Driver Speed Research Articles

Adapting V ISA Technology: Driver Behaviour along Interchange Ramp and Merging/Diverging Terminals

An original in vehicle Intelligent Speed Adaptation System for Visibility (V-ISA) was designed to promote compliance with real-time speed management. The functionality of V-ISA is based on the prevailing sight conditions along the road, and operates in two variants: (i) providing visual information, and (ii) vehicle speed intervention. A road scenario with the driver performing merging and diverging manoeuvres in a motorway section was designed. A within-subject experiment involved 32 participants and a vehicle equipped with the two variants and the system off (baseline condition) under two traffic flow conditions. V ISA had a significant positive effect on the drivers’ longitudinal performance along ramps. This change in behaviour along ramps had no effect on merging and diverging manoeuvres. V ISA had a positive impact on driver speed behaviour in such complex road environment and assisted drivers to modulate the operating speed towards the safe dynamic limits.

Modeling and stability analysis of car-following behavior for connected vehicles by considering driver characteristic

Research of car-following behavior is very important to alleviate traffic congestion and ensure traffic safety. To describe the car-following behavior of connected vehicles and restore the real driving environment, this paper presents an improved car-following model for connected vehicles by considering driver characteristic and speed information of multiple vehicles, which reflects the interaction between adjacent connected vehicles and the influence of driver characteristic on the stability of car-following. The linear stability analysis and nonlinear stability analysis prove that the improved model is effective and can promote the stability of traffic flow more than other models. In addition, the numerical simulations show that the new model performs better in eliminating disturbances than other models. Finally, the parameters of proposed model are calibrated based on NGSIM data. The results show that the new model performs well in car-following process, keeping a safe distance from the leader vehicle without sudden acceleration and deceleration. The new model also can predict the acceleration behavior of the leader vehicle after emergency brake. In summary, the model proposed in this paper can be used as active safety technology to prevent collision accidents, or as a user-defined function or model in the traffic simulation software, or as car-following strategy in driverless algorithms.

Assessment of Reasons for Driver Speeding and Estimation of Penalty Probability

Road safety is a global issue that requires a scientific approach to develop safety research methodologies that lead to sound conclusions. Regarding driver behavior and safety, speed is one of the leading causes of traffic accidents, injuries, and deaths. Speed is, therefore, one of the most studied issues related to road safety. The main objective of this study is to identify the frequency and reasons for a driver speeding in Baghdad city. In addition, drivers have been evaluated in terms of penalty probabilities, penalties imposed, and their type. Finally, this paper also investigated drivers' opinions on the effectiveness of such penalties in changing speed behavior. Eight hundred sixteen drivers were the studied sample in Baghdad city for three years. As a result, it was found that about one-third of the drivers were either driving too fast all the time or sometimes. Among the particular reasons, the most common was the rush, not realizing the speed, limits were too low, or the conditions allowed it. Similarly, the chances of getting caught are considered limited. Additionally, half of the penalized drivers said their speed habits changed due to such penalties. A speeding driver is fully aware that they are violating traffic rules. Approximately 80% of the circumstances for speeding behavior were intended. They are unaware of the dangers of speeding, citing speed limits that are too low and that it is customary when road conditions permit.

Impact of an exclusive narrow automated vehicle lane on adjacent lane driver behavior

