John Golias | National Technical University of Athens (original) (raw)

Papers by John Golias

Transportation research procedia, 2016

Although driver distraction can be considered as part of everyday driving it constitutes a basic ... more Although driver distraction can be considered as part of everyday driving it constitutes a basic contributory factor for increased risk for road accidents internationally. Within this content, cell-phone use and conversation with passenger are two critical invehicle distraction conditions with respect to driver behavior and safety. The objective of this research is the investigation of the effect of area and traffic conditions on driving performance of drivers while talking on the mobile phone or conversing with the passenger. For this purpose, a large driving simulator experiment is carried out, in which 95 drivers from all different age groups (young, middle aged and older) were asked to drive under different types of distraction (no distraction, conversation with passenger, cell phone use) in rural and urban road environment, in low and high traffic. In the next step, an appropriate modelling methodology has been developed, including first descriptive analysis in order to explore the large database. Then generalized linear models as well as generalized linear mixed models regarding average speed and reaction time were implemented in order to estimate the effect of the examined distraction sources as well as area and traffic characteristics on driving behaviour and road safety. Results indicate that female drivers, especially in rural areas, were found to have the worst reaction times, while being distracted (either conversing with a passenger or talking on the cell phone). This is probably explained by the fact that in urban area, the complex road environment alerts the drivers in order to self-regulate their driving to compensate for any decrease in attention to the driving task. Furthermore, regarding average speed, it is observed that in rural areas drivers reduce the speed while distracted either by talking on the mobile phone (older drivers) or by conversing with the passenger (young and middle aged drivers), especially at high traffic volume while in urban areas suggesting a driver's compensatory behaviour. The next steps of the present research could focus on the investigation of the impact of mobile phone use, not only when the drivers talk on mobile phone using a hand-held device, but also when they use a hands-free device, a Bluetooth, or when they type messages.

International journal of transportation, Dec 31, 2017

The driving ability can be affected by various motor, visual, cognitive and perceptual deficits w... more The driving ability can be affected by various motor, visual, cognitive and perceptual deficits which are either age-related or caused by neurologic disorders. More specifically, diseases affecting a person's brain functioning may significantly impair the person's driving ability. The objective of this paper is to examine the driving performance profiles of drivers with some brain pathology in rural driving environment, in low and high traffic conditions, by means of a driving simulator experiment. Various driving performance measures are examined, e.g. mean driving speed, lateral position, steering angle, headway and reaction time at unexpected events. The driving performance of patients with brain pathologies is compared to that of healthy controls. 114 participants of above 55 years of age have completed the experimental procedure. Results suggest that there are differences between the two examined groups. Patients drive at lower speeds, present higher lateral position variability, keep larger headways and demonstrate worse reaction times than the control group.

Zenodo (CERN European Organization for Nuclear Research), Jul 20, 2023

Urban pricing strategies have been widely implemented in order to reduce externalities generated ... more Urban pricing strategies have been widely implemented in order to reduce externalities generated by traffic. These strategies have been considered effective schemes that not only it is possible to relieve congestion from metropolitan areas that have heavy traffic, but can also reduce emissions from cars and promote public transport usage. The scope of this paper is to investigate the users' perceptions towards the measure of urban tolls in the center of Athens. Applying discrete choice models to data from a stated preference survey, it was resulted that the majority of respondents would not accept such measure. Furthermore, it was found that drivers are willing to pay an extra 8-euro cents in order to save 1 minute on the travel time of their trip.

This volume describes motivation, methodology and results of an analysis of the correlation betwe... more This volume describes motivation, methodology and results of an analysis of the correlation between weather and PTW accidents. It is a matter of common sense that PTW (powered two-wheelers, i.e. moped, motorcycles) accidents strongly depend on the actual weather. This impact can derive from the difference of intrinsic risk of riding under different weather conditions, from differences in risk taking behaviour of riders under different weather conditions as well as the impact of weather on exposure. However, such relations have not been researched so far.

