Dataset Information

Simulator Pre-Screening of Underprepared Drivers Prior to Licensing On-Road Examination: Clustering of Virtual Driving Test Time Series Data.

ABSTRACT: BACKGROUND:A large Midwestern state commissioned a virtual driving test (VDT) to assess driving skills preparedness before the on-road examination (ORE). Since July 2017, a pilot deployment of the VDT in state licensing centers (VDT pilot) has collected both VDT and ORE data from new license applicants with the aim of creating a scoring algorithm that could predict those who were underprepared. OBJECTIVE:Leveraging data collected from the VDT pilot, this study aimed to develop and conduct an initial evaluation of a novel machine learning (ML)-based classifier using limited domain knowledge and minimal feature engineering to reliably predict applicant pass/fail on the ORE. Such methods, if proven useful, could be applicable to the classification of other time series data collected within medical and other settings. METHODS:We analyzed an initial dataset that comprised 4308 drivers who completed both the VDT and the ORE, in which 1096 (25.4%) drivers went on to fail the ORE. We studied 2 different approaches to constructing feature sets to use as input to ML algorithms: the standard method of reducing the time series data to a set of manually defined variables that summarize driving behavior and a novel approach using time series clustering. We then fed these representations into different ML algorithms to compare their ability to predict a driver's ORE outcome (pass/fail). RESULTS:The new method using time series clustering performed similarly compared with the standard method in terms of overall accuracy for predicting pass or fail outcome (76.1% vs 76.2%) and area under the curve (0.656 vs 0.682). However, the time series clustering slightly outperformed the standard method in differentially predicting failure on the ORE. The novel clustering method yielded a risk ratio for failure of 3.07 (95% CI 2.75-3.43), whereas the standard variables method yielded a risk ratio for failure of 2.68 (95% CI 2.41-2.99). In addition, the time series clustering method with logistic regression produced the lowest ratio of false alarms (those who were predicted to fail but went on to pass the ORE; 27.2%). CONCLUSIONS:Our results provide initial evidence that the clustering method is useful for feature construction in classification tasks involving time series data when resources are limited to create multiple, domain-relevant variables.

SUBMITTER: Grethlein D

PROVIDER: S-EPMC7333075 | biostudies-literature | 2020 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Simulator Pre-Screening of Underprepared Drivers Prior to Licensing On-Road Examination: Clustering of Virtual Driving Test Time Series Data.

Grethlein David D Winston Flaura Koplin FK Walshe Elizabeth E Tanner Sean S Kandadai Venk V Ontañón Santiago S

Journal of medical Internet research 20200618 6

<h4>Background</h4>A large Midwestern state commissioned a virtual driving test (VDT) to assess driving skills preparedness before the on-road examination (ORE). Since July 2017, a pilot deployment of the VDT in state licensing centers (VDT pilot) has collected both VDT and ORE data from new license applicants with the aim of creating a scoring algorithm that could predict those who were underprepared.<h4>Objective</h4>Leveraging data collected from the VDT pilot, this study aimed to develop and ...[more]

PMID: 32554384

Similar Datasets

Project description:Objectives: Attention Restoration Theory (ART) suggests that walking or being in natural settings, as opposed to urban environments, benefits cognitive skills because it is less demanding on attentional resources. However, it is unclear whether the same occurs when the person is performing a complex task such as driving, although it is proven that driving through different road environments is associated with different levels of fatigue and may engage attention differently. The present study investigated whether exposure to rural vs. urban road environments while driving would affect attentional capacity in young people after the drive, in line with the classic ART paradigms. Methods: We asked 38 young participants to complete the Sustained Attention to Response Task (SART) before and after being exposed to a rural or urban road in a virtual reality environment while driving in a full vehicle immersive driving simulator. Changes in SART performance based on environmental exposure where explored in terms of target sensitivity, accuracy, reaction times, and inverse efficiency. We analyzed potential road type effects on driving speed and accuracy. Possible effects of driving on attention were tested by comparing the sample performance to that of a control group of 15 participants who did not drive and sat on the passenger seat instead. Results: Exposure to rural or urban road environments in the driving sample was not associated with any significant changes in attentional performance. The two exposure groups did not differ significantly in terms of driving behavior. Comparisons between the driving sample and the control group controlling for age indicated that participants who drove were more accurate but slower at the SART than those who were passengers. Conclusion: The present study does not support the hypothesis that a short drive in a natural setting may promote attention restoration as compared to an urban setting. Methodological considerations as well as recommendations for future research are discussed.

