Automated Assessment of Driver Distraction Using Multimodal Wearable Data and Squeeze-Excitation Networks.

Driver distraction, crucial for road safety, can benefit from multimodal physiological signals assessment. However, fusion of heterogeneous data is highly challenging. In this study, we address this challenge by exploring 1D convolution neural network (CNN) with squeeze and excitation networks (SEcNN) on multimodal data. For this, electrocardiogram (256Hz) and respiration (128Hz) are obtained from subjects (N=10) while using textile electrodes and driving in different scenarios namely normal, texting and calling. The obtained multimodal data is preprocessed and SEcNN to identify driver distraction. Experiments are performed using Leave-one-out-subject cross validation. The proposed approach is able to discriminate drivers distraction. It is observed that SEcNN yields average accuracy 57.03% and average F1 score 54.90% for shorter segments. Thus, the proposed approach using wearable shirts could be useful for non-intrusive monitoring in real world driver scenarios.

CBAM VGG16: An efficient driver distraction classification using CBAM embedded VGG16 architecture.

Driver monitoring systems (DMS) are crucial in autonomous driving systems (ADS) when users are concerned about driver/vehicle safety. In DMS, the significant influencing factor of driver/vehicle safety is the classification of driver distractions or activities. The driver's distractions or activities convey meaningful information to the ADS, enhancing the driver/ vehicle safety in real-time vehicle driving. The classification of driver distraction or activity is challenging due to the unpredictable nature of human driving. This paper proposes a convolutional block attention module embedded in Visual Geometry Group (CBAM VGG16) deep learning architecture to improve the classification performance of driver distractions. The proposed CBAM VGG16 architecture is the hybrid network of the CBAM layer with conventional VGG16 network layers. Adding a CBAM layer into a traditional VGG16 architecture enhances the model's feature extraction capacity and improves the driver distraction classification results. To validate the significant performance of our proposed CBAM VGG16 architecture, we tested our model on the American University in Cairo (AUC) distracted driver dataset version 2 (AUCD2) for cameras 1 and 2 images. Our experiment results show that the proposed CBAM VGG16 architecture achieved 98.65% classification accuracy for camera 1 and 97.85% for camera 2 AUCD2 datasets. The CBAM VGG16 architecture also compared the driver distraction classification performance with DenseNet121, Xception, MoblieNetV2, InceptionV3, and VGG16 architectures based on the proposed model's accuracy, loss, precision, F1 score, recall, and confusion matrix. The drivers' distraction classification results indicate that the proposed CBAM VGG16 has 3.7% classification improvements for AUCD2 camera 1 images and 5% for camera 2 images compared to the conventional VGG16 deep learning classification model. We also tested our proposed architecture with different hyperparameter values and estimated the optimal values for best driver distraction classification. The significance of data augmentation techniques for the data diversity performance of the CBAM VGG16 model is also validated in terms of overfitting scenarios. The Grad-CAM visualization of our proposed CBAM VGG16 architecture is also considered in our study, and the results show that VGG16 architecture without CBAM layers is less attentive to the essential parts of the driver distraction images. Furthermore, we tested the effective classification performance of our proposed CBAM VGG16 architecture with the number of model parameters, model size, various input image resolutions, cross-validation, Bayesian search optimization and different CBAM layers. The results indicate that CBAM layers in our proposed architecture enhance the classification performance of conventional VGG16 architecture and outperform the state-of-the-art deep learning architectures.

A randomized trial of behavioral interventions yielding sustained reductions in distracted driving.

Distracted driving is responsible for nearly 1 million crashes each year in the United States alone, and a major source of driver distraction is handheld phone use. We conducted a randomized, controlled trial to compare the effectiveness of interventions designed to create sustained reductions in handheld use while driving (NCT04587609). Participants were 1,653 consenting Progressive® Snapshot® usage-based auto insurance customers ages 18 to 77 who averaged at least 2 min/h of handheld use while driving in the month prior to study invitation. They were randomly assigned to one of five arms for a 10-wk intervention period. Arm 1 (control) got education about the risks of handheld phone use, as did the other arms. Arm 2 got a free phone mount to facilitate hands-free use. Arm 3 got the mount plus a commitment exercise and tips for hands-free use. Arm 4 got the mount, commitment, and tips plus weekly goal gamification and social competition. Arm 5 was the same as Arm 4, plus offered behaviorally designed financial incentives. Postintervention, participants were monitored until the end of their insurance rating period, 25 to 65 d more. Outcome differences were measured using fractional logistic regression. Arm 4 participants, who received gamification and competition, reduced their handheld use by 20.5% relative to control (P < 0.001); Arm 5 participants, who additionally received financial incentives, reduced their use by 27.6% (P < 0.001). Both groups sustained these reductions through the end of their insurance rating period.

