Showing papers in "Journal of Advanced Transportation in 2019"

Driver Distraction Identification with an Ensemble of Convolutional Neural Networks

Abstract: The World Health Organization (WHO) reported 1.25 million deaths yearly due to road traffic accidents worldwide and the number has been continuously increasing over the last few years. Nearly fifth of these accidents are caused by distracted drivers. Existing work of distracted driver detection is concerned with a small set of distractions (mostly, cell phone usage). Unreliable ad hoc methods are often used. In this paper, we present the first publicly available dataset for driver distraction identification with more distraction postures than existing alternatives. In addition, we propose a reliable deep learning-based solution that achieves a 90% accuracy. The system consists of a genetically weighted ensemble of convolutional neural networks; we show that a weighted ensemble of classifiers using a genetic algorithm yields a better classification confidence. We also study the effect of different visual elements in distraction detection by means of face and hand localizations, and skin segmentation. Finally, we present a thinned version of our ensemble that could achieve 84.64% classification accuracy and operate in a real-time environment.

Spatiotemporal Traffic Flow Prediction with KNN and LSTM

Abstract: The traffic flow prediction is becoming increasingly crucial in Intelligent Transportation Systems. Accurate prediction result is the precondition of traffic guidance, management, and control. To improve the prediction accuracy, a spatiotemporal traffic flow prediction method is proposed combined with k-nearest neighbor (KNN) and long short-term memory network (LSTM), which is called KNN-LSTM model in this paper. KNN is used to select mostly related neighboring stations with the test station and capture spatial features of traffic flow. LSTM is utilized to mine temporal variability of traffic flow, and a two-layer LSTM network is applied to predict traffic flow respectively in selected stations. The final prediction results are obtained by result-level fusion with rank-exponent weighting method. The prediction performance is evaluated with real-time traffic flow data provided by the Transportation Research Data Lab (TDRL) at the University of Minnesota Duluth (UMD) Data Center. Experimental results indicate that the proposed model can achieve a better performance compared with well-known prediction models including autoregressive integrated moving average (ARIMA), support vector regression (SVR), wavelet neural network (WNN), deep belief networks combined with support vector regression (DBN-SVR), and LSTM models, and the proposed model can achieve on average 12.59% accuracy improvement.

A Survey on the Electric Vehicle Routing Problem: Variants and Solution Approaches

Abstract: In order to ensure high-quality and on-time delivery in logistic distribution processes, it is necessary to efficiently manage the delivery fleet. Nowadays, due to the new policies and regulations related to greenhouse gas emission in the transport sector, logistic companies are paying higher penalties for each emission gram of /km. With electric vehicle market penetration, many companies are evaluating the integration of electric vehicles in their fleet, as they do not have local greenhouse gas emissions, produce minimal noise, and are independent of the fluctuating oil price. The well-researched vehicle routing problem (VRP) is extended to the electric vehicle routing problem (E-VRP), which takes into account specific characteristics of electric vehicles. In this paper, a literature review on recent developments regarding the E-VRP is presented. The challenges that emerged with the integration of electric vehicles in the delivery processes are described, together with electric vehicle characteristics and recent energy consumption models. Several variants of the E-VRP and related problems are observed. To cope with the new routing challenges in E-VRP, efficient VRP heuristics and metaheuristics had to be adapted. An overview of the state-of-the-art procedures for solving the E-VRP and related problems is presented.

Rapid Driving Style Recognition in Car-Following Using Machine Learning and Vehicle Trajectory Data

Abstract: Rear-end collision crash is one of the most common accidents on the road. Accurate driving style recognition considering rear-end collision risk is crucial to design useful driver assistance systems and vehicle control systems. The purpose of this study is to develop a driving style recognition method based on vehicle trajectory data extracted from the surveillance video. First, three rear-end collision surrogates, Inversed Time to Collision (ITTC), Time-Headway (THW), and Modified Margin to Collision (MMTC), are selected to evaluate the collision risk level of vehicle trajectory for each driver. The driving style of each driver in training data is labelled based on their collision risk level using K-mean algorithm. Then, the driving style recognition model’s inputs are extracted from vehicle trajectory features, including acceleration, relative speed, and relative distance, using Discrete Fourier Transform (DFT), Discrete Wavelet Transform (DWT), and statistical method to facilitate the driving style recognition. Finally, Supporting Vector Machine (SVM) is applied to recognize driving style based on the labelled data. The performance of Random Forest (RF), K-Nearest Neighbor (KNN), and Multi-Layer Perceptron (MLP) is also compared with SVM. The results show that SVM overperforms others with 91.7% accuracy with DWT feature extraction method.

