Evaluation of mobility impact on urban work zones using statistical models

Journal of Central South University - This work correlated the detailed work zone location and time data from the WisLCS system with the five-min inductive loop detector data. One-sample percentile...     

A multi-pattern deep fusion model for short-term bus passenger flow forecasting

Short-term passenger flow forecasting is one of the crucial components in transportation systems with data support for transportation planning and management. For forecasting bus passenger flow, this paper proposes a multi-pattern deep fusion (MPDF) approach that is constructed by fusing deep belief networks (DBNs) corresponding to multiple patterns. The dataset of the short-term bus passenger flow is first segmented into different clusters by an affinity propagation algorithm. The passenger flow distribution of these clusters is subsequently analyzed for identifying different patterns. In each pattern, a DBN is developed as a deep representation for the passenger flow. The outputs of the DBNs are finally fused by chronological order rearrangement. Taking a bus line in Guangzhou city of China as an example, the present MPDF approach is modeled. Five approaches, non-parametric and parametric models, are applied to the same case for comparison. The results show that, the proposed model overwhelms all the peer methods in terms of mean absolute percentage error, root-mean-square error, and determination coefficient criteria. In addition, there exists significant difference between the addressed model and the comparison models. It is recommended from the present study that the deep learning technique incorporating the pattern analysis is promising in forecasting the short-term passenger flow.     

Effects of extraordinary snowfall on traffic safety

Snowfall affects traffic safety by causing changes in roadway surface and visibility that result in crashes, spinouts, and breakdowns. Using data collected at a site that regularly receives nearly 1000 cm of snow during the snow season, this study examines the impact of snowfall quantity, gap between snow events, and weather conditions on crash and incident frequencies. Estimation results from regression analysis show that snowfall severity significantly impacts crashes and incidents but the impact diminishes marginally with each additional centimeter of snow. Gap has a significant fixed effect on crashes but its impact on incidents varies significantly across observations. The effect of the mixed precipitation condition is smaller in comparison to an all-snow condition. These results will help inform policy for snow removal and traffic enforcement in areas of high snowfall.     

多分类支持向量机在公交换乘识别中的应用

为获取居民公交出行的换乘信息,设计了一套基于多分类支持向量机(multi-class support vector machine)的公交换乘识别方法.通过融合GPS数据和公交IC卡数据获取训练样本,利用多分类支持向量机进行样本训练,选取最佳训练样本量,并采用网格搜索法结合粒子优化算法对模型参数进行标定,以获取最优SVM分类模型.测试结果显示模型分类精度可达90%.以佛山市公交车GPS数据和IC卡数据对算法进行验证,并获取公交换乘量、公交换乘比例等基本换乘数据.结果表明:算法可在少样本条件下完成公交换乘识别,且分类识别精度高,尤其适用于公交线网复杂的大城市公交换乘识别,有助于在公交前期规划时进行线路布设和枢纽选址.     

Analysis of injury severity of large truck crashes in work zones

Work zones are critical parts of the transportation infrastructure renewal process consisting of rehabilitation of roadways, maintenance, and utility work. Given the specific nature of a work zone (complex arrangements of traffic control devices and signs, narrow lanes, duration) a number of crashes occur with varying severities involving different vehicle sizes. In this paper we attempt to investigate the causal factors contributing to injury severity of large truck crashes in work zones. Considering the discrete nature of injury severity categories, a number of comparable econometric models were developed including multinomial logit (MNL), nested logit (NL), ordered logit (ORL), and generalized ordered logit (GORL) models. The MNL and NL models belong to the class of unordered discrete choice models and do not recognize the intrinsic ordinal nature of the injury severity data. The ORL and GORL models, on the other hand, belong to the ordered response framework that was specifically developed for handling ordinal dependent variables. Past literature did not find conclusive evidence in support of either framework. This study compared these alternate modeling frameworks for analyzing injury severity of crashes involving large trucks in work zones. The model estimation was undertaken by compiling a database of crashes that (1) involved large trucks and (2) occurred in work zones in the past 10 years in Minnesota. Empirical findings indicate that the GORL model provided superior data fit as compared to all the other models. Also, elasticity analysis was undertaken to quantify the magnitude of impact of different factors on work zone safety and the results of this analysis suggest the factors that increase the risk propensity of sustaining severe crashes in a work zone include crashes in the daytime, no control of access, higher speed limits, and crashes occurring on rural principal arterials.     

Development of a variable speed limit strategy to reduce secondary collision risks during inclement weathers

Inclement weather reduces traveler's sight distance and increases vehicle's stopping distance. Once a collision occurred during inclement weather and resulted in a slow traffic, approaching vehicles may not have adequate time to make emergency responses to the hazardous traffic, resulting in increased potentials of secondary collisions. The primary objective of this study is to develop a control strategy of variable speed limits (VSL) to reduce the risks of secondary collisions during inclement weathers. By analyzing the occurrence condition of secondary collision, the VSL strategy is proposed to dynamically adjust the speed limits according to the current traffic and weather conditions. A car-following model is modified to simulate the vehicle maneuvers with the VSL control. Two surrogate safety measures, based on the time-to-collision notion, are used to evaluate the control effects of VSL. Five weather scenarios are evaluated in simulation. The results show that the VSL strategy effectively reduces the risks of secondary collisions in various weather types. The time exposed time-to-collision (TET) is reduced by 41.45%–50.74%, and the time integrated time-to-collision (TIT) is reduced by 38.19%–41.19%. The safety effects are compared to those with a previous VSL strategy. The results show that in most cases our strategy outperforms the previous one. We also evaluate how driver's compliance to speed limit affects the effectiveness of VSL control.     