Gap acceptance behaviour and crash risks of mobile phone distracted young drivers at roundabouts: A random parameters survival model.

Navigating through complex road geometries, such as roundabouts, poses significant challenges and safety risks for drivers. These challenges may be exacerbated when drivers are distracted by mobile phone conversations. The interplay of road geometry, driving state, and driver characteristics in creating compound risks remains an underexplored area in existing literature. Proper understanding of such compound crash risk is not only crucial to improve road geometric design but also to educate young drivers, who are particularly risk-takers and to devise strict penalties for mobile phone usage whilst driving. To fill this gap, this study examines crash risks associated with gap acceptance manoeuvres at roundabouts in the simulated environment of the CARRS-Q driving simulators, where 32 licenced young drivers were exposed to a gap acceptance scenario in three phone conditions: baseline (no phone conversation), handheld, and hands-free. A parametric random parameters survival modelling approach is adopted to understand safety margins-characterised by gap times-during gap acceptance scenarios at roundabouts, concurrently uncover driver-level heterogeneity with mobile phone distraction and capture repeated measures of experiment design. The model specification includes the handheld phone condition as a random parameter and hands-free phone condition, acceleration noise, gap size, crash history, and gender as non-random parameters. Results suggest that the majority of handheld distracted drivers have smaller safety margins, reflecting the negative consequences of engaging in handheld phone conversations. Interestingly, a group of drivers in the same handheld phone condition have been found to exhibit cautious/safer behaviour, as evidenced by longer gap times, reflecting their risk compensation behaviour. Female distracted drivers are also found to exhibit safer gap acceptance behaviour compared to distracted male drivers. The findings of this study shed light on the compound risk of mobile phone distraction and gap acceptance at roundabouts, requiring policymakers and authorities to devise strict penalties and laws for distracted driving.

Attentional warnings caused by driver monitoring systems: How often do they appear and how well are they understood?

The present study investigated the effects of a driver monitoring system that triggers attention warnings in case distraction is detected. Based on the EuroNCAP protocol, distraction could either be long glances away from the forward roadway (≥3s) or visual attention time sharing (>10 cumulative seconds within a 30 s time interval). In a series of manual driving simulator drives, 30 participants completed both driving related tasks (e.g., changing multiple lanes in dense traffic) and non-driving related tasks (e.g., infotainment operations). Results of warning frequencies revealed that visual attention time sharing warnings occurred more frequently than long distraction warnings. Moreover, there was a large number of attention warnings during driving related tasks. Results also revealed that participants' mental models tended to be less accurate when it came to understanding of the visual attention time sharing warnings as compared to the long distraction warnings, which were understood more accurately. Based on these observations, the work discusses the applicability and design of driver monitoring warnings.

Audiovisual presentation of variable message signs improves message processing in distracted drivers during partially automated driving.

INTRODUCTION: Highly automated driving is expected to reduce the accident risk occurrence by human errors, but it can also increase driver distraction. Previous evidence shows that auditory signals can help drivers take over in critical situations. However, it is still uncertain whether the potential benefit of verbal auditory signals could be generalized to driving situations where drivers are visually and auditorily distracted. METHOD: Our first objective was to compare the effectiveness of complementary audio messages (audio + visual condition) and visual only (visual condition) variable message signs (VMS) messages. The second objective was to explore the potential use of oral messages with traffic information to help highly-automated vehicle drivers identify critical situations. Eye-tracking data were also registered. Twenty-four volunteers participated in a driving simulator study, completing two tasks: (a) a TV series task, where they had to pay attention to an episode of a TV series while traveling along the route; and (b) a VMS task, where they had to recover the manual control of the car if the VMS message was a 'critical message.' RESULTS: General results showed that, when the audio was available, the participants: (a) had a higher ability to discriminate the VMS messages, (b) were less conservative, (c) responded earlier, and (d) their pattern of fixations was more efficient. A complementary analysis showed that the counterbalance order was a moderating factor for the discrimination ability and the response distance measures. This evidence suggests a potential learning effect, not cancelled by counterbalancing the order of the conditions. CONCLUSION: The processing of traffic messages may improve when provided as oral and visual messages. PRACTICAL APPLICATIONS: These results would be of special interest for engineers designing highly automated cars, considering that the design of automated systems must ensure that the driver's attention is sufficient to take over control.