Fully Autonomous Buses: A Literature Review and Future Research Directions

Abstract: Autonomous vehicles (AVs) represent a new, growing segment of transportation research. While there have been prior studies and deployments of AVs worldwide, full autonomy in bus transit has gained interest among researchers and practitioners within the last decade, which presents an opportunity to synthesize early trends. Therefore, the objective of this paper is to provide a review of the latest research on fully autonomous buses to summarize findings and identify gaps needing future research. Forty studies were reviewed in detail, and five main themes were identified, which are (1) technology deployment; (2) user acceptance; (3) safety; (4) social and economic aspects; and (5) regulations, policies, and legal issues. The results reveal that most prior studies have focused on technology development, and the area of regulation and policy would benefit from additional study. Noteworthy differences between research in Europe and the United States were also identified. In Europe, large funded projects involving real-world deployments have focused on user acceptance, security and safety, costs, and related legal issues, whereas in the United States, research has primarily concentrated on simulation modelling with limited real-world deployments. The results of this review are important for policy-makers and researchers as AV technology continues to evolve and become more widely available.

Simulation-Based Connected and Automated Vehicle Models on Highway Sections: A Literature Review

Abstract: This study provides a literature review of the simulation-based connected and automated intelligent-vehicle studies. Media and car-manufacturing companies predict that connected and automated vehicles (CAVs) would be available in the near future. However, society and transportation systems might not be completely ready for their implementation in various aspects, e.g., public acceptance, technology, infrastructure, and/or policy. Since the empirical field data for CAVs are not available at present, many researchers develop micro or macro simulation models to evaluate the CAV impacts. This study classifies the most commonly used intelligent-vehicle types into four categories (i.e., adaptive cruise control, ACC; cooperative adaptive cruise control, CACC; automated vehicle, AV; CAV) and summarizes the intelligent-vehicle car-following models (i.e., Intelligent Driver Model, IDM; MICroscopic Model for Simulation of Intelligent Cruise Control, MIXIC). The review results offer new insights for future intelligent-vehicle analyses: (i) the increase in the market-penetration rate of intelligent vehicles has a significant impact on traffic flow conditions; (ii) without vehicle connections, such as the ACC vehicles, the roadway-capacity increase would be marginal; (iii) none of the parameters in the AV or CAV models is calibrated by the actual field data; (iv) both longitudinal and lateral movements of intelligent vehicles can reduce energy consumption and environmental costs compared to human-driven vehicles; (v) research gap exists in studying the car-following models for newly developed intelligent vehicles; and (vi) the estimated impacts are not converted into a unified metric (i.e., welfare economic impact on users or society) which is essential to evaluate intelligent vehicles from an overall societal perspective.

Panic, Irrationality, and Herding: Three Ambiguous Terms in Crowd Dynamics Research

Abstract: Background. The three terms “panic”, “irrationality”, and “herding” are ubiquitous in the crowd dynamics literature and have a strong influence on both modelling and management practices. The terms are also commonly shared between the scientific and nonscientific domains. The pervasiveness of the use of these terms is to the point where their underlying assumptions have often been treated as common knowledge by both experts and lay persons. Yet, at the same time, the literature on crowd dynamics presents ample debate, contradiction, and inconsistency on these topics. Method. This review is the first to systematically revisit these three terms in a unified study to highlight the scope of this debate. We extracted from peer-reviewed journal articles direct quotes that offer a definition, conceptualisation, or supporting/contradicting evidence on these terms and/or their underlying theories. To further examine the suitability of the term herding, a secondary and more detailed analysis is also conducted on studies that have specifically investigated this phenomenon in empirical settings. Results. The review shows that (i) there is no consensus on the definition for the terms panic and irrationality and that (ii) the literature is highly divided along discipline lines on how accurate these theories/terminologies are for describing human escape behaviour. The review reveals a complete division and disconnection between studies published by social scientists and those from the physical science domain and also between studies whose main focus is on numerical simulation versus those with empirical focus. (iii) Despite the ambiguity of the definitions and the missing consensus in the literature, these terms are still increasingly and persistently mentioned in crowd evacuation studies. (iv) Different to panic and irrationality, there is relative consistency in definitions of the term herding, with the term usually being associated with ‘(blind) imitation’. However, based on the findings of empirical studies, we argue why, despite the relative consistency in meaning, (v) the term herding itself lacks adequate nuance and accuracy for describing the role of ‘social influence’ in escape behaviour. Our conclusions also emphasise the importance of distinguishing between the social influence on various aspects of evacuation behaviour and avoiding generalisation across various behavioural layers. Conclusions. We argue that the use of these three terms in the scientific literature does not contribute constructively to extending the knowledge or to improving the modelling capabilities in the field of crowd dynamics. This is largely due to the ambiguity of these terms, the overly simplistic nature of their assumptions, or the fact that the theories they represent are not readily verifiable. Recommendations. We suggest that it would be beneficial for advancing this research field that the phenomena related to these three terms are clearly defined by more tangible and quantifiable terms and be formulated as verifiable hypotheses, so they can be operationalized for empirical testing.

