Search

Objectives: Distracted driving such as reading phone messages during driving is risky, as it increases the probability of severe crashes. This study proposes an XGBoost model for visual distraction detection based on vehicle dynamics data from a driving simulation study., Methods: A simulated driving experiment involving thirty-six drivers was launched. We obtained the vehicle dynamics parameters required for the model using the time window and fast Fourier transform methods, totaling 26 items. Meanwhile, the effects of varied time window sizes (1-7 s) and amount of input indications on model performance were studied., Results: By conducting a comparative analysis, it has been determined that the ideal time window size is 5 s. Additionally, the optimal number of input indicators was found to be 23. The XGBoost model for distinguishing distractions achieved an accuracy rate of 85.68%, a precision rate of 85.83%, a recall rate of 83.85%, an F1 score of 84.82%, and an AUC value of 0.9319, which were higher than SVM and RF. The gain-based feature rank demonstrated that the standard deviation of vehicle sideslip rate and the mean amplitude of the 0-1 Hz spectrum component of the steering wheel angle were more crucial than other features., Conclusions: The research results indicate that the steering wheel angle and vehicle sideslip angle may be more conducive to identifying distractions. This XGBoost model could potentially be applied in advanced driving assistant systems (ADAS) to warn driver and reduce cellphone involved distracted driving.

Objective: Efficient and safe address entry is crucial to in-vehicle navigation systems. Although various text input methods (TIMs) are commercially available, to date, the details of the driver's interactions with these TIMs in the vehicle are poorly understood. Therefore, the effect of four alternative TIMs conditions on in-vehicle navigation displays usability and driver distraction were directly compared. For reference, the baseline driving task (distraction-free) was also investigated., Methods: A city expressway simulator experiment including 25 young drivers was launched. Under each condition, the driving task was lane-keeping with speed ranging between 40 and 60 km/h, and the navigation task was to enter a 14-characters Chinese address name. In the meantime, usability (text entry time, number of errors, and preference) and driver distraction (NASA-TLX, average speed, the standard deviation of lane position, total glance duration, number of glances, average glance duration, and number of glances exceeding 1.6 s) metrics were measured as dependent variables. A sequence of one-way repeated measure analyses of variance (ANOVA) was performed to examine which type of TIMs can maximize in-vehicle navigation displays usability and minimize driver distraction., Results: Generally, lateral driving performance deteriorated with the addition of the address inputting task, and the four alternative TIMs might fall into three levels: Speech is optimal, Qwerty followed, Shape-writing and Handwriting ranked last. Specifically, word-based speech remains performed best on all observed metrics for Chinese address names. There was an insignificant difference in text entry time and total glance duration among Qwerty, Shape-writing, and Handwriting. However, Shape-writing and Handwriting are not suitable for young drivers since the nature of uninterruptible causes excessive errors, more considerable lane position variation, longer average glance duration, and more glances exceeding 1.6 s., Conclusions: This study provides valuable insights into young drivers' interactions with four alternative TIMs. Importantly, it is beneficial to the automotive user interfaces design of in-vehicle navigation displays and other sub-functions of in-vehicle information systems (IVISs), such as music playback and text messaging, which positively mitigate driver distraction and prevent traffic injuries.