This study contributes to understanding the behavioral impacts of infrastructure adaptation to Automated Vehicles (AVs) on non-AV drivers. It attempts to answer the question of how a narrow (9 ft) lane dedicated to AVs would affect the behavior of drivers in terms of safety measures who are driving in the adjacent lane to the right. To this end, a custom designed driving simulator world was designed mimicking the Interstate 15 smart corridor in San Diego. A group of participants were assigned to drive next to the simulated 9 ft narrow lane while a control group were assigned to drive next to a regular 12 ft AV lane. Behavior of drivers was analyzed by measuring the mean lane position, mean speed, and the mental effort. In addition to AV lane width, AV headway, gender, and right lane traffic were taken into consideration in the experimental design to investigate interaction effects. The results showed no significant differences in speed and mental effort of drivers while indicating significant differences in lane positioning. Although the overall effect of AV lane width was not significant, there were some significant interaction effects between lane width and other factors (i.e., driver gender and presence of traffic on the next regular lane to the right). In all the significant interactions, there was no case in which those factors stayed constant while AV lane width changed between the groups indicating that the significant difference might be stemmed from the other factors rather than the lane width. However, the trend observed was that drivers driving next to the 12 ft lane had better lane centering compared to the 9 ft lane. The analysis also showed that while in general female drivers tended to drive further away from the 9 ft lane and performed worse in terms of lane centering, they performed better than male drivers when right lane traffic was present.

WITHDRAWN: 3 Axis Gyro Accelerometer & Artificial Intelligence based Enhancement of GPS Accuracy

The accuracy of positioning is a problem for location-based applications when using a cheap GPS receiver (GPS). This research, however, provides an alternative literature review on the topic of how to enhance the positioning precision of inexpensive GPS receivers used in real-time navigation. Scientists have developed a method for precisely estimating a vehicle's location based on GPS coordinates (latitude, longitude, time, and velocity) by combining information about the vehicle's heading, its current speed, and the distance between two waypoints. Coordinate translation, as well as checks for invalid data, and utilization of the previously estimated valuable reference point, all contribute to an increase in precision. As such, a GPS simulation can be used to assess the reliability of GPS velocity readings. Thanks to GPS, the researcher can track the driver's location, speed, and acceleration in real time. A driver's propensity for taking chances can be uncovered in a GIS setting. Second, researchers can get high-resolution data on vehicle activity just before an accident, which makes it easier to estimate speeds with less error and bias. In this paper, we present a double-antenna method for improving GPS precision by utilizing both an active antenna and a ground plane antenna. The author has proposed improvement in GPS Receiver Accuracy Using Antenna Optimization Techniques like Ground Plane Enhancement for SNR Improvement along with Sensor Fusion combined with Artificial Intelligence. Sensor Fusion Primarily comprises of 3-Axis Accelerometer With 3-Axis Gyroscope forming an IMU, which along with AI, is used to predict navigation parameters in absence of GPS Signal, and when GPS drop communication with satellite due to any cause, Once GPS signal is lost with any cause then this change in delta latitude and delta longitude will compute by our trained artificial neural network, then according to this interpolation, artificial neural network calculates latitude and longitude.

The probable excitation mechanism of kink oscillations of coronal loops

Oscillations in various structures of the solar atmosphere, such as transverse (kink) oscillations of coronal loops, can be used in seismology. Transvers kink oscillations of coronal loops are often accompanied by solar flares. Despite the intensive study of kink oscillations of coronal loops in recent years, the excitation mechanism of these oscillations are still not known. In this paper, we aim to clarify the excitation mechanisms of transverse oscillations of coronal loops. For this purpose, first 458 oscillation events were identified by the Atmospheric Imaging Assembly (AIA) onboard the Solar Dynamics Observatory (SDO) during its first ten years (2010–2019) with the use of the Helioviewer, JHelioviewer and Heliophysics Events Knowledgebase (HEK). Then, the association of these oscillation events with probable mechanism for exciting the kink oscillations such as flares, lower coronal eruptions and plasma ejections, and coronal mass ejections bursts were listed. Finally, about 138 suitable kink oscillations out of 485 oscillations with high-amplitude, long oscillation period and visible through the naked eye that were accompanied with other probable excitation mechanism of kink oscillations, were selected. This statistical analysis of the transverse oscillation coronal loops showed that that 102 of these 138 oscillation events (74 %) were associated with lower coronal eruptions or plasma ejections. About 38 oscillations out of 138 transverse oscillations (27.5%) were associated with coronal mass ejections/eruption. Also, 65 events (47 %) were associated with flares. The required speed of hypothetical drivers of transverse oscillations were calculated. The magnitude values of calculated speeds for shock wave of flares were found to be lower than 500±100 km/s in 87% of the cases. Also, the magnitude values of speeds for lower coronal mass eruption/ejection were obtained to be lower than 500±125 km/s in 94% of the cases. The magnitude values of these speeds are acceptable for lower coronal mass eruption/ejection. But, such low speeds do not favor the association of the oscillation excitation with a shock wave of flares, as usually assumed. Also, statistical analysis of start time and time difference of hypothetical drivers of transverse oscillations showed that there is no clear correlation between them. The results of this study indicated that shock wave of flares cannot be the main cause of transverse oscillations of coronal loops. So, this analysis shows that the most probable excitation mechanism of the kink oscillations of coronal loops are eruptions or plasma ejections rather than the blast shock waves ignited by flares. ‎