How Have Travelers Changed Mode Choices for First/Last Mile Trips after the Introduction of Bicycle-Sharing Systems: An Empirical Study in Beijing, China

Abstract: In recent years, there has been rapid development in bicycle-sharing systems (BSS) in China. Moreover, such schemes are considered promising solutions to the first/last mile problem. This study investigates the mode choice behaviors of travelers for first/last mile trips before and after the introduction of bicycle-sharing systems. Travel choice models for first/last mile trips are determined using a multinomial logit model. It also analyzes the differences in choice behavior between the young and other age groups. The findings show that shared bicycles become the preferred mode, while travelers preferred walking before bicycle-sharing systems were implemented. Gender, bicycle availability, and travel frequency were the most significant factors before the implementation of bicycle-sharing systems. However, after implementation, access distance dramatically affects mode choices for first/last mile trips. When shared bicycles are available, the mode choices of middle-aged group depend mainly on gender and access distance. All factors are not significant for the young and aged groups. More than 80% of public transport travelers take walking and shared bicycles as feeder modes. The proposed models and findings contribute to a better understanding of travelers’ choice behaviors and to the development of solutions for the first/last mile problem.

A Machine Learning Method for Predicting Driving Range of Battery Electric Vehicles

Abstract: It is of great significance to improve the driving range prediction accuracy to provide battery electric vehicle users with reliable information. A model built by the conventional multiple linear regression method is feasible to predict the driving range, but the residual errors between -3.6975 km and 3.3865 km are relatively unfaithful for real-world driving. The study is innovative in its application of machine learning method, the gradient boosting decision tree algorithm, on the driving range prediction which includes a very large number of factors that cannot be considered by conventional regression methods. The result of the machine learning method shows that the maximum prediction error is 1.58 km, the minimum prediction error is -1.41 km, and the average prediction error is about 0.7 km. The predictive accuracy of the gradient boosting decision tree is compared against that of the conventional approaches.

Impact of Transport Cost and Travel Time on Trade under China-Pakistan Economic Corridor (CPEC)

Abstract: China is the second biggest economy in the world and almost 40% of its trade in 2016 is transported through the South China Sea. China needs a small, secure, and low-cost path to trade with Europe and the Middle East and China-Pakistan Economic Corridor (CPEC) is a feasible solution to this requirement. This research analyzes the effect of CPEC on trade in terms of transport cost and travel time. In addition, the study compares the existing routes and the new CPEC route. The research methodology consists of qualitative and descriptive statistical methods. The variables (transport cost and travel time) are calculated and compared for both the existing route and new CPEC route. The results show that transport cost for 40-foot container between Kashgar and destination ports in the Middle East is decreased by about $1450 dollars and for destination ports in Europe is decreased by $1350 dollars. Additionally, travel time is decreased by 21 to 24 days for destination ports in the Middle East and 21 days for destination ports in Europe. The distance from Kashgar to destination ports in the Middle East and Europe is decreased by 11,000 to 13,000 km.

