Insights into the long-term effects of COVID-19 responses on transportation facilities.

The impacts of COVID-19 on transportation sector have received a substantial research attention, however, less is known about localized COVID-19 responses that provided safe space for mobility and other daily activities. We applied logistic regression and text mining approaches on the Shifting Streets COVID-19 Mobility Dataset to explore the long-term outcomes of the localized responses. We explored the purpose, affected space, function, and implementation approach. We found that responses instituted for economic recovery and public health are less likely to be long-term, while responses meant to improve safety or bicycle/pedestrian mobility are more likely to be long-term. Further, operational or regulatory responses are less likely to be long-term. Additionally, responses affecting curb space are more likely to be long-term than those affecting other right-of-way areas. Text-mining of responses' narratives revealed key patterns for both short-term and long-term outcomes. Study findings showcase the possible design and operations changes during post-COVID-19 era.

Unlocking the Narrative: Using Text Mining to Reveal the Hidden Factors behind Suicide Related Traffic Crashes.

Suicide is the deliberate act of ending a person's own life due to multifarious reasons. In the U.S., suicide is the 10th major cause of death. Nearly 45,000 people died by suicide in 2016 across the nation. It is anticipated that not all traffic crashes can be considered as accidents. Traffic crash related injuries are occasionally considered a means of suicide, and some crashes occur due to the suicidal attempts. These attempts can be made by operators of motor vehicles, jumpers into the pathway of trains, and pedestrians deliberately jumping into the vehicle trajectory. There are a handful of studies that have focused on traffic crashes (both railroad and roadway) related to suicidal incidents. This study aimed to explore the insights associated with suicide related traffic crashes (SRTCs) by collecting traffic data for seven years (2010-2016) from Louisiana. At first, exploratory data analysis was performed to examine the five Ws (who, what, why, when, and where) associated with SRTCs. Later, this study applied text network analysis, which was not performed in any of the previous studies, to provide additional contexts of these crashes. The findings of this study can shed lights on an unexplored arena of transportation safety research.

A comparative study of collision types between automated and conventional vehicles using Bayesian probabilistic inferences.

INTRODUCTION: Automated vehicle (AV) technology is a promising technology for improving the efficiency of traffic operations and reducing emissions. This technology has the potential to eliminate human error and significantly improve highway safety. However, little is known about AV safety issues due to limited crash data and relatively fewer AVs on the roadways. This study provides a comparative analysis between AVs and conventional vehicles on the factors leading to different types of collisions. METHOD: A Bayesian Network (BN) fitted using the Markov Chain Monte Carlo (MCMC) was used to achieve the study objective. Four years (2017-2020) of AV and conventional vehicle crash data on California roads were used. The AV crash dataset was acquired from the California Department of Motor Vehicles, while conventional vehicle crashes were obtained from the Transportation Injury Mapping System database. A buffer of 50 feet was used to associate each AV crash and conventional vehicle crash; a total of 127 AV crashes and 865 conventional vehicle crashes were used for analysis. RESULTS: Our comparative analysis of the associated features suggests that AVs are 43% more likely to be involved in rear-end crashes. Further, AVs are 16% and 27% less likely to be involved in sideswipe/broadside and other types of collisions (head-on, hitting an object, etc.), respectively, when compared to conventional vehicles. The variables associated with the increased likelihood of rear-end collisions for AVs include signalized intersections and lanes with less than 45 mph speed limit. CONCLUSIONS: Although AVs are found to improve safety on the road in most types of collisions by limiting human error leading to vehicle crashes, the current state of the technology shows that safety aspects still need improvement.

Seeing through eyes of Drivers: Space consideration in investigating visibility of Vulnerable road users involved in crashes from Driver's perspective.

Vulnerable Road User's (VRUs) invisibility by vehicle drivers hasn't been well explored despite having a substantial influence on crash involvement and resulting severity level. Additionally, obtaining comparison crashes for analysis of the VRU invisibility has been a challenge. For that reason, this study used crashes that occurred between 2017 and 2022 in Ohio to understand VRU invisibility from the driver's perspective. The study further proposes the comparison of crashes as those that occurred within 250 feet of the crashes involving drivers not seeing the VRU. Two logistic regression models, one for the entire dataset (full model) and the second for only crashes that occurred within 250 feet (space-constrained model), were developed. It was found that the results from the full model and space-constrained model differ significantly in terms of the magnitude and the direction of the effect. Using the space-constrained model, the topmost key factors associated with the highest likelihood of VRU invisibility are lighting conditions, pre-action of the driver, and senior VRU involvement. Further, text network analysis was performed to understand the key reasons for VRU invisibility. The text network revealed that the VRU invisibility related to left turning pre-action was due to the driver's failure to yield at an intersection's pedestrian crossing. Further, the most invisible VRUs in the dark conditions were on the side of the roadway. Additionally, drivers backing up were more likely to report that they did not see pedestrians walking behind them. Lastly, senior-related crashes were associated with crossing in front of turning vehicles. The findings can be utilized to enhance VRU visibility at various locations to improve safety.

