This page has only limited features, please log in for full access.

Unclaimed
Wei Fan
USDOT Center for Advanced Multimodal Mobility Solutions and Education (CAMMSE, Department of Civil and Environmental Engineering, University of North Carolina at Charlotte, Charlotte, North Carolina, USA

Honors and Awards

The user has no records in this section


Career Timeline

The user has no records in this section.


Short Biography

Dr. Wei (David) Fan currently serves as a full professor in the Department of Civil and Environmental Engineering (CEE) at The University of North Carolina at Charlotte (UNCC). He is the Director of the USDOT University Transportation Center for Advanced Multimodal Mobility Solutions and Education.

Following
Followers
Co Authors
The list of users this user is following is empty.
Following: 0 users

Feed

Earlycite article
Published: 16 August 2021 in Smart and Resilient Transport
Reads 0
Downloads 0

Purpose Metropolitan areas suffer from frequent road traffic congestion not only during peak hours but also during off-peak periods. Different machine learning methods have been used in travel time prediction, however, such machine learning methods practically face the problem of overfitting. Tree-based ensembles have been applied in various prediction fields, and such approaches usually produce high prediction accuracy by aggregating and averaging individual decision trees. The inherent advantages of these approaches not only get better prediction results but also have a good bias-variance trade-off which can help to avoid overfitting. However, the reality is that the application of tree-based integration algorithms in traffic prediction is still limited. This study aims to improve the accuracy and interpretability of the models by using random forest (RF) to analyze and model the travel time on freeways. Design/methodology/approach As the traffic conditions often greatly change, the prediction results are often unsatisfactory. To improve the accuracy of short-term travel time prediction in the freeway network, a practically feasible and computationally efficient RF prediction method for real-world freeways by using probe traffic data was generated. In addition, the variables’ relative importance was ranked, which provides an investigation platform to gain a better understanding of how different contributing factors might affect travel time on freeways. Findings The parameters of the RF model were estimated by using the training sample set. After the parameter tuning process was completed, the proposed RF model was developed. The features’ relative importance showed that the variables (travel time 15 min before) and time of day (TOD) contribute the most to the predicted travel time result. The model performance was also evaluated and compared against the extreme gradient boosting method and the results indicated that the RF always produces more accurate travel time predictions. Originality/value This research developed an RF method to predict the freeway travel time by using the probe vehicle-based traffic data and weather data. Detailed information about the input variables and data pre-processing were presented. To measure the effectiveness of proposed travel time prediction algorithms, the mean absolute percentage errors were computed for different observation segments combined with different prediction horizons ranging from 15 to 60 min.

ACS Style

Bo Qiu; Wei Fan. Travel time forecasting on a freeway corridor: a dynamic information fusion model based on the random forests approach. Smart and Resilient Transport 2021, ahead-of-p, 1 .

AMA Style

Bo Qiu, Wei Fan. Travel time forecasting on a freeway corridor: a dynamic information fusion model based on the random forests approach. Smart and Resilient Transport. 2021; ahead-of-p (ahead-of-p):1.

Chicago/Turabian Style

Bo Qiu; Wei Fan. 2021. "Travel time forecasting on a freeway corridor: a dynamic information fusion model based on the random forests approach." Smart and Resilient Transport ahead-of-p, no. ahead-of-p: 1.

Journal article
Published: 31 July 2021 in Sustainability
Reads 0
Downloads 0

Travel time prediction plays a significant role in the traffic data analysis field as it helps in route planning and reducing traffic congestion. In this study, an XGBoost model is employed to predict freeway travel time using probe vehicle data. The effects of different parameters on model performance are investigated and discussed. The optimized model outputs are then compared with another well-known model (i.e., Gradient Boosting model). The comparison results indicate that the XGBoost model has considerable advantages in terms of both prediction accuracy and efficiency. The developed model and analysis results can greatly help the decision makers plan, operate, and manage a more efficient highway system.

ACS Style

Zhen Chen; Wei Fan. A Freeway Travel Time Prediction Method Based on an XGBoost Model. Sustainability 2021, 13, 8577 .

AMA Style

Zhen Chen, Wei Fan. A Freeway Travel Time Prediction Method Based on an XGBoost Model. Sustainability. 2021; 13 (15):8577.

Chicago/Turabian Style

Zhen Chen; Wei Fan. 2021. "A Freeway Travel Time Prediction Method Based on an XGBoost Model." Sustainability 13, no. 15: 8577.

Journal article
Published: 28 July 2021 in Journal of Transportation Safety & Security
Reads 0
Downloads 0

Vulnerable road users (VRUs) including pedestrians and cyclists tend to experience more severe injuries when they are involved in crashes compared with motorized vehicle users. Such concern has been expressed as an impediment to the promotion of environment-friendly transportation. To provide insights on the causes of crashes involving VRUs, this study aims to explore the underlying factors that contribute to VRUs injury severity levels and provide constructive recommendations to mitigate injury severity in crashes. In order to minimize heterogeneity existing in the collected data, a latent class clustering method is conducted to categorize collected crash records into different groups. Then the mixed logit models are developed for each cluster as well as the overall crash data. The analysis is conducted based on the crash data retrieved from the Highway Safety Information System (HSIS) from 2012 to 2016 in North Carolina. Distinguished sets of significant factors are identified for clusters with different dominant features. Some factors are found to yield different or even opposite effects in identified clusters, including male gender and non-roadway location. These findings would enhance the understanding of the vulnerable road user (VRU) injury severity mechanism and help policymakers to make reasoned and efficient decisions to improve safety.

