A two-dimensional surrogate safety measure based on fuzzy logic model.

Surrogate Safety Measures (SSM) are extensively applied in safety analysis and design of active vehicle safety systems. However, most existing SSM focus only on the one-dimensional interactions along the vehicle traveling direction and cannot handle the crash risks associated with vehicle lateral movements such as sideswipes and angle crashes. To bridge this important knowledge gap, this study proposes a two-dimensional SSM defined based on Fuzzy Logic and the Inverse Time to Collision (FL-iTTC), which accounts for neighboring vehicles' lateral kinematics and the uncertainty of their movements. The proposed FL-iTTC are proven to be more accurate than traditional SSM in identifying typical risky scenarios, including harsh decelerations, sudden lane-changes, cut-ins and pre-crashes that are extracted from the NGSIM dataset. Additionally, other naturalistic driving scenarios are extracted from the NGSIM dataset and are used to evaluate the effectiveness of different SSM in quantifying crash risks. FL-iTTC is compared with other two-dimensional SSM including Anticipated Collision Time (ACT) and Probabilistic Driving Risk Field (PDRF) based on the confusion matrix and the receiver operating characteristic (ROC) curve. The Area under the ROC Curve (AUC) is 0.923 for FL-iTTC, while only 0.891 for ACT and 0.907 for PDRF, which indicates FL-iTTC outperforms other two-dimensional SSM in risk assessment. Overall, the proposed FL-iTTC greatly complements existing SSM and provides a reliable and useful tool to evaluate various crash risks associated with vehicle lateral movements such as cut-in and sideswipe.

Safety-oriented automated vehicle longitudinal control considering both stability and damping behavior.

Extensive research has examined the potential benefits of Automated Vehicles (AVs) for increasing traffic capacity and improving safety. However, previous studies on AV longitudinal control have focused primarily on control stability and instability or tradeoffs between safety and stability, neglecting the importance of vehicle damping characteristics. This study aims to demonstrate the significance of explicitly considering safety in addition to stability in AV longitudinal control through damping behavior analysis. Specifically, it proposes a safety-oriented AV longitudinal control and provides recommendations on the control parameters. For the proposed AV control, an Adaptive Cruise Control (ACC) model is integrated with damping behavior analysis to model AV safety under continuous traffic perturbations. Numerical simulations are conducted to quantify the relationship between mobility and safety for AVs considering both damping behavior and control stability. Different ACC control parameters are evaluated in terms of damping and stability properties, and their safety impacts are assessed based on various surrogate safety measures such as Deceleration Rate to Avoid Crash (DRAC), Crash Potential Index (CPI) and Time-Integrated Time-to-collision (TIT). The results indicate that an underdamped state (ACC damping ratio < 1) is less safe than the critically damped state (ACC damping ratio = 1) and the overdamped state (ACC damping ratio > 1). Furthermore, given the same AV car-following time lag, ACC with a damping ratio between 1 and 1.2 provides better safety performance. Increasing the AV car-following time lag can improve both safety and stability when the remaining ACC control parameters are kept the same. In this case, the optimal safety-oriented ACC regions also increase. The findings of this study provide important insights into designing safe and stable AV longitudinal control algorithms.

A simulation study of cooperative and autonomous vehicles (CAV) considering courtesy, ethics, and fairness.

Autonomous vehicles (AV) can be programmed to act cooperatively. Previous research on cooperative and autonomous vehicles (CAV) suggests they can substantially improve traffic system operations in terms of mobility and safety. However, these studies do not explicitly take each vehicle's potential gain/loss into consideration and ignore their individual levels of willingness to cooperate. They do not account for ethics and fairness either. In this study, several cooperation/courtesy strategies are proposed to address the above issues. These strategies are grouped into two categories based on non-instrumental and instrumental principles. Non-instrumental strategies make courtesy/cooperation decisions based on some courtesy proxies and a user-specified courtesy level, while instrumental strategies are based only on courtesy proxies related to local traffic performance. Also, a new CAV behavior modeling framework is proposed based on our previous work on cooperative car-following and merging (CCM) control. With such a framework, the proposed courtesy strategies can be easily implemented. The proposed framework and courtesy strategies are coded in SUMO microscopic traffic simulator. They are evaluated considering different levels of traffic demand on a freeway corridor consisting of a work zone and three weaving areas of different types. Interesting findings are drawn from the simulation results, one of which is that the instrumental Local Utilitarianism strategy performs the best in terms of mobility, safety, and fairness. In the future, auction-based strategies can be considered to model how CAV make decisions.