Assessing the determinants of crash propensity using structural equation modeling: Role of distractions caused by fellow drivers.

INTRODUCTION: Aggressive behavior of drivers is a source of crashes and high injury severity. Aggressive drivers are part of the driving environment, however, excessive aggressive driving by fellow drivers may take the attention of the recipient drivers away from the road resulting in distracted driving. Such external distractions caused by the aggressive and discourteous behavior of other road users have received limited attention. These distractions caused by fellow drivers (DFDs) may agitate recipient drivers and ultimately increase crash propensity. Aggressive driving behaviors are quite common in South Asia and, thus, it is necessary to determine their contribution to distractions and crash propensity. METHOD: Our study aimed to evaluate the effects of DFDs using primary data collected through a survey conducted in Lahore, Pakistan. A total of 801 complete responses were obtained. Various hypotheses were defined to explore the associations between the latent factors such as DFDs, anxiety/stress (AS), anxiety-based performance deficits (APD), hostile behavior (HB), acceptability of vehicle-related distractions (AVRD), and crash propensity (CP). Structural Equation Modeling (SEM) was employed as a multivariate statistical technique to test these hypotheses. RESULTS: The results supported the hypothesis that DFDs lead to AS among recipient drivers. DFDs and AS were further found to have positive associations with APDs. Whereas, there was a significant negative association between DFD, AS, and AVRD. As hypothesized, DFD and AS had positive associations with CP, indicating that distractions caused by aggressive behaviors leads to stress and consequently enhances crash propensity. PRACTICAL APPLICATIONS: The results of this study provide a statistically sound foundation for further exploration of the distractions caused by the aggressive behaviors of fellow drivers. Further, the results of this study can be utilized by the relevant authorities to alter aggressive driving behaviors and reduce DFDs.

The utility of telematics data for estimating the prevalence of driver handheld cellphone use, 2019-2022.

INTRODUCTION: Driver distraction from handheld cellphone use contributes to fatal crashes every year but is underreported in terms of the proportion of crashes attributed to any distraction or cellphone use specifically. Existing methods to estimate the prevalence of cellphone distractions are also limited (e.g., observing drivers stopped at intersections, when crash risk is low). Our study used data from Cambridge Mobile Telematics to estimate the prevalence of drivers' handheld calls and cellphone manipulation while driving, with "cellphone motion" based on movement recorded by the phones' gyroscopes used as a surrogate for manipulation. METHOD: We compared the telematics measures with the National Highway Traffic Safety Administration's roadside observations of driver electronic device use, and logistic regression tested relationships between regional, legislative, and temporal factors and the odds of cellphone behaviors occurring on a trip or at a given point in time. RESULTS: Results showed 3.5% of trips included at least one handheld phone call and 33.3% included at least an instance of cellphone motion, with handheld calls occurring during 0.78% of overall trip duration and cellphone motion during 2.4% of trip duration. CONCLUSIONS: Correspondence between trends in cellphone distractions across regional, legislative, and temporal factors suggest telematics data have considerable utility and appear to complement existing datasets.

Demographic characteristics and trends of cell phone use while driving citations in selected states in the United States, 2010-2020.