International journal of transportation science and technology, Oct 1, 2016

Acquiring and processing video streams from static cameras has been proposed as one of 27 the mos... more Acquiring and processing video streams from static cameras has been proposed as one of 27 the most efficient tools for visualizing and gathering traffic information. With the latest 28 advances in technology and visual media, combined with the increased needs in dealing 29 with congestion more effectively and directly, the use of Unmanned Aerial Systems 30 (UAS) has emerged in the field of traffic engineering. In this paper, we review studies 31 and applications that incorporate UAS in transportation research and practice with the 32 aim to set the grounds from the proper understanding and implementation of UAS related 33 surveillance systems in transportation and traffic engineering. The studies reviewed are 34 categorized in different transportation engineering areas. Additional significant applica-35 tions from other research fields are also referenced to identify other promising applica-36 tions. Finally, issues and emerging challenges in both a conceptual and methodological 37 level are revealed and discussed.

Power-two wheelers (PTW) are overrepresented in road accidents worldwide. Rider conspicuity has b... more Power-two wheelers (PTW) are overrepresented in road accidents worldwide. Rider conspicuity has been long recognized as an important PTW crash contributory factor. The objective of this chapter is to examine the main determinants of riders' accident risk that are related to conspicuity issues. We perform a literature review to explore the role of conspicuity in PTW crash occurrences. We organize PTW conspicuity risk factors in (i) human-related, (ii) vehicle-related, and (iii) road environment-related factors. Human-related factors responsible for different information processing failures (alcohol, distraction, fatigue, and so on) have been largely unaddressed. Turning to accident frequency, empirical evidence indicates that conspicuity treatments should primarily target intersections (T-junctions in urban areas at daytime and roundabouts in inter-urban areas at nighttime). Absolute accident figures are higher at daytime. If considering accident severities instead, the priority should be given to nighttime treatments. Overall, the conspicuity hypothesis testing remains inconclusive as long as several data and methodological limitations hold on a present level.

Journal of transport and health, Jun 1, 2015

Although older drivers are involved in a few accidents in terms of absolute numbers, they represe... more Although older drivers are involved in a few accidents in terms of absolute numbers, they represent one of the highest risk categories for accidents involving fatalities and serious injuries per number of drivers and per distance travelled probably because of their great fragility and reduced tolerance to injury. Furthermore, cell phone use is estimated to be an important cause of vehicle accidents. Even if cell phone use can be considered as part of everyday the increased use of cell phones from drivers of all age groups while driving makes the investigation of their influence on driving behaviour and on road safety very essential. In addition, as there are a lot of different methods and measures that exist for evaluating driving performance, the selection of the specific measures for driver distraction research, as in other areas of research, should be guided by a number of general rules related to the nature of the task examined as well as the specific research questions. Within this framework, reaction time measures is an increasingly popular set of variables primary because of the relationship with accident risk.

Transportation Letters: The International Journal of Transportation Research, Mar 4, 2016

The present paper employs advanced statistical modeling in order to assess the spatial factors th... more The present paper employs advanced statistical modeling in order to assess the spatial factors that may influence the maneuverability of Powered Two-Wheelers (PTW) in urban corridors during overtaking. Using trajectory data from video recordings, two types of maneuvers are examined: those that occur with a lane change and those conducted without speed change and/or lane change (on the fly). The modeling approach has two parts: First, the probability to conduct an overtake is statistically modeled. Second, a Multiple Indicators-Multiple Causes (MIMIC) latent variable model is developed to assess the microscopic traffic characteristics and other critical factors that may affect the maneuverability of PTW. Results show that during overtaking, speed difference from the preceding vehicle is the most significant factor. Further results from the MIMIC model indicate that the PTW maneuverability is related to the type of overtake, the distance between the PTW and the vehicle being overtaken, as well as speeds.

IEEE transactions on intelligent vehicles, Mar 1, 2018

In the modern challenging urban environment, Powered Two Wheelers (PTW) are selected for their ev... more In the modern challenging urban environment, Powered Two Wheelers (PTW) are selected for their everyday commuting. The way motorcycles and scooters travel through traffic is systematically emphasized in the recent relevant literature as being complex, especially in relation to overtaking. In this paper, meta-optimized Decision Trees, a special case of Machine Learning (ML) models, are developed in order to model the unconventional overtaking patterns of PTW drivers. Based on detailed naturalistic trajectory data collected using video footage from Unmanned Aerial Vehicles (UAV) in a three-lane arterial in Athens, Greece, two different models of PTW driving behavior are developed. The first model addresses the decision of the PTW driver to overtake or not the preceding vehicle. The second model focuses on PTW driver's intention to overtake or undertake (pass from the right) it. The developed decision tree models are further analyzed in relation to the revealed significant factors during overtaking. Following, the applicability of the developed algorithms in the context of Intelligent Transportation Systems (ITS) and Connected Vehicles (CV) is discussed, which reveals the importance of acquiring quality data using advanced equipment combined with advanced Machine Learning approaches for advanced modeling methods.

