How is the duration of distraction related to safety-critical events? Harnessing naturalistic driving data to explore the role of driving instability.

INTRODUCTION: Due to a variety of secondary tasks performed by drivers, distracted driving has become a critical concern. At 50 mph, sending/reading a text for 5 seconds is equivalent to driving the length of a football field (360 ft) with eyes closed. A fundamental understanding of how distractions lead to crashes is needed to develop appropriate countermeasure strategies. A key question is whether distraction increases driving instability, which then further contributes to safety-critical events (SCEs). METHODS: By harnessing newly available microscopic driving data and using the safe systems approach, a subsample of naturalistic driving study data were analyzed, collected through the second strategic highway research program. Rigorous path analysis (including Tobit and Ordered Probit regressions) is used to jointly model the instability in driving (using coefficient of variation of speed) and event outcomes (including baseline, near-crash, and crash). The marginal effects from the two models are used to compute direct, indirect, and total effects of distraction duration on SCEs. RESULTS: Results indicate that a longer duration of distraction was positively but non-linearly associated with higher driving instability and higher chances of SCEs. Where, the chance of a crash and near-crash was higher by 34% and 40%, respectively, with a unit increase in driving instability. Based on the results, the chance of both SCEs significantly increases non-linearly with an increase in distraction duration beyond 3 seconds. For instance, the chance of a crash is 16% for a driver distracted for 3 seconds, which increases to 29% if a driver is distracted for 10 seconds. CONCLUSIONS AND PRACTICAL APPLICATIONS: Using path analysis, the total effects of distraction duration on SCEs are even higher when its indirect effects on SCEs through driving instability are considered. Potential practical implications including traditional countermeasures (changes in roadway environments) and vehicle technologies are discussed in the paper.

Heterogeneous ensemble learning for enhanced crash forecasts - A frequentist and machine learning based stacking framework.

INTRODUCTION: This study aims to increase the prediction accuracy of crash frequency on roadway segments that can forecast future safety on roadway facilities. A variety of statistical and machine learning (ML) methods are used to model crash frequency with ML methods generally having a higher prediction accuracy. Recently, heterogeneous ensemble methods (HEM), including "stacking," have emerged as more accurate and robust intelligent techniques providing more reliable and accurate predictions. METHODS: This study applies "Stacking" to model crash frequency on five-lane undivided (5 T) segments of urban and suburban arterials. The prediction performance of "Stacking" is compared with parametric statistical models (Poisson and negative binomial) and three state-of-the-art ML techniques (Decision tree, random forest, and gradient boosting), each of which is termed as the base-learner. By employing an optimal weight scheme to combine individual base-learners through stacking, the problem of biased predictions in individual base-learners due to differences in specifications and prediction accuracies is avoided. Data including crash, traffic, and roadway inventory were collected and integrated from 2013 to 2017. The data are split into training (2013-2015), validation (2016), and testing (2017) datasets. After training five individual base-learners using training data, prediction outcomes are obtained for the five base-learners using validation data that are then used to train a meta-learner. RESULTS: Results of statistical models reveal that crashes increase with the density (number per mile) of commercial driveways whereas decrease with average offset distance to fixed objects. Individual ML methods show similar results - in terms of variable importance. A comparison of out-of-sample predictions of various models or methods confirms the superiority of "Stacking" over the alternative methods considered. CONCLUSIONS AND PRACTICAL APPLICATIONS: From a practical standpoint, "stacking" can enhance prediction accuracy (compared to only one base-learner with a particular specification). When applied systemically, stacking can help identify more appropriate countermeasures.

Copula-based bivariate count data regression models for simultaneous estimation of crash counts based on severity and number of vehicles.

Statistical models of crash frequency typically apply univariate regression models to estimate total crash frequency or crash counts by various categories. However, a possible correlation between the dependent variables or unobserved variables associated with the dependent variables is not considered when univariate models are used to estimate categorized crash counts-such as different severity levels or numbers of vehicles involved. This may lead to inefficient parameter estimates compared to multivariate models that directly consider these correlations. This paper compares the results obtained from univariate negative binomial regression models of property-damage only (PDO) and fatal plus injury (FI) crash frequencies to models using traditional bivariate and copula-based bivariate negative binomial regression models. A similar comparison was made using models for the expected crash frequency of single- (SV) and multi-vehicle (MV) crashes. The models were estimated using two-lane, two-way rural highway segment-level data from an engineering district in Pennsylvania. The results show that all bivariate negative binomial models (with or without copulas) outperformed the corresponding univariate negative binomial models for PDO and FI, as well as SV and MV, crashes. Second, the statistical association of various traffic and roadway/roadside features with PDO and FI, as well as SV and MV crashes, were not the same relative to their corresponding relationships in the univariate models. The bivariate negative binomial model with normal copula outperformed all other models based on the goodness-of-fit statistics. The results suggest that copula-based bivariate negative binomial regression models may be a valuable alternative for univariate models when simultaneously modeling two disaggregate levels of crash counts.