OBJECTIVE: Distracted driving is a leading cause of motor vehicle crashes, and cell phone use is a major source of in-vehicle distraction. Many states in the United States have enacted cell phone use laws to regulate drivers' cell phone use behavior to enhance traffic safety. Numerous studies have examined the effects of such laws on drivers' cell phone use behavior based on self-reported and roadside observational data. However, little was known about who actually violated the laws at the enforcement level. This study sought to uncover the demographic characteristics of drivers cited for cell phone use while driving and whether these characteristics changed over time since the enactment of cell phone laws. METHODS: We acquired useable traffic citation data for 7 states in the United States from 2010 to 2020 and performed descriptive and regression analyses. RESULTS: Male drivers were cited more for cell phone use while driving. Handheld and texting bans were associated with a greater proportion of cited drivers aged 40 and above, compared to texting-only bans. Trends in the citations issued based on drivers' age group following the enactment of different cell phone laws were also uncovered. The proportion of citations issued to drivers aged 60 and above increased over time but the temporal trend remained insignificant when population effect was considered. CONCLUSIONS: This study examined the demographic characteristics of drivers cited for cell phone use while driving in selected states with texting-only bans or handheld and texting bans. The results reveal policy-based differences in trends in the proportion of citations issued to drivers in different age groups.

Modeling distracted driving behavior considering cognitive processes.

The modeling of distracted driving behavior has been studied for many years, however, there remain many distraction phenomena that can not be fully modeled. This study proposes a new method that establishes the model using the queuing network model human processor (QN-MHP) framework. Unlike previous models that only consider distracted-driving-related human factors from a mathematical perspective, the proposed method reflects the information processing in the human brain, and simulates the distracted driver's cognitive processes based on a model structure supported by physiological and cognitive research evidence. Firstly, a cumulative activation effect model for external stimuli is adopted to mimic the phenomenon that a driver responds only to stimuli above a certain threshold. Then, dual-task queuing and switching mechanisms are modeled to reflect the cognitive resource allocation under distraction. Finally, the driver's action is modeled by the Intelligent Driver Model (IDM). The model is developed for visual distraction auditory distraction separately. 773 distracted car-following events from the Shanghai Naturalistic Driving Study data were used to calibrate and verify the model. Results show that the model parameters are more uniform and reasonable. Meanwhile, the model accuracy has improved by 57% and 66% compared to the two baseline models respectively. Moreover, the model demonstrates its ability to generate critical pre-crash scenarios and estimate the crash rate of distracted driving. The proposed model is expected to contribute to safety research regarding new vehicle technologies and traffic safety analysis.

Examining the impact of interventions in reducing self-reported engagement in distracted driving: A systematic review.

Despite the implementation of legal countermeasures, distracted driving remains a prevalent concern for road safety. This systematic review (following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines) summarised the literature on the impact of interventions targeting attitudes/intentions towards, and self-reported engagement in, distracted driving. Studies were eligible for this review if they examined self-reported behaviour/attitudes/intentions pertaining to distracted driving at baseline and post-intervention. Databases searched included PubMed, ProQuest, Scopus, and TRID. The review identified 19 articles/interventions, which were categorised into three intervention types. First, all program-based interventions (n = 6) reduced engagement in distracted driving. However, there were notable limitations to these studies, including a lack of control groups and difficulties implementing this intervention in a real-world setting. Second, active interventions (n = 9) were commonly utilised, yet a number of studies did not find any improvements in outcomes. Finally, four studies used a message-based intervention, with three studies reporting reduced intention and/or engagement in distracted driving. There is opportunity for message-based interventions to be communicated effortlessly online and target high-risk driving populations. However, further research is necessary to address limitations highlighted in the review, including follow-up testing and control groups. Implications are discussed with particular emphasis on areas where further research is needed.

Distracted on duty: A theory-based exploration of influences leading to mobile phone distracted riding among food delivery workers.

Using mobile phones while riding is a form of distracted riding that significantly elevates crash risk. Regrettably, the factors contributing to mobile phone use while riding (MPUWR) among food delivery riders remain under-researched. Addressing this literature gap, the current study employs the Job Demands-Resources (JD-R) model and various socio-economic factors to examine the determinants of MPUWR. The research incorporates data from 558 delivery workers in Hanoi and Ho Chi Minh City, Vietnam. The study utilizes two analytical methods to empirically test the hypotheses, considering non-linear relationships between variables: Partial Least Square Structural Equation Modelling (PLS-SEM) and Artificial Neural Network (ANN). The results reveal mixed impacts of factors connected to job resources. Although social support appears to deter MPUWR, work autonomy and rewards seemingly encourage it. Furthermore, a predisposition towards risk-taking behaviour significantly impacts the frequency of mobile phone usage among delivery riders. Interestingly, riders with higher incomes and those who have previously been fined by the police exhibit more frequent mobile phone use. The findings of this study present valuable insights into the crucial factors to be addressed when designing interventions aimed at reducing phone use among food delivery riders.