Optimized Wiper Design using Computational Fluid Dynamics

This paper presents the robust use of Computational Fluid Dynamics (CFD) techniques as complement to wind tunnel testing for the performance assessment of rain water and wiper wash behavior on windscreen surfaces. The objective of this paper is to predict windscreen wiper design performance and its effectiveness with the help of CFD. Clear visibility to the occupants is the key for stress free and safer driving experience, therefore it is important to study the windscreen wiper system performance under different work load conditions. A multi-phase CFD code is used to simulate rain drops and its impingent on the vehicle is modeled with the help of thin liquid film. The wiper blade motion is defined with inputs from multi body dynamics (MBD) considering the driver and passenger side wiper blade speed and extent. Time-dependent results for the wiper blade location, water fluid film spread, and its height on the windscreen, A-pillar, leaf-screen rain gutters were obtained. The CFD results then equated with the physical test data. The calculated water film pattern found to be associated with the observed patterns of the waterways on the test vehicle. Multiple design studies were performed on the CFD model which are also reliable with similar test configurations. From the results, it is concluded that numerical simulation of water behavior on vehicle surfaces is possible, and CFD method is effective tool to assist engineers in envisaging, analyzing, and designing water management systems. A Computational Fluid Dynamics code had been introduced in order to simulate the cleaning performance of the automobile wash. Multi-phase thin film with rigid body motion models were used for this purpose. The objectives of the project were to quantify the water flow, enhance visualization, and develop a CAE methodology which will assist in the product development process.

Technical electrogenerating tools for road facilities: systematics and design specifics

BACKGROUND: Currently the Russian Federation Government has a strong focus to roads safety. This is due to the national project Safe High-Quality Roads. One of tools of pedestrian safety in an urban are road bumps. They are need for drivers speed slow.
 Contrarily world scientists create alternative sources of electrical energy. It led to tools type as technical electrogenerating devices.
 Whereas technical electrogenerating tools have big amount of developments by russian and world scientists. But in modern scientific literature there is no systematic concept about this tools type.
 AIMS: The paper purpose is knowledge summary about technical electrogenerating tools and develop their classification.
 METHODS: Energy of a moving car is accumulated and converted into electrical energy by devices type. Concept of technical electrogenerating tools is based on convertion of energy pulse of speed bump into electrical energy at the moment of car runover. This energy can be used for electricity supply of road infrastructure (crosswalk lighting, road sign ligtht, powering traffic lights).
 RESULTS: The basic classification feature of these tools is device type converting moving car energy into electrical energy: piezoelectric, hydraulic, electromechanical. In turn technical electrogenerating tools with electromechanical converter are classified by criteria: amount of motor, type of transmission mechanism, design of pressing platform and type of generator.
 CONCLUSIONS: The developed classification provides to systematize contributions of russian and world scientists designing devices of technical electrogenerating tools.

