International Journal of Transportation Science and Technology最新文献

Paratransit users have reportedly been unsatisfied with the quality of service that they receive. Efforts at replacing the service or formalizing operations to meet users’ mobility needs have faced challenges or outrightly resisted. Approaches such as providing travel information and deploying interventions along the roadway infrastructure where the government has authority have been suggested. Deploying any of these approaches will require insights from empirical data. The study considered a key measure of service quality to users and operators alike – travel time. It investigated factors affecting the travel time of paratransit at the route and segment levels. A travel time survey that employed a mobile app (Trands) onboard paratransit vehicle was used to collect travel time, stop, and other related information on a selected route. The backward stepwise regression technique was used to determine factors affecting paratransit travel were. Dwell time, signal delay, recurrent congestion index (RCI), non-trip stops, and deviation from route were significant variables at the route level. All the factors affecting segment travel were also part of those involving route travel time except the segment length. Interestingly, deviation from the route increased overall travel time, which is against its logic. Insights gained from the study were used in suggesting proposals that can reduce travel time and improve the service quality of paratransit.

The conditional generative adversarial network (CGAN) is used in this paper for empirical Bayes (EB) analysis of road crash hotspots. EB is a well-known method for estimating the expected crash frequency of sites (e.g. road segments, intersections) and then prioritising these sites to identify a subset of high priority sites (e.g. hotspots) for additional safety audits/improvements. In contrast to the conventional EB approach, which employs a statistical model such as the negative binomial model (NB-EB) to model crash frequency data, the recently developed CGAN-EB approach uses a conditional generative adversarial network, a form of deep neural network, that can model any form of distributions of the crash frequency data. Previous research has shown that the CGAN-EB performs as well as or better than NB-EB, however that work considered only a small range of crash data characteristics and did not examine the spatial and temporal transferability. In this paper a series of simulation experiments are devised and carried out to assess the CGAN-EB performance across a wide range of conditions and compares it to the NB-EB. The simulation results show that CGAN-EB performs as well as NB-EB when conditions favor the NB-EB model (i.e. data conform to the assumptions of the NB model) and outperforms NB-EB in experiments reflecting conditions frequently encountered in practice (i.e. low sample mean crash rates, and when crash frequency does not follow a log-linear relationship with covariates). Also, temporal and spatial transferability of both approaches were evaluated using field data and both CGAN-EB and NB-EB approaches were found to have similar performance.

Motorists are required to interact with both roadway infrastructure and various users. The complexity of the driving task in certain scenarios can influence the frequency and severity of crashes. Turning vehicles at intersections, for example, pose a collision risk for both motorized and non-motorized road users. The primary goal of this paper is to investigate the underlying factors which contribute to right-turn crashes at signalized intersections. Five years of crash data across Oregon were collected. A random parameters binary logit model was developed to predict the likelihood of whether a crash resulted in an injury or fatality. It was found that 14 variables were statistically significant in contributing to crash severity. The results obtained show that dry conditions and a posted speed limit of 30 mi/hr or 35 mi/hr contributed to a higher percentage of severe crashes, while fixed-object crashes and snowy weather had a higher likelihood of resulting in no injury crashes. Time-of-day (9:00 p.m. to 6:00 a.m.), lighting conditions (dusk), gender (male driver), crash type (vehicle–pedestrian and rear-end), and driver-level crash cause (driver sped too fast for conditions, driver did not yield right-of-way, and driver disregarded the traffic control device) all led to an increase in probability of a fatal or injury crash. The vehicle–pedestrian conflict variable had the highest impact on increasing the probability of such a crash while turning right at a signalized intersection. This observation is important because right turns are often permitted during the pedestrian walk and clearance indications, and often drivers do not give right-of-way to pedestrians.

Freight has become one of the major contributors to air pollution. This research proposes a method to systematically estimate truck vehicle emissions at the road segment level through localizing MOVES, a widely-used vehicle emission estimation model. We first design a protocol of converting percentage values of rotating speed and torque of engine to second-by-second vehicle speed to accommodate the differences between driving cycles adopted in local emission standards and those used in MOVES. In order to identify the best model year for estimating emissions under different local emission standards, we propose an approach of comparing emission outcomes rather than emission factors, considering the differences in unit used between MOVES and emission standards. To calculate road segment level emission factors, we weight original factors by integrating vehicle fleet information which contains the shares of vehicles under different emission standards and at different ages. We apply the approach to a major freight corridor area in Shanghai and calculate emission factors by air pollutant, average speed of road sections, and road type. Dynamic emissions of each road section per hour are calculated to reflect the spatial distribution of truck emissions. The research outcomes may help local departments, especially in developing countries, better estimate freight vehicle emissions and make policies correspondingly to control their impacts on public health.

