Traffic Situation Research Articles

Perceptions of novice driver education needs; Development of a scale based on the Goals for driver education using young driver and parent samples

Professional driver education and training has traditionally been used to improve the driving skills of young people with the expectation that they will drive more safely and therefore be less likely to crash. Despite this, much research has failed to find such an effect. The Goals for Driver Education (GDE) is a theoretical framework developed to improve the effectiveness of driver education. The GDE seeks to draw attention to a broader array of factors that may influence the driving of young people and hence increase the scope of what is included in driver education and training. Within the GDE, factors affecting driving and driver education are grouped into combinations of four hierarchical levels that represent influences on driving at increasing levels of abstraction (GDE level 1: Vehicle manoeuvring; GDE level 2: Mastery of traffic situations; GDE level 3: Goals and contexts of driving; GDE level 4: Goals for life and skills for living) and three types of individual competencies (Knowledge and skills; Risk-increasing factors; Self-evaluation skills). However, to date there have been few, if any, attempts to operationalise the GDE in a quantitative way. In response, the Perceptions of Driver Education Scale (PDES) was developed to gain an understanding of what two important stakeholder groups in the driver education and training ecosystem perceived to be important to be taught to novice drivers. Understanding these perceptions may lead to greater acceptance of the driver education and training that is designed and make it more effective. Following rigorous scale development procedures, thirty-five items were developed a priori using expert opinion and deployed, via an online survey, to a sample of parents of novice drivers (N = 518) and a separate sample of novice drivers (N = 247), both from Queensland, Australia. Exploratory Factor Analysis was performed on the parent responses and Confirmatory Factor Analysis was performed using the novice driver responses. A 29-item 9 factor solution was judged to be the best fit with the overall scale and each of the factors displaying strong levels of internal consistency. The 9 factors cover most hierarchical level and competency combinations, although removal of items meant that there is no representation concerning perceptions of Self-evaluation skills related to Level 3: Goals and contexts of driving within the PDES. Overall, the PDES is a valid and reliable instrument for investigating the aspects of driver education and training that are perceived as important by novice drivers and parents. The scale may also be applicable for use with other stakeholder groups and could also be used to evaluate pre-existing driver education and training programs.

Interdependence theory in humans’ interaction with automated vehicles: The impact of perceived situational factors on trust and cooperation

With the progressive development of automated vehicles (AVs), drivers and AVs need to share driving tasks as the AVs are yet unable to cope with every traffic situation. As these systems continue to evolve, AVs are increasingly perceived as social interaction partners that drivers must trust and with which they must be willing to cooperate. The presented study investigates how drivers’ social evaluation of situational characteristics affects their willingness to cooperate with and exhibit trust toward AVs. The study (n = 82) was conducted online using the random situation design in which participants imagine, describe, and evaluate an interaction with an AV. To evaluate the self-imagined situation, the interdependence theory and its dimensions measured by the Human–Machine-Interaction-Interdependence (HMII) questionnaire (conflict, power, mutual dependence, information certainty, and future interdependence) were used. The results show that 42% of the variance of trust and 35% of the willingness to cooperate could be explained by conflict, information certainty, power, and mutual dependence. Moreover, the findings imply that the interdependence theory can provide a framework needed in driver–vehicle research that can uniformly describe the influence of the social evaluation of the interaction with AVs on trust and willingness to cooperate. The study provides the first evidence that the interdependence theory is a fundamental social cognitive evaluation strategy humans use for interaction with AVs and automated systems in general.