Transportation Research Board 96th Annual MeetingTransportation Research Board, 2017

The investigation of crash severity with freeway traffic and weather data has recently received s... more The investigation of crash severity with freeway traffic and weather data has recently received significant attention by researchers. This paper extends previous research by proposing nonlinear models for modeling crash injury severity enhanced with traffic and weather data collected from urban arterials in Athens, Greece. Cusp catastrophe models are applied and compared with traditional statistical models. The results of crash severity models support the potential applicability of the cusp catastrophe theory to road safety, at least when crash severity is expressed as the number of severely and fatally injured by total number of persons involved in a crash. Variations in speed, average flow upstream of the location of interest, crash type and wind speed, were found to have a potential effect on the system dynamics. However, findings do not always confirm the strong presence of nonlinearity. When crash severity is expressed as the number of injured persons by the total number of vehicles involved in a crash, linear models could also be used to describe the underlying phenomenon.

Transportation Research Board 96th Annual MeetingTransportation Research Board, 2017

Transportation Research Board 95th Annual MeetingTransportation Research Board, 2016

The study of maneuverability of vehicles in high demand urban road networks through vehicles’ tra... more The study of maneuverability of vehicles in high demand urban road networks through vehicles’ trajectories is a challenge for traffic engineers and researchers. The collection of such high resolution data has been exclusively supported by costly fixed location camera systems and computer vision algorithms in isolated or sequential sections. Recently, with the advances in computer vision, low cost cameras have been used with quite a success in extracting kinematic characteristics. In this paper, the authors discuss several limitations accompanying the use of camcorders and how they can be alleviated with the use of Unmanned Aerial Vehicles (UAVs). Following, a low-cost semi-automatic way of extracting detailed vehicle trajectory data through UAV video footage is presented. Steps to reduce errors due to camera instability and to achieve sufficient calibration are also described. Two experiments are presented; the first refers to vehicle tracking at a four legged intersection and the second to tracking pedestrian flow. Following, a discussion concerning the use of UAVs to replace or extend current systems’ capabilities is conducted.

A methodology has been developed for the use of microscopic traffic simulation modelling for the ... more A methodology has been developed for the use of microscopic traffic simulation modelling for the investigation of road safety impact from the introduction of two advanced driver assistance systems (ADAS). The simulations modelled key parameters (headway, speed) for several scenarios of different traffic levels and assumed penetration levels of Adaptive Cruise Control and Intelligent Speed Adaptation systems. Results from the simulations, studied in the context of existing relationships between the number of road accidents and traffic parameters, allowed the estimation of the related traffic safety impact. This impact was investigated in relation to the corresponding changes in average speed, in headways, in time-to-collision and in lane changing. Even though an overall straightforward answer to the safety impact of ADAS systems was not possible due to the complexity of the traffic safety phenomenon, several positive effects on safety were identified.

ABSTRACT We discuss recent findings on the statistical properties of short-term traffic flow in u... more ABSTRACT We discuss recent findings on the statistical properties of short-term traffic flow in urban freeway systems. In, particular, the complexity, nonlinearity and nonstationarity of freeway travel speed patterns are studied using the recurrence plots and the recurrence quantification analysis. Results indicate a variable statistical behavior of the speed’s temporal evolution, especially during the morning and peak periods of both the weekdays and weekend. Moreover, a clear deterministic evolution of speed patterns with variable nonlinear and laminar characteristics is observed during congested conditions.

