Driver Information Research Articles

On the importance of working memory in the driving safety field: A systematic review

In recent years, many studies have used poor cognitive functions to explain risk safety differences among drivers. Working memory is a cognitive function with information storage and attentional control that plays a crucial role in driver information processing. Furthermore, it is inextricably linked to parameters such as driving performance, driving eye movements and driving neurophysiology, which have a significant impact on drivers' risky behavior and crash risk. In particular, crash risk is a serious risk to social safety and economic development. For this reason, it is necessary to understand how risk-related working memory affects driving so that pre-driving safety pre-training programs and in-vehicle safety assistance systems for driving can be developed accordingly, contributing to the development of semi-autonomous vehicles and even autonomous vehicles. In this paper, a systematic search of the literature over the past 23 years resulted in 78 articles that met the eligibility criteria and quality assessment. The results show that higher working memory capacity, as measured neuropsychologically, is associated with more consistent and safer driving-related parameters for drivers (e.g., lane keeping) and may be related to pupil dilation during risk perception while driving, which is associated with driving outcomes (tickets, pull-overs, penalty points and fines,and driving accidents) is closely related to the perceived usefulness of the human–machine interface, reaction time, standard deviation of steering wheel corners, etc. when the autonomous driving takes over. In addition, higher working memory load interference was associated with more inconsistent and unsafe driving-related parameters (including but not limited to eye movements, electrophysiology, etc.), with higher working memory load being associated with easier driver concentration on the road, faster heart rate, lower heart rate variability, and lower oxyhemoglobin (OxyHb) and deoxyhemoglobin (DeoxyHb). Only a limited number of studies have simultaneously investigated the relationship between working memory capacity, working memory load and driving, showing an interaction between working memory capacity and working memory load on lane change initiation and lane change correctness, with working memory capacity acting as a covariate that mediated the effect of working memory load on braking reaction time. In addition, working memory-related cognitive training had a transfer effect on improving driving ability. Overall, working memory capacity determines the upper limit of the number of working memory attention resources, while working memory load occupies part of the working memory attention resources, thus influencing information perception, decision judgment, operational response, and collision avoidance in driving. Future effective interventions for safe driving can be combined with capacity training and load alerting. These findings contribute to our understanding of the role of working memory in driving and provide new insights into the design of driver safety training programs and automated driving personalized in-vehicle safety systems and roadside devices such as signage.

Accurate Prediction of Cancer Prognosis by Exploiting Patient-Specific Cancer Driver Genes

Accurate prediction of the prognoses of cancer patients and identification of prognostic biomarkers are both important for the improved treatment of cancer patients, in addition to enhanced anticancer drugs. Many previous bioinformatic studies have been carried out to achieve this goal; however, there remains room for improvement in terms of accuracy. In this study, we demonstrated that patient-specific cancer driver genes could be used to predict cancer prognoses more accurately. To identify patient-specific cancer driver genes, we first generated patient-specific gene networks before using modified PageRank to generate feature vectors that represented the impacts genes had on the patient-specific gene network. Subsequently, the feature vectors of the good and poor prognosis groups were used to train the deep feedforward network. For the 11 cancer types in the TCGA data, the proposed method showed a significantly better prediction performance than the existing state-of-the-art methods for three cancer types (BRCA, CESC and PAAD), better performance for five cancer types (COAD, ESCA, HNSC, KIRC and STAD), and a similar or slightly worse performance for the remaining three cancer types (BLCA, LIHC and LUAD). Furthermore, the case study for the identified breast cancer and cervical squamous cell carcinoma prognostic genes and their subnetworks included several pathways associated with the progression of breast cancer and cervical squamous cell carcinoma. These results suggested that heterogeneous cancer driver information may be associated with cancer prognosis.