Link handling for the atmospheric turbulence using LSTM neural networks in free space optical (FSO) communication

Abstract Free-space optical (FSO) communication is an emerging technology that uses light waves to transmit data, providing a faster and more efficient alternative to traditional wired communication. However, FSO communication is susceptible to atmospheric turbulence caused by factors such as rain, snow, and fog. To overcome this challenge, this study employs artificial neural network (ANN) and long short-term memory (LSTM) models to analyze the impact of atmospheric turbulence on FSO communication. The results indicate that higher wavelengths experience less attenuation than lower wavelengths in the presence of fog. The use of ANN and LSTM models to analyze the attenuation of various wavelengths in the presence of fog has shown that higher wavelengths experience less attenuation than lower wavelengths. Additionally, the LSTM model outperforms the ANN model in handling atmospheric turbulence, with an accuracy of 64.68 % compared to 63.98 %. These findings highlight the need for adaptive networks that can quickly adjust to traffic situations while being cost-effective. As the fiber optics industry continues to expand and evolve, there is potential for further developments in optical communications that prioritize speed, efficiency, and flexibility. As technology advances, the pursuit of faster and more reliable communication will continue to drive innovation in this field.

Real-time traffic control and monitoring

In today's scenario, congestion has become a major issue. Mainly the urban cities hit the hardest and its ever- increasing nature, real time knowledge of automobile road traffic density is essential for improved control of traffic signals and efficient management of traffic. The factors that contribute to traffic congestion are inadequate capacity, constrained demand, significant delays at red lights, etc. Capacity constraints and demand constraints are somehow related, but the delay for each signal is hard coded and traffic independent. So, to better meet this growing demand, the traffic control needs to be simulated and optimized. In recent times, image processing and surveillance systems are established in passenger information, access measurement and traffic control for real- time updates. Estimation of traffic bulkiness can also be performed using image processing. Tracing images of the moving automobiles can provide a quantitative explanation of traffic flow. This paper demonstrates how to utilize real-time live video feeds from cameras at intersections to perform instantaneous traffic bulkiness calculations using image processing and vehicle detection using EfficientDet architecture and TensorFlow lite. It also aims to reduce traffic jams and accidents by focusing on algorithms that switch signal lights on the basis of density of vehicles on the road and the priority set for specific emergency vehicles. In turn, it provides people with safe transportation, reduces fuel consumption and waiting times. Vehicle recognition is done by the system from images and not by using electronic sensors mounted on the roadway. Installation of camera is done next to the traffic light, which captures the video feed sent to the Raspberry Pi. The proposed algorithm aids to manage the timing of the traffic lights which in turn helps to achieve the goal of automatic control of traffic situations.

An Incremental Approach for Understanding Collision Avoidance of an Industrial Path Planner

Autonomous Driving Systems (ADSs) are complex systems that must consider different aspects such as safety, compliance to traffic regulations, comfort, etc. The relative importance of these aspects is usually balanced in a weighted cost function. However, there is generally no optimal set of weights, and different driving situations may require different weights values to guarantee a safe drive. Recent testing approaches can generate diverse driving scenarios in which different ADS configurations lead to various degrees of hazard. These tests need to be properly analyzed to improve the ADS's safety. In this paper, we propose \paolo{an analysis approach} that is able to assess the relation between the ADS configurations and the level of hazard that is obtained in some particular traffic situations. The approach uses fuzzification to partition ADS weights in different categories, and a spectrum-based analysis to identify which weights categories are related to hazard and safety. The occurrence of a hazard could be due to a single weight or to combinations of two or more weights. For scalability, the approach performs an incremental analysis, in which first single weights are considered, and then weight combinations of higher order. The approach has been applied to an industrial path planner.

Time-Driven and Privacy-Preserving Navigation Model for Vehicle-to-Vehicle Communication Systems

Effective time-driven navigation is an operative way to alleviate traffic congestion, which is also a challenging problem in the Internet of Vehicles context. Most existing centralized navigation systems often cannot react promptly to real-time local traffic situations, while most existing distributed navigation systems are vulnerable to privacy attacks. To overcome these drawbacks, we propose a learning model that provides a provable guarantee of vehicles' privacy while still enabling efficient navigation under real-time traffic conditions. The proposed model adopts a novel multi-agent system with customized differentially private mechanisms. To verify the effectiveness and stability of our approach, we implement the proposed method on CARLA, which is an autonomous driving simulator. In four experimental tasks with varying parameters, we demonstrate fully that our proposed method outperforms other benchmarks.

