Driver Information Research Articles

Artificial intelligence abnormal driving behavior detection for mitigating traffic accidents

Annually, a tragic toll of 1.3 million lives is lost on roads across the globe, with tens of millions more suffering injuries or disabilities. The necessity for precise detection of abnormal driving behavior is paramount in reducing traffic accidents. This paper aims to bridge the gap between normal and abnormal driving patterns, offering near-flawless detection capabilities. This paper presents a novel AI tachograph prototype, the first of its kind, that can classify driving behavior into normal and abnormal in real time with an impressive accuracy of 99.99 %. This high level of accuracy is achieved by using a bias-reduction method. The bias-reduction method focuses on minimizing biases in the dataset, such as surrounding situations, location, driver information, and car types. This approach significantly enhances the prediction accuracy of existing machine learning algorithms. The dataset used for this research is quite extensive, consisting of anomaly data collected from 10,181 commercial vehicles and 12,530 drivers in just 0.1 s. This rich dataset is crucial for building a reliable model. The effectiveness of the proposed method was validated using 10-fold cross validation on 480 k to 540 k instances with 36 determinants. The results clearly demonstrated that reducing bias leads to higher prediction accuracy. The paper also plans to compare the prediction accuracy of balanced and imbalanced datasets. The findings from this research have broader implications as the proposed method can be applied generally to machine learning to improve prediction accuracy.

Forecasting Nighttime Frost-induced Black Ice Formation on Bridges Using Atmospheric Data

Background Faced with the tragedies caused by black ice in winter, especially on bridges, it is imperative to forecast black ice for preventive maintenance and to notify drivers approaching the dangerous spots. Methods In this study, three different machine learning algorithms—Deep Neural Network (DNN), Random Forest (RF), and Support Vector Machine (SVM)—were employed to predict nighttime black ice induced by frost on three bridges in Korea. Input data consisted of atmospheric data (air temperature, relative humidity, dew point, and differences between air temperature and relative humidity over two consecutive days) provided by the weather agency. Results To assess the employed models, reference data were generated based on the physical principle that ice forms when the pavement temperature is lower than the dew point temperature and negative. The pavement temperature was obtained using an infrared surface temperature sensor mounted on a maintenance patrol vehicle. Consequently, DNN and RF showed higher performance with an accuracy of 95%, followed by SVM with an accuracy of 92.5%. Conclusion Due to the use of easily obtainable atmospheric data, the findings of this study can be practically applied to preventive maintenance and driver information, thereby enhancing traffic safety.

Auditing learner driver information about floodwaters: An environmental scan of government issued resources in Australia

Introduction: Vehicles driving, or being swept, into floodwaters is a leading cause of flood-related death. Establishing safe behaviors among learner drivers may reduce risk throughout their driving lifetime. Methods: An environmental scan of publicly available government issued learner and driver handbooks across the eight Australian jurisdictions was conducted to identify information provided regarding floodwaters. Search terms included ‘flood,’ ‘rain,’ ‘water,’ and ‘wet.’ A visual audit of flood-related signage was also conducted. Results: Twelve documents, across eight jurisdictions, were analyzed. Four jurisdictions’ documents provided no information on flooding. Of the four jurisdictions that provided information, content varied. This included highlighting risks and discouraging entering floodwaters in a vehicle, including penalties associated with travel on closed roads, to advising depth and current checks if crossing a flooded roadway, with recommendations based on vehicle size (preference given to bigger vehicles, i.e., 4wds). Information on flood-related signage was found in one jurisdiction. Discussion: Learner and driver handbooks represent a missed opportunity to provide flood safety information. Currently, information is not provided in all jurisdictions, despite flood-related vehicle drowning deaths of drivers and passengers being a national issue. Where information is presented, it is limited, often lacks practical guidance on how to assess water depth, current, and road base stability, and could better use evidence regarding the psychological factors underpinning, and behavioral prompts for performing, or avoiding, risky driving behavior during floods. Conclusions: The provision and content of information in learner driver and driver handbooks must be improved, particularly within the context of increasing flooding and extreme weather associated with the effects of climate change. Practical applications: We encourage all jurisdictions to provide practical information that draws on evidence-based risk factors and empirically established psychological factors for behavioral change to help establish safe driver behaviors around floods in the formative years of learning to drive.