In this paper, a novel method for the design of flexible pavements is elaborated. The method is based on fuzzy inference system with genetic algorithm (GA) aided optimized rule base. The model is founded on layered fuzzy antecedent and consequent conjunctive rules. The data for the model consists of 300 flexible pavement design instances that breaks up in to 25% of the data drawn from research and real field applications and 75% of data generated in spread sheets compliant with Indian road congress (IRC) code guidelines. In the first step, the inputs and outputs were fuzzified and around 110 rules were generated using training data set. GA was implemented to find optimal and a compact rule set. GA was able to garner 35 rules that are adequate to predict the thickness of base course, sub base and surface course with high accuracy. The model with optimized rules was validated using test data set. The results of the evaluation are encouraging with low values of RMSE ranging between 3.6–11 for GSB, binder course (BC) and surface course (SC). The coefficient of determination is also high and between 0.85–0.90 indicating accuracy in prediction. Correlation coefficient values stood at an average of 0.92 indicating closeness between predicted and actual values of thickness of courses.

Automated Traffic Signal Performance Measures (ATSPMs) uses high-resolution data to develop operational performance measures for signalized intersections. Split Failure (SFs) is one of the primary metrics to identify intersections with operational issues. These SFs are determined by measuring vehicle occupancy for a given movement during its green time (i.e., Green Occupancy Ratio or GOR) and immediately after the signal turns red (i.e., Red Occupancy Ratio or ROR₅). While the SF metric is a great tool for signal operations and rebalancing green times, it focuses entirely on vehicular measures and ignores the treatment of pedestrians at the intersection. Prioritizing vehicular movements may lead to excess pedestrian delay, which may cause pedestrians to violate traffic signals.

To address this issue, this paper examines the relationship between pedestrian delay and GOR or ROR₅. The main objective was to identify whether the GOR and ROR₅ could be adequately used as a proxy for pedestrian delays. To achieve this goal, high-resolution data was collected from the ATSPMs database at a signalized intersection in Salt Lake City, Utah. To predict GOR or ROR₅ as a function of pedestrian delay, a linear regression model was developed. The results reveal that there is very weak to no relationship between these metrics. This implies that using only GOR or ROR₅ in quantifying signal performance does not meaningfully capture pedestrian delay and thus might overemphasize vehicle movements. Specific pedestrian delay metrics should be included in a signal operation analysis to identify operational issues.

Signal timings at signalized intersections are frequently optimized by considering commonly used vehicle delay models. It is generally believed that reducing the average number of stops can also decrease the average vehicle delay. Therefore, the aim of this research is to address the question: “Can similar performance outcomes be achieved through the Minimization of Average Vehicle Delay (MAVD) and the Minimization of Average Number of Stops (MANS)?” The first phase of the study entails the creation of two distinct signal timing optimization models based on the Akcelik average vehicle delay and average number of stops models. Subsequently, scripts were developed in MATLAB to identify the optimal signal timings for both approaches utilizing the Differential Evolution Algorithm. In the third phase, 30 traffic scenarios were generated, each varying in overall traffic volumes at the intersection. Subsequently, the signal timings derived from the MAVD and MANS approaches were applied independently to these scenarios, and performance indicators (average vehicle delay and average number of stops) were compared. The results reveal that the utilization of MANS-based signal timings instead of MAVD may lead to an increase in average vehicle delays of up to 113.55%. Additionally, it is demonstrated that when MAVD-based signal timings are applied instead of MANS, the average number of stops can increase by up to 16.28%. Finally, it is concluded that as the overall traffic volume at the intersection increases, these growth rates tend to decrease.