Transportation Research Part F-traffic Psychology and Behaviour, May 1, 2017

The objective of this research was the analysis of the driving performance of drivers with Mild C... more The objective of this research was the analysis of the driving performance of drivers with Mild Cognitive Impairment (MCI) or Alzheimer's disease (AD), in different road and traffic conditions, on the basis of a driving simulator experiment. In this experiment, healthy ''control" drivers, patients with MCI, and patients with AD, drove at several scenarios at the simulator, after a thorough neurological and neuropsychological assessment. The scenarios include driving in rural and urban areas in low and high traffic volumes. The driving performance of healthy and impaired drivers was analysed and compared by means of Repeated Measures General Linear Modelling techniques. A sample of 75 participants was analysed, out of which 23 were MCI patients and 14 were AD patients. Various driving performance measures were examined, including longitudinal and lateral control measures. The results suggest that the two examined cerebral diseases do affect driving performance, and there were common driving patterns for both cerebral diseases, as well as particular characteristics of specific pathologies. More specifically, cognitively impaired drivers drive at lower speeds and with larger headway compared to healthy drivers. Moreover, they appear to have difficulties in positioning the vehicle on the lane. The group of patients had difficulties in all road and traffic environments, and especially when traffic volume was high. Most importantly, both cerebral diseases appear to significantly impair reaction times at incidents. The results of this research suggest that compensatory behaviours developed by impaired drivers are not adequate to counterbalance the direct effects of these cerebral diseases on driving skills. They also demonstrate that driving impairments increase as cognitive impairments become more severe (from MCI to AD).

International journal of transportation science and technology, Dec 1, 2016

PTW overtaking and models the specific behavior using concepts of Game Theory. Both 28 the PTW dr... more PTW overtaking and models the specific behavior using concepts of Game Theory. Both 28 the PTW driver and the lead vehicle's driver are assumed rational decision-makers that 29 develop strategies, trying to maximize their payoffs. These strategies may be cooperative 30 or not with respect to the distances and safety gaps and other behavioral aspects. The pay-31 off function is formulated based on a novel latent statistically determined driving indicator, 32 which quantifies both the driving risk and comfort. The proposed model is evaluated using 33 trajectory data from video recordings on an urban arterial. Results show that both drivers 34 have maximized gains by following a cooperative strategy. Findings also reveal that the 35 successful overtaking rate is higher, when the PTW driver is non-cooperative, whereas 36 lower overtaking rates occur, when the driver of the lead vehicle is non-cooperative. 37 Finally, the concepts of Dominant Strategies, bounded rationality and the construction of 38 the optimum payoff function are further discussed.

International journal of transportation science and technology, Sep 1, 2021

This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

Case Studies on Transport Policy

Short-term demand forecasting is essential for the public transit system, allowing for effective ... more Short-term demand forecasting is essential for the public transit system, allowing for effective operations planning. This is especially relevant in the highly uncertain environment created by the SARS‑CoV‑2 pandemic. In this paper, we attempt to develop accurate prediction models of transit ridership in Athens, Greece, using Autoregressive Fractional Integrated time series models enhanced with SARS‑CoV‑2-related exogenous variables. The selected exogenous variables are, from the one hand, the ratio of weekly SARS‑CoV‑2 infections over the infections 3 weeks before (capturing the dynamics of the pandemic, as a proxy for fear of transmitting the disease while commuting), and from the other hand, an index of the stringency of the government’s SARS‑CoV‑2-related measures and regulations. The developed ARFIMAX models have been fitted separately on bus and metro ridership data and wield comparable and statistically significant results. In both models, the exogenous variables prove to be statistically significant and their values are intuitive, suggesting a linear interrelation between them and transit ridership.

European Transport Conference, 2000, Cambridge, United Kingdom, 2000

To address the significant problem of traffic safety, the riskier of road user behaviours can be ... more To address the significant problem of traffic safety, the riskier of road user behaviours can be identified and then targeted by traffic safety campaigns, which have proven to be effective in a number of circumstances. Effective campaigns must target the right groups of drivers with the appropriate message. Using a large data base of 20,725 questionnaires from19 European countries, this paper uses a combination of factor analysis and tree based regression to determine relatively homogeneous driver groups which share attitudes toward safety, in an effort to design and implement more effective safety campaigns. To achieve this, the question of driver behaviour toward safety is addressed by examining habits such as attitudes toward speeding, reckless driving, seat belt use, and drinking and driving. The results suggest that speeding and general reckless (dangerous) behaviour are related, perhaps capturing driver's risk taking behaviour. Similarly, seat belt use and driving under the influence of alcohol are also related and may represent a driver's law abiding tendency. Further, young male drivers appear to be the demographic group which can benefit the most from systematic safety campaigns. (A) For the covering abstract see ITRD E107957.