Improving safety of interactions between conventional and autonomous ships

Automatic controllers work best when the system they control can be sufficiently well modelled. This is a problem for control of autonomous ships in mixed traffic situations where the autonomous ship interacts with conventional ships, as the crew on other ships can and will exert unexpected behaviour that cannot be easily modelled. This paper analyses the problem of information acquisition, situational assessment and how to predict other ship's actions for autonomous ships that need to interact with conventional ships. We identify causes for the interaction problem and classify these into a decision making model. We also identify possible measures to overcome the problems and based on an impact analysis where technical, procedural and regulatory aspects are considered, we discuss and propose some possible ways to reduce or solve this problem. The conclusion is that the most likely and effective short-term solution is to assist the autonomous ships with human operators and the best longer-term solution may be to improve the information exchange between the ships, complemented with changes in COLREGs.

Perceived Challenges and Effects of Flexible Learning at Ilocos Sur Polytechnic State College Tagudin Campus

Flexible learning modalities are implemented by learning institutions to address the challenges of pandemic, war, flood, heavy traffic, unbearable temperature and other extreme situations and to continue educating the learners. The study assessed the implementation of flexible learning modality among ISPSC Tagudin Campus students by identifying the challenges towards financial and psychological aspects including academic performances. The researchers used the descriptive research design and an online survey questionnaire was administered as the primary data gathering tool to 249 College of Arts and Sciences students as respondents. The collected data were subjected to simple statistical analysis such as frequency count, percentage, mean and Pearson Product Moment Coefficient Correlation (Pearson r). The researchers found out that the respondents were mostly young adults who belong to poor households and were residing in rural areas; they faced minor challenges in their online and modular distance learning and their financial, psychological, and academic performances were affected in the utilization of flexible learning modalities. Social class has a significant correlation on the challenges of using flexible learning modalities. Students are encouraged to consistently develop and maintain academic motivation while using the flexible learning modality (modular instruction, face-to-face learning delivery and online instruction). Despite adverse conditions being experienced, the college administration should provide ways and means to alleviate the financial difficulties of students through the provision of stable internet connection in school and the provision of online or printed learning materials to facilitate a healthy and conducive learning environment while on their online classes.

Implementation of a gamified e-learning platform focusing on traffic knowledge and skills among Vietnamese adolescents

Adolescents are considered as vulnerable road users and education is one way to increase their traffic knowledge and riding skills. In this study, a version of an e-learning platform tailored to the Vietnamese context is used to improve four specific competences, i.e. traffic-related knowledge, situation awareness, risk detection, and risk management. Images and short videos from authentic traffic situations are used as learning stimuli and users have the possibility to self-test their competences via a separate “finale”. Gamification elements (i.e., points, levels, badges and cups) are incorporated into the platform to encourage user engagement. The purpose of this study is to conduct a pilot study using a gamified e-learning platform, and to assess user experience. 47 adolescents (aged 15-16) participated in a single arm (i.e., test group only) within-subject design with baseline and post-measurement. Results indicate that scores on the post-measurement were statistically significantly higher as compared to baseline performance. Scores were better for the risk management module. There were no statistically significantly different in scores between familiar situations (i.e., coming from the city where participants are living) and unfamiliar situations. Males overall performed better than females. Results for user experience are also discussed.

Coping with Randomness in Highly Complex Sys-tems Using the Example of Quantum-Inspired Traffic Flow Optimization

Developing new solutions to complicated large-scale problems typically requires large-scale numerical simulation. Therefore, traffic simulations often run against randomized simulations instead of real-world traffic situations. This paper demonstrates a method to calculate the statistical significance of numerical simulations and optimizations in the presence of numerous random variables in complex systems using one-sided paired t-tests. While the paper covers a specific Fujitsu traffic-optimization project which uses SUMO for simulating the traffic situation, the method can be applied to many similar projects where a complete investigation of the solution space is not feasible due to the size of the solution space.

