Driving Performance Indicators Research Articles

How Tired is Too Tired to Drive? A Systematic Review Assessing the Use of Prior Sleep Duration to Detect Driving Impairment.

Driver fatigue is a contributory factor in approximately 20% of vehicle crashes. While other causal factors (eg, drink-driving) have decreased in recent decades due to increased public education strategies and punitive measures, similar decreases have not been seen in fatigue-related crashes. Fatigued driving could be managed in a similar way to drink-driving, with an established point (ie, amount of prior sleep) after which drivers are "deemed impaired". This systematic review aimed to provide an evidence-base for the concept of deemed impairment and to identify how much prior sleep may be required to drive safely. Four online databases were searched (PubMed, Web of Science, Scopus, Embase). Eligibility requirements included a) measurement of prior sleep duration and b) driving performance indicators (eg, lane deviation) and/or outcomes (eg, crash likelihood). After screening 1940 unique records, a total of 61 studies were included. Included studies were categorised as having experimental/quasi-experimental (n = 21), naturalistic (n = 3), longitudinal (n = 1), case-control (n = 11), or cross-sectional (n = 25) designs. Findings suggest that after either 6 or 7 hours of prior sleep, a modest level of impairment is generally seen compared with after ≥ 8 hours of prior sleep (ie, well rested), depending on the test used. Crash likelihood appears to be ~30% greater after 6 or 7 hours of prior sleep, as compared to individuals who are well rested. After one night of either 4 or 5 hours of sleep, there are large decrements to driving performance and approximately double the likelihood of a crash when compared with well-rested individuals. When considering the scientific evidence, it appears that there is a notable decrease in driving performance (and associated increase in crash likelihood) when less than 5h prior sleep is obtained. This is a critical first step in establishing community standards regarding the amount of sleep required to drive safely.

Driving simulator performance worsens after the Spring transition to Daylight Saving Time

SummaryCircadian desynchrony and sleep deprivation related to the Spring transition to Daylight Saving Time (DST) have been associated with several unfavorable outcomes, including an increase in road traffic accidents. As previous work has mainly focused on analyzing historical crash/hospitalization data, there is virtually no literature investigating the effects of DST on specific driving performance indicators. Here, the effect of the Spring transition to DST on driving performance was investigated by means of a driving simulator experiment, in which participants completed two trials (one week distance, same time and day of the week) on exactly the same simulated route, the second trial taking place in the week after the transition to DST. Results were compared to those of a control group (who also underwent two trials, both before the DST transition), and documented significant worsening of driving performance after DST, as measured by a comprehensive set of simulator-derived indices.

Effect of Distracting Factors on Driving Performance: A Review

The number of traffic accidents because of distracted driving is increasing rapidly worldwide. Hence, the main objective of the present study is to review the effects of different distracting factors on driving performance indicators. Distracting factors considered in this study are roadside advertisements (billboards), mobile use, in-built vehicle systems, and sleepiness; and driving performance indicators are lane deviation, reaction time, and speed variation. Studies from existing literature reveal that all the distracting factors distract drivers from forwarding roadways in many ways. The location and content displayed on the billboard and the use of mobile phones increase reaction time. However, the former decreases the driver’s ability to control the vehicle, and the latter increases the speed variation and reduces lane-keeping capacity. Lateral vehicle control and reaction time are compromised when drivers engage in searching for songs or videos on music players. When sleepiness occurs, drivers exhibit a higher standard deviation of speed and a decreased headway distance. Nevertheless, most of the studies in this area are carried out in developed countries like the USA and European countries. Therefore, a detailed study and further research in developing countries like India, where activities like installing billboards and mobile phone use are increasing day by day due to the rapid urbanization of major cities in the country, are quite essential. Doi: 10.28991/CEJ-2022-08-02-014 Full Text: PDF

The Influence of In-Vehicle Subtasks on Driving Performance Using the Lane-Changing Test