Radioehlektronika, Feb 1, 1991

Transportation research procedia, 2016

Although driver distraction can be considered as part of everyday driving it constitutes a basic ... more Although driver distraction can be considered as part of everyday driving it constitutes a basic contributory factor for increased risk for road accidents internationally. Within this content, cell-phone use and conversation with passenger are two critical invehicle distraction conditions with respect to driver behavior and safety. The objective of this research is the investigation of the effect of area and traffic conditions on driving performance of drivers while talking on the mobile phone or conversing with the passenger. For this purpose, a large driving simulator experiment is carried out, in which 95 drivers from all different age groups (young, middle aged and older) were asked to drive under different types of distraction (no distraction, conversation with passenger, cell phone use) in rural and urban road environment, in low and high traffic. In the next step, an appropriate modelling methodology has been developed, including first descriptive analysis in order to explore the large database. Then generalized linear models as well as generalized linear mixed models regarding average speed and reaction time were implemented in order to estimate the effect of the examined distraction sources as well as area and traffic characteristics on driving behaviour and road safety. Results indicate that female drivers, especially in rural areas, were found to have the worst reaction times, while being distracted (either conversing with a passenger or talking on the cell phone). This is probably explained by the fact that in urban area, the complex road environment alerts the drivers in order to self-regulate their driving to compensate for any decrease in attention to the driving task. Furthermore, regarding average speed, it is observed that in rural areas drivers reduce the speed while distracted either by talking on the mobile phone (older drivers) or by conversing with the passenger (young and middle aged drivers), especially at high traffic volume while in urban areas suggesting a driver's compensatory behaviour. The next steps of the present research could focus on the investigation of the impact of mobile phone use, not only when the drivers talk on mobile phone using a hand-held device, but also when they use a hands-free device, a Bluetooth, or when they type messages.

International journal of transportation, Dec 31, 2017

The driving ability can be affected by various motor, visual, cognitive and perceptual deficits w... more The driving ability can be affected by various motor, visual, cognitive and perceptual deficits which are either age-related or caused by neurologic disorders. More specifically, diseases affecting a person's brain functioning may significantly impair the person's driving ability. The objective of this paper is to examine the driving performance profiles of drivers with some brain pathology in rural driving environment, in low and high traffic conditions, by means of a driving simulator experiment. Various driving performance measures are examined, e.g. mean driving speed, lateral position, steering angle, headway and reaction time at unexpected events. The driving performance of patients with brain pathologies is compared to that of healthy controls. 114 participants of above 55 years of age have completed the experimental procedure. Results suggest that there are differences between the two examined groups. Patients drive at lower speeds, present higher lateral position variability, keep larger headways and demonstrate worse reaction times than the control group.

Zenodo (CERN European Organization for Nuclear Research), Jul 20, 2023

Urban pricing strategies have been widely implemented in order to reduce externalities generated ... more Urban pricing strategies have been widely implemented in order to reduce externalities generated by traffic. These strategies have been considered effective schemes that not only it is possible to relieve congestion from metropolitan areas that have heavy traffic, but can also reduce emissions from cars and promote public transport usage. The scope of this paper is to investigate the users' perceptions towards the measure of urban tolls in the center of Athens. Applying discrete choice models to data from a stated preference survey, it was resulted that the majority of respondents would not accept such measure. Furthermore, it was found that drivers are willing to pay an extra 8-euro cents in order to save 1 minute on the travel time of their trip.

This volume describes motivation, methodology and results of an analysis of the correlation betwe... more This volume describes motivation, methodology and results of an analysis of the correlation between weather and PTW accidents. It is a matter of common sense that PTW (powered two-wheelers, i.e. moped, motorcycles) accidents strongly depend on the actual weather. This impact can derive from the difference of intrinsic risk of riding under different weather conditions, from differences in risk taking behaviour of riders under different weather conditions as well as the impact of weather on exposure. However, such relations have not been researched so far.