ACS Style

Shaojie Liu; Zijing Lin; Wei (David) Fan. Investigating contributing factors to injury severity levels in crashes involving pedestrians and cyclists using latent class clustering analysis and mixed logit models. Journal of Transportation Safety & Security 2021, 1 -28.

AMA Style

Shaojie Liu, Zijing Lin, Wei (David) Fan. Investigating contributing factors to injury severity levels in crashes involving pedestrians and cyclists using latent class clustering analysis and mixed logit models. Journal of Transportation Safety & Security. 2021; ():1-28.

Chicago/Turabian Style

Shaojie Liu; Zijing Lin; Wei (David) Fan. 2021. "Investigating contributing factors to injury severity levels in crashes involving pedestrians and cyclists using latent class clustering analysis and mixed logit models." Journal of Transportation Safety & Security , no. : 1-28.

Journal article
Published: 15 July 2021 in Traffic Injury Prevention
Reads 0
Downloads 0

The objective of this research is to identify and compare contributing factors to pedestrian injury severities in pedestrian-vehicle crashes considering both time-of-day and day-of-week. The pedestrian-vehicle crash data are collected from 2007 to 2018 in North Carolina with categorical factors of pedestrian, driver, vehicle type, crash group, geography, environment, and traffic control characteristics. The final dataset includes 17,904 observations with 69 categorized variables. Four mixed logit models are developed to analyze the crash dataset with segmentations of weekday daytime, weekday nighttime, weekend daytime, and weekend nighttime. A total number of 31 fixed significant factors and 6 random parameter factors to the pedestrian injury severity are detected in four mixed logit models. According to marginal effects, large vehicle involved, pedestrians with age over 65, hit and run, drunk pedestrian, down/dusk light, dark without roadside light, and industrial land use are identified as the contributing factors that result in more than a 0.08 increase in the probability of fatal injury. Compared to the daytime, most factors are found to have more impact on severe injuries in the nighttime. Also, most factors are found to result in more severe injuries on weekends than on weekdays. This study identifies and compares the factors to pedestrian injury severity in pedestrian-vehicle crashes considering the temporal variance in time-of-day (i.e., daytime vs. nighttime) and day-of-week (i.e., weekdays vs. weekends). Random effects are explored in mixed logit models. Differences and possible reasons for the significant factors’ impact within and across time-of-day and day-of-week are also investigated. Corresponding countermeasures and suggestions to mitigate the impacts of major factors are also discussed, which give practical guidance to planners and engineers, and provide a solid reference to further explore the temporal variance of the crash data.

ACS Style

Li Song; Yang Li; Wei (David) Fan; Pengfei Liu. Mixed logit approach to analyzing pedestrian injury severity in pedestrian-vehicle crashes in North Carolina: Considering time-of-day and day-of-week. Traffic Injury Prevention 2021, 1 -6.

AMA Style

Li Song, Yang Li, Wei (David) Fan, Pengfei Liu. Mixed logit approach to analyzing pedestrian injury severity in pedestrian-vehicle crashes in North Carolina: Considering time-of-day and day-of-week. Traffic Injury Prevention. 2021; ():1-6.

Chicago/Turabian Style

Li Song; Yang Li; Wei (David) Fan; Pengfei Liu. 2021. "Mixed logit approach to analyzing pedestrian injury severity in pedestrian-vehicle crashes in North Carolina: Considering time-of-day and day-of-week." Traffic Injury Prevention , no. : 1-6.

Journal article
Published: 06 July 2021 in Journal of Safety Research
Reads 0
Downloads 0

Problem: The rollover crash is a serious crash type that often causes higher injury severities. Moreover, factors that contribute to the injury severities of rollover crashes may show instabilities in different vehicle types and time periods, which requires further investigations. This study utilizes the rollover crash data in North Carolina from Highway Safety Information System (HSIS) to study the effect instabilities of factors in vehicle type and time periods in rollover crashes. Methods: The injury severities of drivers are estimated using the random parameters logit (RPL) model with heterogeneity in means and variances. Available factors in HSIS have been categorized into three groups, which are drivers, road, and environment, respectively. This study also justifies the segmentations through transferability tests. The effects of identified significant factors are evaluated using marginal effects. Results: Factors such as FWP (farm, wood, and pasture areas), unhealthy physical condition, impaired physical condition, road adverse, and so forth have shown instabilities in marginal effects among vehicle types and time periods. Practical Applications: The finding of this research could provide important references for policy makers and automobile manufactures to help mitigate the injury severity of rollover crashes.