Exploring pathways from driving errors and violations to crashes: The role of instability in driving.

This study explores how different driving errors, violations, and roadway environments contribute to safety-critical events through instability in driving speed. We harness a subsample (N = 9239) of the naturalistic driving study (NDS) data collected through the Second Strategic Highway Research Program (SHRP2). From a methodological standpoint, we use the safe systems approach relying on path analysis to jointly model outcomes. This accounts for the potential correlation between unobserved factors associated with both instability in driving speed and epoch (video stream) outcomes, i.e., baseline or event-free driving, near-crashes, and crashes. Tobit and ordered Probit regressions are estimated to model the coefficient of variation (COV) of speed and epoch outcomes, respectively. Results from the Tobit model indicate that driving errors and violations are associated with instability in the driving speed of the subject driver (COV of speed). The Probit model reveals that driving errors, violations, and instability in driving speed are associated with higher chances of crashes and near-crashes. Our key finding is that driving errors and violations not only induce event risk directly but also indirectly through instability in driving speed. For instance, recognition errors associate with higher crash risk by 6.78 % but this error is accompanied by instability in driving speed, which further increases event risk by 4.73 %, bringing the total increase in risk to 11.51 %. Moreover, significant correlations were found between unobserved factors reflected in the error terms of the two models. Ignoring such correlations can lead to inefficient parameter estimates. Based on the findings, practical implications are discussed, which can lead to effective countermeasures that effectively reduce crash risk.

Toward better measurement of traffic injuries - Comparison of anatomical injury measures in predicting the clinical outcomes in motorcycle crashes.

INTRODUCTION: Little evidence exists in the literature regarding the discrimination power of better anatomical injury measures in differentiating clinical outcomes in motorcycle crashes. Furthermore, multiple injuries to different body parts of the rider are seldom analyzed. This study focuses on comparing anatomical injury measures such as the injury severity score (ISS) and the new injury severity score (NISS) in capturing injuries of multiple injured riders and examining the discriminatory capabilities of the ISS and NISS in predicting clinical outcomes post motorcycle crash. METHODS: The study harnessed unique and comprehensive injury data on 322 riders from the US DOT Federal Highway Administration's Motorcycle Crash Causation Study (MCCS). Detailed exploratory analysis is performed and discrete/ordered statistical models are estimated for three clinical outcomes: mortality risk, trauma risk, and trauma status. RESULTS: Around 9% of the riders died and 45% of the riders had injuries. Around 36% of the riders were hospitalized, disabled, or institutionalized. While a very strong dependence was found between ISS and NISS, ISS underestimated injuries sustained by riders. Statistical models for mortality risk revealed that a unit increase in the ISS and NISS was correlated with a 1.18 and 1.17 times increase in the odds of mortality, respectively. Moreover, a unit increase in ISS and NISS values was correlated with a higher trauma risk by 1.48 and 1.36 times, respectively. Our analysis reveals that the probability of a rider being hospitalized or disabled/institutionalized increases with an increase in the NISS. Conclusions and practical applications: The NISS exhibits significantly better calibration and discriminatory ability in differentiating survivors and non-survivors and in predicting trauma status - underscoring the importance of accounting for microscopic body-part-level injury data in motorcycle crashes. We consider that compared with the KABCO scale, the ISS and NISS are more nuanced scores that can better measure the overall injury intensity and can lead to more targeted countermeasures.

Understanding how relationships between crash frequency and correlates vary for multilane rural highways: Estimating geographically and temporally weighted regression models.

Safety Performance Functions (SPFs) are critical tools in the management of highway safety projects. SPFs are used to predict the average number of crashes per year at a location, such as a road segment or an intersection. The Highway Safety Manual (HSM) provides default safety performance functions (SPFs), but it is recommended that states in the U.S. develop jurisdiction-specific SPFs using local crash data. To do this for the state of Tennessee, crash and road inventory data were integrated for multi-lane rural highway segments for the years 2013-2017. In addition to developing SPFs similar to those contained in the HSM, this study applied a new methodology to capture variation in crashes in both space and time. Specifically, Geographically and Temporally Weighted Regression (GTWR) models for the localization of SPFs were developed. The new methodology incorporates temporal aspects of crashes in the models because the impact of a specific variable on crash frequency may vary over time due to several reasons. Results indicate that GTWR models remarkably outperform the traditional regression models by capturing spatio-temporal heterogeneity. Most parameter estimates were found to vary substantially across space and time. In other words, the association of contributing variables with the number of crashes can vary from one region or period of time to another. This finding weakens the idea of transferring default SPFs to other states and applying a single localized SPF to all regions of a state. Enabled by growing computational power, these results emphasize the importance of accounting for spatial and temporal heterogeneity and developing highly localized SPFs. The methodology of this study can be used by researchers to follow the temporal trend and location of critical factors to identify sites for safety improvements.