A safe and efficient decision algorithm for ramp merging based on a hierarchical planner and model predictive control

Due to highly dynamic interactions between vehicles, ramp merging decision is extraordinarily challenging in dense traffic. To deal with the non-convexity and inter-coupling of the decision-making problem, a top-level behavioural planner is proposed, which considers both the overall traffic situation and the individual characteristics of other interacting drivers. To ensure the implementability and efficiency of planning, a bottom-level motion planner is further designed with the guide of the top-level behavioural planner. The validation simulation using a naturalistic driving dataset shows that the proposed planning algorithm can achieve a success rate of 97.65% and has similar gap selection decision as human drivers. Then to track the planned vehicle motion, a nonlinear model predictive controller considering actuator delay and lag characteristics is proposed. Finally, the proposed planning and control modules are deployed in a turbocharged test vehicle, with satisfactory vehicle lateral and speed tracking errors, which validate the implementability of the proposed ramp merging decision algorithms.

Antecedents of Waze Mobile Application Usage as a Solution for Sustainable Traffic Management among Gen Z

The study aimed to investigate Gen Z’s intentions to utilize the Waze mobile application as a solution for sustainable traffic management in Metro Manila. The extended technology acceptance model (TAM) was used to define user behavior and technology usage to determine the factors influencing Filipino drivers’ acceptance of the Waze application. The study utilized a survey given to 300 Filipino drivers travelling within the National Capital Region to accurately measure various factors and their connections to usage intention and actual use. The analytical approach used for this investigation was partial least squares structural equation modelling (PLS-SEM). The study’s data results revealed that system quality, perceived location accuracy, perceived usefulness, and perceived ease of use affect Gen Z’s intentions to use traffic navigation applications, particularly Waze. The study’s results can be applied as a theoretical framework for future researchers of Waze mobile applications, Waze route accuracy, and Waze overall application performance, as well as the features of the Waze application, to evaluate how the use of the Waze mobile application could help in the effective management of traffic situations in Metro Manila. The study assessed the effectiveness of the Waze navigation app as a platform for efficiently managing traffic situations in Metro Manila and highlighted the application performance of Waze and its acceptance by Gen Z users in Metro Manila. The study also highlighted the need a critical review of Waze’s application performance. The study recommends that similar future studies must consider samples from a more diverse geographic backgrounds to obtain a more accurate representation of Filipino users. Future researchers are also advised to adopt a qualitative research design to gain more detailed insights into Filipinos regarding their experience with the Waze application.

A rule-based maritime traffic situation complex network approach for enhancing situation awareness of vessel traffic service operators

The development of the shipping industry has led to increasingly busy traffic near many port areas, which leads to higher demands for vessel traffic service operators (VTSOs), and challenges to maintain situational awareness. However, an effective rule-based method for analyzing waterway traffic from a systemic perspective to improve situational awareness is lacking. Therefore, this article proposes a method to assess the maritime traffic situation complexity for this purpose. Referring to the COLREGs, a rule-based maritime traffic situation complex network (R-MTSCN) model is established by taking ships as nodes, and the collision avoidance relationship between ships as the directed edges. In addition, network topology features such as degree, vertex strength, and vertex strength distributions are used to statistically characterize the evolution of the complexity of maritime traffic systems. By analyzing the AIS data of ships navigating the Yangtze River estuary, the concept of the proposed model is demonstrated, thus providing a pathway to develop intelligent, digital, and data-driven Vessel Traffic Services, aiming to enhance efficiency of vessel traffic management and improve maritime safety.

Spatio-Temporal Meta-Graph Learning for Traffic Forecasting

Traffic forecasting as a canonical task of multivariate time series forecasting has been a significant research topic in AI community. To address the spatio-temporal heterogeneity and non-stationarity implied in the traffic stream, in this study, we propose Spatio-Temporal Meta-Graph Learning as a novel Graph Structure Learning mechanism on spatio-temporal data. Specifically, we implement this idea into Meta-Graph Convolutional Recurrent Network (MegaCRN) by plugging the Meta-Graph Learner powered by a Meta-Node Bank into GCRN encoder-decoder. We conduct a comprehensive evaluation on two benchmark datasets (i.e., METR-LA and PEMS-BAY) and a new large-scale traffic speed dataset called EXPY-TKY that covers 1843 expressway road links in Tokyo. Our model outperformed the state-of-the-arts on all three datasets. Besides, through a series of qualitative evaluations, we demonstrate that our model can explicitly disentangle the road links and time slots with different patterns and be robustly adaptive to any anomalous traffic situations. Codes and datasets are available at https://github.com/deepkashiwa20/MegaCRN.