Smart Eye – The Vehicle Surveillance System

Most vehicle checkpoints have a security officer who checks the entry information by inspecting the identification document as part of the entry process for visitors, staff, and others entering the region. Given that this process is manual and involves validation and registration, there is a high likelihood that human error will be present. Manually entering admission and exit data and recording it on a register can be a difficult and time-consuming operation for security personnel at the checkpoint. It is challenging to disseminate the information entered because it is on paper. Thus we need an automatic system, which will reduce manual entry process and minimize the security personal effort. When a vehicle reaches the vicinity of the check point, the security personnel can scan the vehicle number plate and the drivers face and verify their identity from the database and will also store the information. Through this system, security and authorized personnel will be able to keep track of vehicle movement along with its drivers information. The suggested approach will shorten check-in and check-out times while also suggesting additional advantages for managing parking and traffic.

Weather Conditions and Telematics Panel Data in Monthly Motor Insurance Claim Frequency Models

Risk analysis in motor insurance aims to identify factors that increase the frequency of accidents. Telematics data is used to measure behavioural information of drivers. Contextual variables include temperature, rain, wind and traffic conditions that are external to the driver, but may also influence the probability of having an accident, as well as vehicle and personal characteristics. This paper uses a monthly panel data structure and the Poisson model to predict the expected frequency of claims over time. Some meteorological information is included. Two types of claims are considered separately: only those related to at-fault third-party liability accidents, and all types of claims including assistance on the road. A sample of drivers in Spain in 2018–2019 is analysed with information on claiming frequency per month. Drivers were observed for seven months. Our analysis is novel because monthly summaries of telematics information are combined with weather data in a panel structure, revealing that external factors affect the expected claims frequencies. Reckless speeding behaviours and intense urban circulation increase the risk of an accident, which also increases with windy conditions.

Assessing Ecosystem State Space Models: Identifiability and Estimation

Hierarchical probability models are being used more often than non-hierarchical deterministic process models in environmental prediction and forecasting, and Bayesian approaches to fitting such models are becoming increasingly popular. In particular, models describing ecosystem dynamics with multiple states that are autoregressive at each step in time can be treated as statistical state space models (SSMs). In this paper, we examine this subset of ecosystem models, embed a process-based ecosystem model into an SSM, and give closed form Gibbs sampling updates for latent states and process precision parameters when process and observation errors are normally distributed. Here, we use simulated data from an example model (DALECev) and study the effects changing the temporal resolution of observations on the states (observation data gaps), the temporal resolution of the state process (model time step), and the level of aggregation of observations on fluxes (measurements of transfer rates on the state process). We show that parameter estimates become unreliable as temporal gaps between observed state data increase. To improve parameter estimates, we introduce a method of tuning the time resolution of the latent states while still using higher-frequency driver information and show that this helps to improve estimates. Further, we show that data cloning is a suitable method for assessing parameter identifiability in this class of models. Overall, our study helps inform the application of state space models to ecological forecasting applications where (1) data are not available for all states and transfers at the operational time step for the ecosystem model and (2) process uncertainty estimation is desired.

Aggregative Game for Distributed Charging Strategy of PEVs in a Smart Charging Station

This paper proposes a charging strategy for plug-in electric vehicles (PEVs) in a smart charging station (SCS) that considers load constraints and time anxieties. Due to the rapidly growing load demand of PEVs and the load capacity investments in infrastructure, PEV charging needs to be subject to overload limits, beyond which failures can occur. The time anxiety is presented to address some of the uncertainties that may arise while charging PEVs. Under an aggregative game framework, this paper constructs a price-driven charging model to minimize costs by choosing the optimal charging strategy. Meanwhile, since the driver information is an aggregated item in the PEV cost function, the drivers’ privacy can be protected. Then, a distributed reflected forward–backward (RFB) splitting method is developed to search for the generalized Nash equilibria (GNE) of the game. The convergence of the proposed algorithm and the effectiveness of the charging strategy are verified by the detailed simulation and results.