An Initial Investigation of the Effects of a Fully Automated Vehicle Fleet on Geometric Design

Abstract: This paper investigates the potential changes in the geometric design elements in response to a fully autonomous vehicle fleet. When autonomous vehicles completely replace conventional vehicles, the human driver will no longer be a concern. Currently, and for safety reasons, the human driver plays an inherent role in designing highway elements, which depend on the driver’s perception-reaction time, driver’s eye height, and other driver related parameters. This study focuses on the geometric design elements that will directly be affected by the replacement of the human driver with fully autonomous vehicles. Stopping sight distance, decision sight distance, and length of sag and crest vertical curves are geometric design elements directly affected by the projected change. Revised values for these design elements are presented and their effects are quantified using a real-life scenario. An existing roadway designed using current AASHTO standards has been redesigned with the revised values. Compared with the existing design, the proposed design shows significant economic and environmental improvements, given the elimination of the human driver.

Optimization of Base Location and Patrol Routes for Unmanned Aerial Vehicles in Border Intelligence, Surveillance, and Reconnaissance

Abstract: The location-routing problem (LRP) of unmanned aerial vehicles (UAV) in border patrol for Intelligence, Surveillance, and Reconnaissance is investigated, where the locations of UAV base stations and the UAV flying routes for visiting the targets in border area are jointly optimized. The capacity of the base station and the endurance of the UAV are considered. A binary integer programming model is developed to formulate the problem, and two heuristic algorithms combined with local search strategies are designed for solving the problem. The experiment design for simulating the distribution of stations and targets in border is proposed for generating random test instances. Also, an example based on the practical border in Guangxi is presented to illustrate the problem and the solution approach. The performance of the two algorithms is analysed and compared through randomly generated instances.

Efficiency of Semi-Autonomous and Fully Autonomous Bus Services in Trunk-and-Branches Networks

Abstract: Automation technology is expected to change the public transport sector radically in the future. One rising issue is whether to embrace the intermediate stage of semi-autonomous buses or to wait un ...

ST-LSTM: A Deep Learning Approach Combined Spatio-Temporal Features for Short-Term Forecast in Rail Transit

Abstract: The short-term forecast of rail transit is one of the most essential issues in urban intelligent transportation system (ITS). Accurate forecast result can provide support for the forewarning of flow outburst and enables passengers to make an appropriate travel plan. Therefore, it is significant to develop a more accurate forecast model. Long short-term memory (LSTM) network has been proved to be effective on data with temporal features. However, it cannot process the correlation between time and space in rail transit. As a result, a novel forecast model combining spatio-temporal features based on LSTM network (ST-LSTM) is proposed. Different from other forecast methods, ST-LSTM network uses a new method to extract spatio-temporal features from the data and combines them together as the input. Compared with other conventional models, ST-LSTM network can achieve a better performance in experiments.

A Hybrid Method for Traffic Incident Duration Prediction Using BOA-Optimized Random Forest Combined with Neighborhood Components Analysis

Abstract: Predicting traffic incident duration is important for effective and real-time traffic incident management (TIM), which helps to minimize traffic congestion, environmental pollution, and secondary incident related to this incident. Traffic incident duration prediction methods often use more input variables to obtain better prediction results. However, the problems that available variables are limited at the beginning of an incident and how to select significant variables are ignored to some extent. In this paper, a novel prediction method named NCA-BOA-RF is proposed using the Neighborhood Components Analysis (NCA) and the Bayesian Optimization Algorithm (BOA)-optimized Random Forest (RF) model. Firstly, the NCA is applied to select feature variables for traffic incident duration. Then, RF model is trained based on the training set constructed using feature variables, and the BOA is employed to optimize the RF parameters. Finally, confusion matrix is introduced to measure the optimized RF model performance and compare with other methods. In addition, the performance is also tested in the absence of some feature variables. The results demonstrate that the proposed method not only has high accuracy, but also exhibits excellent reliability and robustness.

Effects of on-Board Unit on Driving Behavior in Connected Vehicle Traffic Flow

Abstract: Connected vehicle technology has potentials to increase traffic safety, reduce traffic pollution, and ease traffic congestion. In the connected vehicle environment, the information interaction among people, cars, roads, and the environment is significantly enhanced, and driver behavior will change accordingly due to increased external stimulation. This paper designed a Vehicle-to-Vehicle (V2V) on-board unit (OBU) based on driving demand. In addition, a simulation platform for the interconnection and communication between the OBU and simulator was built. Thirty-one test drivers were investigated to drive an instrumented vehicle in four scenarios, with and without the OBU under two different traffic states. Collected trajectory data of the subject vehicle and the vehicle in front, as well as sociodemographic characteristics of the test drivers were used to evaluate the potential impact of such OBUs on driving behavior and traffic safety. Car-following behavior is an essential component of microsimulation models. This paper also investigated the impacts of the V2V OBU on car-following behaviors. Considering the car-following related indicators, the k-Means algorithm was used to categorize different car-following modes. The results show that the OBU has a positive impact on drivers in terms of speed, front distance, and the time to stable regime. Furthermore, drivers’ opinions show that the system is acceptable and useful in general.