To improve the specification and applicability of performance indicators for in-vehicle subtask impact experiments, additional driving performance indicators were added to the international standard test environment, the lane-changing test (LCT). The comprehensive characteristics of multiple indicators were studied using the C4.5 decision tree. The paired memory test was selected as a subtask, and data on driving trajectory, speed, and steering angle were collected and analyzed under three task conditions (baseline, easy task, and difficult task). The results showed that the newly added indicators such as lane offset times, initial lane-changing distance, and correct lane-changing ratio could reflect the new driving characteristics from the aspects of the times of lateral deviation over threshold events, driver response, error proportion, etc. Subjects with different driving states were grouped into the lane-keeping indicator and lane-changing indicator. By using the C4.5 decision tree, classification accuracies of 85.2% and 91.3% were achieved, respectively, which indicated a high accuracy rate of task state discrimination. The overall performance of lane keeping and lane changing was different under the action of the subtasks, especially the lane-changing performance.

Evaluating the impacts of situational awareness and mental stress on takeover performance under conditional automation

Several safety concerns emerge for the transition of control from the automated driving system to a human driver after the vehicle issues a takeover warning under conditional vehicle automation (SAE Level 3). In this context, recent advances in in-vehicle driver monitoring systems enable tracking drivers’ physiological indicators (e.g., eye-tracking and heart rate (HR) measures) to assess their real-time situational awareness (SA) and mental stress. This study seeks to analyze differences in driver’s SA and mental stress over time (i.e., successive experiment runs) using these physiological indicators to assess their impacts on takeover performance. We use eye-tracking measures (i.e., on-road glance rate and road attention ratio) as indicators of driver’s SA during automated driving. Further, we use the pre-warning normalized HR (NHR) and HR variability (HRV) as well as the change in NHR and HRV after the takeover warning as indicators of mental stress immediately before and the change in mental stress after the takeover warning, respectively. To analyze the effects of driver state (in terms of SA and mental stress) on the overall takeover performance, this study uses a comprehensive metric, Takeover Performance Index (TOPI), proposed in our previous work (Agrawal & Peeta, 2021). The TOPI combines multiple driving performance indicators while partly accounting for their interdependencies. Results from statistical analyses of data from 134 participants using driving simulator experiments illustrate significant differences in driver state over successive experiment runs, except for the change in mental stress after the takeover warning. Some significant correlations were found between the physiological indicators of SA and mental stress used in this study. Takeover performance model results illustrate a significant negative effect of change in NHR after the takeover warning on the TOPI. However, none of the other physiological indicators show significant impacts on takeover performance. The study findings provide valuable insights to auto manufacturers for designing integrated in-vehicle driver monitoring and warning systems that enhance road safety and user experience.

Evaluating the impacts of driver’s pre-warning cognitive state on takeover performance under conditional automation

To design better fallback procedures and enhance road safety for conditionally automated vehicles (SAE Level 3), it is important to understand the factors that affect driver’s takeover performance (i.e., driving performance while resuming manual control). This study investigates the impacts of driver’s pre-warning cognitive state (i.e., before the issuance of a takeover warning) on takeover performance. Most existing studies assess takeover performance by independently analyzing driving performance indicators (e.g., minimum time-to-collision and maximum deceleration), and thereby ignore their associated interdependencies. This study proposes a novel comprehensive takeover performance metric, Takeover Performance Index (TOPI), that combines multiple driving performance indicators representing three aspects of takeover performance: risk of collision, the intensity of the driver’s response, and trajectory quality. Further, the driver’s pre-warning cognitive state is estimated by analyzing neurophysiological data (i.e., brain electrical activity) measured using an electroencephalogram (EEG) for 118 participants in driving simulator experiments. Linear mixed models are estimated for takeover performance to analyze its linkages to the driver’s pre-warning cognitive state, novelty in takeover experience (i.e., prior experience with a takeover situation), type of takeover warning (i.e., non-mandatory takeover vs. mandatory takeover), age, and driving experience. In this study, most drivers intervened in non-mandatory takeover scenarios and exhibited poor takeover performance. We observed three crashes across 287 runs. The study results show that takeover performance decreases with age but increases with driving experience when the driver is under certain pre-warning cognitive states, including fatigue, drowsiness, passive attention, and low level of alertness. They also illustrate that the novelty in takeover experience and mandatory takeover warning negatively affects takeover performance. The study findings provide insights for developing operator training and licensing strategies, designing regulations for the use of automated vehicles, and factoring driver cognition in designing fallback procedures in automated vehicles.