Web-based Bus Tracking System in the Internet of Things IoT

Public transportation has become integral to daily life, as individuals rely on it to commute between their homes, workplaces, and colleges. However, unnecessary waiting times during transport often result in time wastage. Students frequently find themselves in lines, longing to know the whereabouts of buses and their estimated arrival times at the bus stop. To address these issues, this study presents the development of a web-based system that highlights the routes taken by each bus during its journey. Integrated with Google Maps, the system enables students to conveniently access the routes and schedules of buses. The system provides users with information, including real-time updates on the bus's live location, displayed on the map interface. The system offers additional details about the bus driver, such as their names, phone numbers, bus numbers, and start and end times of their shifts. Users can access this information from anywhere, whether they are at home, work, or college, utilizing the web-based application and an internet connection. Also, a QR code scanning feature is available at bus stops, allowing people to quickly access the desired information. By implementing this system, users, particularly students, gain enhanced visibility into bus routes and schedules, enabling better planning and minimizing waiting times. The web-based platform offers convenience and accessibility, empowering users to make informed decisions about their journeys. The integration of live bus tracking, driver information, and QR code scanning improves the overall user experience and provides a comprehensive solution for public transportation users.

Factors Influencing Driver’s Psychological Vulnerability Judgment When Sharing the Road With Driverless Vehicles

To judge whether drivers of manned vehicles sharing the road with driverless vehicles think they are in a vulnerable state and find out what makes drivers feel they will be in a state we called “driver’s psychological vulnerability judgment”, this paper conducted a questionnaire to collect information about the attitude, perceived usefulness, trust, perceived risk, and demographic information of drivers in a hypothetical situation involving driving on the same road as driverless vehicles. Our goal was to identify areas where the drivers felt that they would be in a “vulnerable psychological state”, i.e., that they would be more vulnerable to making poor psychological judgments. A total of 945 valid questionnaires were collected through Credamo questionnaire survey platform. The survey results indicated that 43.7 % of the respondents believed that they would be in a vulnerable state in mixed traffic competition, 30.2 % of the respondents did not know whether they would be in a vulnerable state. Further, women, people with a higher education, people with a more aggressive driving personality, older people, and those with more driving experience were more inclined to think that they would not be in a vulnerable state. Attitude, trust, and perceived usefulness all had positive impacts on driver’s psychological vulnerability judgment, and perceived risk had a negative impact. Therefore, the early promotion of driverless technology should give priority to people with a higher education, more driving experience, older age, and more aggressive driving personality, and focus on attitudes towards this technology, and perceived usefulness, trust, perceived risk.

Study on Improving the Safety and Performance of Vehicle Traffic Assistance Systems

More intricate applications for road safety have come from advances in information technology. These systems offer a lot of potential for improving road transportation. The integrated method provided in this research addresses two primary topics: protection and performance. As a result, it is recommended that Vehicle Traffic Assistance (VTA) for rural and intercity contexts be developed and implemented. VTA is made up of an electronic control unit (ECU) that receives data from cameras positioned strategically around the vehicle to recognise traffic conditions and deliver data to the ECU. In the event that the driver deviates from the traffic laws, the ECU compares the input data from the cameras to reference data stored in the ECU memory and assists the driver by offering instructions through the output speaker device. VTA not only assists drivers, but it also monitors and prevents them from breaking traffic laws. It also ensures safety by personalising driver information in the ECU to avoid car theft.

A provably secure key transfer protocol for the fog-enabled Social Internet of Vehicles based on a confidential computing environment

In recent years, the Social Internet of Vehicles (SIoV) has been widely used in transportation, dramatically enhancing people's lifestyles. SIoV can collect and process traffic information in real-time, alleviate traffic congestion, and realize smart transportation in smart cities. However, the data generated by vehicles moving with servers are transmitted on public channels, so the sensitive information of drivers can be easily intercepted and tampered with by attackers. In addition, the massive amount of real-time data generated by these vehicles, devices, drivers, passengers, and other social relationships impose a tremendous load on servers. Therefore, in this paper, we propose a secure authentication protocol using confidential computing environments. Moreover, we also innovatively offer a better key transfer phase to reduce the computing pressure on cloud servers. We use the Real-Oracle Random model to demonstrate the proposed protocol is provably secure. Experimental evaluation shows that the proposed protocol has excellent computational and communication performance.