Field testing anti-speeding messages

PurposeDetermine whether anti-speeding messages displayed on roadside variable message signage (VMS) influence drivers’ speed choice selections. MethodSpeed detection tubes were installed across a single carriageway 60 km/h limit road section at positions prior to, immediately after, and at a longer distance from VMS display of anti-speeding messages during study Week2. Bi-directional vehicle speed data were collected continuously during the week prior to VMS installation (Week1), throughout the week that the anti-speeding messages were displayed (Week2), and a post-display week (Week3). ResultsOf six separately measured locations, Week2 southbound mean speeds (facing signage) and percent of drivers/riders exceeding the signed speed limit were consistently below those recorded during Week1 for all time periods. Aggregated Week3 (post-VMS) southbound data for all time periods, showed consistent patterns for mean speed and percent of drivers exceeding the signed speed limit, being higher than in Week2 (VMS displayed) but lower than during Week1 (pre-VMS). DiscussionCompared with Week1, messages influenced aggregate driver speed selection during Week2, with a residual positive effect (slower speeds) in Week3. While all three messages had positive effects, differences occurred in relative effectiveness between daytime (school and non-school hours) and night-time periods. Separately disaggregated data revealed differential effects for the three messages. ConclusionsFindings demonstrated the value of implementing theoretically informed message content and provided evidence for the impact that roadside road safety messaging can have on driver speed selection.

The prototype willingness model: An application to adolescent driver speeding

Introduction: Many young drivers are involved in crashes due to speeding. Some studies have used the Prototype Willingness Model (PWM) to explain the risky driving behavior of young people. However, many have measured PWM constructs in a manner inconsistent with its formulation. The PWM asserts that the social reaction pathway is underpinned by a heuristic comparison of oneself with a cognitive prototype of someone who engages in a risky behavior. This proposition has not been comprehensively examined and few PWM studies specifically examine social comparison. The current study investigates intentions, expectations, and willingness to speed by teen drivers using operationalizations of PWM constructs more aligned with their original conceptualizations. Additionally, the influence of dispositional social comparison tendency on the social reaction pathway is examined to further test the original propositions underpinning the PWM. Method: Two hundred and eleven independently driving adolescents completed an online survey including items measuring PWM constructs and social comparison tendency. Hierarchical multiple regression was used to investigate the influence of perceived vulnerability, descriptive and injunctive norms, and prototypes on speeding intentions, expectations, and willingness. A moderation analysis examined the effect of social comparison tendency on the association between prototype perceptions and willingness. Results: The regression models explained substantial amounts of variance in intentions (39%), expectations (49%), and willingness (30%) to speed. There was no evidence that social comparison tendency influences the relationship between prototypes and willingness. Conclusions: The PWM is useful for predicting teenage risky driving. More studies should confirm that social comparison tendency does not moderate the social reaction pathway. However, there may be need for further theoretical development of the PWM. Practical applications: The study suggests that it may be possible to develop interventions to reduce adolescent driver speeding based on manipulation of PWM constructs such as speeding driver prototypes.

Exploring pathways from driving errors and violations to crashes: The role of instability in driving

This study explores how different driving errors, violations, and roadway environments contribute to safety–critical events through instability in driving speed. We harness a subsample (N = 9239) of the naturalistic driving study (NDS) data collected through the Second Strategic Highway Research Program (SHRP2). From a methodological standpoint, we use the safe systems approach relying on path analysis to jointly model outcomes. This accounts for the potential correlation between unobserved factors associated with both instability in driving speed and epoch (video stream) outcomes, i.e., baseline or event-free driving, near-crashes, and crashes. Tobit and ordered Probit regressions are estimated to model the coefficient of variation (COV) of speed and epoch outcomes, respectively. Results from the Tobit model indicate that driving errors and violations are associated with instability in the driving speed of the subject driver (COV of speed). The Probit model reveals that driving errors, violations, and instability in driving speed are associated with higher chances of crashes and near-crashes. Our key finding is that driving errors and violations not only induce event risk directly but also indirectly through instability in driving speed. For instance, recognition errors associate with higher crash risk by 6.78 % but this error is accompanied by instability in driving speed, which further increases event risk by 4.73 %, bringing the total increase in risk to 11.51 %. Moreover, significant correlations were found between unobserved factors reflected in the error terms of the two models. Ignoring such correlations can lead to inefficient parameter estimates. Based on the findings, practical implications are discussed, which can lead to effective countermeasures that effectively reduce crash risk.