Driving Performance Indicator (DPI) to Classify Distracted Driving Conditions in the Elderly Females


 
 
 The driving performance and distracted driving conditions are among the key elements in road safety assessments. Quantitative measurements were reportedly used to characterize the driving performance. However, the main Driving Performance Indicators (DPI) that evaluate and distinguish the distracted driving conditions are unknown. The present study aimed to select the top three DPIs that best classify three levels of driving distractions targeting the elderly female group based on the publicly available database. Data involved eight driving session records of 15 subjects (female of elderly age group) captured in 62,284 instances x 6 attributes (5 DPI and 1 DriveCondition class) that were extracted based on the inclusion criteria set. The DPI features were selected based on the Correlation-based Feature Selection (CFS) and CorrelationAttributeEval (CA) algorithms of WEKA 3.8, reasoned by DPI's Pearson's correlation results. The Simple Random Undersampling approach was used to resolve the class imbalance state. The 'All' and 'with DPI feature selection DPI' (CFS and CA) datasets were classified using 1NN and J-48 algorithms at 10-fold cross-validation mode into three predefined classes of distracted driving conditions (Relax, Moderate and Intense). Classification accuracies achieved from 'All' and 'with DPI feature selection DPI' (CFS and CA) datasets were 66.10% to 68.86% (1NN) and 68.50% to 71.01% (J-48), respectively. The main DPI subsets nominated by CFS: {Speed, Acceleration, Steering, Laneoffset} and CA: {Speed, LaneOffset, Acceleration} each decreased classification accuracy from All datasets by a minimal 0.4% to 2.8% each. Findings demonstrated that Speed, Acceleration, and Lane Offset were high-ranked DPIs that sufficiently distinguished driving distraction classes for the elderly female drivers.
 
 

Effectiveness of the compensatory strategy adopted by older drivers: Difference between professional and non-professional drivers

It has been a controversial issue for the effect of ageing population on driving safety. Apparently, drivers’ physiological and cognitive performances deteriorate with age. However, older drivers may compensate for the elevated risk by adjusting their behaviors, known as compensatory strategy. Despite the extensive research on this topic, the compensatory strategy of older professional drivers is not well understood since many studies focused on the differences in compensatory behavior between older and young drivers. Professional drivers tend to be more skillful and able to cope with the unfavorable driving environments, thus presenting a higher capability to mitigate the risk. This study attempts to examine the compensatory behavior and its safety effect amongst older professional drivers, as compared to those of older non-professional drivers, using the driving simulator approach. In the driving simulator experiment, participants were asked to follow a leading vehicle for one hour, and two sudden brake events were presented. 41 (mid-aged and older) drivers completed the driving tests. Each participant was required to complete a car-following test, either under high or low traffic flow conditions. Performance indicators include driving capability (i.e. lateral control, longitudinal control, and brake reaction time) and compensatory behavior (i.e. average speed, and time headway). Additionally, two modified traffic conflict measures: time exposed time-to-collision (TET) and time integrated time-to-collision (TIT) are applied to indicate the traffic conflict risk. The random parameter Tobit models were estimated to measure the association between conflict risk and driver attributes, and random intercept models were used to assess other driving performance indicators. Results show that despite the impaired lateral control performance and longer brake reaction time of older drivers, the likelihood of severe traffic conflict of older drivers is lower than that of mid-aged drivers. Furthermore, though both older professional and older non-professional drivers adopted longer time headway, the reduction in the risk of severe traffic conflict is more profound among the older professional drivers. Such findings suggest that older professional drivers are more capable of mitigating the possible collision risk by adopting the compensatory strategy, as compared to older non-professional drivers. This justifies the existence of compound effect by the compensatory strategy of older driver and better driving skills of professional driver. This research provides useful insights into driver training and management strategies for employers, as older drivers would become a major cohort in the transportation industry.