International journal of transportation science and technology, Oct 1, 2016

Acquiring and processing video streams from static cameras has been proposed as one of 27 the mos... more Acquiring and processing video streams from static cameras has been proposed as one of 27 the most efficient tools for visualizing and gathering traffic information. With the latest 28 advances in technology and visual media, combined with the increased needs in dealing 29 with congestion more effectively and directly, the use of Unmanned Aerial Systems 30 (UAS) has emerged in the field of traffic engineering. In this paper, we review studies 31 and applications that incorporate UAS in transportation research and practice with the 32 aim to set the grounds from the proper understanding and implementation of UAS related 33 surveillance systems in transportation and traffic engineering. The studies reviewed are 34 categorized in different transportation engineering areas. Additional significant applica-35 tions from other research fields are also referenced to identify other promising applica-36 tions. Finally, issues and emerging challenges in both a conceptual and methodological 37 level are revealed and discussed.

Power-two wheelers (PTW) are overrepresented in road accidents worldwide. Rider conspicuity has b... more Power-two wheelers (PTW) are overrepresented in road accidents worldwide. Rider conspicuity has been long recognized as an important PTW crash contributory factor. The objective of this chapter is to examine the main determinants of riders' accident risk that are related to conspicuity issues. We perform a literature review to explore the role of conspicuity in PTW crash occurrences. We organize PTW conspicuity risk factors in (i) human-related, (ii) vehicle-related, and (iii) road environment-related factors. Human-related factors responsible for different information processing failures (alcohol, distraction, fatigue, and so on) have been largely unaddressed. Turning to accident frequency, empirical evidence indicates that conspicuity treatments should primarily target intersections (T-junctions in urban areas at daytime and roundabouts in inter-urban areas at nighttime). Absolute accident figures are higher at daytime. If considering accident severities instead, the priority should be given to nighttime treatments. Overall, the conspicuity hypothesis testing remains inconclusive as long as several data and methodological limitations hold on a present level.

Journal of transport and health, Jun 1, 2015

Although older drivers are involved in a few accidents in terms of absolute numbers, they represe... more Although older drivers are involved in a few accidents in terms of absolute numbers, they represent one of the highest risk categories for accidents involving fatalities and serious injuries per number of drivers and per distance travelled probably because of their great fragility and reduced tolerance to injury. Furthermore, cell phone use is estimated to be an important cause of vehicle accidents. Even if cell phone use can be considered as part of everyday the increased use of cell phones from drivers of all age groups while driving makes the investigation of their influence on driving behaviour and on road safety very essential. In addition, as there are a lot of different methods and measures that exist for evaluating driving performance, the selection of the specific measures for driver distraction research, as in other areas of research, should be guided by a number of general rules related to the nature of the task examined as well as the specific research questions. Within this framework, reaction time measures is an increasingly popular set of variables primary because of the relationship with accident risk.

Transportation Letters: The International Journal of Transportation Research, Mar 4, 2016

The present paper employs advanced statistical modeling in order to assess the spatial factors th... more The present paper employs advanced statistical modeling in order to assess the spatial factors that may influence the maneuverability of Powered Two-Wheelers (PTW) in urban corridors during overtaking. Using trajectory data from video recordings, two types of maneuvers are examined: those that occur with a lane change and those conducted without speed change and/or lane change (on the fly). The modeling approach has two parts: First, the probability to conduct an overtake is statistically modeled. Second, a Multiple Indicators-Multiple Causes (MIMIC) latent variable model is developed to assess the microscopic traffic characteristics and other critical factors that may affect the maneuverability of PTW. Results show that during overtaking, speed difference from the preceding vehicle is the most significant factor. Further results from the MIMIC model indicate that the PTW maneuverability is related to the type of overtake, the distance between the PTW and the vehicle being overtaken, as well as speeds.

IEEE transactions on intelligent vehicles, Mar 1, 2018

In the modern challenging urban environment, Powered Two Wheelers (PTW) are selected for their ev... more In the modern challenging urban environment, Powered Two Wheelers (PTW) are selected for their everyday commuting. The way motorcycles and scooters travel through traffic is systematically emphasized in the recent relevant literature as being complex, especially in relation to overtaking. In this paper, meta-optimized Decision Trees, a special case of Machine Learning (ML) models, are developed in order to model the unconventional overtaking patterns of PTW drivers. Based on detailed naturalistic trajectory data collected using video footage from Unmanned Aerial Vehicles (UAV) in a three-lane arterial in Athens, Greece, two different models of PTW driving behavior are developed. The first model addresses the decision of the PTW driver to overtake or not the preceding vehicle. The second model focuses on PTW driver's intention to overtake or undertake (pass from the right) it. The developed decision tree models are further analyzed in relation to the revealed significant factors during overtaking. Following, the applicability of the developed algorithms in the context of Intelligent Transportation Systems (ITS) and Connected Vehicles (CV) is discussed, which reveals the importance of acquiring quality data using advanced equipment combined with advanced Machine Learning approaches for advanced modeling methods.