Smart City Garbage Monitoring System

Abstract: In Sri Lanka, garbage dumping has long been a problem. The regional organizations have made various attempts to address this issue. But unfortunately, no appropriate action has been taken thus far. As a consequence, there are several environmental issues as well as human health issues, particularly among children. As a result, we have suggested some approaches to resolving these issues so that we can advance the nation. The prime objective of the suggested system is to provide a nation free from waste, and the suggested solutions support this objective as well. The suggested approach will benefit the municipality council in a variety of ways, reducing both labour and capital costs. The proposed system will calculate the amount of garbage that has been piled up effectively, giving truck drivers information that can be tracked via a mobile application. The system will warn pedestrians if they attempt to dump garbage out of the bin and also if they pile particular garbage in a different type of a bin other than designated bin. This will aid road cleaners in efficiently collecting garbage other than focusing more collecting trash from the roads. It will improve the garbage segregation process because the designated types of bins are also kept separately and can be utilized by the local bodies as they require, which helps to achieve our objective of this system

Effect of Situation Kinematics on Drivers’ Rear-End Collision Avoidance Behaviour—A Combined Effect of Visual Looming, Speed, and Distance Analysis

Considering the large proportion of rear-end collisions occurring in our daily life and the severity it may lead to, the objective of this study was to investigate the effect of situation kinematics on drivers’ rear-end collision avoidance behaviour after brake onset. A wide range of lead vehicle deceleration scenarios were designed based on driving simulator experiments to collect drivers’ deceleration behaviour data. Different from measures (e.g., speed, the lead vehicle’s deceleration et al.) often adopted in previous studies, a visual looming-based measure at different time points was calculated combined with analysis of speed and distance to quantify situation kinematics in this study. The Spearman’s nonparametric rank correlation test was firstly conducted to examine the correlation between visual looming-based metrics and related deceleration behaviour. The mixed model was performed on drivers’ brake jerk and maximum deceleration rate, while the logistic model was then performed to predict the probability of the occurrence of rear-end collisions. Spearman’s nonparametric test showed that both deceleration ramp-up and drivers’ maximum deceleration rate increase significantly as the looming traces increase faster. Results of the logistic model indicated that the probability of occurrence of a potential collision might be higher if the situation at the brake onset is quite urgent and braking is moderate. It was demonstrated that both drivers’ deceleration ramp-up and maximum deceleration rate could be highly kinematic-dependent, and visual looming, driving speed, and distance can be useful information for drivers to take relative deceleration actions.

A mechanistic approach to include climate change and unplanned urban sprawl in landslide susceptibility maps

Empirical evidence shows that climate, deforestation and informal housing (i.e. unregulated construction practices typical of fast-growing developing countries) can increase landslide occurrence. However, these environmental changes have not been considered jointly and in a dynamic way in regional or national landslide susceptibility assessments. This gap might be due to a lack of models that can represent large areas (>100km2) in a computationally efficient way, while simultaneously considering the effect of rainfall infiltration, vegetation and housing. We therefore suggest a new method that uses a hillslope-scale mechanistic model to generate regional susceptibility maps under changing climate and informal urbanisation, which also accounts for existing uncertainties. An application in the Caribbean shows that the landslide susceptibility estimated with the new method and associated with a past rainfall-intensive hurricane identifies ~67.5 % of the landslides observed after that event. We subsequently demonstrate that the hypothetical expansion of informal housing (including deforestation) increases landslide susceptibility more (+20 %) than intensified rainstorms due to climate change (+6 %). However, their combined effect leads to a much greater landslide occurrence (up to +40 %) than if the two drivers were considered independently. Results demonstrate the importance of including both land cover and climate change in landslide susceptibility assessments. Furthermore, by modelling mechanistically the overlooked dynamics between urban growth and climate change, our methodology can provide quantitative information of the main landslide drivers (e.g. quantifying the relative impact of deforestation vs informal urbanisation) and locations where these drivers are or might become most detrimental for slope stability. Such information is often missing in data-scarce developing countries but is key for supporting national long-term environmental planning, for targeting financial efforts, as well as for fostering national or international investments for landslide mitigation.