Using a new algorithm in Machine learning Approaches to estimate level-of-service in hourly traffic flow data in vehicular ad hoc networks

The primary goals of transportation agencies and researchers studying traffic operations are to ease traffic and increase road safety through the use of vehicular ad hoc networks. Agencies can't achieve their goals without reliable and consistent data on the current traffic situation. The Level-of-Service (LOS) index is a helpful measure of freeway traffic operations. Conventional fixed-location cameras and sensors are impractical and expensive for gathering reliable traffic density data on every road in large networks. Flow data is a new, low-cost option that has the potential to boost safety and operations. This study proposes an algorithm for hourly LOS assessment by incorporating flow data provided by the MIDAS (Motorway Incident Detection and Automatic Signaling) system. The proposed algorithm uses machine learning techniques to classify LOS data based on the flow of traffic. The input features that are subject to prediction are a group of technical indicators. The real-world LOS was determined by analyzing data from stationary sensors. The outcomes demonstrate that technical indicators can be utilized to enhance the accuracy of LOS estimation (Random Forest= 93.1, k-nearest neighbors = 92.5, and Support Vector Machine = 91.4). The current work introduces a novel approach to the selection of technical indicators and their use as features, which allows for highly accurate short-term prediction of LOS estimation.

Travel Time Probability Prediction Based on Constrained LSTM Quantile Regression

Travel time reliability assessment has been widely used in recent years to evaluate the performance of transportation networks and measure the operation level of transportation systems. Weather, as one of the important factors influencing travel time reliability, affects the relationship between the supply and requirement of urban road networks. Considering the traffic characteristics under different traffic conditions, a study on the influence of weather on travel time reliability under different conditions is proposed to predict the probability of travelers completing their trips within the expected time under different weather conditions. Based on the urban road network data and cab trajectory data of Harbin city, this paper correlates the floating vehicle location with the road network information through a hidden Markov model to reduce the influence of vehicle trajectory errors on the calculation results of path travel time. To analyze the entire distribution of extreme travel time and its impact on the reliability of travel time under various traffic situations, it captures the tail features of the travel time distribution based on extreme value theory. Then, to increase the predictability of each quantile, it combines a deep-learning LSTM model and a quantile regression model to create a probabilistic travel time prediction model utilizing combined layers. The proposed model is compared with the linear quantile regression and neural network quantile regression models, and the model is evaluated in terms of point prediction results and probabilistic prediction results, respectively, to ensure the accuracy of predictions from the model. As a result, the prediction accuracy of the model in this paper is greatly improved, and the degree of violating quantile constraints is greatly reduced.

A Novel Energy-Efficient Reservation System for Edge Computing in 6G Vehicular Ad Hoc Network.

The roadside unit (RSU) is one of the fundamental components in a vehicular ad hoc network (VANET), where a vehicle communicates in infrastructure mode. The RSU has multiple functions, including the sharing of emergency messages and the updating of vehicles about the traffic situation. Deploying and managing a static RSU (sRSU) requires considerable capital and operating expenditures (CAPEX and OPEX), leading to RSUs that are sparsely distributed, continuous handovers amongst RSUs, and, more importantly, frequent RSU interruptions. At present, researchers remain focused on multiple parameters in the sRSU to improve the vehicle-to-infrastructure (V2I) communication; however, in this research, the mobile RSU (mRSU), an emerging concept for sixth-generation (6G) edge computing vehicular ad hoc networks (VANETs), is proposed to improve the connectivity and efficiency of communication among V2I. In addition to this, the mRSU can serve as a computing resource for edge computing applications. This paper proposes a novel energy-efficient reservation technique for edge computing in 6G VANETs that provides an energy-efficient, reservation-based, cost-effective solution by introducing the concept of the mRSU. The simulation outcomes demonstrate that the mRSU exhibits superior performance compared to the sRSU in multiple aspects. The mRSU surpasses the sRSU with a packet delivery ratio improvement of 7.7%, a throughput increase of 5.1%, a reduction in end-to-end delay by 4.4%, and a decrease in hop count by 8.7%. The results are generated across diverse propagation models, employing realistic urban scenarios with varying packet sizes and numbers of vehicles. However, it is important to note that the enhanced performance parameters and improved connectivity with more nodes lead to a significant increase in energy consumption by 2%.