Differences in state drug testing and reporting by driver type in U.S. fatal traffic crashes

IntroductionDriving under the influence of drugs, including marijuana, has become more prevalent in recent years despite local, state, and federal efforts to prevent such increases. The Fatality Analysis Reporting System (FARS) is the primary source of drugged driving data for fatal crashes in the United States but lacks the completeness required to calculate unbiased estimates of drug use among drivers involved in fatal crashes.MethodsThis article uses the 2013 FARS dataset to present differences in state drug testing rates by driver type, driver fault type, and state-level factors; discusses limitations related to analysis and interpretation of drugged driving data; and offers suggestions for improvements that may enable appropriate use of FARS drug testing data in the future.ResultsResults showed that state drug testing rates were highest among drivers who died at the scene of the crash (median = 70.8%) and drivers who died and were at fault in the crash (median = 64.4%). The lowest testing rates were seen among surviving drivers who were not transported to a hospital (median = 14.0%) and surviving drivers who were not at fault in the crash (median = 10.0%). Drug testing rates differed by state blood alcohol content (BAC) testing rate across all driver types and driver fault types, and in general, states that tested a higher percentage of drivers for BAC had higher drug testing rates.DiscussionTesting rates might be increased through standardization and mandatory testing policies. FARS data users should continue to be cautious about the limitations of using currently available data to quantify drugged driving. More efforts are needed to improve drug testing and reporting practices, and more research is warranted to establish drug concentration levels at which driving skills become impaired.     

Exploring Bikesharing Travel Patterns and Trip Purposes Using Smart Card Data and Online Point of Interests

The primary objective of this study was to investigate the bikesharing travel patterns and trip purposes by combining smart card data and online point of interests (POIs). A large-scale smart card trip data was collected from the bikesharing system in New York City. The POIs surrounding each station were obtained from Google Places API. K-means clustering analysis was first applied to divide bikesharing stations into five types based on their surrounding POIs. The Latent Dirichlet Allocation (LDA) analysis was then conducted to discover the hidden bikesharing travel patterns and trip purposes using the identified station types and smart card data. The performance of the LDA models with and without POI data was compared to identify whether the POI data should be used. Finally, a practical application of the proposed methods in bikesharing planning and operation was discussed. The result of comparative analyses verified the importance of POI data in exploring bikesharing travel patterns and trip purposes. The results of LDA model showed that the most prevalent travel purpose in New York City is taking public bike for eating, followed by shopping and transferring to other public transit systems. In addition, the result also suggested that people living around the bikesharing stations are more likely to transfer to other commuting tools on the morning peak and ride for home after work. The proposed methods can be used to provide useful guidance and suggestions for transportation agency to develop strategies and regulation that aim at improving the operations of bikesharing systems.     

A modification of local path marginal cost on the dynamic traffic network

Railway Engineering Science - Path marginal cost (PMC) is the change in total travel cost for flow on the network that arises when time-dependent path flow changes by 1 unit. Because it is...     

Empirical investigation on safety constraints of merging pedestrian crowd through macroscopic and microscopic analysis

A recent crowd stampede during a New Year's Eve celebration in Shanghai, China resulted in 36 fatalities and over 49 serious injuries. Many of such tragic crowd accidents around the world resulted from complex multi-direction crowd movement such as merging behavior. Although there are a few studies on merging crowd behavior, none of them have conducted a systematic analysis considering the impact of both merging angle and flow direction towards the safety of pedestrian crowd movement. In this study, a series of controlled laboratory experiments were conducted to examine the safety constraints of merging pedestrian crowd movements considering merging angle (60°, 90° and 180°) and flow direction under slow running and blocked vision condition. Then, macroscopic and microscopic properties of crowd dynamics are obtained and visualized through the analysis of pedestrian crowd trajectory data derived from video footage. It was found that merging angle had a significant influence on the fluctuations of pedestrian flows, which is important in a critical situation such as emergency evacuation. As the merging angle increased, mean velocity and mean flow at the measuring region in the exit corridors decreased, while mean density increased. A similar trend was observed for the number of weaving and overtaking conflicts, which resulted in the increase of mean headway. Further, flow direction had a significant impact on the outflow of the individuals while blocked vision had an influence on pedestrian crowd interactions and merging process. Finally, this paper discusses safety assessments on crowd merging behaviors along with some recommendations for future research. Findings from this study can assist in the development and validation of pedestrian crowd simulation models as well as organization and control of crowd events.