Built environment, driving errors and violations, and crashes in naturalistic driving environment.

Driving errors and violations are highly relevant to the safe systems approach as human errors tend to be a predominant cause of crash occurrence. In this study, we harness highly detailed pre-crash Naturalistic Driving Study (NDS) data 1) to understand errors and violations in crash, near-crash, and baseline (no event) driving situations, and 2) to explore pathways that lead to crashes in diverse built environments by applying rigorous modeling techniques. The "locality" factor in the NDS data provides information on various types of roadway and environmental surroundings that could influence traffic flow when a precipitating event is observed. Coded by the data reductionists, this variable is used to quantify the associations of diverse environments with crash outcomes both directly and indirectly through mediating driving errors and violations. While the most prevalent errors in crashes were recognition errors such as failing to recognize a situation (39 %) and decision errors such as not braking to avoid a hazard (34 %), performance errors such as poor lateral or longitudinal control or weak judgement (8 %) were most strongly correlated with crash occurrence. Path analysis uncovered direct and indirect relationships between key built-environment factors, errors and violations, and crash propensity. Possibly due to their complexity for drivers, urban environments are associated with higher chances of crashes (by 6.44 %). They can also induce more recognition errors which correlate with an even higher chances of crashes (by 2.16 % with the "total effect" amounting to 8.60 %). Similar statistically significant mediating contributions of recognition errors and decision errors near school zones, business or industrial areas, and moderate residential areas were also observed. From practical applications standpoint, multiple vehicle technologies (e.g., collision warning systems, cruise control, and lane tracking system) and built-environment (roadway) changes have the potential to reduce driving errors and violations which are discussed in the paper.

Injury severity analysis of pedestrian and bicyclist trespassing crashes at non-crossings: A hybrid predictive text analytics and heterogeneity-based statistical modeling approach.

Non-motorists involved in rail-trespassing crashes are usually more vulnerable to receiving major or fatal injuries. Previous research has used traditional quantitative crash data for understanding factors contributing to injury outcomes of non-motorists in train involved collisions. However, usually overlooked crash narratives can provide useful and unique contextual crash-specific information regarding factors associated with injury outcomes. The main objective of this study is to harness the rapid advancements in more sophisticated qualitative analysis procedures for identifying thematic concepts in unstructured crash narrative data. A two-staged hybrid approach is proposed where text mining is applied first to extract valuable information from crash narratives followed by inclusion of the new variables derived from text mining in formulation of advanced statistical models for injury outcomes. By using ten-year (2006-2015) non-motorist non-crossing trespassing injury data obtained from the Federal Railroad Administration, statistical procedures and advanced machine learning text analytics are applied to extract unique information on contributory factors of trespassers' injury outcomes. The key concepts are systematically categorized into trespasser, injury, train, medical, and location related factors. A total of 13 unique variables are extracted from the thematic concepts that are not present in traditional tabular crash data. The analysis reveals a positive statistically significant association between presence of crash narrative and trespasser's injury outcome (coded as minor, major, and fatal injury). Compared to crashes with minor injuries, crashes involving major and fatal injuries are more likely to be reported with crash narratives. A crosstabulation of new variables derived from text mining with injury outcomes revealed that trespassers with confirmed suicide attempts, trespassers wearing headphones, or talking on cell phones are more likely to receive fatal injuries. Among other factors identified, trespassers under alcohol influence, trespasser hit by commuter train, and advance warnings by engineer are associated with more severe (major and fatal) trespasser injury outcomes. Accounting for unobserved heterogeneity and controlling for other factors, fixed and random parameter discrete outcome models are developed to understand the heterogeneous correlations between trespasser injury outcomes and the new crash specific explanatory variables derived from text mining - providing deeper insights. Practical implications and future research directions are discussed.

A taxonomy of driving errors and violations: Evidence from the naturalistic driving study.

