scholarly journals 0203 To and From the Night Shift: Risky On-the-Road Driving in Night Shift Workers

SLEEP ◽  
2020 ◽  
Vol 43 (Supplement_1) ◽  
pp. A79-A80
Author(s):  
N Murugan ◽  
C Sagong ◽  
A S Cuamatzi Castelan ◽  
K Moss ◽  
T Roth ◽  
...  
Keyword(s):  
Night Shift ◽  
Driving Safety ◽  
Drowsy Driving ◽  
Risky Driving ◽  
Shift Workers ◽  
The Road ◽  
Circadian Phase ◽  
Driving Behaviors ◽  
On The Road ◽  
Risky Driving Behaviors

Abstract Introduction Drowsy driving is a common occupational hazard for night shift workers (NSWs). While sleep loss is commonly identified as the primary culprit of drowsy driving, another critical factor to consider is circadian phase. However, the role of circadian phase in driving safety has not been well characterized in NSWs. This study examined if dim light melatonin offset (DLMOff, i.e. the cessation of melatonin secretion) is also a relevant phase marker of susceptibility to four different subtypes of risky on-the-road driving behaviors. Methods On-the-road driving was monitored over 8 weeks via a mobile application that tracked risky driving behaviors using accelerometer and GPS data from cell phones (N=15; 3052 total driving events recorded). Risky driving behaviors included: 1) frequency of hard-braking events, 2) frequency of aggressive-acceleration events, 3) duration of excessive-speeding, and 4) duration of phone-usage. At week 2, participants spent 24 hours in-lab where hourly saliva samples were collected and assayed for melatonin, and DLMOff was calculated. Phase angle of driving events relative to DLMOff was used as the predictor in nested mixed-effects regressions, with risky driving behaviors as the outcome variables. Results The most common occurrences of risky driving were phone-usage and hard-braking. On average, NSWs had 46.7% and 42.0% of driving events with at least one occurrence of phone-usage and hard-braking, respectively. Rates of aggressive-acceleration and speeding were 24.4% and 20.4%. Positive phase angles (i.e. driving after DLMOff) were associated with reduced rates of hard-braking and aggressive-acceleration, but not of phone-usage and excessive-speeding. Specifically, rates of hard-braking and aggressive-acceleration decreased by 4.5% (p<.01) and 3.4% (p=.05) every two hours following DLMOff, respectively. Conclusion The study suggests DLMOff appears to be an important variable for predicting accident risk in NSWs. If replicated, circadian phase should be considered in recommendations to increase occupational health and safety of NSWs. Support Support for this study was provided to PC by NHLBI (K23HL138166).

Spanish Young Adults' Perceptions of the Costs and Benefits of Risky Driving Behaviors

2012 ◽  
Vol 15 (2) ◽  
pp. 638-647 ◽  
Author(s):  
Mandeep K. Dhami ◽  
Rocío García-Retamero
Keyword(s):  
Young Adults ◽  
Risk Taking ◽  
Road Safety ◽  
Risky Behaviors ◽  
Costs And Benefits ◽  
Theoretical Understanding ◽  
The Road ◽  
Driving Behaviors ◽  
On The Road ◽  
Risky Driving Behaviors

We used an open-ended survey to elicit Spanish young adults' perceptions of the benefits and drawbacks of speeding and not wearing a seatbelt (or helmet).Around half of the sample reported past engagement in these two risky behaviors, although forecasted engagement was low. Past and forecasted risk taking were positively correlated. Participants provided more drawbacks than benefits of each risky behavior. Drawbacks typically referred to a combination of behavioral acts and social reactions (e.g., accident, punishment) that occurred during the journey. By contrast, benefits largely referred to personal effects (e.g., save time, comfort) that occurred after the journey had ended (speeding) or during the journey (not wearing a seatbelt/helmet). These findings contribute to our theoretical understanding of young adults' risk taking on the road, and to the development of road safety programs.