Fatigue is an important cause of traffic crashes, and effective fatigue detection models can reduce these crashes. Research has found large differences in fatigued driving performance from driver to driver, as well as a significant cumulative effect of fatigue on a given driver over time. Both sources of variation can decrease the accuracy of detection systems, but previous studies have not done enough to evaluate these differences. The purpose of this study is therefore to develop a fatigue detection model that considers individual differences and the time cumulative effect of fatigue. Data on the lateral position of the car in its lane, steering wheel movement, speed, and eye movement were collected from 22 drivers using a driving simulator with an eye-tracking system. Drivers’ subjective fatigue scores were collected using the Karolinska Sleepiness Scale. State space models (SSMs) were built to detect fatigue in each driver, considering his or her individual features. As a time series model, the SSM can also address the time cumulative effect of fatigue, and it does not require a large dataset to achieve high levels of accuracy. The differences in SSM results confirm that diversity does exist among drivers’ fatigued driving performance, so the ability of the SSM to take into account driver-specific information from each individual driver suggests that it is more suitable for fatigue detection than models that use aggregated driver data. Results show that the fatigue detection accuracy of the SSM (77.73%) is higher than that of artificial neural network models (61.37%). The advantages of accuracy, high interpretability, and flexibility make the SSM a comprehensive and valuable individualized fatigue detection model for commercial use.

Access to healthcare services using public transportation (PT-based healthcare accessibility) is a crucial aspect in achieving healthcare equity as it affects individuals’ ability to receive healthcare. Previous research has focused on the spatial features of healthcare accessibility. However, less attention has been given to its temporal characteristics, which can be influenced by transit schedules, multimodal connectivity, congestion, and other factors. This study proposes a framework to better understand the impacts of temporally varying PT-based healthcare accessibility on healthcare equity. A case study of Shanghai, China is used to illustrate the temporal variation of healthcare accessibility, with a focus on hourly inter- and intra-regional disparities. These disparities are captured using the Gini coefficient and Theil index. Additionally, the study introduces bivariate local Moran’s I to identify healthcare shortage areas and evaluate the spatial autocorrelation between population density and healthcare accessibility. The findings of this study reveal that the accessibility to healthcare services experiences significant fluctuations throughout the day, leading to temporal variations in healthcare equity. Subway service quality contributes more to temporal variations than bus service quality. The lowest point of such equity is reached when PT operates at its full capacity. On a spatial level, individuals residing in newly developed regions, which surround the historical urban core or recently planned city subcenters, tend to experience decreased accessibility to healthcare via public transportation. Consequently, it results in a heightened reliance on motorized transportation in these areas. These findings provide insights that can inform the design of PT accessibility-based strategies, healthcare improvement plans and inclusive housing policies, to address healthcare equity issues in metropolitan areas. By considering both spatial and temporal factors, we can better understand the complex relationships between transportation and healthcare accessibility to promote equitable access to healthcare services and foster social equity.

The volume of instant delivery has witnessed a significant growth in recent years. Given the involvement of numerous heterogeneous stakeholders, instant delivery operations are inherently characterized by dynamics and uncertainties. This study introduces two order dispatching strategies, namely task buffering and dynamic batching, as potential solutions to address these challenges. The task buffering strategy aims to optimize the assignment timing of orders to couriers, thereby mitigating demand uncertainties. On the other hand, the dynamic batching strategy focuses on alleviating delivery pressure by assigning orders to couriers based on their residual capacity and extra delivery distances. To model the instant delivery problem and evaluate the performances of order dispatching strategies, Adaptive Agent-Based Order Dispatching (ABOD) approach is developed, which combines agent-based modelling, deep reinforcement learning, and the Kuhn-Munkres algorithm. The ABOD effectively captures the system's uncertainties and heterogeneity, facilitating stakeholders learning in novel scenarios and enabling adaptive task buffering and dynamic batching decision-makings. The efficacy of the ABOD approach is verified through both synthetic and real-world case studies. Experimental results demonstrate that implementing the ABOD approach can lead to a significant increase in customer satisfaction, up to 275.42%, while simultaneously reducing the delivery distance by 11.38% compared to baseline policies. Additionally, the ABOD approach exhibits the ability to adaptively adjust buffering times to maintain high levels of customer satisfaction across various demand scenarios. As a result, this approach offers valuable support to logistics providers in making informed decisions regarding order dispatching in instant delivery operations.