Objective: Auto-complete (AC) has become ubiquitous on domain-specific systems and is mainly divided into two types (static-AC and dynamic-AC). Specifically, static-AC only presents the possible completions not changing with user input in the suggestion list for users to select. Dynamic-AC constantly filters out inconsistent content with user input and shows the possible completions at the top of the suggestion list. However, the details of the driver's interactions with AC in the vehicle are poorly understood. Therefore, we investigated the effect of three alternative AC (non-AC, static-AC, and dynamic-AC) on the usability of in-vehicle dialing displays and driver distraction. As a reference, the baseline task (only driving) was also surveyed in each AC condition., Methods: A simulated driving experiment consisting of 24 participants was conducted. The primary task was a lane-keeping task with speed ranging between 60 and 120 km/h over the stretch. The secondary task was dialing an 11-digit phone number. Usability metrics (task completion time and number of errors) and driver distraction metrics (NASA-reduced task load index (NASA-RTLX), mean speed, lateral position variation, total glance time, number of glances, mean glance time, and number of glances over 1.6 s) in each condition were measured. A series of one-way repeated measure analyses of variance was used to examine whether and which type of AC can maximize the usability of in-vehicle dialing displays and minimize driver distraction., Results: Generally, the AC-based in-vehicle dialing display gains a more positive effect. Specifically, we observed that among the three alternative AC conditions, dynamic-AC performed optimally on usability metrics similar to previous studies and various driver distraction metrics, notwithstanding it is still not up to the level of the baseline condition. However, static-AC did not exhibit the advantages described in previous studies except for fewer errors and NASA-RTLX owing to the possibility of position bias and boundary effect., Conclusions: This study provides valuable insights into drivers' interactions with AC-based in-vehicle dialing displays and broadened its applications in safety-critical situations. More importantly, it informs the design of a more effective in-vehicle system, which positively contributes to mitigating driver distraction and preventing traffic accidents.

Objective: Texting while driving (TWD) is considered a particularly hazardous form of distracted driving. It is highly prevalent among young drivers, but fewer studies of TWD among adult drivers exist and these prevalence rates may approach those of younger drivers. The effectiveness of measures to prevent distracted driving, and TWD specifically, is unclear. On September 1, 2015, Ontario introduced increased penalties for distracted driving accompanied by public education programs to increase public awareness of the new regulations. Provincial police also introduced enhanced enforcement efforts. The current study examined self-reported TWD in a representative sample of Ontario adults before and after introduction of the new legislation and the enhanced public education and enforcement efforts. Methods: Data were based on telephone interviews with 1,846 respondents who reported having driven in the past year. Data were derived from the 2015-2016 cycles of the Centre for Addiction and Mental Health (CAMH) Monitor , an ongoing cross-sectional telephone survey of adults aged 18+ years in Ontario, Canada. A binary logistic regression analysis of TWD in the previous 30 days was conducted, adjusting for demographic characteristics (sex, age), driving exposure, and introduction of the legislation (before versus after). Results: The proportion of the sample reporting TWD declined significantly from 37.6% before the law was introduced to 24.2% after the law was introduced. The impact appeared to be most pronounced among drivers who reported TWD more frequently. Adjusted odds of TWD declined 42% following introduction of the legislation and associated enhanced public education and enforcement. Conclusions: These results identify a decrease in TWD following the introduction of enhanced penalties with corresponding public education and enforcement efforts, adding to the existing evaluative evidence base to inform transportation safety policy. These results also support the need to examine TWD and its determinants among all age groups.

Objective: To evaluate whether an educational campaign on distracted driving will have an impact in a given community., Methods: Investigators were stationed in an employee parking lot of a 256-bed hospital to determine baseline distracted driving followed by a 4-week hospital-wide distracted-driving awareness campaign. The campaign included signs/posters in the hospital, a booth outside of the cafeteria with flyers, a large banner in the employee lot and an opportunity for people to sign a pledge form to drive distraction free. The same employee lot was observed at the same time of the day to re-assess distracted driving immediately following the campaign. The observations were repeated again one year later to evaluate the short and long-term impact of the campaign., Results: A total of 485 vehicles were observed pre-campaign, identifying 170 (35%) distracted drivers at baseline. The awareness campaign resulted in 525 people pledging to drive distraction free. Following the campaign, 495 vehicles were observed and the number of distracted drivers was 64 (12.9%), showing a significant decrease in the number of distracted drivers by 22.1% (p < 0.01). One year later, 530 drivers were observed with 150 (28%) displaying one form of distraction., Conclusions: A local distracted driving educational campaign resulted in a significant decrease in the number of distracted drivers immediately following the campaign. However, one year after the campaign, there was an increase in distracted driving. The proportion of distracted drivers was still significantly lower than the initial rate of distracted-drivers.