Using Real-Time and Post Hoc Feedback to Improve Driving Safety for Novice Drivers

2016 ◽  
Vol 60 (1) ◽  
pp. 1936-1940 ◽  
Author(s):  
Sheila G. Klauer ◽  
Tina B. Sayer ◽  
Peter Baynes ◽  
Gayatri Ankem
Keyword(s):  
Real Time ◽  
Motor Vehicle ◽  
Driving Behavior ◽  
Driving Safety ◽  
Risky Driving ◽  
Novice Drivers ◽  
Safe Driving ◽  
Driving Behaviors ◽  
Post Hoc ◽  
Risky Driving Behaviors

Introduction. Motor vehicle crashes remain the leading cause of fatalities among teens in the U.S. (National Center for Injury Prevention and Control, 2013). Prior research suggests that real-time and post hoc feedback can improve teen driver behavior. The Driver Coach Study (DCS) aimed to improve teens’ safe driving habits by providing them real-time feedback and post hoc feedback to a broader range of risky driving behaviors that have never been used in previous studies. Exposure data were also collected so that rates of risky driving behaviors over time could be assessed. Post hoc feedback, which included an electronic report card of risky driving behavior as well as video clips, was provided to both teens and parents via email and secure website link. Method. Ninety-two teen/parent dyads were recruited in southwest Virginia to have a data acquisition system (DAS) installed in their vehicles within two weeks of receiving their learner’s permit. Data were collected through the nine-month (minimum) learner’s permit phase plus seven months of provisional licensure. Feedback was only provided for the first six months of post licensure, then turned off to assess whether teenagers returned to unsafe driving behavior. Trained data coders reviewed 15 seconds of video surrounding each risky driving maneuver, and recorded driver errors such as poor vehicle control, poor speed selection, drowsiness, etc., for each event. Results. In this paper, the relationship between driver coaching and driver errors will be examined across the six-month feedback phase and also compared to the seventh month when feedback was turned off. Conclusions. This study has implications for the design of future monitoring and feedback systems, as it is currently unknown whether these devices can improve novice drivers’ crash rates.

Perceived Self-Efficacy and Risky Driving Behaviors

2010 ◽  
Vol 69 (4) ◽  
pp. 233-238 ◽  
Author(s):  
Nolwenn Morisset ◽  
Florence Terrade ◽  
Alain Somat
Keyword(s):  
Self Efficacy ◽  
Risky Driving ◽  
Driving Behaviors ◽  
Conduite Automobile ◽  
Risky Driving Behaviors

Les recherches dans le domaine de la santé, et notamment en matière de conduite automobile, attestent que le jugement subjectif du risque (comparatif et absolu) et l’auto-efficacité perçue sont impliqués dans les comportements à risque. Cette étude avait pour objectif d’étudier l’influence de l’auto-efficacité perçue sur le jugement subjectif du risque, évalué au moyen d’une mesure indirecte, et de tester le rôle médiateur de ce facteur entre l’auto-efficacité perçue et les comportements auto-déclarés. Les participants, 90 hommes, lisaient deux scénarii décrivant les deux comportements les plus impliqués dans l’accidentologie: la vitesse et l’alcool au volant. Les résultats ne montrent pas de lien significatif entre l’auto-efficacité perçue et le score de jugement comparatif mais une relation significative avec les deux évaluations absolues du risque (autrui et soi). De plus, le jugement absolu du risque pour soi médiatise partiellement la relation entre auto-efficacité perçue et comportements auto-déclarés relatifs aux deux risques routiers étudiés.

Real-Time Prediction of Vehicle Trajectories for Proactively Identifying Risky Driving Behaviors at High-Speed Intersections

2018 ◽  
Vol 2672 (38) ◽  
pp. 233-244 ◽  
Author(s):  
Chaopeng Tan ◽  
Nan Zhou ◽  
Fen Wang ◽  
Keshuang Tang ◽  
Yangbeibei Ji
Keyword(s):  
Phase Transition ◽  
High Speed ◽  
Red Light ◽  
Risky Behaviors ◽  
Risky Driving ◽  
Red Light Running ◽  
Driving Behaviors ◽  
Vehicle Trajectories ◽  
Single Vehicle ◽  
Risky Driving Behaviors