Evaluation of Drivers' Driving Behavior in Heavy Traffic Situations from OBD-II Data

The analysis and discussion of the onboard diagnostic data will help understand the driver's behavioral characteristics and develop a sustainable transportation system. The research content of this paper is to mine the driving behavior data through the vehicle preload equipment, analyze the factors affecting safe driving and establish a prediction model. This study collected data from 50 Taiwanese drivers while operating in heavy traffic. Understand the driver's behavioral characteristics through data analysis, such as calculating the times of the driver's emergency braking is based on the driving speed. From this result, the index of dangerous driving is defined. In addition, the dangerous driving index and other variables were analyzed, and it was found that there was a significant relationship between dangerous driving and vehicle mileage and maximum speed. According to the results, the drive speed increases the driving risk, the mileage reduces the risk probability, and the prediction accuracy is 78.9%. Complete data needs to be collected to evaluate complete driving behavior characteristics for developing sustainable transportation goals.

DYNAMICS AND CAUSES OF CRASHES ON LITHUANIAN ROADS

Lithuania is the only European Union country that has reduced the number of road deaths by more than 50% from 2011 to 2021. However, even with significant progress, Lithuania has 53 deaths per 1 million inhabitants and Lithuania is still behind the EU average, which was 45 deaths per 1 million inhabitants in 2021. The purpose of this study is to determine the dynamics of deaths on Lithuanian roads in 2019–2021 using statistical methods and to systematically assess the causes of fatal traffic accidents. Also to propose factors (criteria) that would allow to improve the traffic safety situation in Lithuania and reach the average of European Union countries. The study carried out an analysis of traffic accidents in which people died on Lithuanian roads in 2019–2021. The dynamics of the distribution of events according to their causes during the studied period were analysed. It was established that the most important causes of fatal traffic accidents in Lithuania are related to inappropriate behaviour of drivers and pedestrians. This is driving under the influence of alcohol or drugs, exceeding the speed limit, or driving at an unsafe speed. Also, inadequate, or unsafe infrastructure and poor technical condition of vehicles have a significant impact on fatal traffic accidents. After analysing the results of other scientists’ research, evaluating the experience of other countries, a list of measures (actions) divided into 3 groups was created. The use of these measures would further reduce the number of incidents in Lithuania. In future studies, it is planned to determine the importance of the presented factors based on the opinion of experts.

Data-Driven Optimization of Urban Traffic using AI and Real-Time Analysis

Optimizing urban traffic is a significant problem for cities all over the world. This research aimsto tackle this issue by utilizing real-time analysis and artificial intelligence (AI). The project's keycomponents are data collection, the creation of a 2D map, object detection using the YOLO algorithm, 3Dsegmentation, visualization, and data integration. To ensure the precision of data collection, we employ amulti-GNSS RTK approach for precise location determination. This method allows us to generate exactcoordinates for urban road networks, which provides the basis for additional research. We are able todisplay urban traffic flows on a 2D visualization map, allowing us to spot crowded locations and improvetraffic flow. The YOLO method is used in conjunction with 3D segmentation to identify objects. Throughtraining, we allow this algorithm to recognize and categorize a wide range of objects, including movingvehicles, pedestrians, and particular vehicle types (such as minibusses and taxis), which significantlycontribute to traffic congestion. Our project makes better use of real-time object detection to enable wellinformed decision-making and improve understanding of the traffic situation.