ACS Style

Shaojie Liu; Wei David Fan; Yang Li. Injury severity analysis of rollover crashes for passenger cars and light trucks considering temporal stability: A random parameters logit approach with heterogeneity in mean and variance. Journal of Safety Research 2021, 78, 276 -291.

AMA Style

Shaojie Liu, Wei David Fan, Yang Li. Injury severity analysis of rollover crashes for passenger cars and light trucks considering temporal stability: A random parameters logit approach with heterogeneity in mean and variance. Journal of Safety Research. 2021; 78 ():276-291.

Chicago/Turabian Style

Shaojie Liu; Wei David Fan; Yang Li. 2021. "Injury severity analysis of rollover crashes for passenger cars and light trucks considering temporal stability: A random parameters logit approach with heterogeneity in mean and variance." Journal of Safety Research 78, no. : 276-291.

Journal article
Published: 05 July 2021 in Analytic Methods in Accident Research
Reads 0
Downloads 0

Using data of multi-vehicle crashes with drivers under the influence of alcohol/drugs in North Carolina from 2008 to 2017, this paper explores time-of-day variations (daytime vs. nighttime) and temporal instabilities of factors affecting alcohol/drug-impaired crash injury severities during three crash cycle phases after the Great Recession. Random parameters logit models with heterogeneity in the means and variances are utilized to identify significant factors, explore unobserved heterogeneity, reveal correlations between factors, and suggest possible impacts of economic conditions on the factors. Different likelihood ratio tests indicate that the effects of factors vary significantly across time-of-day and economic-related cycle periods. Significant time-of-day variations imply more severe injury alcohol/drug involved crashes during the nighttime compared to the daytime. Meanwhile, temporal instabilities are also observed in marginal effects of several factors across three-cycle periods. Proficient and cautious elder drivers were safer than young drivers during the depression period. Also, both depressing and expanding periods could affect the involvement of alcohol/drugs for drivers. Shifts in alcohol/drug use behaviors underscore the importance of accounting time-of-day variations, temporal instabilities, and heterogeneity in the means and variances inherent in alcohol/drug-impaired crash factors after the Great Recession. The insights of this study should be valuable to improve specific enforcements, qualify punishments, organize targeted campaigns, and design other preventive activities for alcohol/drug-impaired crashes.

ACS Style

Li Song; Wei (David) Fan; Yang Li. Time-of-day variations and the temporal instability of multi-vehicle crash injury severities under the influence of alcohol or drugs after the Great Recession. Analytic Methods in Accident Research 2021, 32, 100183 .

AMA Style

Li Song, Wei (David) Fan, Yang Li. Time-of-day variations and the temporal instability of multi-vehicle crash injury severities under the influence of alcohol or drugs after the Great Recession. Analytic Methods in Accident Research. 2021; 32 ():100183.

Chicago/Turabian Style

Li Song; Wei (David) Fan; Yang Li. 2021. "Time-of-day variations and the temporal instability of multi-vehicle crash injury severities under the influence of alcohol or drugs after the Great Recession." Analytic Methods in Accident Research 32, no. : 100183.

Journal article
Published: 03 July 2021 in Sustainability
Reads 0
Downloads 0

Due to the increasing traffic volume in metropolitan areas, short-term travel time prediction (TTP) can be an important and useful tool for both travelers and traffic management. Accurate and reliable short-term travel time prediction can greatly help vehicle routing and congestion mitigation. One of the most challenging tasks in TTP is developing and selecting the most appropriate prediction algorithm using the available data. In this study, the travel time data was provided and collected from the Regional Integrated Transportation Information System (RITIS). Then, the travel times were predicted for short horizons (ranging from 15 to 60 min) on the selected freeway corridors by applying four different machine learning algorithms, which are Decision Trees (DT), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Long Short-Term Memory neural network (LSTM). Many spatial and temporal characteristics that may affect travel time were used when developing the models. The performance of prediction accuracy and reliability are compared. Numerical results suggest that RF can achieve a better prediction performance result than any of the other methods not only in accuracy but also with stability.

ACS Style

Bo Qiu; Wei Fan. Machine Learning Based Short-Term Travel Time Prediction: Numerical Results and Comparative Analyses. Sustainability 2021, 13, 7454 .

AMA Style

Bo Qiu, Wei Fan. Machine Learning Based Short-Term Travel Time Prediction: Numerical Results and Comparative Analyses. Sustainability. 2021; 13 (13):7454.

Chicago/Turabian Style

Bo Qiu; Wei Fan. 2021. "Machine Learning Based Short-Term Travel Time Prediction: Numerical Results and Comparative Analyses." Sustainability 13, no. 13: 7454.