How do the type and duration of distraction affect speed selection and crash risk? An evaluation using naturalistic driving data

Distracted driving is among the leading causes of roadway crashes worldwide. However, due to limitations of police-reported crash data, it is often challenging to understand the nature and magnitude of this problem. Distraction has also been shown to affect driver speed selection, which is important as both mean speed and speed variance have substantive impacts on crash risk. This study utilizes naturalistic driving data to investigate the relationship between the engagement in various secondary (non-driving) tasks and driver speed selection under different driving contexts. Separate analyses were conducted for low-speed and high-speed driving environments. Two-way random effects linear regression models were estimated for both speed regimes, while controlling for driver, roadway, and traffic characteristics. The differences were assessed based upon ten types of secondary tasks. In general, engagement in all tasks was found to decrease speeds in high-speed environments while the effects were mixed in low-speed settings. The changes in speeds were much pronounced for secondary tasks that include a combination of visual, manual, and cognitive distractions, such as cell phone use. Among all secondary tasks, an average episode of a driver talking on a handheld cellphone was associated with a 6-mph speed reduction in high-speed environments, but a 3.5-mph increase in low-speed settings. In addition to examining impacts on speed selection, the risk of involvement in crash and near-crash events was also evaluated in consideration of the type and duration of distraction. Interestingly, distractions tended to show similar relationships, in both direction and magnitude, with the risk of involvement in both crash and near-crash events. From a policy standpoint, this study provides further motivation for legislation and other programs aimed at curbing distracted driving.

Analyzing Drivers’ Speed Behavior on Various Roads in Baghdad City

This study investigates the driver behavior of a certain number of drivers using a questionnaire method. The questionnaire contains a part of drivers' demographics, including age, gender, and the type of transportation most used by the drivers. It was divided into three parts. Each part deals with a specific type of road in Baghdad City: multi-lane, two-lane, and local. The questions were about the number of times they drove the vehicle on each type of road, the speed at which they drove the vehicle and did not cause accidents, the distance traveled during the last week on each type of road, and the number of times the speed limit was exceeded. The most prominent reasons for increasing the speed of drivers were also indicated, and solutions were suggested to reduce the speed of drivers. The results show that the driver's age was considered an important factor in the driver’s behavior. It was found that the older the driver, the more committed he was to the proposed speed limits for each type of road. In addition, spreading public awareness about speed reduction to reduce violations and accidents is vital.

Multi-objective optimization of shield construction parameters based on random forests and NSGA-II

Metro shield construction will inevitably cause changes in the stress and strain state of the surrounding soil, resulting in stratum deformation and surface settlement (SS), which will seriously endanger the safety of nearby buildings, roads and underground pipe networks. Therefore, in the design and construction stage, optimizing the shield construction parameters (SCP) is the key to reducing the SS rate and increasing the safe driving speed (DS). However, optimization of existing SCP are challenged by the need to construct a unified multiobjective model for optimization that are efficient, convenient, and widely applicable. This paper innovatively proposes a hybrid intelligence framework that combines random forest (RF) and non-dominant classification genetic algorithm II (NSGA-II), which overcomes the shortcomings of time-consuming and high cost for the establishment and verification of traditional prediction models. First, RF is used to rank the importance of 10 influencing factors, and the nonlinear mapping relationship between the main SCP and the two objectives is constructed as the fitness function of the NSGA-II algorithm. Second, a multiobjective optimization framework for RF-NSGA-II is established, based on which the optimal Pareto front is calculated, and reasonable optimized control ranges for the SCP are obtained. Finally, a case study in the Wuhan Rail Transit Line 6 project is examined. The results show that the SS is reduced by 12.5% and the DS is increased by 2.5% with the proposed framework. Meanwhile, the prediction results are compared with the back-propagation neural network (BPNN), support vector machine (SVM), and gradient boosting decision tree (GBDT). The findings indicate that the RF-NSGA-II framework can not only meet the requirements of SS and DS calculation, but also used as a support tool for real-time optimization and control of SCP.

