traffic safety, safety attitudes questionnaire, and ridiing behavior questionnaire. this study also apply item response theory (IRT) to analyze driving knowledge items and motorcyclists’ knowledge abilities. This study includes 556 questionnaires from riding motorcyclists in both Taipei City and Taipei County, and the numbers of questionnaires with valid answers are 501, occupying 90% of the total questionnaires. According to the result of this study, most of the motorcyclists lacks of driving knowledge, we could also know that if we gain much knowledge about safety driving we could reduce the dangers caused by ignorance, but not significant in intentional driving behaviors.
42
YU-FENG, LI, and 李毓峰. "Effect of stress on driving behavior." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/88374107795437595723.
Full textAbstract:
碩士開南大學
觀光運輸學院碩士在職專班
102
Extant research has shown that aberrant driving behaviors correlate closely with car accidents. The research investigates the effect of work and driving stress on aberrant driving behaviors, and proposes a causal framework among work stress, driving stress, and aberrant driving behaviors where the two stress factors are adopted as antecedents of aberrant driving behaviors, and coping strategies are adopted as a moderator. To examine the proposed framework, this study collected 241 valid questionnaires from military units where employees suffered particular working stress. An exploratory factors analysis was employed to extract the underlying factor structure of the stresses and driving behaviors; two-stage classification and structural equation modeling were then adopted to examine the factor structure across groups with different coping strategies. The analytic results show significant positive effects of driving stress, including irritation, aggressiveness, and confidence, on aberrant driving behaviors; however, the effect of work stress on aberrant driving behaviors was nonsignificant. The participants were divided into two groups based on their coping strategies. The significant relationships of driving stress with aberrant driving behaviors were found in those with positive coping strategies; on the contrary, only the relationship between irritation and aberrant driving behaviors was found to be significant in those with negative coping strategies. This implies that as long as drivers could adopt positive coping strategies, it is possible to reduce aberrant driving behaviors by reducing the sources of driving stress especially irritation, aggressiveness, and confidence. Corresponding strategies to reduce aberrant driving behaviors in military employees are discussed and provided in the thesis.
43
李家春. "Driving Behavior Analysis of Variable Speed Limit Signs for Bus Driving on Freeways by Driving Simulation." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/35692048140892340228.
Full text
44
Chu, Li-ling, and 朱禮伶. "Applying Driving Simulator to the Analysis of Drunk Driving Behavior and Response." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/24165801323319010757.
Full textAbstract:
碩士國立成功大學
交通管理學系碩博士班
97
In Taiwan, traffic accidents have become one of the top ten leading causes of death. Due to the increasing number of automobiles, road has become much and much crowded. According to the statisics on cause of traffic accidents, drunk driving has been ranked the top cause since 2005. Even though the laws against drunk driving are much more strict than other developed countries such as England and America. But drunk driving accidents never vanish in our society. It really deserves to do further research which might give us a chance to avoid it happening again and again. We use the traffic accidents data base of Tainan city for our research and example. Drunk driving accidents frequently happened in the intersection area or fast lane in midnight. This research uses Driving Simulation System to construct city road scene by Virtual Reality Technology. To investigate the effect upon drivers with different BrAC (no drinking, 0.15 mg/l, 0.25 mg/l and 0.55 mg/l), we recruited 16 drivers for our experiment. Drivers’ perception reaction time, route, collisions, and values of acceleration and deceleration with unexpected accidents were all recorded. After this research was done, we can’t prove drunk driving will certainly lead to traffic accidents, but according to experimental statistics, drunk driving will raise the accident rate. The higher the alcohol consistency is, the more possibility the accident will happen. Thus, it’s better to set stricter standard.
45
"Driving while under control: The effects of self-regulation on driving behavior." Master's thesis, 2012. http://hdl.handle.net/2286/R.I.15170.
Full textAbstract:
abstract: Modern day driving continues to burgeon with attention detractors found inside and outside drivers' vehicles (e.g. cell phones, other road users, etc.). This study explores a regularly disregarded attention detractor experienced by drivers: self-regulation. Results suggest self-regulation and WMC has the potential to affect attentional control, producing maladaptive changes in driving performance in maximum speed, acceleration, and time headway.Dissertation/Thesis
M.S. Applied Psychology 2012
46
Khoza, Vukayibambe Isaac. "Deviant driving behaviour : an epidemiological study." Thesis, 2004. http://hdl.handle.net/10530/432.