Mining patterns of autonomous vehicle crashes involving vulnerable road users to understand the associated factors.

Autonomous or automated vehicles (AVs) have the potential to improve traffic safety by eliminating majority of human errors. As the interest in AV deployment increases, there is an increasing need to assess and understand the expected implications of AVs on traffic safety. Until recently, most of the literature has been based on either survey questionnaires, simulation analysis, virtual reality, or simulation to assess the safety benefits of AVs. Although few studies have used AV crash data, vulnerable road users (VRUs) have not been a topic of interest. Therefore, this study uses crash narratives from four-year (2017-2020) of AV crash data collected from California to explore the direct and indirect involvement of VRUs. The study applied text network and compared the text classification performance of four classifiers - Support Vector Machine (SVM), Naïve Bayes (NB), Random Forest (RF), and Neural Network (NN) and associated performance metrics to attain the objective. It was found that out of 252 crashes, VRUs were, directly and indirectly, involved in 23 and 12 crashes, respectively. Among VRUs, bicyclists and scooterists are more likely to be involved in the AV crashes directly, and bicyclists are likely to be at fault, while pedestrians appear more in the indirectly involvements. Further, crashes that involve VRUs indirectly are likely to occur when the AVs are in autonomous mode and are slightly involved minor damages on the rear bumper than the ones that directly involve VRUs. Additionally, feature importance from the best performing classifiers (RF and NN) revealed that crosswalks, intersections, traffic signals, movements of AVs (turning, slowing down, stopping) are the key predictors of the VRUs-AV related crashes. These findings can be helpful to AV operators and city planners.

Exploring pre-crash gate violations behaviors of drivers at highway-rail grade crossings using a mixed multinomial logit model.

The highway-rail grade crossings (HRGCs) across the United States have been experiencing about 2500 crashes each year. Previous studies analyzed crash frequencies and fatalities; however, factors pertaining to drivers' gate violation behaviors are little known. Also, applied methodologies for gate violation behaviors analysis did not consider their heterogeneity across regions. This study uses 20-year of crash data (1999-2018) to evaluate pre-crash drivers' behaviors at HRGCs. A mixed multinomial logit model was developed to associate such behaviors with demographic factors, vehicle characteristics, temporal and environmental factors, as well as crossing-related factors. The study results indicated a high intra-class correlation coefficient which signifies the importance of including the random-effect parameter in the model. Further, the study found that male drivers are more likely to drive around the gate, while older drivers are more likely to stop and proceed before a train has passed. Furthermore, compared to trucks, all other vehicle types are more likely to drive around the gate. The influence of train speed, vehicle occupancy, visibility, among others, on drivers' pre-crash behaviors, is also presented. Understanding the impact of these factors on pre-crash behaviors may assist in improving the motorist's safety at the highway-rail grade crossings across the United States.

Exploring geographical distribution of transportation research themes related to COVID-19 using text network approach.

The COVID-19 outbreak has extremely impacted the globe due to travel restrictions and lockdowns. Geographically, COVID-19 has shown disproportional impacts; however, the research themes' distribution is yet to be explored. Thus, this study explored the geographical distribution of the research themes that relate to COVID-19 and the transportation sector. The study applied a text network approach on the bibliometric data of over 400 articles published between December 2019 and December 2020. It was found that the researches and the associated themes were geographically distributed based on the events that took place in the respective countries. Most of the articles were published by the authors from four countries, the USA, China, Japan, and the UK. The text network results revealed that the USA-based studies mainly focused on international travelers, monitoring, travel impacts of COVID-19, and social-distancing measures. The Japanese-based studies focused on the princess diamond cruise ship incident. On the other hand, Chinese authors published articles related to travel to Wuhan and China, passenger health, and public transportation. The UK-based studies had diverse topics of interest. Lastly, the remaining 62 countries' studies focused on returning travelers from China, public transportation, and the global spread of COVID-19. The findings are crucial to the transportation sector's researchers for various applications.