AR4CAD

Infrastructure-mounted sensors that monitor roads can provide essential information for manual drivers and automated vehicles, e.g., positions of other vehicles occluded by buildings. However, human drivers and passengers have to trust and accept their use. This raises the question of how trust can be increased in such a scenario. One important factor for this is understanding the available information, including its quality and, for passengers of automated vehicles, the actions planned based on it. For this, augmented reality is a promising visualization technology because it can present the relevant information integrated into the physical world. Thus, this work develops a taxonomy of augmented reality visualizations for connected automated and manual driving. It is intended to classify and compare existing visualizations, identify novel visualizations, and provide a common language for discussions. The use case infrastructure-supported automated driving is explored by suggesting augmented reality visualizations to inform passengers of automated vehicles and are intended to increase trust. They present information available from infrastructure and onboard sensors as well as the driving decisions based on it. Finally, we evaluated the visualizations' influence on trust in an automated vehicle by conducting a driving simulator study (N=18). Results indicate a high dependency of trust on presenting driving decisions and information on road users but less on location-specific information.

Driver profiling: The pathway to deeper personalization

Defining driver behavior profiles is an essential step to create unique and tailored driving experience. Depending on the driver information used, two types of profiles can be distinguished. The driver’s preferences in terms of car settings constitute the static profile while his driving behavior constitutes the dynamic profile. In this paper, instead of profiling the driving behavior as one of classical behavior classes (e.g. aggressive, normal, and drowsy), we propose a more personalized approach, where the dynamic profile is represented as a graph, automatically built using the driver’s data. The graph states are learned from the driver data using clustering techniques, namely map matching clustering for GPS data and k-means clustering for kinematics data. To avoid duplicate and overlapping clusters, rules for cluster harmonization are defined. The feasibility of our approach was demonstrated, by applying our framework to two driving datasets, UAH-Driveset and Hcilab. The quality of clustering is later validated using the leave one out cross validation method and two newly defined metrics, namely FDR and RoC, measuring the rate of undiscovered behaviors and the stability of the clusters, respectively. The obtained results show that the proposed approach has a low FDR (an average of 8% for Hcilab dataset and 6% for UAH-driverset).

Driver's attitudes and preferences toward connected vehicle information system

Connected vehicle (CV) and vehicle-to-everything (V2X) technologies enhance connectivity among vehicle, road user, and road infrastructure and can provide timely and concisely coordination information among drivers. Currently, there are far more studies on the technical aspects of V2X than on the demands of users. This study investigated the attitudes and preferences of drivers concerning the design of connected vehicle information system (CVIS) in this context. Focus group discussions followed by a questionnaire survey were conducted to gather driver's attitudes and preferences information. Results indicate that participants believed CVISs would help improve the efficiency of roadway communication, thereby improving safety, efficiency, and convenience of the overall traffic system. Visual warning signals and descriptive verbal speech were preferred over tactile warnings. Safety-related information (e.g., rescue services, reminding vehicle malfunction, and information about surroundings hazards) was valued most. Furthermore, age, gender, risk perception, privacy expectations, and technology inclination played essential roles in associating the attitudes toward CVISs. The outcome of this research provides an overview of the opinion of Chinese drivers toward CVISs and suggests practical implications regarding the design of CVISs for intelligent transportation.

Comparing the key contributory factors for driver injury severities in opposite-direction collision accidents

Opposite-direction collision (ODC) accidents are more harmful than other collision types and often cause severe casualties and property losses. Based on the ordered discrete choice model, this study selects the data of 19623 ODCs from January 2010 to June 2018 in Victoria, Australia. The ordered logit model, the random-parameters ordered logit model and the heteroscedastic ordered logit (HOL) model are used to quantify the driver injury severities in ODC accidents. The study shows that HOL model can exploit more potential injury severity information of drivers involved from the original ODC accident data properly. The model results showed that some variables (e.g. elderly drivers, female, high speed limits of more than 50 km/h, number of injuries) increases the possibility of severe and fatal injury outcomes in ODC accidents significantly. In contrast, some variables, including give way sign control, non-darkness conditions (i.e. daytime, dusk/dawn, night lighting), slippery pavement, non-frontal collision types, number of individuals involved, and types of vehicles involved (small truck, bus/passenger car, large trucks/heavy vehicles, other), significantly decrease the serious injury and fatality probabilities in such accidents. Based on the model's findings, countermeasures are recommended, such as ongoing safe driving education, enforcing stricter speed limit rules, and setting up warning signs and lighting facilities on dangerous locations and segments.