Effect of cognitive load on drivers’ State and task performance during automated driving: Introducing a novel method for determining stabilisation time following take-over of control

This research paper explores the impact of cognitive load on drivers’ physiological state and driving performance during an automated driving to manual control transition scenario, using a driving simulator. Whilst driving in the automated mode, cognitive load was manipulated using the “N-Back” task, which participants engaged with via a visual display. Results suggest that non-optimal levels of workload during the automated driving conditions impair driving performance, especially lateral control of the vehicle, and the magnitude of this impairment varied with increasing cognitive load. In addition to these findings, the present paper introduces a novel method for determining stabilisation times of both driver state and driving performance indicators following a transition of vehicle control. Using this method we demonstrate that mean and standard deviation of lane position impairments were found to take longer to stabilise following transition to manual driving following a higher level of cognitive load during the automated driving period, taking up to 22 s for driving performance to normalise after take-over. In addition, heart rate parameters take between 20 and 30 s to stabilise following a planned take-over request. Finally, this paper demonstrates how the magnitude of cognitive load can be estimated in context of automated driving using physiological measures, captured by consumer electronic devices. We discuss the impact our findings have on the design of SAE Level 3 systems. Relevant suggestions are provided to the research community and automakers working on future implementation of vehicles capable of conditional automation.

Messages beyond the phone: Processing variable message signs while attending hands-free phone calls

We examined the effects of different types of cognitive distraction coming from a hands-free phone conversation on the processing of information provided by variable message signs (VMS), on driving performance indicators, and on a physiological index of mental effort (heart rate). Participants drove a route in a driving simulator and had to respond to VMS messages under three conditions: no-distraction, visuospatial distraction (attending phone calls with questions inducing visuospatial processing), and conceptual distraction (attending phone calls with questions requiring semantic memory). Results showed more errors responding to VMS messages in the visuospatial distraction condition. In addition, both types of questions increased the intraindividual variability of response distances and the heart rate, as compared to the no-distraction condition. These results provide new evidence that talking on a hands-free phone entails costs in the processing of traffic information (in particular, text messages displayed on VMS) and it increases the driver’s cognitive effort. Interestingly, the cognitive distraction had no effect on the driver’s control of the vehicle speed or lateral position. Therefore, the effects of potential risk factors can critically vary among the different driving subtasks due to modulatory factors, such as the level of attentional task demands (relatively high in the processing of messages on VMS, but relatively low in controlling the speed and lateral position of the vehicle in quiet traffic conditions). In consequence, the current paper provides new evidence to discuss hands-free phone policies and highlights the importance of designing technological countermeasures to prevent drivers missing critical information displayed on VMS.

Characteristics of driver cell phone use and their influence on driving performance: A naturalistic driving study

Cell phone use while driving is becoming a key problem in traffic safety as it causes visual-manual distraction and has been linked to increases in crash rates. The use of hand-held phones has been banned in several countries, yet research comparing the safety of hands-free phone use with hand-held has produced inconsistent results. Analysis of specific phone use characteristics could help move this traffic safety problem toward a solution, but few studies have considered the influence on driving performance of specific sets of phone use characteristics in combination with other factors such as driving context and driver demographic characteristics. The main objective of this paper is therefore to identify and analyze these factors to determine their effects on driving performance indicators such as speed changes. To this end, 1244 phone events were collected from 52 drivers from the Shanghai Naturalistic Driving Study (SH-NDS), the first naturalistic driving data in China. Because subtasks within a phone event may cause different visual-manual distractions, a hierarchical coding structure for phone events was built. A total of 5662 eyes-off-road (EOR) cases and 4237 subtasks were extracted. The results showed that on average, the participating drivers used the phone for 6.08 % of their driving time; for 17 % of phone use time, drivers used both hands to manipulate the phone; and their average EOR time was 3.16 s, which is equivalent to driving blindly for 22.82 m at an average speed of 7.22 m/s, or 26 km/hr. The effect of phone use on driving performance, including speed, headway, and lane offset, was analyzed with ANOVA. Results showed that standard deviations (SD) of all three parameters were significantly lower during phone periods than during baseline periods. The speed SD during phone use was 0.95 lower than baseline, the headway SD was 2.48 lower, and the absolute lane offset SD was 685.72 lower than baseline. These lower SDs indicate that drivers operated their vehicles with less fluctuation during phone use. While we were unable to find similar differences in mean speed and mean headway, mean lane offset was also significantly lower with phone use than without. A decision tree was developed to identify the factors influencing driver speed change. Results showed that drivers increased, decreased, or maintained speed depending on the type and duration of phone tasks, the duration of the trip, and the type of roadway. Greater understanding of the specific aspects of phone use and their influences on driver distraction and performance will permit the development of more effective countermeasures, including legislation, enforcement, blocking technologies, social norms education, and sending Do Not Disturb messages to callers, all of which will be required to mitigate continued deaths and injuries from phone use while driving.