Extracting Vehicle Trajectories Using Unmanned Aerial Vehicles in Congested Traffic Conditions

Abstract: Obtaining the trajectories of all vehicles in congested traffic is essential for analyzing traffic dynamics. To conduct an effective analysis using trajectory data, a framework is needed to efficiently and accurately extract the data. Unfortunately, obtaining accurate trajectories in congested traffic is challenging due to false detections and tracking errors caused by factors in the road environment, such as adjacent vehicles, shadows, road signs, and road facilities. Unmanned aerial vehicles (UAVs), with incorporating machine learning and image processing, can mitigate these difficulties by their ability to hover above the traffic. However, research is lacking regarding the extraction and evaluation of vehicle trajectories in congested traffic. In this study, we propose and compare two learning-based frameworks for detecting vehicles: the aggregated channel feature (ACF), which is based on human-made features, and the faster region-based convolutional neural network (Faster R-CNN), which is based on data-driven features. We extend the detection results to extract vehicle trajectories in congested traffic conditions from UAV images. To remove the errors associated with tracking vehicles, we also develop a postprocessing method based on motion constraints. Then, we conduct detailed performance analyses to confirm the feasibility of the proposed framework on a congested expressway in Korea. The results show that Faster R-CNN outperforms the ACF in images with large objects and in those with small objects if sufficient data are provided. This framework extracts the vehicle trajectories with high precision, making them available for analyzing traffic dynamics based on the training of just a small number of positive samples. The results of this study provide a practical guideline for building a framework to extract vehicles trajectories based on given conditions.

Travel Behavior Analysis Using 2016 Qingdao’s Household Traffic Surveys and Baidu Electric Map API Data

Abstract: Household traffic surveys are widely used in travel behavior analysis, especially in travel time and distance analysis. Unfortunately, any one kind of household traffic surveys has its own problems. Even all household traffic survey data is accurate, it is difficult to get the trip routes information. To our delight, electric map API (e.g., Google Maps, Apple Maps, Baidu Maps, and Auto Navi Maps) could provide the trip route and time information, which remedies the traditional traffic survey’s defect. Thus, we can take advantage of the two kinds of data and integrate them into travel behavior analysis. In order to test the validity of the Baidu electric map API data, a field study on 300 taxi OD pairs is carried out. According to statistical analysis, the average matching rate of total OD pairs is 90.74%, which reflects high accuracy of electric map API data. Based on the fused data of household traffic survey and electric map API, travel behavior on trip time and distance is analyzed. Results show that most purposes’ trip distances distributions are concentrated, which are no more than 10 kilometers. It is worth noting that students have the shortest travel distance and company business’s travel distance distribution is dispersed, which has the longest travel distance. Compared to travel distance, the standard deviations of all purposes’ travel time are greater than the travel distance. Car users have longer travel distance than bus travelers, and their average travel distance is 8.58km.

Approximating Betweenness Centrality to Identify Key Nodes in a Weighted Urban Complex Transportation Network

Abstract: The key nodes in a complex transportation network have a significant influence on the safety of traffic operations, connectivity reliability, and the performance of the entire network. However, the identification of key nodes in existing urban transportation networks has mainly focused on nonweighted networks and the network information of the nodes themselves, which do not accurately reflect their global status. Thus, the present study proposes a key node identification algorithm that combines traffic flow features and is based on weighted betweenness centrality. This study also uses weighted roads to construct an L-space weighted transportation network and an approximate algorithm for betweenness centrality in order to reduce the complexity of the calculations. The results of the simulation indicate that the proposed algorithm is not only capable of identifying the key nodes in a relatively short amount of time, but it does so with high accuracy. The findings of this study can be used to provide decision-making support for road network management, planning, and urban traffic construction optimization.