Gaze entropy metrics for mental workload estimation are heterogenous during hands-off level 2 automation.

As the level of vehicle automation increases, drivers are more likely to engage in non-driving related tasks which take their hands, eyes, and/or mind away from the driving task. Consequently, there has been increased interest in creating Driver Monitoring Systems (DMS) that are valid and reliable for detecting elements of driver state. Workload is one element of driver state that has remained elusive within the literature. Whilst there has been promising work in estimating mental workload using gaze-based metrics, the literature has placed too much emphasis on point estimate differences. Whilst these are useful for establishing whether effects exist, they ignore the inherent variability within individuals and between different drivers. The current work builds on this by using a Bayesian distributional modelling approach to quantify the within and between participants variability in Information Theoretical gaze metrics. Drivers (N = 38) undertook two experimental drives in hands-off Level 2 automation with their hands and feet away from operational controls. During both drives, their priority was to monitor the road before a critical takeover. During one drive participants had to complete a secondary cognitive task (2-back) during the hands-off Level 2 automation. Changes in Stationary Gaze Entropy and Gaze Transition Entropy were assessed for conditions with and without the 2-back to investigate whether consistent differences between workload conditions could be found across the sample. Stationary Gaze Entropy proved a reliable indicator of mental workload; 92 % of the population were predicted to show a decrease when completing 2-back during hands-off Level 2 automated driving. Conversely, Gaze Transition Entropy showed substantial heterogeneity; only 66 % of the population were predicted to have similar decreases. Furthermore, age was a strong predictor of the heterogeneity of the average causal effect that high mental workload had on eye movements. These results indicate that, whilst certain elements of Information Theoretic metrics can be used to estimate mental workload by DMS, future research needs to focus on the heterogeneity of these processes. Understanding this heterogeneity has important implications toward the design of future DMS and thus the safety of drivers using automated vehicle functions. It must be ensured that metrics used to detect mental workload are valid (accurately detecting a particular driver state) as well as reliable (consistently detecting this driver state across a population).

Comparison of concurrent cognitive load measures during n-back tasks.

The cognitive load experienced by humans is an important factor affecting their performance. Cognitive overload or underload may result in suboptimal human performance and may compromise safety in emerging human-in-the-loop systems. In driving, cognitive overload, due to various secondary tasks, such as texting, results in driver distraction. On the other hand, cognitive underload may result in fatigue. In automated manufacturing systems, a distracted operator may be prone to muscle injuries. Similar outcomes are possible in many other fields of human performance such as aviation, healthcare, and learning environments. The challenge with such human-centred applications is that the cognitive load is not directly measurable. Only the change in cognitive load is measured indirectly through various physiological, behavioural, performance-based and subjective means. A method to objectively assess the performance of such diverse measures of cognitive load is lacking in the literature. In this paper, a performance metric for the comparison of different measures to determine the cognitive workload is proposed in terms of the signal-to-noise ratio. Using this performance metric, several measures of cognitive load, that fall under the four broad groups were compared on the same scale for their ability to measure changes in cognitive load. Using the proposed metrics, the cognitive load measures were compared based on data collected from 28 participants while they underwent n-back tasks of varying difficulty. The results show that the proposed performance evaluation method can be useful to individually assess different measures of cognitive load.

Assessing the effectiveness of psychoeducational interventions on driving behavior: A systematic review and meta-analysis.