Vehicle collisions analysis on highways based on multi-user driving simulator and multinomial logistic regression model on US highways in Michigan

Traffic collision on the highway has become a serious issue because they delay the sustainable development of society. Highway accidents on I-69 have one of the highest crash rates in the U.S. in Michigan and a higher fatality rate than average. This study aimed to identify the factors contributing to highway user crashes on I-69 in Flint, Michigan. This study also aims to find the relationship between the change in the speed limit in certain weather conditions and the number of crashes that are likely to occur as a sequence of this change. A multi-user driving simulator is applied in this study with ten driving simulator scenarios. The multinomial logistic regression (MNL) model has been investigated in this study to identify statistically significant factors that contribute to crashes. The analyses indicated that speeding and speed limits during inclement road/weather conditions significantly affected crashes. Most frequent crashes occur during snowy and icy weather conditions and by changing the speed limit during these weather conditions. Therefore, driver speed is suspected to be the most factor that caused the Vehicle crash on I-69. The method of developing Crash modification factors (CMFs) used in this study will help to reduce crashes and improve traffic system safety performance on highways in Michigan.

Stage-Dependent Activity and Pro-Chondrogenic Function of PI3K/AKT during Cartilage Neogenesis from Mesenchymal Stromal Cells

Differentiating mesenchymal stromal cells (MSCs) into articular chondrocytes (ACs) for application in clinical cartilage regeneration requires a profound understanding of signaling pathways regulating stem cell chondrogenesis and hypertrophic degeneration. Classifying endochondral signals into drivers of chondrogenic speed versus hypertrophy, we here focused on insulin/insulin-like growth factor 1 (IGF1)-induced phosphoinositide 3-kinase (PI3K)/AKT signaling. Aware of its proliferative function during early but not late MSC chondrogenesis, we aimed to unravel the late pro-chondrogenic versus pro-hypertrophic PI3K/AKT role. PI3K/AKT activity in human MSC and AC chondrogenic 3D cultures was assessed via Western blot detection of phosphorylated AKT. The effects of PI3K inhibition with LY294002 on chondrogenesis and hypertrophy were assessed via histology, qPCR, the quantification of proteoglycans, and alkaline phosphatase activity. Being repressed by ACs, PI3K/AKT activity transiently rose in differentiating MSCs independent of TGFβ or endogenous BMP/WNT activity and climaxed around day 21. PI3K/AKT inhibition from day 21 on equally reduced chondrocyte and hypertrophy markers. Proving important for TGFβ-induced SMAD2 phosphorylation and SOX9 accumulation, PI3K/AKT activity was here identified as a required stage-dependent driver of chondrogenic speed but not of hypertrophy. Thus, future attempts to improve MSC chondrogenesis will depend on the adequate stimulation and upregulation of PI3K/AKT activity to generate high-quality cartilage from human MSCs.

How does the mural decoration of the long tunnel sidewall affect the driver's speed control ability?