Data accuracy in Vehicle-to-X cooperative awareness messages: An experimental study for the first commercial deployment of C-ITS in Europe

Cooperative Intelligent Transportation Systems have achieved a mature technology stage and are in an early phase of mass deployment in Europe. Relying on Vehicle-to-X communication, these systems were primarily developed to improve traffic safety, efficiency, and driving comfort. However, they also offer great opportunities for other use cases. One of them is forensic accident analysis, where the received data provide details about the status of other traffic participants, give insights into the accident scenario, and therefore help in understanding accident causes. A high accuracy of the sent information is essential: For safety use cases, such as traffic jam warning, a poor accuracy of the data may result in wrong driver information, undermine the usability of the system and even create new safety risks. For accident analysis, a low accuracy may prevent the correct reconstruction of an accident. This paper presents an experimental study of the first generation of Cooperative Intelligent Transportation Systems in Europe. The results indicate a high accuracy for most of the data fields in the Vehicle-to-X messages, namely speed, acceleration, heading and yaw rate information, which meet the accuracy requirements for safety use cases and accident analysis. In contrast, the position data, which are also carried in the messages, have larger errors. Specifically, we observed that the lateral position still has an acceptable accuracy. The error of the longitudinal position is larger and may compromise safety use cases with high accuracy requirements. Even with limited accuracy, the data provide a high value for the accident analysis. Since we also found that the accuracy of the data increases for newer vehicle models, we presume that Vehicle-to-X data have the potential for exact accident reconstruction.

Progress in Research on Equivalent Consumption Minimization Strategy Based on Different Information Sources for Hybrid Vehicles

In recent years, hybrid electric vehicles (HEVs) have become one of the leading technologies for renewable energy and environment-friendly automobiles. Since an HEV has two or more power sources whose high-efficiency regions usually do not overlap, it is crucial to choose suitable energy management strategies (EMS) for HEVs to allocate the power outputs, improving the vehicular fuel economy and reducing emissions effectively. The equivalent consumption minimization strategy (ECMS) has become one of the most promising and widely studied EMS due to its merits of optimization potential and onboard real-time availability. This paper reviews and discusses the progress in the state-of-the-art ECMS methods utilizing different information sources. It is proposed to classify various ECMS methods into two groups, i.e., the ECMS with and without external information according to the utilization of road, vehicle, and driver information. The principles, advantages and disadvantages, and application features of those methods are analyzed and compared in detail. Furthermore, ECMS execution methods with state-of-charge correction and ECMS multi-objective optimization are also discussed. Finally, the outlook of research on the ECMS is presented.

Stability of Traffic Equilibria in a Day-to-Day Dynamic Model of Route Choice and Adaptive Signal Control

Adaptive traffic signal control has the potential to promote the efficient use of road intersections, thus contributing to the effectiveness of urban traffic management schemes. However, the reaction of drivers to repeatedly updated signal settings and the ensuing route choice dynamics may trigger the emergence of various kinds of network instability. In this study, the joint evolution of traffic flows and adaptive signal settings in a road network is investigated at the level of day-to-day dynamics with an explicit focus on the stability issue. We show how a Logit form signal control policy can be used, in interaction with route choice, to counter the emergence of instabilities possibly arising as a consequence of various behavioral factors and network conditions. After providing a general formulation of the model as a discrete time, deterministic nonlinear dynamical system, an explicit analysis of fixed-point stability is carried out for a simple network. Numerical results obtained from the implementation of the model on two example networks are presented in order to support the analytical findings of this study. We conclude that, in an integrated traffic management and information system, a properly calibrated adaptive signal control policy has the potential to offset the destabilizing effect of highly accurate driver information supplied by navigational aids. Our findings also suggest that the Logit-like control policy performs better than the Equisaturation signal setting method, in terms of average intersection delay at equilibrium, for all levels of driver information and travel demand tested in the experiment.