This review aimed to quantitatively summarize the evidence concerning the effectiveness of psychoeducational interventions on driving behavior. A final pool of 138 studies, totaling approximately 97,000 participants, was included in the analyses and covered all types of driving behavior targeted by the interventions. Using a random effects model, significant results were found for almost all driving outcomes, both post-intervention and long-term. The strongest effect was for reducing distracted driving at post-intervention (d = 1.87 [1.12, 2.60], Z = 4.94, p < 0.001). The only non-significant effects were for reducing errors in the long term (d = 0.50 [-0.87, 1.86], Z = 0.71, p = 0.48) and driving under the influence at post-intervention (d = 0.35 [0.00, 0.71], Z = 1.96, p = 0.05). Concerning which type of intervention was more effective, feedback, training and motivational ones appear to work best. Educational interventions show only weak effects, while awareness interventions seem mostly ineffective. Overall, our results show that most interventions can reduce different types of driving behaviors, but there are specific aspects to be considered based on the targeted behavior.

Integrating visual large language model and reasoning chain for driver behavior analysis and risk assessment.

Driver behavior is a critical factor in driving safety, making the development of sophisticated distraction classification methods essential. Our study presents a Distracted Driving Classification (DDC) approach utilizing a visual Large Language Model (LLM), named the Distracted Driving Language Model (DDLM). The DDLM introduces whole-body human pose estimation to isolate and analyze key postural features-head, right hand, and left hand-for precise behavior classification and better interpretability. Recognizing the inherent limitations of LLMs, particularly their lack of logical reasoning abilities, we have integrated a reasoning chain framework within the DDLM, allowing it to generate clear, reasoned explanations for its assessments. Tailored specifically with relevant data, the DDLM demonstrates enhanced performance, providing detailed, context-aware evaluations of driver behaviors and corresponding risk levels. Notably outperforming standard models in both zero-shot and few-shot learning scenarios, as evidenced by tests on the 100-Driver dataset, the DDLM stands out as an advanced tool that promises significant contributions to driving safety by accurately detecting and analyzing driving distractions.

Unraveling the differences in distracted driving injury severities in passenger car, sport utility vehicle, pickup truck, and minivan crashes.

Distracted driving poses a significant risk on the roadway users, with the level of distraction and crash outcomes varying depending on the type of vehicle. Drivers of passenger cars, sport utility vehicles (SUVs), pickup trucks, minivans experience distinct levels of distraction, leading to potential crashes. This study investigates into the severity of driver injuries resulting from distracted driving in these vehicle categories, shedding light on the variations in single-vehicle crashes. Focusing on single-vehicle crashes in Florida during 2019, involving passenger cars, SUVs, pickup trucks, and minivans caused by distracted driving, the study examines various distractions such as, electronic communication devices (cell phones), electronic devices (navigation systems, music players), internal and external disturbances, texting, and inattentive driving. To analyze the severity of injuries resulting from distracted driving in passenger cars, SUVs, pickup trucks, and minivans, the study employs random parameter multinomial logit models with heterogeneity in means and variances. The model estimates highlight thirty-five significant factors influencing the severity of driver injuries resulting from distracted driving. Notably, the impact of these factors varies significantly depending on the vehicle type (i.e., passenger cars, SUVs, pickup trucks, and minivans). While many explanatory variables are specific to each vehicle type, only one factor (restraint belt usage) is common across all vehicle types, with varying magnitudes in injury outcomes. The likelihood ratio tests indicate that injury severity must be analyzed and modeled separately for passenger cars, SUVs, pickup trucks, and minivans. Vehicle characteristics play a crucial role in driver distraction and crash outcomes. Analyzing a year of crash data, categorized by four vehicle types, has provided valuable insights into distracted driving patterns in passenger cars, SUVs, pickup trucks, and minivans, influencing potential prevention strategies. To combat against distracted driving effectively, priority should be given to driver education and training, roadway design, vehicle technology, enforcement, and automobile insurance. The automobile industry, especially for passenger cars, SUVs, pickup trucks, and minivans, should consider implementing advanced in-vehicle technologies tailored to the specific characteristics of each vehicle type (e.g., advanced driver assistance systems (ADAS)) to proactively prevent driver distraction. These proactive measures will contribute significantly to enhancing road safety and reducing the risks associated with distracted driving.

Use of smartphone apps while driving: Variations on driving performances and perceived risks.