Project description:BACKGROUND:Distracted driving attributable to the performance of secondary tasks is a major cause of motor vehicle crashes both among teenagers who are novice drivers and among adults who are experienced drivers. METHODS:We conducted two studies on the relationship between the performance of secondary tasks, including cell-phone use, and the risk of crashes and near-crashes. To facilitate objective assessment, accelerometers, cameras, global positioning systems, and other sensors were installed in the vehicles of 42 newly licensed drivers (16.3 to 17.0 years of age) and 109 adults with more driving experience. RESULTS:During the study periods, 167 crashes and near-crashes among novice drivers and 518 crashes and near-crashes among experienced drivers were identified. The risk of a crash or near-crash among novice drivers increased significantly if they were dialing a cell phone (odds ratio, 8.32; 95% confidence interval [CI], 2.83 to 24.42), reaching for a cell phone (odds ratio, 7.05; 95% CI, 2.64 to 18.83), sending or receiving text messages (odds ratio, 3.87; 95% CI, 1.62 to 9.25), reaching for an object other than a cell phone (odds ratio, 8.00; 95% CI, 3.67 to 17.50), looking at a roadside object (odds ratio, 3.90; 95% CI, 1.72 to 8.81), or eating (odds ratio, 2.99; 95% CI, 1.30 to 6.91). Among experienced drivers, dialing a cell phone was associated with a significantly increased risk of a crash or near-crash (odds ratio, 2.49; 95% CI, 1.38 to 4.54); the risk associated with texting or accessing the Internet was not assessed in this population. The prevalence of high-risk attention to secondary tasks increased over time among novice drivers but not among experienced drivers. CONCLUSIONS:The risk of a crash or near-crash among novice drivers increased with the performance of many secondary tasks, including texting and dialing cell phones. (Funded by the Eunice Kennedy Shriver National Institute of Child Health and Human Development and the National Highway Traffic Safety Administration.).

Project description:ObjectiveRoad traffic injuries (RTIs) are recognized as one of the most important causes of morbidity and mortality throughout the world, especially in developing countries. Human behavior is reportedly one of the critical factors in the occurrence of such injuries. The purpose of this study is to evaluate the correlation of abnormal driving behaviors with the frequency and severity of RTIs among drivers in Hamadan, west of Iran.MethodsThe present cross-sectional study was conducted on 800 people driving, who were selected by multistage cluster sampling technique. Data were collected using a three-part self-administered questionnaire including demographic, social and driving characteristics; the Manchester driver behavior questionnaire (DBQ); as well as information on a history of the occurrence of the injuries caused by the crashes and the severity of them. Data were statistically analyzed using numerical indices, linear regression analysis, Pearson correlation, ordinal logistic regression model and multinomial logistic regression.ResultsThe highest and lowest mean percentages of abnormal driving behavior were related to unintentional violations (19.13) and Lapses (16.44), respectively. "Changing radio stations and listening to music while driving", "overtaking a driver who drives slowly", and "unintentionally exceeding the speed limit" were the three highest behaviors associated with road traffic injuries, with the mean and standard deviation of (1.93 ± 1.4), (1.90±1.4), (1.58±1.3), respectively. Age, gender, educational level, driving experience and driving hours during the day were significantly associated with DBQ dimensions and severity of road traffic injuries.ConclusionsThe results of this study showed that socio-demographic characteristics were significantly correlated with driving behavior. In addition, driving behaviors were correlated with traffic crashes and the resulting injuries. The findings of this study can be utilized to develop driving behavior interventions among the drivers.