At high-speed intersections in many Chinese cities, a traffic-light warning sequence at the end of the green phase—three seconds of flashing green followed by three seconds of yellow—is commonly implemented. Such a long phase transition time leads to heterogeneous decision-making by approaching drivers as to whether to pass the signal or stop. Therefore, risky driving behaviors such as red-light running, abrupt stop, and aggressive pass are more likely to occur at these intersections. Proactive identification of risky behaviors can facilitate mitigation of the dilemma zone and development of on-board safety altering strategies. In this study, a real-time vehicle trajectory prediction method is proposed to help identify risky behaviors during the signal phase transition. Two cases are considered and treated differently in the proposed method: a single vehicle case and a following vehicle case. The adaptive Kalman filter (KF) model and the K-nearest neighbor model are integrated to predict vehicle trajectories. The adaptive KF model and intelligent driver model are fused to predict the following vehicles’ trajectories. The proposed models are calibrated and validated using 1,281 vehicle trajectories collected at three high-speed intersections in Shanghai. Results indicate that the root mean square error between the predicted trajectories and the actual trajectories is 5.02 m for single vehicles and 2.33 m for following vehicles. The proposed method is further applied to predict risky behaviors, including red-light running, abrupt stop, aggressive pass, speeding pass, and aggressive following. The overall prediction accuracy is 95.1% for the single vehicle case and 96.2% for the following vehicle case.

scholarly journals Identifying and Labeling Potentially Risky Driving: A Multistage Process Using Real-World Driving Data

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Charles Marks ◽  
Arash Jahangiri ◽  
Sahar Ghanipoor Machiani
Keyword(s):  
Real World ◽  
Traffic Accidents ◽  
Network Models ◽  
Multistage Process ◽  
Neural Network Models ◽  
Risky Driving ◽  
Vehicle Accidents ◽  
Driving Behaviors ◽  
Novel Approach ◽  
Risky Driving Behaviors

Every year, over 50 million people are injured and 1.35 million die in traffic accidents. Risky driving behaviors are responsible for over half of all fatal vehicle accidents. Identifying risky driving behaviors within real-world driving (RWD) datasets is a promising avenue to reduce the mortality burden associated with these unsafe behaviors, but numerous technical hurdles must be overcome to do so. Herein, we describe the implementation of a multistage process for classifying unlabeled RWD data as potentially risky or not. In the first stage, data are reformatted and reduced in preparation for classification. In the second stage, subsets of the reformatted data are labeled as potentially risky (or not) using the Iterative-DBSCAN method. In the third stage, the labeled subsets are then used to fit random forest (RF) classification models—RF models were chosen after they were found to be performing better than logistic regression and artificial neural network models. In the final stage, the RF models are used predictively to label the remaining RWD data as potentially risky (or not). The implementation of each stage is described and analyzed for the classification of RWD data from vehicles on public roads in Ann Arbor, Michigan. Overall, we identified 22.7 million observations of potentially risky driving out of 268.2 million observations. This study provides a novel approach for identifying potentially risky driving behaviors within RWD datasets. As such, this study represents an important step in the implementation of protocols designed to address and prevent the harms associated with risky driving.

Real-Time V2V Communication With a Machine Learning-Based System for Detecting Drowsiness of Drivers

2021 ◽  
Vol 13 (4) ◽  
pp. 35-50
Author(s):  
Ahmed Y. Awad ◽  
Seshadri Mohan
Keyword(s):  
Machine Learning ◽  
Traffic Accidents ◽  
Ad Hoc ◽  
Economic Losses ◽  
Drowsy Driving ◽  
The Road ◽  
V2v Communication ◽  
Physical Injuries ◽  
On The Road ◽  
The U.S

This article applies machine learning to detect whether a driver is drowsy and alert the driver. The drowsiness of a driver can lead to accidents resulting in severe physical injuries, including deaths, and significant economic losses. Driver fatigue resulting from sleep deprivation causes major accidents on today's roads. In 2010, nearly 24 million vehicles were involved in traffic accidents in the U.S., which resulted in more than 33,000 deaths and over 3.9 million injuries, according to the U.S. NHTSA. A significant percentage of traffic accidents can be attributed to drowsy driving. It is therefore imperative that an efficient technique is designed and implemented to detect drowsiness as soon as the driver feels drowsy and to alert and wake up the driver and thereby preventing accidents. The authors apply machine learning to detect eye closures along with yawning of a driver to optimize the system. This paper also implements DSRC to connect vehicles and create an ad hoc vehicular network on the road. When the system detects that a driver is drowsy, drivers of other nearby vehicles are alerted.

E-Bike Riders Risky Driving Behaviors Questionnaire

2018 ◽  
Author(s):  
Chen Wang ◽  
Chengcheng Xu ◽  
Jingxin Xia ◽  
Zhendong Qian
Keyword(s):  
Risky Driving ◽  
Driving Behaviors ◽  
Risky Driving Behaviors
Sign in / Sign up

Export Citation Format

Share Document