Distracted driving increases the crash frequencies on the road and subsequently leads to fatalities involved with crashes. As technology has evolved, drivers are continuously exposed to newer technology in their vehicles and applications in their phones, which has led to technology representing one of the main secondary tasks that distract drivers on the road. The impact of technology-involved distraction appears to be different by the type of distraction since a secondary task that can be exceedingly distracting to the driver causes more reckless and risky driving. Moreover, the impact of distracted driving may differ by roadway geometries since distracted drivers' performance may vary depending on how actively they interact with other vehicles or surrounding environments. This study aims to understand the impacts of smartphone application distractions, in particular social media activities (e.g., video, feed, message), on different road geometries using a mixed-method analysis consisting of a survey, a driving simulator experiment, and individual interview. Results from the interview and simulation experiments show that most social media activities cause unsafe lane changes regardless of road geometry. Among various social-media activities, watching reels (videos) represent an unintentional but deeper level of engagement that consequently causes a driver to deviate in their lane, make unintentional lane changes, suddenly change their speed and acceleration, and headway. The interview also revealed varying levels of risk perception about distracted driving, in particular the lower level of risk perception in using GPS and music applications. This study concludes that the distractions caused by smartphone applications and social media activities combined with lower awareness and risk perception could significantly elevate the crash risks.

Influence of distracted driving of online car-hailing drivers on overall driving performance.

The distraction affects driving performance and induces serious safety issues. To better understand distracted driving, this study examines the influence of distracted driving on overall driving performance. This paper analyzes the distraction behavior (mobile phone use, entertainment activities, and passenger interference) under three driving tasks. The statistical results show that viewing or sending messages is common during driving. Smoking, phone calls, and talking to passengers are evident in cruising, ride request and drop-off, respectively. Then, overall driving performance is proposed based on velocity, longitudinal acceleration (longacc) and yaw_rate. It is divided into three categories, high, medium, and low, by k-means algorithms. The average speed increases from low to high performance; however, the longacc and yaw_rate decrease. Finally, the influence of distracted driving on overall driving performance is analyzed using C4.5 algorithm. The result shows that when time is peak, the probability of high performance (HP) is higher than off-peak. The possibility of HP increases with the increase of duration; the number of, talking to passengers, listening to music or radio, eating; the duration of, viewing or sending messages, phone calls; but reduces with the increase of the number of phone calls. These findings provide theoretical support for driving performance evaluation.

Exploring the Behaviour Change Wheel and the Theoretical Domains Framework in interventions for mobile phone driver distraction: A scoping review.

Mobile phone use while driving remains a significant traffic safety concern. Although numerous interventions have been developed to address it, there is a gap in the synthesis of relevant information through a comprehensive behaviour change lens. This scoping review uses the Behaviour Change Wheel (BCW) and the Theoretical Domains Framework (TDF) to examine the literature to (a) identify behavioural constructs targeted in interventions for mobile phone use while driving, (b) determine if the intervention success varied by sociodemographic group (e.g., age, gender, driving experience), and (c) map interventions to TDF domains to highlight areas for future research. Following the PRISMA extension for scoping reviews, we searched seven databases and identified 5,202 articles. After screening, 50 articles detailing 56 studies met the following inclusion criteria: (a) intervention studies, (b) providing details on methods and results, (c) written in English, and (d) targeting any driver behaviour related to mobile phone use while driving with a bottom-up approach, using not regulation or law enforcement, but individuals' psychological processes, such as cognitive, behavioural, and emotional. Findings show that most interventions targeted young drivers and were typically effective. Except for a few studies, the effectiveness of interventions targeting different sociodemographic groups either remained untested or revealed nonsignificant differences. This finding points to a gap in the literature, indicating a need for further investigation into the efficacy of interventions for different groups, and for tailoring and testing them accordingly. The interventions also often targeted multiple TDF domains, complicating the interpretation of the relative efficacy of specific domains. Most frequently targeted domains included beliefs and consequences, emotions, knowledge, social influence, social/professional role and identity, and behavioural regulation. Physical skills and optimism domains were not targeted in any intervention. Further, almost all interventions addressed deliberate engagement in mobile phone distractions, while the automatic and fast processes involved in such behaviours were often overlooked. Mobile phone distractions are in part habitual behaviours, yet the existing mitigation efforts mostly assumed intentional engagement. More focus on the habitual nature of mobile phone distractions is needed.