Objective: The majority of U.S. teens admit to handheld cellphone use while driving, an increasingly common cause of crashes. Attitudes toward novel cellphone applications and settings that block use while driving are poorly understood, potentially limiting uptake. We examined teens' willingness to reduce cellphone use while driving and perceptions of potential strategies to limit this behavior., Methods: Teen drivers (n = 153) aged 16-17 who owned smartphones and admitted to texting while driving completed an online survey. Survey instruments measured willingness to give up cellphone use and perceptions of technological and behavioral economic strategies to reduce cellphone use while driving. We used chi-square tests to test the hypothesis that willingness to give up certain types of cellphone use while driving and the perceptions of strategies to reduce cellphone use while driving would differ by self-reported frequency of texting while driving in the past 30 days (low [1-5 days] vs. high [6 or more days])., Results: Most teens were willing or somewhat willing to give up reading texts (90%), sending texts (95%), and social media (99%) while driving. However, they were not willing to give up navigation (59%) and music applications (43%). Those who engaged in high-frequency texting while driving were more likely to say that they were not willing to give up navigation applications (73 vs. 44%, P <.001), music applications (54 vs. 32%, P <.001), and reading texts (15 vs. 4%, P =.029). Overall, the following strategies where rated as likely to be very effective for reducing texting while driving: gain-framed financial incentives (75%), loss-framed financial incentives (63%), group-based financial incentives (58%), insurance discounts (53%), automatic phone locking while driving (54%), e-mail notifications to parents (47%), automated responses to incoming texts (42%), peer concern (18%), and parental concern (15%). Those who engaged in high-frequency texting while driving were less likely to say that following strategies would be very effective: automated responses to incoming texts (33 vs. 53%, P =.016), peer concern (9 vs. 29%, P =.002), and parental concern (9 vs. 22%, P =.025). The strongest perceived benefit of cellphone blocking apps was decreasing distraction (86%). The predominant reason for not wanting to use this technology was not wanting parents to monitor their behavior (60%)., Conclusions: Promising strategies for increasing acceptance of cellphone blocking technology among teen drivers include automated screen locking and permitting hands-free navigation and music combined with behavioral economic incentives to sustain engagement.

Introduction: Distracted driving (talking and/or texting) is a growing public safety problem, with increasing incidence among adult drivers. The aim of this study was to identify the incidence of distracted driving (DD) among health care providers and to create awareness against DD. We hypothesized that distracted driving is prevalent among health care providers and a preventive campaign against distracted driving would effectively decrease distracted driving among health care providers., Methods: We performed a 4-phase prospective interventional study of all health care providers at our level 1 trauma center. Phase 1: one week of pre-intervention observation; phase 2: one week of intervention; phase 3: one week of postintervention observation; and phase 4: one week of 6 months of postintervention observation. Observations were performed outside employee parking garage at the following time intervals: 6:30-8:30 a.m., 4:40-5:30 p.m., and 6:30-7:30 p.m. Intervention included an e-mail survey, pamphlets and banners in the hospital cafeteria, and a postintervention survey. Hospital employees were identified with badges and scrubs, employees exiting through employee gate, and parking pass on the car. Outcome measure was incidence of DD pre, post, and 6 months postintervention., Results: A total of 15,416 observations (pre: 6,639, post: 4,220, 6 months post: 4,557) and 520 survey responses were collected. The incident of DD was 11.8% among health care providers. There was a significant reduction in DD in each time interval of observation between pre- and postintervention. On subanalysis, there was a significant decrease in talking (P = .0001) and texting (P = .01) while driving postintervention compared to pre-intervention. In the survey, 35.5% of respondents admitted to DD and 4.5% respondents were involved in an accident due to DD. We found that 77% respondents felt more informed after the survey and 91% respondents supported a state legislation against DD. The reduction in the incidence of DD postintervention was sustained even at 6-month follow-up., Conclusion: There was a 32% reduction in the incidence of distracted driving postintervention, which remained low even at 6-month follow-up. Implementation of an effective injury prevention campaign could reduce the incidence of distracted driving nationally.