Transportation Research Board 96th Annual MeetingTransportation Research Board, 2017

The investigation of crash severity with freeway traffic and weather data has recently received s... more The investigation of crash severity with freeway traffic and weather data has recently received significant attention by researchers. This paper extends previous research by proposing nonlinear models for modeling crash injury severity enhanced with traffic and weather data collected from urban arterials in Athens, Greece. Cusp catastrophe models are applied and compared with traditional statistical models. The results of crash severity models support the potential applicability of the cusp catastrophe theory to road safety, at least when crash severity is expressed as the number of severely and fatally injured by total number of persons involved in a crash. Variations in speed, average flow upstream of the location of interest, crash type and wind speed, were found to have a potential effect on the system dynamics. However, findings do not always confirm the strong presence of nonlinearity. When crash severity is expressed as the number of injured persons by the total number of vehicles involved in a crash, linear models could also be used to describe the underlying phenomenon.

Transportation Research Board 96th Annual MeetingTransportation Research Board, 2017

Transportation Research Board 95th Annual MeetingTransportation Research Board, 2016

The study of maneuverability of vehicles in high demand urban road networks through vehicles’ tra... more The study of maneuverability of vehicles in high demand urban road networks through vehicles’ trajectories is a challenge for traffic engineers and researchers. The collection of such high resolution data has been exclusively supported by costly fixed location camera systems and computer vision algorithms in isolated or sequential sections. Recently, with the advances in computer vision, low cost cameras have been used with quite a success in extracting kinematic characteristics. In this paper, the authors discuss several limitations accompanying the use of camcorders and how they can be alleviated with the use of Unmanned Aerial Vehicles (UAVs). Following, a low-cost semi-automatic way of extracting detailed vehicle trajectory data through UAV video footage is presented. Steps to reduce errors due to camera instability and to achieve sufficient calibration are also described. Two experiments are presented; the first refers to vehicle tracking at a four legged intersection and the second to tracking pedestrian flow. Following, a discussion concerning the use of UAVs to replace or extend current systems’ capabilities is conducted.

A methodology has been developed for the use of microscopic traffic simulation modelling for the ... more A methodology has been developed for the use of microscopic traffic simulation modelling for the investigation of road safety impact from the introduction of two advanced driver assistance systems (ADAS). The simulations modelled key parameters (headway, speed) for several scenarios of different traffic levels and assumed penetration levels of Adaptive Cruise Control and Intelligent Speed Adaptation systems. Results from the simulations, studied in the context of existing relationships between the number of road accidents and traffic parameters, allowed the estimation of the related traffic safety impact. This impact was investigated in relation to the corresponding changes in average speed, in headways, in time-to-collision and in lane changing. Even though an overall straightforward answer to the safety impact of ADAS systems was not possible due to the complexity of the traffic safety phenomenon, several positive effects on safety were identified.

ABSTRACT We discuss recent findings on the statistical properties of short-term traffic flow in u... more ABSTRACT We discuss recent findings on the statistical properties of short-term traffic flow in urban freeway systems. In, particular, the complexity, nonlinearity and nonstationarity of freeway travel speed patterns are studied using the recurrence plots and the recurrence quantification analysis. Results indicate a variable statistical behavior of the speed’s temporal evolution, especially during the morning and peak periods of both the weekdays and weekend. Moreover, a clear deterministic evolution of speed patterns with variable nonlinear and laminar characteristics is observed during congested conditions.

