Modern vehicles are designed to protect occupants in the event of a crash with some vehicles better at this than others. However, passenger protection during an accident has shown to be not enough in many high impact crashes. Statistics have shown that the human error is the number one contributor to road accidents. This research study explores how driver error can be reduced through technology which observes driver behaviour and reacts when certain unwanted patterns in behaviour have been detected. Finally a system that detects driver fatigue and driver distraction has been developed using non-invasive machine vision concepts to monitor observable driver behaviour. / Electrical Engineering / M. Tech. (Electrical Engineering)

<p>Profesionalnim vozačima osnovno zanimanje je upravljanje motornim vozilom. Izvođenje radnih zadatka podrazumeva stalnu napregnutost pažnje vezanu za vidne i zvučne podražaje koji se brzo smenjuju, &scaron;to zahteva da vozač adekvatno i tačno reaguje na promene. Prijem informacija, obrada, dono&scaron;enje odluke i izvr&scaron;avanje motornog odgovora su procesi koji prate jedni druge i čine vreme percepcije-reakcije (VPR). Uslovi i zahtevi rada za profesionalne vozače su isti i za mlađe i starije radnike i povezani su sa velikom odgovorno&scaron;ću za ljudske živote i materijalna dobra, bez obzira na to &scaron;to je poznato, da se radna sposobnost menja zbog prirodnog procesa starenja. Merenje i utvrđivanje vrednosti VPR je važan deo ispitivanja u okviru procene zdravstvene sposobnosti za bezbednu vožnju. Ciljevi: Utvrđivanje vrednosti VPR kod profesionalnih vozača i poređenje sa kontrolnom grupom. Ispitivanje uticaja starosti i vozačkog iskustva na VPR kod profesionalnih vozača. Materijal i metode : Ova studija procenjuje deo sposobnosti profesionalnih vozača merenjem VPR prostog i složenog, važnih za sigurnost u vožnji. Istraživanje je sprovedeno u vremenskom periodu od devet meseci i obuhvatilo je 548 ispitanika mu&scaron;kog pola, starosti od 21 do 65 godina. Eksperimentalnu grupu je činilo 278 ispitanika (profesionalni vozači), a kontrolnu 270 ispitanika kojima osnovno zanimanje nije profesionalna vožnja. Testiranje je izvedeno pomoću hardversko-softverskog sistema za određivanje vrednosti VPR na proste i složene audio-vizuelne podražaje. Merenja su sprovedena na tri nivoa težine zadatka: prosto VPR, i testovi složenog VPR na promenu pozicije podražaja i vrste boje. Rezultati: Utvrđene su značajno niže srednje vrednosti VPR na sva tri nivoa testiranja u grupi profesionalnih vozača u poređenju sa kontrolnom grupom. Utvrđena je pozitivna povezanost srednjih vrednosti VPR sa godinama života i dužinom profesionalnog vozačkog radnog staža na svim testovima u grupi profesionalnih vozača. Nisu utvrđene značajne razlike u procentu pogre&scaron;nih odgovora u odnosu na životno doba i dužinu vozačkog staža, &scaron;to govori o pozitivnim efektima profesionalne prakse u vožnji. Nisu utvrđene značajne razlike srednjih vrednosti VPR kod vozača u gradskom ili međugradskom saobraćaju, kao i u odnosu na broj pređenih kilometara mesečno na svim testovima. Obeležja poput starosti (godine života), profesionalne prakse (iskustvo u godinama profesionalne vožnje), neke promene zdravstvenog stanja (postojanje bolesti ili drugih poremećaja) u grupi profesionalnih vozača pokazale su se kao prediktori sa značajnim nivoom povezanosti sa vrednostima VPR. Metodom vi&scaron;estruke regresione analize smo ispitali smo povezanost vrednosti VPR sa posmatranim prediktorima kada ih analiziramo zajedno uzimajući u obzir njihovu međusobnu interakciju. Regresioni model pokazuje kako skup posmatranih obeležja predviđa promene VPR. Zaključak: Utvrđene vrednosti i prediktivni model promena VPR profesionalnih vozača mogu biti korisni podaci u svakodnevnom radu zdravstvenim ustanovama koje procenjuju vozačku sposobnost, kako bi se identifikovali potencijalno rizični vozači sa vi&scaron;im vrednostima VPR, zamorenih i osoba sa početnim o&scaron;tećenjima nervnog sistema, sklonih povredama u saobraćaju i na radu, u cilju prevencije saobraćajnih udesa i povreda, kao i osiguranja da vozači imaju sposobnosti neophodne za bezbednu vožnju. Utvrđene vrednosti VPR mogle bi naći primenu pri oceni radne sposobnosti i kod radnika na drugim zanimanjima gde se očekuje brza i tačna reakcija na određeni podražaj.</p> / <p>The term professional driver refers to people whose main occupation is driving a motor vehicle. Performing work tasks implies a constant strain of attention related to visual and audible stimuli that change quickly, which requires the driver to respond adequately and accurately to changes. Receiving information, processing, making a decision and executing a motor response are processes that accompany each other and make up the perception-reaction time (PRT). The working conditions and requirements for professional drivers are the same for both younger and older workers and are associated with great responsibility for human lives and material goods, regardless of the fact that it is known that working ability changes due to the natural aging process. Measuring and determining the value of PRT is an important part of testing as part of the assessment of health fitness for safe driving. Aims: Determination of PRT values in professional drivers and comparison with the control group. Examination of the effects of aging and driving experience on the PRT of professional drivers. Material and methods: This study assesses part of the ability of professional drivers by measuring simple and complex PRT important for driving safety. The study was conducted over a period of nine months and included 548 male respondents, aged 21 to 65 years. The experimental group consisted of 278 respondents (professional drivers), and the control group consisted of 270 respondents whose main occupation is not professional driving. Testing was performed using a hardware-software system to determine the value of PRT on simple and complex audio-visual stimuli. Measurements were carride out at three levels of task difficulty: simple PRT, and complex PRT tests to change stimuli position and color type. Results: Significantly lower PRT mean values were found at all three levels of testing in the group of professional drivers compared to the control group. A positive correlation was found between the mean PRT values with age and experience of professional driving on all tests in the group of professional drivers. No significant differences were found in the percentage of incorrect answers in relation to the age and driving experience, which shows the positive effects of professional driving practice. No significant differences were found in the mean PRT values on all tests for drivers in urban or interurban traffic and in relation to the number of kilometers per month. Individual characteristics as, aging, professional practice (experience in years of professional driving), changes in health status (existence of diseases or other disorders) in the group of professional drivers showed to be predictors with a significant level of correlation with PRT values. Using the method of multiple regression analysis, we examined the correlation of PRT values with the observed predictors when we analyze them together, taking into account their mutual interaction.The regression model shows how the set of observed features predicts changes in PRT. Conclusion: The determined values and the predictive model of changes PRT of professional drivers can be useful data in the daily work of health institutions that assess driving ability, in order to identify potentially risky drivers with higher PRT values,, tired and people with initial nervous system damage, prone to traffic injuries and at work, in order to prevent traffic accidents and injuries, as well as to ensure that drivers have the skills necessary for safe driving. The determined values of PRT could be used in the assessment of work ability and in workers in other occupations where a quick and accurate response to a particular stimulus is expected.</p>