Articles
Published: 29 June 2021 in Transportation Planning and Technology
Reads 0
Downloads 0

To investigate the effects of different market penetration rates (MPRs) of intelligent vehicles – Intelligent Driving Model (IDM) for autonomous vehicles (AVs), Adaptive Cruise Control (ACC) for AVs, and Cooperative Adaptive Cruise Control (CACC) for connected and automated vehicles (CAVs) – in mixed traffic flows with human driving vehicles (HDVs) at intersections, three signalized intersections (fixed signal, gap-based actuated signal, and delay-based actuated signal-controlled intersections) with low, medium, and high traffic demands are investigated. The simulation results indicate that CAVs with the CACC system outperform AVs with ACC or IDM systems and could reduce the average delay under low and high demand scenarios by 49% to 96%. CAVs with the CACC system could also significantly reduce average delay with a 20% MPR, while significant drops could only be observed after 60% and 80% MPRs for AVs with the ACC/IDM system. Gap-based and delay-based actuated signal control schemes are preferred under medium traffic flow demand, and CACC/ACC systems could significantly improve the performance of actuated signal-controlled intersections under high traffic flow demand.

ACS Style

Li Song; Wei (David) Fan; Pengfei Liu. Exploring the effects of connected and automated vehicles at fixed and actuated signalized intersections with different market penetration rates. Transportation Planning and Technology 2021, 1 -17.

AMA Style

Li Song, Wei (David) Fan, Pengfei Liu. Exploring the effects of connected and automated vehicles at fixed and actuated signalized intersections with different market penetration rates. Transportation Planning and Technology. 2021; ():1-17.

Chicago/Turabian Style

Li Song; Wei (David) Fan; Pengfei Liu. 2021. "Exploring the effects of connected and automated vehicles at fixed and actuated signalized intersections with different market penetration rates." Transportation Planning and Technology , no. : 1-17.

Articles
Published: 29 June 2021 in Transportation Planning and Technology
Reads 0
Downloads 0

With the development of artificial intelligence and wireless communication technology, connected and autonomous vehicles (CAVs) have been treated as a promising strategy to increase road capacity and mitigate traffic congestion. Besides the technology of CAVs, innovative intersection design was also originally introduced as a countermeasure for dealing with traffic congestion at intersections. Though many studies have been conducted to explore the benefits of CAVs under various transportation scenarios, few have been implemented to explore the impact of CAVs on traffic flow at innovative intersections. Hence, to achieve a better understanding of the impacts of CAVs on existing transportation infrastructure, this study conducts a simulation-based study to investigate the operational performance of CAVs with available Signal Phase and Timing (SPaT) information in the environment of typical innovative intersection design, i.e. superstreets. The impact of CAVs with different market penetration rates on the operational performance of a superstreet is identified. The operational performance of the superstreet increases as the market penetration rate increases overall. Average speed and average traffic delay for vehicles in the superstreet system can be improved with the increase of market penetration rates.

ACS Style

Shaojie Liu; Wei (David) Fan. Investigating the operational performance of connected and autonomous vehicles on signalized superstreets. Transportation Planning and Technology 2021, 1 -14.

AMA Style

Shaojie Liu, Wei (David) Fan. Investigating the operational performance of connected and autonomous vehicles on signalized superstreets. Transportation Planning and Technology. 2021; ():1-14.

Chicago/Turabian Style

Shaojie Liu; Wei (David) Fan. 2021. "Investigating the operational performance of connected and autonomous vehicles on signalized superstreets." Transportation Planning and Technology , no. : 1-14.

Research article
Published: 15 June 2021 in Journal of Transportation Safety & Security
Reads 0
Downloads 0

Pedestrian injury has become a national traffic-safety concern as the share of pedestrian fatality continues to increase in the last decade. Pedestrian injury severities are influenced by many factors that include driver, pedestrian, vehicle, roadway, temporal, and environmental characteristics. Results indicate that some of the factors affecting pedestrian injury severity at intersection and non-intersection locations are statistically different and using the same model to perform the estimate at both locations may result in biased results. However, few studies have been conducted to explore different contributing factors at such locations. Mixed logit models are developed to independently identify the contributing factors to pedestrian injury severity resulting from crashes at intersections and non-intersections. The estimation shows factors such as male driver, alcohol, pedestrian above 65, truck, and higher speed limit significantly increase the probability of pedestrian serious injury severities in both locations. However, the impacts tend to be more severe at intersections. Urban and wet road surfaces decrease the likelihood of suffering fatal injury at intersections. Furthermore, crash time only has impacts at intersections, while traffic control, severe weather, and day-of-week only have impacts at non-intersections. The results provide insights on developing more effective countermeasures to promote pedestrian safety.

ACS Style

Bo Qiu; Wei (David) Fan. Mixed logit models for examining pedestrian injury severities at intersection and non-intersection locations. Journal of Transportation Safety & Security 2021, 1 -25.

AMA Style

Bo Qiu, Wei (David) Fan. Mixed logit models for examining pedestrian injury severities at intersection and non-intersection locations. Journal of Transportation Safety & Security. 2021; ():1-25.

Chicago/Turabian Style

Bo Qiu; Wei (David) Fan. 2021. "Mixed logit models for examining pedestrian injury severities at intersection and non-intersection locations." Journal of Transportation Safety & Security , no. : 1-25.