Project description:The number of older drivers is steadily increasing, and advancing age is associated with a high rate of automobile crashes and fatalities. This can be attributed to a combination of factors including decline in sensory, motor, and cognitive functions due to natural aging or neurodegenerative diseases such as HIV-Associated Neurocognitive Disorder (HAND). Current clinical assessment methods only modestly predict impaired driving. Thus, there is a need for inexpensive and scalable tools to predict on-road driving performance. In this study EEG was acquired from 39 HIV+ patients and 63 healthy participants (HP) during: 3-Choice-Vigilance Task (3CVT), a 30-min driving simulator session, and a 12-mile on-road driving evaluation. Based on driving performance, a designation of Good/Poor (simulator) and Safe/Unsafe (on-road drive) was assigned to each participant. Event-related potentials (ERPs) obtained during 3CVT showed increased amplitude of the P200 component was associated with bad driving performance both during the on-road and simulated drive. This P200 effect was consistent across the HP and HIV+ groups, particularly over the left frontal-central region. Decreased amplitude of the late positive potential (LPP) during 3CVT, particularly over the left frontal regions, was associated with bad driving performance in the simulator. These EEG ERP metrics were shown to be associated with driving performance across participants independent of HIV status. During the on-road evaluation, Unsafe drivers exhibited higher EEG alpha power compared to Safe drivers. The results of this study are 2-fold. First, they demonstrate that high-quality EEG can be inexpensively and easily acquired during simulated and on-road driving assessments. Secondly, EEG metrics acquired during a sustained attention task (3CVT) are associated with driving performance, and these metrics could potentially be used to assess whether an individual has the cognitive skills necessary for safe driving.

Project description:The success of driver graduated licensing systems (GLS) is demonstrated primarily in jurisdictions that licence at young ages with requirements expiring at age 18. In Australia, GLS requirements typically apply for all applicants aged under 25. In 2007, the Queensland licensing system was strengthened, extending the learner and introducing a 100-hour supervised driving requirement, introducing restrictions on passenger carriage at night and high-powered vehicles for provisional drivers, and on phone use for all novice drivers (learner and provisional). The objective of the current research was to evaluate whether these changes were associated with reductions in crashes (all) and killed-and-serious-injury (KSI) crashes involving novice drivers, and respective casualties. Government licensing and police crash records were linked and interrupted time series analysis was used to examine potential shifts in crash trends by rates of licensed drivers per month. Substantial declines were found in novice driver crashes (13.1% per year; 95%CI -0.0130, -0.0096), crash casualties (13.9% per year; 95%CI -0.0137, -0.0101), KSI crashes (5.4% per year; 95%CI -0.0080, -0.0046) and associated casualties (5.2% per year; 95%CI -0.0075, -0.0039). Compared to the total licensed driver population, declines in crashes (3.0% per year; 95%CI -0.0027, -0.0007) and crash casualties (2.9% per year; 95%CI -0.0029, -0.0006) but not KSI outcomes were observed. More narrowly, declines were found for provisional-licensed driver crashes (9.3% per year; 95%CI -0.0096, -0.0063) and KSI crashes (3.6% per year; 95%CI -0.0004, -0.0128) that were approximately 2.6% and 1.2% greater than respective declines for 25-29-year-old open-licensed drivers. Substantial declines also were observed in novice driver single-vehicle, night, passenger and alcohol crashes. Overall, these results demonstrate that GLS can be effective in a later age licensing jurisdiction. However, KSI outcomes were limited. Modelling research is recommended on ways to further strengthen Queensland's GLS to achieve greater trauma reductions.

Dataset Information

Simulator Pre-Screening of Underprepared Drivers Prior to Licensing On-Road Examination: Clustering of Virtual Driving Test Time Series Data.

Publications

Simulator Pre-Screening of Underprepared Drivers Prior to Licensing On-Road Examination: Clustering of Virtual Driving Test Time Series Data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets