Submitted by (ana.araujo@ufrpe.br) on 2016-08-03T14:07:18Z No. of bitstreams: 1 Luiz Jose Rodrigues dos Santos.pdf: 1081987 bytes, checksum: 435fc2cb438881b9c3905e16b4b41ed0 (MD5) / Made available in DSpace on 2016-08-03T14:07:42Z (GMT). No. of bitstreams: 1 Luiz Jose Rodrigues dos Santos.pdf: 1081987 bytes, checksum: 435fc2cb438881b9c3905e16b4b41ed0 (MD5) Previous issue date: 2008-02-28 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / Urban traffic represents a phenomenon of great socioeconomic importance,whose modeling from the point of view of prevision on the basis of initial conditions, still represents a challenge for modern science. Computational methods (computer simulations) represent a powerful tool for modeling and prediction of a number of effects, where systems of coupled differential equations may be used to simulate different phenomena observed in traffic systems. In particular, a quantity of high importance for maintenance and planning of road systems is the vehicular capacity which can be supported without traffic jams, whose description and prevision is still not well understood. In this work, a generalization of an existing microscopic traffic model, the Intelligent Driver Model (IDM), is proposed by implementing a distribution of desired velocities, where it is shown that vehicle capacity of multiple lane roads can be measured in a rather realistic manner, as a function of model parameters,which may be adjusted to real observations. / O tráfego urbano representa um fenômeno de grande importância sócio econômica, cuja modelagem de ponto de vista de previsão a partir de condições iniciais, ainda representa um desafio para a ciência moderna. Métodos computacionais (simulação computacional) representam uma ferramenta poderosa para modelagem e previsão de diversos efeitos, nos quais sistemas de equações diferenciais acopladas podem simular diversos fenômenos observados no sistema de tráfego. Em particular, uma grandeza de alto impacto para o gerenciamento e planejamento de rodovias é a capacidade veicular que elas podem suportar sem que aconteça o efeito de congestionamento, cuja descrição e previsão ainda não estão bem entendida. Neste trabalho, propõe-se uma generalização de um modelo microscópico computacional existente, o Intelligent Driver Model (IDM), aplicando uma distribuição de velocidades desejadas, onde torna-se possível medir de forma bastante realista a capacidade veicular de rodovias com múltiplas faixas, em função de parâmetros de modelo, que podem ser ajustados às observações reais.

Este trabalho apresenta um estudo a respeito dos acidentes de trânsito envolvendo o transporte público urbano por ônibus e objetiva, principalmente, a relação dos acidentes versus comportamento dos condutores. Os dados utilizados, a partir do estudo de caso realizado na cidade de Ribeirão Preto-SP, têm duas origens: dados da operação do sistema (quantidade de horas operadas, quilometragem e frota) e dados gerados pelo monitoramento por câmeras. Este último tem como principais variáveis o comportamento dos condutores durante a condução dos veículos. Através de índices de exposição, utilizando as variáveis da operação do sistema, juntamente com os acidentes por linha, foi possível identificar quais as linhas com piores indicadores, ou seja, quais linhas merecem maior atenção na criação de intervenções ou campanhas para redução do número de acidentes. Foram tratados aproximadamente 72 mil dados e a partir dos dados extraídos e processados estatisticamente para obtenção das variáveis mais significativas com relação aos acidentes. A variável com maior peso foi a utilização de telefones celulares durante a condução e que tem alta utilização nos horários de pico, da ordem de 53% dos eventos ocorrem em horários de maior movimento de passageiros e de tráfego intenso. O tempo de utilização do celular durante a condução do ônibus é majoritariamente maior que 5 minutos, ou seja, 33% dos eventos mostram que os condutores utilizam o telefone celular por mais de 5 minutos. Criou-se uma taxonomia do comportamento dos condutores, baseando-se, principalmente, no banco de dados e tem como função instituir uma base teórica dos comportamentos, ajudando a descrevê-los e entendê-los. É dessa maneira que a segunda variável foi discutida. O avanço do sinal amarelo, com nível de significância alta, não representa em sua totalidade um comportamento decidido (decisões conscientes do condutor), mas algumas vezes comportamento involuntário (falhas e lapsos). Essa distinção de comportamento decidido ou involuntário é complexa, mas sabemos que decisões conscientes são mais frequentes. Este trabalho identificou quais as linhas que necessitam de intervenções e quais os problemas com o comportamento dos condutores, direcionando o operador do sistema de transporte às campanhas necessárias para redução dos acidentes, ou mesmo possibilitando outras empresas a replicarem as análises para a sua realidade operacional. / This work presents a study about the traffic accidents involving urban public transport by bus and objective, especially the relation of accidents versus driver behavior. The data used from the case study in the city of Ribeirão Preto, have two sources: System operation data (number of operated hours, mileage and fleet) and data generated by the monitoring camera system. The latter\'s main variables driver behavior while driving the vehicle. Through levels of exposure, using the system operating variables, along with accidents per line, it was possible to identify lines with worse indicators, or which lines deserve close attention in setting up operations or campaigns to reduce the number of accidents. Approximately 72,000 data were treated and statistically processed to obtain the most significant variables in relation to accidents. The most significant variable was the use of mobile phones while driving and which has high utilization during peak hours, the order of 53% of events occur when there is a large number of passengers and traffic jam. The utilization of the cellphone while driving the bus is overwhelmingly greater than 5 minutes, i.e., 33% of the events showed that drivers use the mobile phone for more than 5 minutes. Has been created drivers behavior taxonomy, based mainly in the database and with aim to establish a theoretical basis of bus drivers behavior, helping to describe and understand them. This is how the second significant variable was discussed. The advance of the yellow sign is not totally a decided behavior (conscious decisions of the driver), but sometimes involuntary behavior (failures and lapses). This decided or involuntary behavior distinction is complex, but we know that conscious decisions are more frequent. This work identified which lines needed intervention and what are the problems with the behavior of drivers, orienting the operator of the transportation system to needed campaigns to reduce accidents, or even allowing other companies to replicate the analysis to their operational reality.

Inom trafikforskningen är det allmänt känt att sömnighet är en starkt bidragande faktor vid trafikolyckor. Tidigare forskning har visat att sömnighet hos förare är närvarande i 16–-23 procent av alla bilolyckor. Inom flyg- och järnvägsdomänen har en metod, med en stark influens från human factors-området, kallad Fatigue risk management (FRM) använts för att undersöka hur sociala och organisatoriska faktorer påverkar personalens sömnighetsnivå. Dock har denna metod inte använts för att undersöka lastbilsförares sömnighetsnivå i någon större utsträckning. Studiens syfte var att undersöka hur lastbilsförare upplever, motarbetar och motverkar sömnighet i deras dagliga arbetssituation. Resultaten visar att lastbilsförare i sitt arbete möter en stor mängd trötthetsbidragande faktorer, som kan härledas både till organisatoriska faktorer och individuellt beteende. Möjliga sätt att motverka sömnighet bland lastbilsförare, riktade mot både individen och organisationen, föreslås. / In the traffic domain it is commonly known that sleepiness is a highly contributing factor in traffic accidents. Research has shown that sleepiness among drivers is present in about 16-–23 per cent of all car accidents. In the aviation and railway industry a method or framework with some shared influences from the Human Factors approach, called Fatigue Risk Management (FRM) has been used to investigate how social and organisational factors affect the personnel’s level of sleepiness. The overall aims of this study are to investigate how truck drivers’ experience, fight and counteract sleepiness in their daily work environment. The results show that drivers face a wide variety of sleep contributing factors, stemming from both organisational factors and individual behaviour. Possible ways of counteracting truck driver sleepiness, concerning both the individual and the organisation, are also suggested.

Driving a vehicle involves a series of events, which are related to and evolve with the mental state (such as sleepiness, mental load, and stress) of the driv- er. These states are also identified as causal factors of critical situations that can lead to road accidents and vehicle crashes. These driver impairments need to be detected and predicted in order to reduce critical situations and road accidents. In the past years, physiological signals have become conven- tional measures in driver impairment research. Physiological signals have been applied in various studies to identify different levels of mental load, sleepiness, and stress during driving. This licentiate thesis work has investigated several artificial intelligence algorithms for developing an intelligent system to monitor driver mental state using physiological signals. The research aims to measure sleepiness and mental load using Electroencephalography (EEG). EEG signals, if pro- cessed correctly and efficiently, have potential to facilitate advanced moni- toring of sleepiness, mental load, fatigue, stress etc. However, EEG signals can be contaminated with unwanted signals, i.e., artifacts. These artifacts can lead to serious misinterpretation. Therefore, this work investigates EEG arti- fact handling methods and propose an automated approach for EEG artifact handling. Furthermore, this research has also investigated how several other physiological parameters (Heart Rate (HR) and Heart Rate Variability (HRV) from the Electrocardiogram (ECG), Respiration Rate, Finger Tem- perature (FT), and Skin Conductance (SC)) to quantify drivers’ stress. Dif- ferent signal processing methods have been investigated to extract features from these physiological signals. These features have been extracted in the time domain, in the frequency domain as well as in the joint time-frequency domain using wavelet analysis. Furthermore, data level signal fusion has been proposed using Multivariate Multiscale Entropy (MMSE) analysis by combining five physiological sensor signals. Primarily Case-Based Reason- ing (CBR) has been applied for drivers’ mental state classification, but other Artificial intelligence (AI) techniques such as Fuzzy Logic, Support Vector Machine (SVM) and Artificial Neural Network (ANN) have been investigat- ed as well. For drivers’ stress classification, using the CBR and MMSE approach, the system has achieved 83.33% classification accuracy compared to a human expert. Moreover, three classification algorithms i.e., CBR, an ANN, and a SVM were compared to classify drivers’ stress. The results show that CBR has achieved 80% and 86% accuracy to classify stress using finger tempera- ture and heart rate variability respectively, while ANN and SVM reached an accuracy of less than 80%. / Vehicle Driver Monitoring

An increasing amount of technology in cars makes new ideas and solutions necessary. This study will explore the idea of a personalized driver environment and investigate possible benefits and drawbacks with such a feature. The study consists of three parts: a pre-study exploring personalization, a survey investigating the attitudes towards personal settings, and finally an interview testing a specific solution. The survey was distributed in USA and Sweden while the interviews were conducted with Swedish subjects. Overall, the concept of a personalized car has been well received. This study has shown that the most requested settings are associated with the driver position, hi-fi system and climate. The study also suggests that feeling in control of the personalization is more important than the benefits associated with automation. The user prefers visible solutions, such as a personal button on the key before hidden (e.g. using a button sequence or a menu system). Such a button promotes the feature while allowing the user to interact with the car in a familiar way. However, since little real user experience exists with such solutions it is important to continue research when further developing personalization of a car.

This thesis is about the development of a function that assists the driver of a heavy vehicle to do an estimation over the possibilities to overtake a preceding heavy vehicle. The function utilizes Look-Ahead and vehicle-to-vehicle communication to do a calculation of the distance between the vehicles in some road distance ahead. Consequently the report also contains an investigation of what data that is needed to be known about a vehicle to be able to do a satisfying estimation about this vehicle. The most vital problem is to estimate what velocity the vehicle will get in an uphill/downhill slope. A Simulink model is developed to simulate the function with two independent vehicles. Real tests are also performed to evaluate the velocity estimation part of the function.