Safety and congestion are ever present and increasingly severe transportation problems in urban areas throughout the nation and world. These phenomena can have wide-ranging consequences relating to safety, the economy, and the environment. Adverse weather conditions represent another significant challenge to safety and mobility on highways. Oregon is not immune from either of these global issues. Oregon Route (OR) 217, to the southwest of the downtown Portland, is one of the worst freeways for congestion in the state and is also subject to the Pacific Northwest's frequently inclement and unpredictable climate. High crash rates, severe recurrent bottlenecks and highly unreliable travel times continuously plague the corridor, making it a major headache for the thousands of commuters using it every day. In an effort to more effectively combat both congestion and adverse weather, transportation officials all over the world have been turning to increasingly technological strategies like Active Traffic Management (ATM). This can come in many forms, but among the most common are variable speed limit (VSL) systems which use real-time data to compute and display appropriate reduced speeds during congestion and/or adverse weather. After numerous studies and deliberations, Oregon Department of Transportation (ODOT) selected Oregon Route (OR) 217 as one of the first locations in the state to be implemented with an advisory VSL system, and that system began operation in the summer of 2014. This thesis seeks to evaluate the effectiveness of this VSL system through the first eight months of its operation through an in-depth and wide-ranging "before and after" analysis. Analysis of traffic flow and safety data for OR 217 from before the VSL system was implemented made clear some of the most prevalent issues which convinced ODOT to pursue VSL. Using those issues as a basis, a framework of seven specific evaluation questions relating to both performance and safety, as well as both congestion and adverse weather, was established to guide the "before and after" comparisons. Hypotheses, and measures of effectiveness for each question were developed, and data were obtained from a diverse array of sources including freeway detectors, ODOT's incident database, and the National Oceanic and Atmospheric Administration (NOAA). The results of the various "before and after" comparisons performed as a part of this thesis indicate that conditions have changed on OR 217 in a number of ways since the VSL system was activated. Many, but not all, of the findings were consistent with the initial hypotheses and with the findings from other VSL studies in the literature. Certain locations along the corridor have seen significant declines in speed variability, supporting the common notion that VSL systems have a harmonizing effect on traffic flow. Crash rates have not decreased, but crashes have become less frequent in the immediate vicinity of VSL signs. Flow distribution between adjacent lanes has been more even since VSL implementation during midday hours and the evening peak, and travel time reliability has seen widespread improvement in three of the corridor's four primary travel lanes during those same times. The drops in flow that generally occur upstream of bottlenecks once they form have had diminished magnitudes, while the drops in flow downstream of the same bottlenecks have grown. Finally, the increase in travel times that is usually brought about by adverse weather has been smaller since VSL implementation, while the decline in travel time reliability has largely disappeared.

Indiana University-Purdue University Indianapolis (IUPUI) / The Pedestrian Automatic Emergency Braking System (PAEB) can utilize on-board sensors to detect pedestrians and take safety related actions. However, PAEB system only benefits the individual vehicle and the pedestrians detected by its PAEB. Additionally, due to the range limitations of PAEB sensors and speed limitations of sensory data processing, PAEB system often cannot detect or do not have sufficient time to respond to a potential crash with pedestrians. For further improving pedestrian safety, we proposed the idea for integrating the complimentary capabilities of V2V and PAEB (V2V-PAEB), which allows the vehicles to share the information of pedestrians detected by PAEB system in the V2V network. So a V2V-PAEB enabled vehicle uses not only its on-board sensors of the PAEB system, but also the received V2V messages from other vehicles to detect potential collisions with pedestrians and make better safety related decisions. In this thesis, we discussed the architecture and the information processing stages of the V2V-PAEB system. In addition, a comprehensive Matlab/Simulink based simulation model of the V2V-PAEB system is also developed in PreScan simulation environment. The simulation result shows that this simulation model works properly and the V2V-PAEB system can improve pedestrian safety significantly.