Journal article
Published: 01 April 2021 in Journal of Transportation Engineering, Part A: Systems
Reads 0
Downloads 0

Public transit is a critical component of transportation planning. One important task is to optimize the public transit service for people by improving current service or having new investments. Under such circumstances, the main objective of this study is to develop optimization models for improving transit equity and accessibility for people by integrating the transit gap index (TGI), a performance metric using the General Transit Feed Specification (GTFS) data. TGI was developed by considering demographic features, as well as spatial and temporal transit service characteristics. Two models were built with the intention to optimize the transit equity by mitigating the transit deficiency (i.e., TGI). Two different conditions were considered while developing both models: (1) maximizing the level of transit services under the constraint of a limited budget that will be invested in the new constructions of public transit stops; and (2) minimizing the total cost for constructing new public transit stops with constraints on certain improvements of transit services for a certain amount of block groups. Finally, a case study in the City of Charlotte, North Carolina, was conducted, and comprehensive numerical results and analyses based on the proposed models are provided.

ACS Style

Yang Li; Wei “David” Fan. Optimizing Transit Equity and Accessibility of the City of Charlotte, North Carolina, by Integrating Transit Gap Index, a General Transit Feed Specification Data-Relevant Performance Metric. Journal of Transportation Engineering, Part A: Systems 2021, 147, 04021005 .

AMA Style

Yang Li, Wei “David” Fan. Optimizing Transit Equity and Accessibility of the City of Charlotte, North Carolina, by Integrating Transit Gap Index, a General Transit Feed Specification Data-Relevant Performance Metric. Journal of Transportation Engineering, Part A: Systems. 2021; 147 (4):04021005.

Chicago/Turabian Style

Yang Li; Wei “David” Fan. 2021. "Optimizing Transit Equity and Accessibility of the City of Charlotte, North Carolina, by Integrating Transit Gap Index, a General Transit Feed Specification Data-Relevant Performance Metric." Journal of Transportation Engineering, Part A: Systems 147, no. 4: 04021005.

Research article
Published: 05 January 2021 in Transportation Planning and Technology
Reads 0
Downloads 0

Connected and autonomous vehicle (CAV) technologies are expected to improve the quality of intersection operations through Vehicle-to-Infrastructure (V2I) and Infrastructure-to-Vehicle (I2V) communications. This study investigates mobility and environmental impacts of CAVs on signalized intersections. With I2V communication capability, CAVs are able to receive the real-time traffic signal information while approaching the intersections. A speed control strategy for CAVs is developed and optimal speeds for CAVs are calculated based on their locations and signal conditions. The analysis is conducted in a mixed traffic environment with combination of regular vehicles, autonomous vehicles, and CAVs. The vehicle delay and emissions at the selected intersection are quantified with respect to different market penetration rates of CAVs. The results indicate that CAVs can reduce vehicle delay by as much as 46.06% and 33.47% in emissions compared to regular vehicles. The proposed strategy can effectively improve the mobility and environment at signalized intersections.

ACS Style

Pengfei Liu; Wei David Fan. Exploring the impact of connected and autonomous vehicles on mobility and environment at signalized intersections through vehicle-to-infrastructure (V2I) and infrastructure-to-vehicle (I2V) communications. Transportation Planning and Technology 2021, 44, 129 -138.

AMA Style

Pengfei Liu, Wei David Fan. Exploring the impact of connected and autonomous vehicles on mobility and environment at signalized intersections through vehicle-to-infrastructure (V2I) and infrastructure-to-vehicle (I2V) communications. Transportation Planning and Technology. 2021; 44 (2):129-138.

Chicago/Turabian Style

Pengfei Liu; Wei David Fan. 2021. "Exploring the impact of connected and autonomous vehicles on mobility and environment at signalized intersections through vehicle-to-infrastructure (V2I) and infrastructure-to-vehicle (I2V) communications." Transportation Planning and Technology 44, no. 2: 129-138.

Journal article
Published: 31 December 2020 in International Journal of Transportation Science and Technology
Reads 0
Downloads 0

The fatal rate of truck-involved crashes is increasing and crashes become more severe than passenger vehicles in recent years. Much research has been dedicated to exploring the truck crash factors while scarce research focused on the intersection scenarios. This study investigates the factors that affect the severity level of truck-involved crashes at cross- and T-intersections. Due to the unobserved heterogeneity inherent in crash data, latent class analysis is firstly conducted to divide the crash dataset into relatively homogeneous clusters. Considering the ordinal feature of the severities, general ordered logit models are subsequently developed to further explore the specific factors within each cluster. This study uses the North Carolina’s truck-involved crash at intersection data during 2005 to 2017 from the Highway Safety Information System (HSIS). The estimated parameters and associated marginal effects are combined to interpret the impact of the significant variables within specific clusters. Many factors are found to contribute to the severities, and T-intersection is found to be safer than cross-intersection. For driving behaviors, followed too closely, disregarded signs, disregarded signals, failed to yield, and exceeded speed are found to be top five factors that increase the crash severity at intersections. These results indicate that distraction and speed limits violation always result in severe injury for humans involved in the truck crashes at the intersections. The results of this research provide more reliable analysis for the impact factors of truck-involved crashes at intersections to engineering practitioners and researchers.