This study was a concurrent validation of a paper and pencil test battery used at a national trucking company. Forty-eight driver managers were rated by their immediate supervisors with the performance appraisal covering 12 dimensions of job behavior that was developed by the experimenter. The driver managers were also administered the Wesman Personnel Classification Test, the Watson-Glaser Critical Thinking Appraisal, and the California Psychological Inventory (CPI). A biographical information blank was also developed and validated. Most validity correlations were nonsignificant, with the exception of the Dominance scale r = .25 (p < .05), the Self-control scale r = -.25 (p < .05), the Communanlity scale r = .29 (p < .05), and the Flexibility scale r = -.39 (p < .05), with overall performance.

The goal of this thesis is to develop a smartphone application for augmented reality view; it is an initial attempt to realize a driver assistance functionality using just a smartphone and an external lens. Initially it depicts a brief analysis about the most feasible development technologies for mobile application development, selecting a proper lens and positioning of the smartphone in the car. Later, it discusses the strategies for real-time object detection using OpenCV; the video frames are processed using the strategies to find patterns in the videos. Different techniques like Hough-line transform, watershed, contour detection, color segmentation, color thresholding and HAAR cascades are implemented and compared in terms of real time detection of the desired objects. Then a unified algorithm is implemented for the given scenario which overcomes the challenges faced during the conceptualization phase. Finally, the results are depicted with the snapshots of the real time detection done from the smartphone and then evaluated against the vision of the application and the achieved tasks. This thesis is concluded by stating the prospects of this mobile application in the future.

Background: The state of exclusivity must be investigated and proven in each particular case. In order to establish the conclusion about the influence of the driver, it is necessary to draw up an expert opinion from the field of health care, the branch of psychiatry (Explanatory Report to Act No. 233/2013 Coll.). Research to date has shown that addictive substances in transport are a serious social and security problem. For recidivent drivers who have committed a criminal offense under the influence of an addictive substance (or a misdemeanor, or have a personal interest in a rehabilitation program), there is a possibility of a rehabilitation course. Goals: The main aim of this work is to bring knowledge about the decision-making practice of the courts in the case of a criminal offense under the influence of addictive substance. Another aim of this work is to map out the problem of the threat of drug addiction and follow-up measures set by the court in imposing sentences and their relation to the recommendation of rehabilitation programs or some of the forms of treatment of problem / addictive use of addictive substances. Methods: The data were obtained by analyzing 50 judgments and four interviews with judges from the Prague 2 District Court, which were held in April 2017. Selection of the...

Older adults are at an increased risk for motor-vehicle collisions (MVCs) once distance driven is considered, a finding that is partly attributed to a decline in attention related processes associated with age. MVCs typically occur in highly specific areas, suggesting a role of the complexity of the driving environment contributing to the occurrence of MVCs. The goal of this thesis was to explore the attentional demands of simulated driving events of varying complexity among young, mature and older drivers. In the present studies, attentional demand associated with driving was assessed through the peripheral detection task (PDT), a method in which a stimulus unrelated to the driving task is presented and drivers manually respond immediately upon its detection; latency to respond is recorded. The complexity of the driving environment was operationalized in terms of vehicle handling and of information processing elements. In the first study, inexperienced drivers completed a series simulated driving scenarios that varied according to their information processing and vehicle handling demands. The results showed a reduction in PDT performance at intersections where information processing is increased as well as when handling maneuvers behind a lead vehicle were required. Building on these findings, the second study employed the identical protocol as the first but examined differences in attentional demand between mid-aged and older drivers. The results indicated that when information processing demands were increased through the addition of traffic, and buildings, all participants exhibited greater workload regardless of age. The third study presented young, mid-aged, and older drivers with a simulated driving assessment course and administered several cognitive tasks. The results of the third study supported the hypothesis in that complex driving situations elicited greater attentional demand among drivers of all ages. Older adults showed greater attentional demand in comparison to young and mid-aged adults even after controlling for baseline response time. Older drivers also scored poorer on a global measure of driving safety. The results of this thesis highlight the roles of intrinsic and extrinsic factors involved in safe driving and are discussed in terms of appropriate interventions to improve road safety.