Explicitly incorporating surrogate safety measures into connected and automated vehicle longitudinal control objectives for enhancing platoon safety.

The concepts of Connected and Automated Vehicles (CAV) and vehicle platooning have generated high expectations regarding the safety performance of future transportation systems. Existing CAV longitudinal control research primarily focuses on efficiency and control stability, by considering different inter-vehicle spacing policies. In very few cases, safety was also considered as a constraint, but not in the main control objectives. Theoretically, stability can only guarantee that CAV platoons eventually achieve an equilibrium state but is unable to promise safety along the process of achieving equilibrium. It is important to note that CAV does not mean absolutely safe, and its longitudinal or platoon control safety performance depends on how the control algorithms are designed, how accurately it can detect and predict its lead vehicle's (could be a human-driven vehicle) next move, and other practical factors such as control and communication delays. To optimize CAV platoon safety, this study integrates surrogate safety measures (SSM) and model predictive control (MPC) into CAV longitudinal control for trajectory optimization. SSM has been widely adopted for modeling the safety consequences of various vehicle control strategies and identifying near-crash events from either simulated or field-captured traffic data. This study directly incorporates three typical SSM into the longitudinal control objectives of CAV and constructs a state-space MPC algorithm to model how these SSM vary as a result of CAV dynamics. Numerical examples are provided to show the performance of these SSM-based optimal CAV longitudinal control methods under traffic flow perturbations. To further confirm the necessity of explicitly considering SSM in CAV longitudinal control and its effectiveness in reducing rear-end collision risk, the proposed methods are compared with three classical longitudinal control models that do not consider SSM based on microscopic traffic simulation. It is noted that all SSM-based optimal control methods perform better than others as manifested by some key risk indicators, demonstrating the importance of explicitly considering SSM and safety in CAV longitudinal control.

On the interpretability of machine learning methods in crash frequency modeling and crash modification factor development.

Machine learning (ML) model interpretability has attracted much attention recently given the promising performance of ML methods in crash frequency studies. Extracting accurate relationship between risk factors and crash frequency is important for understanding the causal effects of risk factors and developing safety countermeasures. However, there is no study that comprehensively summarizes ML model interpretation methods and provides guidance for safety researchers and practitioners. This research aims to fill this gap. Model-based and post-hoc ML interpretation methods are critically evaluated and compared to study their suitability in crash frequency modeling. These methods include classification and regression tree (CART), multivariate adaptive regression splines (MARS), Local Interpretable Model-agnostic Explanations (LIME), Local Sensitivity Analysis (LSA), Partial Dependence Plots (PDP), Global Sensitivity Analysis (GSA), and SHapley Additive exPlanations (SHAP). Model-based interpretation methods cannot reveal the detailed interaction relationships among risk factors. LIME can only be used to analyze the effects of a risk factor at the prediction level. LSA and PDP assume that different risk factors are independently distributed. Both GSA and SHAP can account for the potential correlation among risk factors. However, only SHAP can visualize the detailed relationships between crash outcomes and risk factors. This study also demonstrates the potential and benefits of using ML and SHAP to derive Crash Modification Factors (CMF). Finally, it is emphasized that statistical and ML models may not directly differentiate causation from correlation. Understanding the differences between them is critical for developing reliable safety countermeasures.

Quantifying and comparing the effects of key risk factors on various types of roadway segment crashes with LightGBM and SHAP.