Transportation Research Part F-traffic Psychology and Behaviour, May 1, 2017

The objective of this research was the analysis of the driving performance of drivers with Mild C... more The objective of this research was the analysis of the driving performance of drivers with Mild Cognitive Impairment (MCI) or Alzheimer's disease (AD), in different road and traffic conditions, on the basis of a driving simulator experiment. In this experiment, healthy ''control" drivers, patients with MCI, and patients with AD, drove at several scenarios at the simulator, after a thorough neurological and neuropsychological assessment. The scenarios include driving in rural and urban areas in low and high traffic volumes. The driving performance of healthy and impaired drivers was analysed and compared by means of Repeated Measures General Linear Modelling techniques. A sample of 75 participants was analysed, out of which 23 were MCI patients and 14 were AD patients. Various driving performance measures were examined, including longitudinal and lateral control measures. The results suggest that the two examined cerebral diseases do affect driving performance, and there were common driving patterns for both cerebral diseases, as well as particular characteristics of specific pathologies. More specifically, cognitively impaired drivers drive at lower speeds and with larger headway compared to healthy drivers. Moreover, they appear to have difficulties in positioning the vehicle on the lane. The group of patients had difficulties in all road and traffic environments, and especially when traffic volume was high. Most importantly, both cerebral diseases appear to significantly impair reaction times at incidents. The results of this research suggest that compensatory behaviours developed by impaired drivers are not adequate to counterbalance the direct effects of these cerebral diseases on driving skills. They also demonstrate that driving impairments increase as cognitive impairments become more severe (from MCI to AD).

International journal of transportation science and technology, Dec 1, 2016

PTW overtaking and models the specific behavior using concepts of Game Theory. Both 28 the PTW dr... more PTW overtaking and models the specific behavior using concepts of Game Theory. Both 28 the PTW driver and the lead vehicle's driver are assumed rational decision-makers that 29 develop strategies, trying to maximize their payoffs. These strategies may be cooperative 30 or not with respect to the distances and safety gaps and other behavioral aspects. The pay-31 off function is formulated based on a novel latent statistically determined driving indicator, 32 which quantifies both the driving risk and comfort. The proposed model is evaluated using 33 trajectory data from video recordings on an urban arterial. Results show that both drivers 34 have maximized gains by following a cooperative strategy. Findings also reveal that the 35 successful overtaking rate is higher, when the PTW driver is non-cooperative, whereas 36 lower overtaking rates occur, when the driver of the lead vehicle is non-cooperative. 37 Finally, the concepts of Dominant Strategies, bounded rationality and the construction of 38 the optimum payoff function are further discussed.

International journal of transportation science and technology, Sep 1, 2021

This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

Case Studies on Transport Policy

Short-term demand forecasting is essential for the public transit system, allowing for effective ... more Short-term demand forecasting is essential for the public transit system, allowing for effective operations planning. This is especially relevant in the highly uncertain environment created by the SARS‑CoV‑2 pandemic. In this paper, we attempt to develop accurate prediction models of transit ridership in Athens, Greece, using Autoregressive Fractional Integrated time series models enhanced with SARS‑CoV‑2-related exogenous variables. The selected exogenous variables are, from the one hand, the ratio of weekly SARS‑CoV‑2 infections over the infections 3 weeks before (capturing the dynamics of the pandemic, as a proxy for fear of transmitting the disease while commuting), and from the other hand, an index of the stringency of the government’s SARS‑CoV‑2-related measures and regulations. The developed ARFIMAX models have been fitted separately on bus and metro ridership data and wield comparable and statistically significant results. In both models, the exogenous variables prove to be statistically significant and their values are intuitive, suggesting a linear interrelation between them and transit ridership.

European Transport Conference, 2000, Cambridge, United Kingdom, 2000

To address the significant problem of traffic safety, the riskier of road user behaviours can be ... more To address the significant problem of traffic safety, the riskier of road user behaviours can be identified and then targeted by traffic safety campaigns, which have proven to be effective in a number of circumstances. Effective campaigns must target the right groups of drivers with the appropriate message. Using a large data base of 20,725 questionnaires from19 European countries, this paper uses a combination of factor analysis and tree based regression to determine relatively homogeneous driver groups which share attitudes toward safety, in an effort to design and implement more effective safety campaigns. To achieve this, the question of driver behaviour toward safety is addressed by examining habits such as attitudes toward speeding, reckless driving, seat belt use, and drinking and driving. The results suggest that speeding and general reckless (dangerous) behaviour are related, perhaps capturing driver's risk taking behaviour. Similarly, seat belt use and driving under the influence of alcohol are also related and may represent a driver's law abiding tendency. Further, young male drivers appear to be the demographic group which can benefit the most from systematic safety campaigns. (A) For the covering abstract see ITRD E107957.

Radioehlektronika, Feb 1, 1991