ACS Style

Li Song; Wei (David) Fan. Exploring truck driver-injury severity at intersections considering heterogeneity in latent classes: A case study of North Carolina. International Journal of Transportation Science and Technology 2020, 10, 110 -120.

AMA Style

Li Song, Wei (David) Fan. Exploring truck driver-injury severity at intersections considering heterogeneity in latent classes: A case study of North Carolina. International Journal of Transportation Science and Technology. 2020; 10 (2):110-120.

Chicago/Turabian Style

Li Song; Wei (David) Fan. 2020. "Exploring truck driver-injury severity at intersections considering heterogeneity in latent classes: A case study of North Carolina." International Journal of Transportation Science and Technology 10, no. 2: 110-120.

Journal article
Published: 29 December 2020 in Journal of Safety Research
Reads 0
Downloads 0

Introduction: With the increasing trend of pedestrian deaths among all traffic fatalities in the past decade, there is an urgent need for identifying and investigating hotspots of pedestrian-vehicle crashes with an upward trend. Method: To identify pedestrian-vehicle crash locations with aggregated spatial pattern and upward temporal pattern (i.e., hotspots with an upward trend), this paper first uses the average nearest neighbor and the spatial autocorrelation tests to determine the grid distance and the neighborhood distance for hotspots, respectively. Then, the spatiotemporal analyses with the Getis-Ord Gi* index and the Mann-Kendall trend test are utilized to identify the pedestrian-vehicle crash hotspots with an annual upward trend in North Carolina from 2007 to 2018. Considering the unobserved heterogeneity of the crash data, a latent class model with random parameters within class is proposed to identify specific contributing factors for each class and explore the heterogeneity within classes. Significant factors of the pedestrian, vehicle, crash type, locality, roadway, environment, time, and traffic control characteristics are detected and analyzed based on the marginal effects. Results: The heterogeneous results between classes and the random parameter variables detected within classes further indicate the superiority of latent class random parameter model. Practical Applications: This paper provides a framework for researchers and engineers to identify crash hotspots considering spatiotemporal patterns and contribution factors to crashes considering unobserved heterogeneity. Also, the result provides specific guidance to developing countermeasures for mitigating pedestrian-injury at pedestrian-vehicle crash hotspots with an upward trend.

ACS Style

Li Song; Wei (David) Fan; Yang Li; Peijie Wu. Exploring pedestrian injury severities at pedestrian-vehicle crash hotspots with an annual upward trend: A spatiotemporal analysis with latent class random parameter approach. Journal of Safety Research 2020, 76, 184 -196.

AMA Style

Li Song, Wei (David) Fan, Yang Li, Peijie Wu. Exploring pedestrian injury severities at pedestrian-vehicle crash hotspots with an annual upward trend: A spatiotemporal analysis with latent class random parameter approach. Journal of Safety Research. 2020; 76 ():184-196.

Chicago/Turabian Style

Li Song; Wei (David) Fan; Yang Li; Peijie Wu. 2020. "Exploring pedestrian injury severities at pedestrian-vehicle crash hotspots with an annual upward trend: A spatiotemporal analysis with latent class random parameter approach." Journal of Safety Research 76, no. : 184-196.

Journal article
Published: 13 December 2020 in Journal of Safety Research
Reads 0
Downloads 0

Introduction: Bicyclists are more vulnerable compared to other road users. Therefore, it is critical to investigate the contributing factors to bicyclist injury severity to help provide better biking environment and improve biking safety. According to the data provided by National Highway Traffic Safety Administration (NHTSA), a total of 8,028 bicyclists were killed in bicycle-vehicle crashes from 2007 to 2017. The number of fatal bicyclists has increased rapidly by approximately 11.70% for the past 10 years. In addition, 50,000 bicyclists were injured in 2017 accounting for 1.82% of total injuries in traffic crashes (NHTSA, 2019). Methods: This paper conducts a latent class clustering analysis based on the police reported bicycle-vehicle crash data collected from 2007 to 2014 in North Carolina to identify the heterogeneity inherent in the crash data. First, the most appropriate number of clusters is determined in which each cluster has been characterized by the distribution of the featured variables. Then, partial proportional odds models are developed for each cluster to further analyze the impacts on bicyclist injury severity for specific crash patterns. Results: Marginal effects are calculated and used to evaluate and interpret the effect of each significant explanatory variable. The model results reveal that variables could have different influence on the bicyclist injury severity between clusters, and that some variables only have significant impacts on particular clusters. The results clearly indicate that the latent class clustering can provide more accurate and insightful information on the bicyclist injury severity analysis.