Full textAbstract:
A thesis submitted to the Faculty of Arts in fulfilment of the requirements for the Degree of Doctor of Philosophy in the Department of Criminal Justice at the University of Zululand, 2004.This research is based on an epidemiological study of deviant driving behaviour. The data collection phase implemented a self-report survey to capture data on deviant driving behaviour. The study seeks to establish: • Differences between deviant driving behaviour and respondents' demographic characteristics: gender, race, marital status, occupation, regularity of driving and type of motor vehicle usually driven. • Relationships between deviant driving behaviour and respondents' age, education, income, duration of passing a formal driving test and the period a motor vehicle has been driven. • Whether aggressive and anxious drivers do commit traffic offences more regularly than other drivers. • The differential rating of selected aspects of traffic policing. Research techniques implemented, include: • A literature study of deviant driving behaviour, reflecting various theoretical approaches to the referent object • A measuring instrument (questionnaire), capturing various theoretical constructs and, as such, makes provision for a checklist of deviant driving behaviour in the form of seven statistical scales. • Non-probability sampling through which 722 respondents were selected and included in the study. • Statistical tests of reliability of the measuring instrument and four hypotheses. Statistical findings indicate the following: • Sisnificant sender differences in self-reported deviant drivins behaviour. Male respondents reported the highest scores of aggression; females reported the highest scores of anxiety in driving activities. • Deviant driving behaviour differs significantly according to respondents' race and marital status. • Professional drivers featured predominantly in aggressive and offensive driving behaviour, document offences and the operation of defective vehicles. • Deviant driving behaviour differs significantly according to respondents' driving experience (regularity of motor vehicle driving and type of vehicle). • Significant relationships exist between deviant driving behaviour and respondents' age, education, income, duration of passing a formal driving test and the period a vehicle has been driven. Relationships assume both positive and negative directions. The correlation between anxiety and number of years a vehicle has been driven, is not significant • Drivers who display signs of aggressive and anxious driving behaviour, do commit traffic offences. Positive relationships exist between aggressive-anxious approaches and informal driver training. Positive correlations exist between traffic (driving) offences, document offences and the operation of defective motor vehicles and aggressive behaviour. • No significant correlations have been observed between deviant driving behaviour and informal driver training. Differentiai rating of traffic policing according respondents' education, race, occupation, income, etc., is also observed. Traffic officers' susceptibility to bribery creates a particular problem for authorities. The following non-prescriptive recommendations are entertained: Enhancement of formal driving tests, driver training and traffic education. Disposal of convicted deviant drivers by criminal courts. Pedestrian education. Surcharge. Periodic inspections of motor vehicles. Provision for. more traffic officer employment Prevention of corruption (bribery) in the traffic situation. Establishment of a Road Traffic Infringement Agency. Road engineering. Future research. The study succeeded in revealing "hidden" deviant driving behaviour among respondents who reside in the jurisdiction of the uMhlathuze Qty Council and adjacent areas.
47
You, Yun-Sheng, and 尤雲生. "Kinect for Driving Behavior Monitoring and Warning." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/56548167489517712244.
Full textAbstract:
碩士國立彰化師範大學
電子工程學系
104
The objective of this thesis is to design a system for driving behavior monitoring warning. Kinect has been adopted to analyze the kinematic trajectory of two arms to conclude the driver behavioral events. Finally, those serial temporal events are collected to trigger rules in drivers’ behavioral awareness system for generating corresponding actions to remind driver for safety which can effectively achieve the system goal of vehicle safety guard and awareness system. Additionally, in order to accurately determine the hand joint coordinate of driver in a small car cabin, the D-H model of robot arm has been joined to correct the Kinect sensed coordinate. Finally, the system functions are verified and validated in the real car that have very high accuracy to recognize driver behaviors.
48
Tzeng, I.-Shien, and 曾議賢. "Effects of Cognitive Distraction on Driving Behavior." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/was7pw.
Full textAbstract:
碩士國立交通大學
運輸科技與管理學系
92
This study proposes a procedure to quantitatively estimate cognitive distraction that are not accompanied by any visual diversions to clarify the influence of non-visual distractions to driving. In a laboratory experiment, mental capacities (measured in bits/sec) for three arithmetic tasks were estimated for each subject driver, using the functional relation between the reaction time and the number of alternatives in choice reaction tasks using a subsidiary task method through a mobile phone. The spare capacities obtained correlated significantlyly with the measures of speed control and physiological load during a lane change course negotiation on a test field. There are 18 subject drivers participate the two-part experiments. In the laboratory experiment, it was observed that a direct ratio between the reaction time and the amount of information exists as 5.2 bits/sec in non-arithmetic task、4.92 bits/sec in easy-arithmetic task、4.87 bits/sec in moderate-arithmetic task, and 3.98 bits/sec in difficult-arithmetic task. The laboratory experiment has proved that the arithmetic tasks increase the subject driver’s mental capacities indeed. In the test field experiment, we observed that the arithmetic tasks significantly affect the lateral acceleration、the speed before entering the lane change area、the answer time and the correct ratio. Gender significantly affects the lateral acceleration、the speed before entering the lane change area、the speed during lane change course、the speed of leaving the lane change area and the answer time. The age group significantly affects the speed before entering the lane change area、the speed during lane change course、the speed of leaving the lane change area and the correct ratio.
49
張雅惠. "Construct Analysis of Young Motorcyclists' Driving Behavior." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/18531246523619200915.
Full text
50
Bie, Yu-Wun, and 別宇文. "Investigate Motorcycle Driving Behavior By Motorcycle Simulator." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/81448208162638767420.
Full textAbstract:
碩士龍華科技大學
工程技術研究所
98
Due to the recent rise of oil prices and environmental awareness, making many short-range commuter driving people away from gradually replaced by other means of transport is more fuel-efficient vehicles, due to the convenience of transportation, mobility, easy parking, cheap price, features, motorcycles in Taiwan is the largest number of the most popular means of transport, so the relatively high proportion of traffic accidents. Traffic situation in Taiwan, the number of motorcycles licensed for gradually rose. According to Ministry statistics show, motorcycle by the 2003 year in December of 7,755,339 units to the 2010 year in April of 14,614,091 units, 6,858,752 units during the period increased. Shows the situation of people driving a motorcycle instead increased. Metropolitan area in Taiwan, the number of motorcycles has long exceeded the original design of the road capacity, coupled with the rise of the current wave of cycling, not only made the lane drive very crowded, but the number of vehicles large amount of the land area is small, making road traffic status becomes very crowded and complicated, leading to traffic accidents are frequent, light should be increased use of motorcycles on the public in the training and knowledge, this study design a truly reproduce the actual conditions of the motorcycle road conditions driving simulator, aim to be the driver for the motorcycle road for emergency assessment of the response of other experiments. This study, the 3D virtual scene by motorcycle driving simulator to conduct driving simulation experiment set the scene for the general flat road to motorcycle riding to be moving vehicles, to observe and discuss the subjects were in the motorcycle driving simulation for incident response.