The Influence of Wheelchair Users on Movement in a Bottleneck and a Corridor

Abstract: Emergency exits as bottlenecks in escape routes are important for designing traffic facilities. Particularly, the capacity estimation is a crucial performance criterion for assessment of pedestrians’ safety in built environments. For this reason, several studies were performed during the last decades which focus on the quantification of movement through corridors and bottlenecks. These studies were usually conducted with populations of homogeneous characteristics to reduce influencing variables and for reasons of practicability. Studies which consider heterogeneous characteristics in performance parameters are rarely available. In response and to reduce this lack of data a series of well-controlled large-scale movement studies considering pedestrians using different types of wheelchairs was carried out. As a result it is shown that the empirical relations and are strongly affected by the presence of participants with visible disabilities (such as wheelchair users). We observed an adaption of the overall movement speeds to the movement speeds of participants using a wheelchair, even for low densities and free flow scenarios. Flow and movement speed are in a complex relation and do not depend on density only. In our studies, the concept of specific flow fits for the nondisabled subpopulation but it is not valid for scenario considering wheelchair users in the population.

Ship’s Trajectory Planning Based on Improved Multiobjective Algorithm for Collision Avoidance

Abstract: With vigorous development of the maritime trade, many intelligent algorithms have been proposed to avoid collisions due to resulting casualties and increased costs. According to the international regulations for preventing collisions at sea (COLREGs) and the self-evolution ability of the intelligent algorithm, the collision avoidance trajectory can be more consistent with the requirements of reality and maritime personnel. In this paper, the optimization of ship collision avoidance strategies is realized by both an improved multiobjective optimization algorithm NSGA-II and the ship domain under the condition of a wide sea area without any external disturbances. By balancing the safety and economy of ship collision avoidance, the avoidance angle and the time to the action point are used as the variables encoded by the algorithm, and the fuzzy ship domain is used to calculate the collision avoidance risk to achieve collision avoidance. The simulation results show that the proposed method can optimize the ship collision avoidance strategy and provide a reasonable scheme for ship navigation.

Study of Flight Departure Delay and Causal Factor Using Spatial Analysis

Abstract: Analysis of flight delay and causal factors is crucial in maintaining airspace efficiency and safety. However, delay samples are not independent since they always show a certain aggregation pattern. Therefore, this study develops a novel spatial analysis approach to explore the delay and causal factors which is able to take dependence and the possible problem involved including error correlation and variable lag effect of causal factors on delay into account. The study first explores the delay aggregation pattern by measuring and quantifying the spatial dependence of delay. The spatial error model (SEM) and spatial lag model (SLM) are then established to solve the error correlation and the variable lag effect, respectively. Results show that the SEM and SLM achieve better fit than ordinary least square (OLS) regression, which indicates the effectiveness of considering dependence by employing spatial analysis. Moreover, the outcomes suggest that, aside from the well-known weather and flow control factors, delay-reduction strategies also need to pay more attention to reducing the impact of delay at the previous airport.

Automatic Segmentation and Enhancement of Pavement Cracks Based on 3D Pavement Images

Abstract: Pavement cracking is a significant symptom of pavement deterioration and deficiency. Conventional manual inspections of road condition are gradually replaced by novel automated inspection systems. As a result, a great amount of pavement surface information is digitized by these systems with a high resolution. With pavement surface data, pavement cracks can be detected using crack detection algorithms. In this paper, a fully automated algorithm for segmenting and enhancing pavement crack is proposed, which consists of four major procedures. First, a preprocessing procedure is employed to remove spurious noise and rectify the original 3D pavement data. Second, crack saliency maps are segmented from 3D pavement data using steerable matched filter bank. Third, 2D tensor voting is applied to crack saliency maps to achieve better curve continuity of crack structure and higher accuracy. Finally, postprocessing procedures are used to remove redundant noises. The proposed procedures were evaluated over 200 asphalt pavement images with diverse cracks. The experimental results demonstrated that the proposed method showed a high performance and could achieve average precision of 88.38%, recall of 93.15%, and F-measure of 90.68%, respectively. Accordingly, the proposed approach can be helpful in automated pavement condition assessment.