ACS Style

Zijing Lin; Wei (David) Fan. Exploring bicyclist injury severity in bicycle-vehicle crashes using latent class clustering analysis and partial proportional odds models. Journal of Safety Research 2020, 76, 101 -117.

AMA Style

Zijing Lin, Wei (David) Fan. Exploring bicyclist injury severity in bicycle-vehicle crashes using latent class clustering analysis and partial proportional odds models. Journal of Safety Research. 2020; 76 ():101-117.

Chicago/Turabian Style

Zijing Lin; Wei (David) Fan. 2020. "Exploring bicyclist injury severity in bicycle-vehicle crashes using latent class clustering analysis and partial proportional odds models." Journal of Safety Research 76, no. : 101-117.

Journal article
Published: 03 December 2020 in Analytic Methods in Accident Research
Reads 0
Downloads 0

Using pedestrian-vehicle crash data in North Carolina from 2007 to 2018, this study explores the potential variation in the influence of factors affecting pedestrian injury severity in different time periods (weekday/weekend and three-year period). To capture unobserved heterogeneity, random parameters logit models with heterogeneity in means and variances are employed. In developing the model, several categories of factors are considered, including characteristics of the pedestrian, driver, crash, locality and roadway, time and environment, traffic control, and work zone. Transferability tests are conducted to examine the possible temporal instability of the estimation results between different time periods. According to the results, factors such as “ambulance rescue” and “curved roadway” produce temporally stable effects on pedestrian injury severity. However, strong temporal instabilities in effects on pedestrian injury severity are found for most factors across the three-year period and the weekday/weekend. In regard to structure, the model offers more insights by accounting for possible heterogeneity in the means and variances of the random parameters. Detailed policy-related recommendations are provided based on the analysis results. The findings of this work should be helpful to policymakers in future planning on safety improvements for pedestrians within the transportation system.

ACS Style

Yang Li; Li Song; Wei (David) Fan. Day-of-the-week variations and temporal instability of factors influencing pedestrian injury severity in pedestrian-vehicle crashes: A random parameters logit approach with heterogeneity in means and variances. Analytic Methods in Accident Research 2020, 29, 100152 .

AMA Style

Yang Li, Li Song, Wei (David) Fan. Day-of-the-week variations and temporal instability of factors influencing pedestrian injury severity in pedestrian-vehicle crashes: A random parameters logit approach with heterogeneity in means and variances. Analytic Methods in Accident Research. 2020; 29 ():100152.

Chicago/Turabian Style

Yang Li; Li Song; Wei (David) Fan. 2020. "Day-of-the-week variations and temporal instability of factors influencing pedestrian injury severity in pedestrian-vehicle crashes: A random parameters logit approach with heterogeneity in means and variances." Analytic Methods in Accident Research 29, no. : 100152.

Journal article
Published: 01 December 2020 in Journal of Transportation Engineering, Part A: Systems
Reads 0
Downloads 0

The security and reliability of rail transit vehicles in service are greatly affected by their wheel–rail contact. Thus, modeling the wear of wheelsets and monitoring their status is important for improving safety and reducing costs. A key issue involves evaluating the wheelset status accurately and using this as the basis for developing effective maintenance strategies and measures. However, the open nature of actual wheel–rail systems and their inconsistent environmental conditions make it difficult to construct a precise theoretical model that covers both wheelset wear and status evaluation. In this paper, a synthesis approach for evaluating the wheelset health status of rail transit vehicles is proposed. The wheelset health status is defined, and then a data-driven wheelset health evaluation model is developed. Potential causes of deviations between the model and reality are analyzed based on a theoretical wear mechanism, and application prerequisites for the proposed model are given. A case study involving the Shanghai Metro shows that the proposed approach operates well and can, therefore, be applied in practice.

ACS Style

Wei Zhu; Xin Xiao; Zhaodong Huang; Wei Fan. Evaluating the Wheelset Health Status of Rail Transit Vehicles: Synthesis of Wear Mechanism and Data-Driven Analysis. Journal of Transportation Engineering, Part A: Systems 2020, 146, 04020139 .

AMA Style

Wei Zhu, Xin Xiao, Zhaodong Huang, Wei Fan. Evaluating the Wheelset Health Status of Rail Transit Vehicles: Synthesis of Wear Mechanism and Data-Driven Analysis. Journal of Transportation Engineering, Part A: Systems. 2020; 146 (12):04020139.

Chicago/Turabian Style

Wei Zhu; Xin Xiao; Zhaodong Huang; Wei Fan. 2020. "Evaluating the Wheelset Health Status of Rail Transit Vehicles: Synthesis of Wear Mechanism and Data-Driven Analysis." Journal of Transportation Engineering, Part A: Systems 146, no. 12: 04020139.