Support vector machines for the identification of real-time driving distraction using in-vehicle information systems

IVIS (In-vehicle Information System) is an important factor causing driver distraction. To study the driver distraction detection method when operating IVIS, the effectiveness of driving performance indicators in the identification of driving distraction was verified by the method of variance analysis. Forty participants were selected to conduct the driver distraction experiment when operating IVIS, and the data of driving performance indicators such as eye movement, speed, et al. were obtained. According to the driving performance data of IVIS, a real-time detection of distraction based on driving performance was built by using support vector machine, and three kernel functions of the model were conducted comparative analysis and validation. The results show that SVM models can effectively evaluate the degree of drivers’ distraction. At the same time, when the Radial Basis Function is used as a kernel function, the accuracy for recognizing driver distraction is 89.9%, which is higher than when the sigmoid polynomial kernel function and SAVE-IT model are used. The research could be applied in the design of adaptive in-vehicle systems and the evaluation of driving distraction, providing theoretical support and reference for the development of vehicle-mounted information systems and the management of driver distraction prevention measures. Highlights We verify the effectiveness of driving performance indicators as decision variables for driving distraction. We use driving performance indicators as inputs to a distraction detection algorithm. We examine changes in the level of information about driving distraction. SVMs method can be used to detect driving distraction during IVIS operations in real time. The accuracy for using Radial Basis Function to recognizing the driver’s level of distraction is higher than the Radial Basis Function.

Classification of Fatigued and Drunk Driving Based on Decision Tree Methods: A Simulator Study.

It is a commonly known fact that both alcohol and fatigue impair driving performance. Therefore, the identification of fatigue and drinking status is very important. In this study, each of the 22 participants finished five driving tests in total. The control condition, serving as the benchmark in the five driving tests, refers to alert driving. The other four test conditions include driving with three blood alcohol content (BAC) levels (0.02%, 0.05%, and 0.08%) and driving in a fatigued state. The driving scenario included straight and curved roads. The straight roads connected the curved ones with radii of 200 m, 500 m, and 800 m with two turning directions (left and right). Driving performance indicators such as the average and standard deviation of longitudinal speed and lane position were selected to identify drunk driving and fatigued driving. In the process of identification, road geometry (straight segments, radius, and direction of curves) was also taken into account. Alert vs. abnormal and fatigued vs. drunk driving with various BAC levels were analyzed separately using the Classification and Regression Tree (CART) model, and the significance of the variables on the binary response variable was determined. The results showed that the decision tree could be used to distinguish normal driving from abnormal driving, fatigued driving, and drunk driving based on the indexes of vehicle speed and lane position at curves with different radii. The overall accuracy of classification of “alert” and “abnormal” driving was 90.9%, and that of “fatigued” and “drunk” driving was 94.4%. The accuracy was relatively low in identifying different BAC degrees. This experiment is designed to provide a reference for detecting dangerous driving states.

Climate Change Policy Evaluation and Its Impact on Island Nations: Case Of Singapore And Sri Lanka