An Advanced Driver Information System at Critical Points in the Multimodal Traffic Network

Enhancing traffic safety is one of the fundamental objectives of Intelligent Transport Systems (ITS), and it aligns closely with the principles of sustainable transport. Due to specific differences in infrastructure, vehicles, and users’ behavior, places where different modes of traffic intersect are recognized as critical points of the traffic system, making them crucial areas for the implementation of Sustainable Urban Mobility Plans (SUMPs). The SUMPs aim to create urban mobility that is both environmentally friendly and safe for all users. The continuous development and widespread adoption of innovative ITS technologies have paved the way for a system that can provide drivers with real-time information about both immediate and potential dangers at these critical points. This paper presents a comprehensive review of prior research conducted in the field, investigating the impact of information systems on drivers’ behavior, various detection and communication solutions that can be effectively integrated into such a system, and a brief overview of the models and solutions that have been developed to warn drivers in a similar context. A review of the literature found that warning systems have a significant impact on driver behavior, which contributes to increased traffic safety. Furthermore, there are numerous solutions applicable to a multimodal environment. Yet, they mostly refer either to autonomous vehicles or require an additional unit of infrastructure for communication, which is not realistically applicable to the current state of traffic in most countries of the world. This paper proposes a system architecture framework for future research that would take advantage of widely available technologies and make the system accessible to different users in a multimodal environment.

Analisis Sistem Informasi Driver Maxim Indonesia Menggunakan Pendekatan Evaluasi Usability Heuristik dan Human Resource Information System

Driver information system analysis includes evaluation and in-depth understanding of various aspects of the system used by drivers in a service or platform. Driver information system analysis helps ensure that the technology infrastructure that supports driver operations in application-based transportation services is efficient, safe, and in line with business and driver needs. This research aims to analyze the usability of the driver information system with a case study of the Maxim driver information system. The method used to analyze Maxim drivers uses the Heuristic Evaluation (HE) and Human Resource Information System (HRIS) approaches. The research results found that the Maxim driver information system is easy to use and the information contained in it is quite clear.

A prospective study on the precision of height data from electronic medical records in tidal volume calculation for lung-protective ventilation.

Lung-protective ventilation is now the norm for all patients, regardless of the presence of acute respiratory distress syndrome (ARDS), owing to the mortality associated with higher tidal volumes (TV). Clinicians calculate TV using recorded height from medical records and predicted body weight (PBW); however, the accuracy remains uncertain. Our study aimed to validate accurate TV settings for lung-protective ventilation by examining the correlation between the charted height and bedside measurements. In a single-center study, we compared PBW-based TV calculated from recorded height to PBW-based TV from measured height and identified factors causing height overestimation during charting. Our team measured patient height within 24 hours of admission using metal tape. TV calculated from recorded height (6-8 mL/kg PBW) was significantly larger (391.55 ± 65.98 to 522.07 ± 87.97) than measured height-based TV (162.62 ± 12.62 to 470.28 ± 89.64) (P < .01). In the height overestimated group, 57.7% were prescribed TV by healthcare provider, which was more than TV of 8 mL/kg of PBW, as determined by measured height. Negative predictors for height overestimation were male sex (OR: 0.45 [95% CI: 0.25-0.82]; P = .008) and presence of driver's license information (OR: 0.45 [95% CI: 0.25-0.80]; P = .007), whereas Asian ethnicity was a positive predictor (OR: 4.34 [95% CI: 1.09-17.27]; P = .04). The height overestimation group had a higher in-patient mortality rate (38.5%) than the matched/underestimation group (20%) (P < .01). In stadiometer-limited hospitals, the PBW-based TV is overestimated using the recorded height instead of the measured height. In the group where heights were overestimated, over half of the patients received TV prescriptions from healthcare providers that surpassed the TV of calculated 8 mL/kg PBW based on their measured height. The risk factors for height overestimation include female sex, Asian ethnicity, and missing driver's license data. Alternative height measurement methods should be explored to ensure precise ventilation settings and patient safety.