Journal article
Published: 20 October 2020 in Analytic Methods in Accident Research
Reads 0
Downloads 0

To systematically account for the spatiotemporal features and unobserved heterogeneity within pedestrian-vehicle crashes, this paper employs the spatiotemporal analysis and hierarchical Bayesian random-effects models to explore the factors contributing to pedestrian-injury severities of pedestrian-vehicle crashes involving single vehicle in North Carolina from 2007 to 2018. Ten spatiotemporal patterns of the crashes are identified by applying an improved spatiotemporal analysis. Significant temporal instability and the spatiotemporal instability of the factors to the pedestrian-injury crashes are identified by the likelihood ratio tests. A hierarchical Bayesian random intercept logit model with random-effects across the spatiotemporal groups is firstly employed for the whole dataset. The comparison between different hierarchical models indicates that addressing random-effects across observations and increasing the number of random parameters could both improve the model performance. Then a hierarchical Bayesian random-effects-only logit model, which allows all parameters to be randomly distributed across observations, is developed to further investigate the unobserved heterogeneity in spatiotemporal segmented datasets. The significant improvements in terms of model fit and the hit accuracy underscore the superiority of the random-effects-only model. The marginal effects of the human, vehicle, crash, locality, roadway, environment, time, and traffic control factors for each spatiotemporal dataset also provide insights into possible inherent reasons for the spatiotemporal instability/tendency of the crash and correlated factors. Meanwhile, specific countermeasures are given to locations especially in which the spatially aggregated patterns of the crashes have new, consecutive, and intensifying temporal tendencies. This study provides a framework for engineers and researchers to identify spatiotemporal patterns of the crashes and explore the factors affecting pedestrian-injury severities especially in those existing crash-prone areas.

ACS Style

Li Song; Yang Li; Wei (David) Fan; Peijie Wu. Modeling pedestrian-injury severities in pedestrian-vehicle crashes considering spatiotemporal patterns: Insights from different hierarchical Bayesian random-effects models. Analytic Methods in Accident Research 2020, 28, 100137 .

AMA Style

Li Song, Yang Li, Wei (David) Fan, Peijie Wu. Modeling pedestrian-injury severities in pedestrian-vehicle crashes considering spatiotemporal patterns: Insights from different hierarchical Bayesian random-effects models. Analytic Methods in Accident Research. 2020; 28 ():100137.

Chicago/Turabian Style

Li Song; Yang Li; Wei (David) Fan; Peijie Wu. 2020. "Modeling pedestrian-injury severities in pedestrian-vehicle crashes considering spatiotemporal patterns: Insights from different hierarchical Bayesian random-effects models." Analytic Methods in Accident Research 28, no. : 100137.

Journal article
Published: 01 October 2020 in Journal of Transportation Engineering, Part A: Systems
Reads 0
Downloads 0
ACS Style

Yang Li; Wei “David” Fan. Modeling and Evaluating Public Transit Equity and Accessibility by Integrating General Transit Feed Specification Data: Case Study of the City of Charlotte. Journal of Transportation Engineering, Part A: Systems 2020, 146, 04020112 .

AMA Style

Yang Li, Wei “David” Fan. Modeling and Evaluating Public Transit Equity and Accessibility by Integrating General Transit Feed Specification Data: Case Study of the City of Charlotte. Journal of Transportation Engineering, Part A: Systems. 2020; 146 (10):04020112.

Chicago/Turabian Style

Yang Li; Wei “David” Fan. 2020. "Modeling and Evaluating Public Transit Equity and Accessibility by Integrating General Transit Feed Specification Data: Case Study of the City of Charlotte." Journal of Transportation Engineering, Part A: Systems 146, no. 10: 04020112.

Research article
Published: 19 September 2020 in Journal of Transportation Safety & Security
Reads 0
Downloads 0

In transportation, pedestrians are among the most vulnerable entities. Each year, a total of about 2,000 pedestrians are reported to be involved in traffic crashes with vehicles in North Carolina. Research efforts are needed to identify influencing factors and develop safety improvement measures for pedestrians. This study applies mixed logit (ML) model approach to exploring the potential unobserved heterogeneities across individual injury observations. Factors that significantly contribute to pedestrian injury severities resulting from pedestrian-vehicle crashes are examined under a variety of categories, including motorist, pedestrian, environmental, and roadway (etc.) characteristics. Police reported pedestrian-vehicle crash data collected from 2007 to 2014 in North Carolina are utilized. Parameter estimates and associated elasticities are used to interpret the results.

ACS Style

Yang Li; Wei (David) Fan. Mixed logit approach to modeling the severity of pedestrian-injury in pedestrian-vehicle crashes in North Carolina: Accounting for unobserved heterogeneity. Journal of Transportation Safety & Security 2020, 1 -22.

AMA Style

Yang Li, Wei (David) Fan. Mixed logit approach to modeling the severity of pedestrian-injury in pedestrian-vehicle crashes in North Carolina: Accounting for unobserved heterogeneity. Journal of Transportation Safety & Security. 2020; ():1-22.

Chicago/Turabian Style

Yang Li; Wei (David) Fan. 2020. "Mixed logit approach to modeling the severity of pedestrian-injury in pedestrian-vehicle crashes in North Carolina: Accounting for unobserved heterogeneity." Journal of Transportation Safety & Security , no. : 1-22.