Understanding and quantifying the effects of risk factors on crash frequency is of great importance for developing cost-effective safety countermeasures. In this paper, the effects of key crash contributing factors on total crashes and crashes of different collision types are analyzed separately and compared. A novel Machine Learning (ML) method, Light Gradient Boosting Machine (LightGBM), is introduced to model a Texas dataset consisting of vehicle crashes occurred from 2015 to 2017. Compared with other commonly used ML methods such as eXtreme Gradient Boosting (XGBoost), LightGBM performs significantly better in terms of mean absolute error (MAE) and root mean squared error (RMSE). In addition, the SHapley Additive explanation (SHAP) approach is employed to interpret the LightGBM outputs. Significant risk factors are identified, including speed limits, area type, number of lanes, roadway functional class, shoulder width and shoulder type. With the SHAP method, the importance, total effects, and main and interaction effects of risk factors are quantified. The results suggest that the importance of risk factors vary across collision types. Speed limit is a more important risk factor than right/left shoulder width, lane width, and median width for Rear-End (RE) crashes, while the opposite relationship is found for Run-Off-Road (ROR) crashes. Also, it is found that narrow lanes (8ft to 11ft) increase the risk for all types of crashes (i.e., Total, ROR, and RE) in this study. For road segments with 5 or 6 lanes in both directions combined, a lane width greater than or equal to 12ft may help reduce the risk of all types of crashes. These results have important implications for developing accurate crash modification factors and cost-effective safety countermeasures.

A review of surrogate safety measures and their applications in connected and automated vehicles safety modeling.

Surrogate Safety Measures (SSM) are important for safety performance evaluation, since crashes are rare events and historical crash data does not capture near crashes that are also critical for improving safety. This paper focuses on SSM and their applications, particularly in Connected and Automated Vehicles (CAV) safety modeling. It aims to provide a comprehensive and systematic review of significant SSM studies, identify limitations and opportunities for future SSM and CAV research, and assist researchers and practitioners with choosing the most appropriate SSM for safety studies. The behaviors of CAV can be very different from those of Human-Driven Vehicles (HDV). Even among CAV with different automation/connectivity levels, their behaviors are likely to differ. Also, the behaviors of HDV can change in response to the existence of CAV in mixed autonomy traffic. Simulation by far is the most viable solution to model CAV safety. However, it is questionable whether conventional SSM can be applied to modeling CAV safety based on simulation results due to the lack of sophisticated simulation tools that can accurately model CAV behaviors and SSM that can take CAV's powerful sensing and path prediction and planning capabilities into crash risk modeling, although some researchers suggested that proper simulation model calibration can be helpful to address these issues. A number of critical questions related to SSM for CAV safety research are also identified and discussed, including SSM for CAV trajectory optimization, SSM for individual vehicles and vehicle platoon, and CAV as a new data source for developing SSM.

Association of visual hallucinations with very mild degenerative dementia due to dementia with Lewy bodies.

BACKGROUND AND PURPOSE: Complex, well-formed, and detailed visual hallucinations (VHs) are among the core clinical features of dementia with Lewy bodies (DLB). We investigated the diagnostic value of VHs in different types of very mild degenerative dementia. METHODS: Participants were required to complete a structured interview form recording their basic data, clinical history, neuropsychological tests, and neuropsychiatric symptoms. Basic demographic characteristics of the participants were summarized and compared. The frequency and association factors of VHs were compared among three major degenerative dementia groups, namely, Alzheimer's disease (AD), Parkinson's disease dementia (PDD), and DLB. RESULTS: A total of 197 patients with dementia and a clinical dementia rating of 0.5 were investigated, comprising 124 with AD, 35 with PDD, and 38 with DLB. A significantly higher frequency of VHs was found in the DLB group compared with the other groups (DLB, PDD, and AD = 31.6%, 11.4%, and 4.0%; p < 0.001). A multivariable logistic regression test for associations of positive VHs revealed that DLB was the only independently predictive factor (odds ratio: 13.62; p < 0.001). CONCLUSION: Our findings revealed a high diagnostic value of VHs in very mild degenerative dementia. VHs in this stage of dementia were significantly associated with DLB, and more than 30% of patients with very mild dementia caused by DLB presented with VHs.

Modeling the effects of AADT on predicting multiple-vehicle crashes at urban and suburban signalized intersections.

Annual Average Daily Traffic (AADT) is often considered as a main covariate for predicting crash frequencies at urban and suburban intersections. A linear functional form is typically assumed for the Safety Performance Function (SPF) to describe the relationship between the natural logarithm of expected crash frequency and covariates derived from AADTs. Such a linearity assumption has been questioned by many researchers. This study applies Generalized Additive Models (GAMs) and Piecewise Linear Negative Binomial (PLNB) regression models to fit intersection crash data. Various covariates derived from minor-and major-approach AADTs are considered. Three different dependent variables are modeled, which are total multiple-vehicle crashes, rear-end crashes, and angle crashes. The modeling results suggest that a nonlinear functional form may be more appropriate. Also, the results show that it is important to take into consideration the joint safety effects of multiple covariates. Additionally, it is found that the ratio of minor to major-approach AADT has a varying impact on intersection safety and deserves further investigations.