Driving errors and violations are identified as contributing factors in most crash events. To examine the role of human factors and improve crash investigations, a systematic taxonomy of driver errors and violations (TDEV) is developed. The TDEV classifies driver errors and violations based on their occurrence during the theoretically based perception-reaction process and analyzes their contributions in safety critical events. To empirically explore errors and violations, made by drivers of instrumented vehicles, in diverse built environments, this study harnesses unique and highly detailed pre-crash sensor data collected in the Naturalistic Driving Study (NDS), containing 673 crashes, 1,331 near-crashes and 7,589 baselines (no-event). Human factors are categorized into recognition errors, decision errors, performance errors, and errors due to the drivers' physical condition or their lack of contextual experience/familiarity, and intentional violations. In the NDS data, built environments (measured by roadway localities) are classified based on roadway functional classification and land uses, e.g., residential areas, school zones, and church zones. Based on the crash percentage to baseline percentage in a specific locality, interstates and open country/open residential (rural and semi-rural settings) may pose lower risks, while urban, business/industrial, and school zone locations showed higher crash risk. Human errors and violations by instrumented vehicle drivers contributed to 93% of the observed crashes, while roadway factors contributed to 17%, vehicle factors contributed in 1%, and 4% of crashes contained unknown factors. The most common human errors were recognition and decision errors, which occurred in 39% and 34% of crashes, respectively. These two error types occurred more frequently (each contributing to nearly 39% of crashes) in business or industrial land use environments (but not in dense urban localities). The findings of this study reveal continued prevalence of human factors in crashes. The distribution of driving errors and violations across different roadway environments can aid in the implementation of driver assistance systems and place-based interventions that can potentially reduce these driving errors and violations.

Examining correlations between motorcyclist's conspicuity, apparel related factors and injury severity score: Evidence from new motorcycle crash causation study.

Motorcyclists are vulnerable road users at a particularly high risk of serious injury or death when involved in a crash. In order to evaluate key risk factors in motorcycle crashes, this study quantifies how different "policy-sensitive" factors correlate with injury severity, while controlling for rider and crash specific factors as well as other observed/unobserved factors. The study analyzes data from 321 motorcycle injury crashes from a comprehensive US DOT FHWA's Motorcycle Crash Causation Study (MCCS). These were all non-fatal injury crashes that are representative of the vast majority (82%) of motorcycle crashes. An anatomical injury severity scoring system, termed as Injury Severity Score (ISS), is analyzed providing an overall score by accounting for the possibility of multiple injuries to different body parts of a rider. An ISS ranges from 1 to 75, averaging at 10.32 for this sample (above 9 is considered serious injury), with a spike at 1 (very minor injury). Preliminary cross-tabulation analysis mapped ISS to the Abbreviated Injury Scale (AIS) injury classification and examined the strength of associations between the two. While the study finds a strong correlation between AIS and ISS classification (Kendall's tau of 0.911), significant contrasts are observed in that, when compared to ISS, AIS tends to underestimate the severity of an injury sustained by a rider. For modeling, fixed and random parameter Tobit modeling frameworks were used in a corner-solution setting to account for the left-tail spike in the distribution of ISS and to account for unobserved heterogeneity. The developed random parameters Tobit framework additionally accounts for the interactive effects of key risk factors, allowing for possible correlations among random parameters. A correlated random parameter Tobit model significantly out-performed the uncorrelated random parameter Tobit and fixed parameter Tobit models. While controlling for various other factors, we found that motorcycle-specific shoes and retroreflective upper body clothing correlate with lower ISS on-average by 5.94 and 1.88 units respectively. Riders with only partial helmet coverage on-average sustained more severe injuries, whereas, riders with acceptable helmet fit had lower ISS Methodologically, not only do the individual effects of several key risk factors vary significantly across observations in the form of random parameters, but the interactions between unobserved factors characterizing random parameters significantly influence the injury severity score as well. The implications of the findings are discussed.

Pedestrian's exposure to road traffic crashes in urban environment: A case study of Peshawar, Pakistan.

This study was aimed at exploring accident statistics and suggesting counter measures to mitigate road traffic crashes in Peshawar, Pakistan, and was conducted in 2015-16. Data was extracted from all 30 police stations in cantonment, city and rural circles for the 2003-12 period. A total of 3,280 crashes were reported, including 856(26%) fatal and 2,424(74%) non-fatal ones. Moreover, 602(69%) fatalities and 1,782(59%) injuries of overall road traffic fatalities and injuries during the period studied were borne by pedestrians. No regular annual pattern was noticed for overall and pedestrians' fatalities and injuries. Detailed RTCs' analysis, police officials' interviews and engineering judgement during field visits indicate that there is a dire deficiency of physical infrastructure for pedestrians, signage and markings. There is a need to improve post-crash evaluation and implement counter measures for speed control.