Climate Change (CC) is universally recognized as a major global threat due to its nature of impacts. Island nations are known to be the most vulnerable to CC impacts where many countries have initiated mitigation and adaptation actions through sector-based policy measures. Singapore and Sri Lanka are two Asian island nations with CC induced threats. Two countries are different in terms of economic development, but similar developing countries in the CC agenda. In this context, both the countries have initiated mitigation and adaptation actions through policy measures. This study compares the key climate driven performance indicators with historical data to evaluate the performance of climate change policy of each country. Generally, policy evaluation has been conducted by adopting scientific and non-scientific tools, but it is seldom see that the relation of climate driven indicators along with CC policy. Also the policy research was mostly based on European case studies and Asian island nations were not easy to find in this context. The comparison of two countries in terms of CC policy is to determine the key vulnerable sectors where intervention is necessary for island nations. Mitigation policies are evaluated in Singapore and Sri Lanka using GHG emission pathways under twelve (12) indicators and adaptation policies are measured under the national expenditure of key sectors of the economy under seven (07) indicators. The analysis further elaborated by comparing both countries with key economic sectors that has positive and negative influence on CC impacts. Finally, the analysis outcome is used for lessons to learn from each other in improving the CC policy of Singapore and Sri Lanka. As every country has a unique set of strategies to minimize contributions to CC impacts, unique features that are common to both countries are chosen as variables for the comparison. Policy recommendations are provided to implement solid action plan for post 2020. The study expects to assist island countries to strengthen the CC policy as a national priority to manage unforeseen impacts posed by CC phenomena

Development of statistical models for improving efficiency of emergency evacuation in areas with vulnerable population

Different parts of the world are characterized by frequent occurrences of natural hazards. As such, evacuation planning is an essential part of the natural hazard preparedness, especially in hazard-prone areas. Numerous research efforts have been directed towards improving the efficiency of the evacuation process. However, only a limited number of studies have specifically aimed to identify factors, influencing the driving ability of individuals under emergency evacuation and the occurrence of crashes along the evacuation routes. Furthermore, previous research efforts have focused on a relatively narrow range of factors (primarily driver and traffic flow characteristics). This study aims to fill the existing gap in the state-of-the-art by investigating the effects of a wide range of different factors (including driver characteristics, evacuation route characteristics, driving conditions, and traffic characteristics) on the major driving performance indicators under emergency evacuation. The considered driving performance indicators include travel time, lane deviation, crash occurrence, collision speed, average acceleration pedal pressure, and average braking pedal pressure. A set of statistical models is developed to identify the most significant factors that influence the major driving performance indicators. These models are tested using the data collected from the driving simulator and participants with various socio-demographic characteristics. The results indicate that age, gender, visual disorders, number of lanes, and space headway may substantially impact the driving ability of individuals throughout the emergency evacuation process. Findings from this research can be incorporated within the existing transportation planning models to facilitate the natural hazard preparedness, ensure safety of evacuees, including vulnerable populations, and reduce or even prevent the occurrence of crashes along the evacuation routes.

Effect of driving experience and driving inactivity on young driver’s hazard mitigation skills

Driving skills is an accumulation of driving skills learned from training which are further developed through post-licensure on-road driving. A key driving skill is handling interaction with other road users, of which a critical component is mitigating hazards in order to avoid a crash. Driving skills learned through training during licensure degrade over time if the driver never progresses onto on-road driving (i.e. case of inactive driver). Inactive drivers are quite common in Singapore due to high car ownership cost resulting in many people in the population holding a valid driving licence, but yet having limited opportunity to drive. This research investigated the effect of on-road driving experience as well as driving inactivity on driving performance in terms of hazard mitigation. A sample of 91 participants with a range of driving exposure drove on simulated driving environment in the laboratory. Response latency and its constituent components (lag time, time to fixation and perception-response time) in hazards mitigation were used as driving performance indicators. Participants who are active drivers responded faster than inactive (novice and dormant) drivers. Driving training (during licensure) seemed to play only a small role in preparing drivers for hazard mitigation. On-road driving exposure played an important role to strengthen skills in mitigating hazards. Defensive driving course may help drivers to strengthen their driving competencies especially towards responding to hazardous situations.

BUSINESS VALUE CREATED BY MANAGEMENT ACCOUNTING

Porter stated in his value chain concept that business support activities are contributing to the value creation process of a business organization. In the “classical view” business support activities are considered as indirect productive and not having a clear and direct contribution to the business organization value chain. The information age has enabled and leveraged business support activities to become decisive contributors to the value creation process of any business. Can this value contribution be somehow determined or quantified? Management accounting is a classical business support activity that contributes to the business organization value chain. Through usage of value management and value driven performance indicators, the value contribution can be determined and quantified. The present paper is highlighting one possible alternative to determine the value contribution by using indicators like economic value added and economic profit. The value-based approach is putting indirect productive business activities into a new position, the one of a clear and important business value creator that cannot be ignored in the 21st century, a century driven by data, a nd information and knowledge that can sustain a decisive sustainable competitive advantage.

Visual-Manual Distraction Detection Using Driving Performance Indicators With Naturalistic Driving Data

This paper investigates the problem of driver distraction detection using driving performance indicators from onboard kinematic measurements. First, naturalistic driving data from the integrated vehicle-based safety system program are processed, and cabin camera data are manually inspected to determine the driver’s state (i.e., distracted or attentive). Second, existing driving performance metrics, such as steering entropy, steering wheel reversal rate, and lane offset variance, are reviewed against the processed naturalistic driving data. Furthermore, a nonlinear autoregressive exogenous (NARX) driving model is developed to predict vehicle speed based on the range (distance headway), range rate, and speed history. For each driver, the NARX model is then trained on the attentive driving data. We show that the prediction error is correlated with driver distraction. Finally, two features, steering entropy and mean absolute speed prediction error from the NARX model are selected, and a support vector machine is trained to detect driving distraction. Prediction performances are reported.

Connectivity’s impact on mandatory lane-changing behaviour: Evidences from a driving simulator study

The connected environment provides driving aids to help drivers making efficient and safe driving decisions. The literature to date is devoid of conclusive evidences of the connected environment’s impact on drivers’ mandatory lane-changing (MLC) behaviour. As such, the objective of this study is to examine MLC behaviour through a driving simulator experiment using the CARRS-Q Advanced Driving Simulator. Participants with diverse background performed the experiment in randomised driving conditions: baseline (without the driving aids), connected environment with perfect communication, and connected environment with communication delay. Repeated measure ANOVA in the form of linear mixed model and Generalized Estimation Equation (GEE) are employed to analyse various driving performance indicators during MLC event. We find that drivers in the connected environment tend to wait longer, increase the initial speed, and maintain a larger spacing, compared to when they are driving in the baseline condition. In addition, drivers in the connected environment are likely to reject fewer number of gaps and select relatively bigger gap sizes. Furthermore, post-encroachment time (PET) in the connected environment is higher across different gap sizes, indicating that the connected environment makes MLC safer. The GEE model on gap acceptance suggests that the perfect communication and communication delay has positive and negative impact on the accepted gap size, respectively, and the GEE model on lane-change duration indicates that lane-change duration tends to increase in the connected environment.

Analysis of the sensitivity of heart rate variability and subjective workload measures in a driving simulator: The case of highway work zones

Heart rate variability and subjective workload measures are extensively used to determine workload during driving. However, the sensitivity of heart rate and workload measurements in simulated driving environments is mostly unknown and can significantly affect the experiment results. The objectives of this paper are to determine how heart rate variability and subjective workload are affected in simulated highway work zones and study the relationship between heart rate variability, subjective workload, and driving performance indicators in simulated driving environments. Conventional lane merge (CLM), joint lane merge (JLM) and a road with no work zone are modeled with high and low traffic densities in a full-size driving simulator. NASA-TLX subjective workload measures and heart rate variability measures of root mean square of successive heartbeat differences (RMSSD), low frequency (LF), high frequency (HF) and the ratio of low frequency to high frequency (LF/HF) are collected in 30 participants. Variability in steering angle, braking and speed are used as driving performance indicators. Results show that compared to no work zone, participants experienced higher mental, temporal, and overall workload in the CLM scenario and poorer driving performance ratings in the CLM and JLM scenarios. All workload measures except for performance were higher with high traffic density. However, heart rate variability measures were not sensitive to the differences in driving scenarios and traffic densities. Pearson correlation coefficients indicated an association between RMSSD and all the subjective workload measures (r > 0.21) except performance, and between LF, HF, and LF/HF ratio and mental workload (r > 0.21). Steering angle variability was slightly correlated with LF, HF, and LF/HF ratio (r > 0.16), but brake and speed variability were not associated with physiological outcomes.In conclusion, the subjective workload was higher in simulated work zones and under higher traffic density, but heart rate measures were largely unaffected.