Modeling the safety impacts of driving hours and rest breaks on truck drivers considering time-dependent covariates.

INTRODUCTION: Driving hours and rest breaks are closely related to driver fatigue, which is a major contributor to truck crashes. This study investigates the effects of driving hours and rest breaks on commercial truck driver safety. METHOD: A discrete-time logistic regression model is used to evaluate the crash odds ratios of driving hours and rest breaks. Driving time is divided into 11 one hour intervals. These intervals and rest breaks are modeled as dummy variables. In addition, a Cox proportional hazards regression model with time-dependent covariates is used to assess the transient effects of rest breaks, which consists of a fixed effect and a variable effect. RESULTS: Data collected from two national truckload carriers in 2009 and 2010 are used. The discrete-time logistic regression result indicates that only the crash odds ratio of the 11th driving hour is statistically significant. Taking one, two, and three rest breaks can reduce drivers' crash odds by 68%, 83%, and 85%, respectively, compared to drivers who did not take any rest breaks. The Cox regression result shows clear transient effects for rest breaks. It also suggests that drivers may need some time to adjust themselves to normal driving tasks after a rest break. Overall, the third rest break's safety benefit is very limited based on the results of both models. PRACTICAL APPLICATIONS: The findings of this research can help policy makers better understand the impact of driving time and rest breaks and develop more effective rules to improve commercial truck safety.

The impacts of multiple rest-break periods on commercial truck driver's crash risk.

INTRODUCTION: Driver fatigue has been a major contributing factor to fatal commercial truck crashes, which accounted for about 10% of all fatal motor vehicle crashes that happened between 2009 and 2011. Commercial truck drivers' safety performance can deteriorate easily due to fatigue caused by long driving hours and irregular working schedules. To ensure safety, truck drivers often use off-duty time and short rest breaks during a trip to recover from fatigue. METHOD: This study thoroughly investigates the impacts of off-duty time prior to a trip and short rest breaks on commercial truck safety by using Cox proportional hazards model and Andersen-Gill model. RESULTS: It is found that increasing total rest-break duration can consistently reduce fatigue-related crash risk. Similarly, taking more rest breaks can help to reduce crash risk. The results suggest that two rest breaks are generally considered enough for a 10-hour trip, as three or more rest breaks may not further reduce crash risk substantially. Also, the length of each rest break does not need to be very long and 30min is usually adequate. In addition, this study investigates the safety impacts of when to take rest breaks. It is found that taking rest breaks too soon after a trip starts will cause the rest breaks to be less effective. PRACTICAL APPLICATIONS: The findings of this research can help policy makers and trucking companies better understand the impacts of multiple rest-break periods and develop more effective rules to improve the safety of truck drivers.

Crash frequency analysis of different types of urban roadway segments using generalized additive model.

INTRODUCTION: This paper utilizes generalized additive model to explore the potential non-linear relationship between crash frequency and exposure on different types of urban roadway segments. METHODS: Generalized additive models are used to analyze crash frequency data and compared with the commonly used crash rate method and generalized linear models using a five-year crash data set from Houston, Texas. RESULTS: The study shows that the relationship between crash frequency and exposure varies by segment type and the linearity may only approximately exist in certain segment types. In addition, the generalized additive modeling results suggest that such relationship curves may not be monotonic. Finally, this study demonstrates that generalized additive models in general provide better flexibility and modeling performance than generalized linear models. IMPACT ON INDUSTRY: The generalized additive model provides a very promising alternative for crash frequency modeling and other safety studies.

A multimodal location and routing model for hazardous materials transportation.