Effect of road markings and road signs quality on driving behaviour, driver’s gaze patterns and driver’s cognitive load at night-time

Night-time conditions are one of the most complex driving situations due to limited availability of visual information in the environment and limitations to the human visual system. In such conditions, road markings and road signs are the main source of information for drivers. Research has shown that road markings and road signs, if properly designed and placed, can positively impact driver behaviour and thus overall road safety. However, it is still not completely clear how different levels of road markings and road signs visibility affect drivers in night-time conditions. For this reason, we used a driving simulator to simulate night-time conditions and different levels of visibility of road markings and road signs in order to analyse the connection between the visibility of these road elements and driver behaviour and cognitive load. The results suggest that the level of road markings and road signs visibility slight increased the driving speed (about 2%), but at the same time it had a positive effect on participants’ cognitive load which was at an optimal level during high visibility. Although there was no significant difference in participants’ eye movements and the number of gazes at road markings, the percentage share of looked road signs was the highest in high visibility conditions, which suggests that the participants were in most cases timely informed and aware of the upcoming situation.

Literature review of research progress on car following model

In the past several decades, the car-following model has attracted many experts and scholars from the fields of traffic engineering, computational physics, psychology and so on, these experts and scholars have carried on the thorough research and the exploration to it, causes the model analysis essential factor from simple to rich, from simple to complex. With the continuous improvement of the model, the improved car-following model is more and more in line with the actual traffic conditions. With the development of traffic technology, driver’s car-following behavior will change greatly, which is realized by developing and establishing ITS, driver information guidance system and vehicle automatic intelligent cruise system. Therefore, a lot of car-following models for specific problems have emerged, which is of great practical significance to the further study of car-following theory. In this paper, the research background and significance of car-following model are deeply discussed, the current research status and conclusions are comprehensively analyzed, and the future research direction in this field is prospected.

The adoption and application of Intelligent Speed Assistance by private motorists: User and non-user perspectives

Intelligent Speed Assistance (ISA) is an in-car system that can help drivers to avoid speeding and therefore reduce crash frequency and severity. ISA systems that intervene to reduce vehicle speeds are increasingly available in new cars. Their efficacy in crash reduction will depend on the extent to which they are adopted and used by motorists. Increasing ISA use is therefore a promising new target for behaviour-change interventions seeking to reduce crash involvement. To provide context for intervention development, this study explored the beliefs and attitudes of 20 car drivers who have intervening ISA systems and 20 that do not. Thematic analysis of interview scripts generated five superordinate themes across both sets of drivers relating to: (1) safety, (2) driver control, (3) choice and enforcement, (4) driver identity and behaviour, and (5) enabling roll-out. ISA acceptability was generally high as long as driver choice around turning off and overriding the system was maintained. Drivers described a number of information needs relating to ISA: increased general awareness of ISA, provision of system-specific information for new ISA drivers and reassurances around non-ISA driver concerns (e.g., the responsiveness of the override and the speed control process). Many drivers indicated that ISA adoption would be facilitated by emphasising personal benefits (e.g., protecting driver licences, reduced insurance premiums, improved fuel efficiency, more relaxed driving) as well as safety advantages.

Wearable and self-powered triboelectric sensors based on NaCl/PVA hydrogel for driver multidimensional information monitoring

Dangerous behaviors during driving such as fatigue or making phone calls may seem common in daily life. However, these behaviors are the actual "culprit" of many traffic accidents and pose a serious threat to traffic safety. Therefore, it is necessary to effectively detect dangerous driving behaviors by scientific and technological means. The present detection methods still face many bottlenecks, including individual differences, complex lighting changes, battery power supply, poor wearability, et al. Here, we designed a green and stretchable triboelectric sensor (TES) to monitor dangerous driving behaviors. The performance of the sensor was improved by about 9.99 and 3.58 times through doping sodium chloride solution in PVA hydrogel and introducing a curved contact surface between the electrode and friction layer, respectively. The proposed sensor has a high sensitivity of 1.95 V/kPa in the linear range of 0–11.28 kPa. By employing different machine learning models, we developed an intelligent neck ring based on the proposed sensor array to recognize different neck movements, which has achieved the highest accuracy of 96.10%. Finally, the intelligent neck ring was used to construct a sensing system for driver status monitoring. By collecting detailed driver information, the system can detect dangerous driving behaviors, monitor drivers’ health conditions, and provide appropriate reminders to improve driving safety and prevent the spread of viruses.