Prediction of vehicle occupants injury at signalized intersections using real-time traffic and signal data.

Intersections are among the most dangerous roadway facilities due to the existence of complex movements of traffic. Most of the previous intersection safety studies are conducted based on static and highly aggregated data such as average daily traffic and crash frequency. The aggregated data may result in unreliable findings because they are based on averages and might not necessarily represent the actual conditions at the time of the crash. This study uses real-time event-based detection records, and crash data to develop predictive models for the vehicle occupants' injury severity. The three-year (2017-2019) data were acquired from the arterial highways in the City of Tallahassee, Florida. Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) classifiers were used to identify the important factors on the vehicle occupants' injury severity prediction. The performance comparison of the two classifiers revealed that the XGBoost has a higher balanced accuracy score than RF. Using the XGBoost classifier, five topmost influential factors on injury prediction were identified. The factors are the manner of the collision, through and right-turn traffic volume, arrival on red for through and right-turn traffic, split failure for through traffic, and delays for through and right-turn traffic. Moreover, the partial dependency plots of the influential variables are presented to reveal their impact on vehicle occupant injury prediction. The knowledge gained from this study will be useful in developing effective proactive countermeasures to mitigate intersection-related crash injuries in real-time.

Prediction of drivers and pedestrians' behaviors at signalized mid-block Danish offset crosswalks using Bayesian networks.

INTRODUCTION: This study presents the prediction of driver yielding compliance and pedestrian tendencies to press pushbuttons at signalized mid-block Danish offset crosswalks. METHOD: It applies Bayesian Networks (BNs) analysis, which is basically a graphical non-functional form model, on observational survey data collected from five signalized crosswalks in Las Vegas, Nevada. The BNs structures were learnt from the data by the application of several score functions. By considering prediction accuracy and the Area under the Receiver Operating Characteristic (ROC) curves, the BN learnt using the Bayesian Information Criterion (BIC) score resulted as the best network structure, compared to the ones learnt using K2 and the Akaike Information Criterion (AIC). The BIC score-based structure was then used for parameter learning and probabilistic inference. RESULTS: Results show that, when considering an individual scenario, the highest predicted yielding compliance (81%) is attained when pedestrians arrive at the crosswalk while the flashes are active, whereas the lowest predicted yielding compliance (23.4%) is observed when the pedestrians cross between the yield line and advanced pedestrian crosswalk sign. On the other hand, crossing within marked stripes, approaching the crosswalk from the near side of the pushbutton pole, inactive flashing lights, and being the first to arrive at the crosswalk result in relatively high-predicted probabilities of pedestrians pressing pushbutton. Furthermore, with a combination of scenarios, the maximum achievable predicted yielding probability is 87.5%, while that of pressing the button was 96.3%. Practical applications: Traffic engineers and planners may use these findings to improve the safety of crosswalk users.

Scanning secondary derived crashes from disabled and abandoned vehicle incidents on uninterrupted flow highways.

INTRODUCTION: Extent of secondary crashes derived from primary incidents involving abandoned and disabled vehicles are presented in this paper. METHOD: Using years 2004 to 2010 incident and crash data on selected Tennessee freeways, the study identified secondary crashes that resulted from disabled and abandoned vehicle primary incidents. The relationship between time and distance gaps before the secondary crash with respect to individual incident characteristics were evaluated through descriptive statistics and linear regression. RESULTS: The time and distance gap analysis indicated that a large portion of secondary crashes occurred within 20 min after the primary incidents and within a distance of 0.5 miles upstream. While 76% of incidents involved shoulder, most secondary crashes were related to the closing of right lanes. Overall, 58% of the secondary crashes occurred within 30 min after the occurrence of the primary incidents. Most of the vehicles in the incidents that involved towing and caused secondary crashes were towed or removed out of the travel way within 60 min from the time of occurrence. The study found that most (95%) secondary crashes were property damage only (PDO), while 49% were rear-end crashes. The negative binomial model was used to evaluate the impact of roadway geometry and traffic factors associated with frequency of these secondary crashes. It was found that the posted speed limit, congested segments, segments with high percentages of trucks, and peak hour volumes increased the likelihood of secondary crash occurrence. Roadway segments with wider medians, shoulders, and multilanes decrease the likelihood of secondary crashes caused by abandoned and disabled vehicles as the primary incidents. Practical applications The paper recommends that wider shoulders be provided on any section of freeway to accommodate abandoned or disabled vehicles to avoid blocking of travel lane(s).