The recent US Commodity Flow Survey data suggest that transporting hazardous materials (HAZMAT) often involves multiple modes, especially for long-distance transportation. However, not much research has been conducted on HAZMAT location and routing on a multimodal transportation network. Most existing HAZMAT location and routing studies focus exclusively on single mode (either highways or railways). Motivated by the lack of research on multimodal HAZMAT location and routing and the fact that there is an increasing demand for it, this research proposes a multimodal HAZMAT model that simultaneously optimizes the locations of transfer yards and transportation routes. The developed model is applied to two case studies of different network sizes to demonstrate its applicability. The results are analyzed and suggestions for future research are provided.

Analysis of driver injury severity in rural single-vehicle crashes.

Rural roads carry less than fifty percent of the traffic in the United States. However, more than half of the traffic accident fatalities occurred on rural roads. This research focuses on analyzing injury severities involving single-vehicle crashes on rural roads, utilizing a latent class logit (LCL) model. Similar to multinomial logit (MNL) models, the LCL model has the advantage of not restricting the coefficients of each explanatory variable in different severity functions to be the same, making it possible to identify the impacts of the same explanatory variable on different injury outcomes. In addition, its unique model structure allows the LCL model to better address issues pertinent to the independence from irrelevant alternatives (IIA) property. A MNL model is also included as the benchmark simply because of its popularity in injury severity modeling. The model fitting results of the MNL and LCL models are presented and discussed. Key injury severity impact factors are identified for rural single-vehicle crashes. Also, a comparison of the model fitting, analysis marginal effects, and prediction performance of the MNL and LCL models are conducted, suggesting that the LCL model may be another viable modeling alternative for crash-severity analysis.

Predicting motor vehicle crashes using Support Vector Machine models.

Crash prediction models have been very popular in highway safety analyses. However, in highway safety research, the prediction of outcomes is seldom, if ever, the only research objective when estimating crash prediction models. Only very few existing methods can be used to efficiently predict motor vehicle crashes. Thus, there is a need to examine new methods for better predicting motor vehicle crashes. The objective of this study is to evaluate the application of Support Vector Machine (SVM) models for predicting motor vehicle crashes. SVM models, which are based on the statistical learning theory, are a new class of models that can be used for predicting values. To accomplish the objective of this study, Negative Binomial (NB) regression and SVM models were developed and compared using data collected on rural frontage roads in Texas. Several models were estimated using different sample sizes. The study shows that SVM models predict crash data more effectively and accurately than traditional NB models. In addition, SVM models do not over-fit the data and offer similar, if not better, performance than Back-Propagation Neural Network (BPNN) models documented in previous research. Given this characteristic and the fact that SVM models are faster to implement than BPNN models, it is suggested to use these models if the sole purpose of the study consists of predicting motor vehicle crashes.

Predicting motor vehicle collisions using Bayesian neural network models: an empirical analysis.

Statistical models have frequently been used in highway safety studies. They can be utilized for various purposes, including establishing relationships between variables, screening covariates and predicting values. Generalized linear models (GLM) and hierarchical Bayes models (HBM) have been the most common types of model favored by transportation safety analysts. Over the last few years, researchers have proposed the back-propagation neural network (BPNN) model for modeling the phenomenon under study. Compared to GLMs and HBMs, BPNNs have received much less attention in highway safety modeling. The reasons are attributed to the complexity for estimating this kind of model as well as the problem related to "over-fitting" the data. To circumvent the latter problem, some statisticians have proposed the use of Bayesian neural network (BNN) models. These models have been shown to perform better than BPNN models while at the same time reducing the difficulty associated with over-fitting the data. The objective of this study is to evaluate the application of BNN models for predicting motor vehicle crashes. To accomplish this objective, a series of models was estimated using data collected on rural frontage roads in Texas. Three types of models were compared: BPNN, BNN and the negative binomial (NB) regression models. The results of this study show that in general both types of neural network models perform better than the NB regression model in terms of data prediction. Although the BPNN model can occasionally provide better or approximately equivalent prediction performance compared to the BNN model, in most cases its prediction performance is worse than the BNN model. In addition, the data fitting performance of the BPNN model is consistently worse than the BNN model, which suggests that the BNN model has better generalization abilities than the BPNN model and can effectively alleviate the over-fitting problem without significantly compromising the nonlinear approximation ability. The results also show that BNNs could be used for other useful analyses in highway safety, including the development of accident modification factors and for improving the prediction capabilities for evaluating different highway design alternatives.