A bibliometric review of driver information processing and application studies

A bibliometric review of driver information processing and application studies

Distraction and visual search characteristics of young drivers when using navigation system displays

Navigation systems are fast and efficient sources of road information for drivers. However, they can increase the potential for accidents by distracting drivers. This study investigated the impact of navigation systems on driver distraction and visual search under various driving conditions. Using a driving simulator, eye-tracking technology recorded visual search data from twenty young drivers. The experiment analyzed factors such as driving environment (urban and rural), illumination level (day and night), and navigation system display size (large and small), as well as their interactions. Multiple eye movement metrics were employed, including duration and frequency of GPS fixation, dwell duration on the road ahead, and dwelling on mirrors and side windows. Statistical analysis employed repeated measures ANOVA to analyze the data. Findings revealed that small GPS displays caused greater distraction in terms of average and total gaze duration. Additionally, distraction increased during daytime driving conditions. In terms of visual search, wider and more dispersed search patterns were observed during the day, resulting in improved driving performance. This study aims to compare small and large navigation displays to identify the more effective option in reducing driver distractions. The research contributes to understanding driver distraction and visual search when using navigation system displays.

An analysis of day and night bicyclist injury severities in vehicle/bicycle crashes: A comparison of unconstrained and partially constrained temporal modeling approaches

Due to visibility limitations and other factors, the injuries sustained by bicyclists in nighttime vehicle-bicycle crashes tend to be more severe than daytime crashes. This paper seeks to provide insights into this day/night injury severity phenomenon by studying how day/night bicyclist injury severities have changed in crashes that occurred before, during, and after the COVID-19 lock downs. Using data from vehicle-bicycle crashes in the state of Florida over a three-year period (from 2019 to 2021 inclusive), separate yearly models of bicyclist-injury severities (with possible outcomes of severe injury, minor injury, and no visible injury) were estimated using a random parameters logit approach with possible heterogeneity in the means and variances of random parameters. Likelihood ratio tests were conducted to examine the overall stability of model estimates across the studied years as well as day/night differences, and a comparison of partially constrained and unconstrained temporal modeling approaches was undertaken. A wide range of variables potentially affecting resulting bicyclist injury severities in vehicle/bicycle crashes was considered including bicyclist and vehicle driver information, vehicle features, roadways and environmental conditions, temporal characteristics, and roadway features. The findings show statistically significant injury-severity differences between daytime and nighttime before, during and after the COVID-19 pandemic. Out-of-sample simulation results suggest that improving the visibility of bicyclist through mandated reflectivity, improved roadway illumination, undertaking public awareness campaigns relating to nighttime bicyclist safety, and vulnerable road user detection sensors in vehicles can all contribute to substantially improving nighttime bicyclist safety.

Risk quantification and prediction of non-driving-related tasks on drivers' critical intervention behavior in autonomous driving scenarios

For autonomous driving, drivers’ intervention may be required when vehicles fail or are in a dilemma to detect emergent and unprogrammed events. In such situations, non-driving related tasks may have a great impact on the safety of drivers’ critical intervention behavior thus leading to traffic accidents. Therefore, exploring the impacts of non-driving-related tasks on drivers’ critical intervention behavior, quantifying and predicting the corresponding risks have become important. In this paper, driving simulation experiments are carried out to obtain the vehicle driving state data and visual behavior information of drivers during the autonomous driving scenarios that require critical interventions. To construct the risk quantification model for drivers’ critical intervention behavior, the fuzzy comprehensive evaluation method and the criteria importance though intercriteria correlation (CRITIC) weighting method are employed. Then, for risk prediction, a model is constructed based on the visual behavior information before the occurrences of intervention. Multivariate logistic regression (MLR) and support vector machine are compared. The results show that non-driving tasks significantly postpone driver's critical intervention responses, increasing crash risks of the driving. For prediction, SVM performs better than the MLR in terms of metrics including the precision, the recall, and the overall accuracy. This paper examines the risks during situations requiring drivers’ critical intervention, associated with different non-driving tasks, which has remained much unexplored in the previous research. The methodology of this paper can be applied to smart vehicle systems in alerting vehicles for take-over reactions, with recognizing and predicting potential risks.