Since a tunnel is dark and driving conditions are monotonous, drivers are prone to optical illusions, affecting driving safety in tunnels. Tunnel sidewall decorations can provide visual stimulation to prevent or reduce traffic crashes. Driving simulation experiments with a driving simulator and speed perception experiments with E-Prime software are performed to evaluate the influence of tunnel sidewall murals on the speed control of drivers in a long tunnel. Three mural designs (A2: 1.93 Hz, A3: 1.27 Hz, A4: 0.95 Hz) with different frequencies and a control group (no mural, A1) are evaluated. Four indicators of the driver’s speed control (speed, acceleration, stimulation of subjectively equal speed (SSES), and reaction time) are selected. The results show that the driver’s speed is significantly reduced in the middle of the tunnel and near the tunnel exit, and the driver's speed control is significantly enhanced by the murals. It is recommended to install murals in the middle and near the exit of the tunnel for optimal speed control. The SSES shows that tunnel murals affect drivers’ speed perception and alertness. As the frequency of the mural decreases, speed overestimation changes to underestimation, the degree of speed illusion increases, and the reaction time decreases. A difference is observed between the perceived and actual speed, and this difference depends on the mural’s frequency. Thus, choosing an appropriate mural frequency improves the mural’s effect. The results provide a basis for mural design on the sidewalls of long tunnels to improve tunnel safety, as well as a novel approach for speed reduction.

Three-phase AC Induction Motor Speed Control Based on Variable Speed Driver

Massive loss of power is a concern for many countries because of the high power consumption of alternating current (AC) motors. The motor speed should be controlled to alleviate this problem and save more power. This paper proposes a simple simulation for a variable speed driver (VSD) to control the three-phase induction motor speed. The VSD consists of three parts. The converter performs from full bridge diodes to convert single-phase AC voltage into direct current voltage, and then this voltage is filtered by the RL filter and transferred to the last part, which is the inverter. The model was simulated by using MATLAB/Simulink. Findings show that the VSD controller provides sufficient control over the AC induction motor speed.

Simulator assessment of innovative intersection designs on driver speeds and trajectories

Intersections are over-represented in crash statistics internationally, suggesting that treatments targeting intersections could substantially improve road safety. Aligning with a Safe Systems approach, several innovative intersection configurations have been proposed. We evaluated the effectiveness of five designs on reducing speed and modifying conflict angles using a driving simulator. The designs were 1) cut-through, 2) modified restricted squircle, 3) unrestricted squircle, 4) raised approach, and 5) raised intersection. For the higher speed green light condition, speed reductions for vehicles travelling straight through the intersection were seen for all five innovative designs on approach to the intersection and at critical conflict points within the intersection. Within the intersection specifically, speed reductions ranged from 1) 7–8 km/h for the modified restricted squircle, 2) 12.5–16.5 km/h for the unrestricted squircle, raised approach, and raised intersection, and 3) 15–19 km/h for the cut-through. In contrast, speeds for drivers turning right were either not substantially reduced (modified restricted squircle, unrestricted squircle, and raised intersection) or were increased (raised approach and cut-through). Beneficial modification of conflict angles were also observed at conflict points for three of the five designs: cut-through, and two variations of the squircle design. Innovative intersection designs may be effective in reducing intersection crash risk by reducing speeds and conflict angles.

Driver drowsiness detection in video sequences using hybrid selection of deep features

Monitoring driver’s drowsiness is a complex problem that involves many indicators whether behavioral or physiological. Drowsiness is a challenging problem that can lead to road disasters. Sleeping driver is more dangerous on the road than a speeding driver. Many statistics showed that one-fifth of road accidents in the world were due to driver fatigue, hence safety modules that can alert drowsy drivers in the hopes of reducing the risk of accidents are very important. This paper proposes a framework for driver drowsiness detection based on a computer vision solution. The proposed framework’s first task is to detect the driver’s face. A transfer learning is then performed for extracting the deep features from the driver’s face image using a pre-trained deep convolutional network model trained on a facial recognition dataset. The previous tasks are applied in a sliding temporal window (less than a second) in which the frames are sampled. In this work, 9 frames were the best choice. The extracted features of these frames represent the observation matrix. Then temporal feature aggregation is applied to construct the raw feature vector. To obtain the final feature vector, a proposed feature selection is applied to omit possible irrelevant features. The final feature vector is finally fed to a binary classifier to decide whether there is drowsiness or not. Extensive experiments are applied to NTHU Drowsy Driver Detection (NTHU-DDD) video dataset. The outcomes show the outperformance of the proposed approach compared with the state-of-the-art approaches.