A Survey on Driver Behavior Analysis From In-Vehicle Cameras

Distracted or drowsy driving is unsafe driving behavior responsible for thousands of crashes every year. Studying driver behavior has challenges associated with observing drivers in their natural environment. The naturalistic driving study (NDS) has become the most sought-after approach, since it eliminates the bias of a controlled setup, allowing researchers to understand drivers’ behavior in real-world scenarios. Video recordings collected in NDS research are incredibly insightful in identifying driver errors. Computer vision techniques have been used to autonomously analyze video data and classify drivers’ behavior. While computer vision scientists focus on image analytics, NDS researchers are interested in the factors impacting driver behavior. This survey paper makes a concerted effort to serve both communities by comprehensively reviewing studies, describing their data collection, computer vision techniques implemented, and performance in classifying driver behavior. The scope is limited to studies employing at least one camera observing the driver inside a vehicle. Based on their objective, papers have been classified as detecting low-level (e.g. head orientation) or high-level (e.g. distraction detection) driver information. Papers have been further classified based on the datasets they employ. In addition to twelve public datasets, many private datasets have also been identified, and their data collection design is discussed to highlight any impact on model performance. Across each task, algorithms employed and their performance are discussed to establish a baseline. A comparison of different frameworks for NDS video data analytics throws light on the existing gaps in the state-of-the-art that can be addressed by future computer vision research.

A New Method of Vehicle Positioning Using Bumps and Road Surface Defects

This paper presents the first usage of road surface defects as a means of vehicle position detection. Whilst several applications are possible, this work focuses on use in Formula E racing, where several driver information systems depend heavily upon accurate vehicle position estimation, including energy management advice and split time information, and where use of common positioning systems such as GPS is forbidden. Teams currently estimate the position on track by integrating vehicle speed, but this is susceptible to error accumulation throughout a lap, diminishing the precision and value of driver information systems. This work presents a method to improve the vehicle’s position estimate by detecting bumps in the road surface using suspension damper displacement data, an approach which is novel because it is independent of common positioning techniques such as GPS. These bumps are used as positionally-fixed checkpoints around the track, allowing the positional estimate to be regularly corrected, mitigating drift in the original estimated position. Results of the bump detection algorithm developed show for the first time that this technique can pinpoint the vehicle position with a precision of 1.41m standard deviation, with scope for further improvement. This result is significant for positioning surface vehicles where other more standard techniques are precluded. In the Formula E application the approach is found to improve the precision (consistency) of the vehicle positional estimate for large parts of the circuit, which will allow higher quality and more reliable information to be given to the driver, thereby giving a competitive advantage.

Exploring Uber Taxi Application Using the Technology Acceptance Model

The goal of this study was to investigate the accountability of the technology acceptance model (TAM) for Uber taxi applications. As antecedents of usefulness, this study selected three elements: time information, price information, and driver information. Data was collected using a survey on Amazon Mechanical Turk. The survey participants were users of the Uber taxi application. The number of valid observations for the data analysis was 412. For data analysis, frequency analysis, confirmatory factor analysis, correlation matrix, and structural equation modeling were utilized. The results show that the usefulness is significantly influenced by time and driver information. They further indicate that ease of use positively affects both usefulness and attitude. In addition, usefulness significantly determines attitude, and attitude toward the Uber taxi application exerts a substantial effect on intention to use. This study contributes to the literature by demonstrating the explanatory power of TAM using the Uber taxi application as a research subject.