Automated and Efficient Hotel Management System

The hotel administrator and receptionist can manage all hotel operations online using the desktop-based application known as the hotel management system. Being a very busy individual, the hotel administrator or receptionist does not have time to sit down and oversee all actions manually on paper. He now has the ability and freedom to control the complete system from a single web platform thanks to this programme. It oversees and keeps up the hotel's records of guests, accommodations, staff, and drivers. The project aims to keep the daily state of customer admission/vacation, employee list, room data, etc. The primary goal of this project is to offer hotels a way to handle most of their operations using computerized processes. This software will assist the administrator in managing client information, room assignment information, payment information, driver information, reserving rooms of two distinct types, etc. With the aid of the NetBeans IDE, it is constructed in the Java programming language. Java is used for its frontend and MySQL for its backend.

DrunkChain: Blockchain-Based IoT System for Preventing Drunk Driving-Related Traffic Accidents

Traffic accidents present significant risks to human life, leading to a high number of fatalities and injuries. According to the World Health Organization’s 2022 worldwide status report on road safety, there were 27,582 deaths linked to traffic-related events, including 4448 fatalities at the collision scenes. Drunk driving is one of the leading causes contributing to the rising count of deadly accidents. Current methods to assess driver alcohol consumption are vulnerable to network risks, such as data corruption, identity theft, and man-in-the-middle attacks. In addition, these systems are subject to security restrictions that have been largely overlooked in earlier research focused on driver information. This study intends to develop a platform that combines the Internet of Things (IoT) with blockchain technology in order to address these concerns and improve the security of user data. In this work, we present a device- and blockchain-based dashboard solution for a centralized police monitoring account. The equipment is responsible for determining the driver’s impairment level by monitoring the driver’s blood alcohol concentration (BAC) and the stability of the vehicle. At predetermined times, integrated blockchain transactions are executed, transmitting data straight to the central police account. This eliminates the need for a central server, ensuring the immutability of data and the existence of blockchain transactions that are independent of any central authority. Our system delivers scalability, compatibility, and faster execution times by adopting this approach. Through comparative research, we have identified a significant increase in the need for security measures in relevant scenarios, highlighting the importance of our suggested model.

Validity of Variable Message Sign Information: Is It Influenced by Drivers’ Short-Term Memory?

Variable message signs (VMSs), as a key component of intelligent transportation systems, have been frequently used in the management of urban roads to provide drivers with real-time traffic information. Nevertheless, a lack of unified regulations for VMS design, makes it difficult to accurately determine the validity of VMS information. In practice, inappropriately designed VMSs (e.g., VMSs overloaded with information and long setting distances) are common. In this study, laboratory simulation trials were conducted to assess VMS information validity in relation to the short-term memory (STM) capacity of drivers. Specifically, drivers capacity to easily obtain and respond correctly to valid VMS information based on memorized target information. Sixty participants completed the trials and pre-/postquestionnaires. Subjective evaluation, dynamic information acquisition rate, accuracy, and memory reliability were analyzed to evaluate their relationship with VMS information validity. The results confirmed that STM considering the information demand rate significantly affected the validity of the VMS information. Information validity deteriorated as the information volume and VMS setting distance increased. Reasonable validity was found when memory reliability ranged between 0.85 and 1.5 and the information volume was no more than 90 bits, corresponding to a subjective evaluation of 1, an accuracy of at least 80%, and a suggested STM time of 43.46 s. These criteria would satisfy driver information demand and prevent information redundancy or wasting of resources. These findings provide a basis for determining the thresholds for VMS information to promote practical and user-friendly VMS designs on urban roads.