Does High-Speed Rail Promote Enterprises Productivity? Evidence from China

Abstract: High-speed rail (HSR) is often claimed to bring different regions and cities closer together by shortening travel times, which can reduce the costs and increase enterprises productivity to promote a sustainable economy. However, another view argues that HSR transfers economic activities from peripheral cities to core cities, resulting in unbalanced regional economic development and damaging the sustainability of the economy. Based on microdata from China, this paper empirically investigates the impact of HSR on the enterprises productivity in both core cities and peripheral cities and explores the impact mechanism from the perspective of allocation effect and distribution effect caused by HSR. The results show that the connection of HSR positively affects the enterprises productivity in core cities, while it negatively affects the enterprises productivity in peripheral cities, with effect values of 1.38% and -8.45%, respectively. The conclusion still holds after endogenous treatment and multiple robustness tests are conducted. Additionally, the allocation effect analysis shows that the market access caused by HSR has an optimization effect on the resource allocation efficiency of both core cities and peripheral cities. The distribution effect analysis reveals that the distribution of enterprise productivity in peripheral cities has market heterogeneity, regional heterogeneity, and location heterogeneity. The important policy significance of this paper is that, in order to promote the sustainable development of enterprises and the economy, it should reduce policy restrictions and promote the effective flow of capital and talents, carry out the dislocation development of industry for peripheral cities, and “build a nest to attract the phoenix.”

Quantifying the Impact of Weather Events on Travel Time and Reliability

Abstract: It is of practical significance to understand the specific impact of weather events on the operating condition of the surface transportation system so that proactive and reactive strategies can be quickly implemented by transportation agencies to minimize the negativity resulted from adverse weather events. Many studies have been conducted on quantifying such effects yet suffer from limitations such as subjectively defining a time window under uncongested conditions and not being able to account for the severe impact from weather events which result in travel time unreliability. To overcome those shortcomings in existing literature, an integrated data mining framework based on decision tree and quantile regression techniques is developed in this study. The results demonstrate that the approach is effective in characterizing time periods with different traffic characteristics and quantifying the impact of rain and snow events on both congestion and reliability aspects of the transportation system. It is observed that snow events impose more significant impact on travel times than that from rain events. In addition, the impact from weather events is even more severe on travel time reliability than average delay. The impact magnitude is directly related to the level of recurrent congestion under study. Other insights with regard to the capability of quantile regression and future improvement on the methodological design are also offered.

Discrete Train Speed Profile Optimization for Urban Rail Transit: A Data-Driven Model and Integrated Algorithms Based on Machine Learning

Abstract: Energy-efficient train speed profile optimization problem in urban rail transit systems has attracted much attention in recent years because of the requirement of reducing operation cost and protecting the environment. Traditional methods on this problem mainly focused on formulating kinematical equations to derive the speed profile and calculate the energy consumption, which caused the possible errors due to some assumptions used in the empirical equations. To fill this gap, according to the actual speed and energy data collected from the real-world urban rail system, this paper proposes a data-driven model and integrated heuristic algorithm based on machine learning to determine the optimal speed profile with minimum energy consumption. Firstly, a data-driven optimization model (DDOM) is proposed to describe the relationship between energy consumption and discrete speed profile processed from actual data. Then, two typical machine learning algorithms, random forest regression (RFR) algorithm and support vector machine regression (SVR) algorithm, are used to identify the importance degree of velocity in the different positions of profile and calculate the traction energy consumption. Results show that the calculation average error is less than 0.1 kwh, and the energy consumption can be reduced by about 2.84% in a case study of Beijing Changping Line.

Role of Customized Bus Services in the Transportation System: Insight from Actual Performance

Abstract: After attaining great prevalence from the end of 2013, customized bus (CB) transit services have experienced a huge decline in China. The feasibility of this new bus sharing system is thus being questioned. Therefore, it is imperative to investigate the actual role of CB services in the overall transportation system based on successful cases, as the role of the CB service determines its primary service object, system construction, marketing orientation, and even government function. To examine the role of CB services, this study investigates the practical performance, advantages, and spatial and temporal coverage of a successful CB system based on practical subscription data for more than two years. The results illustrate that the CB service is an eclectic choice that can balance service quality and cost between traveling by traditional public transportation (PT) and private cars/taxis. Even though the travel cost increased to a limited extent, the CB service significantly improved the travel experience in terms of the travel time, travel speed, number of stations, and difference arrival time compared to PT services. The multinomial logit model and regression models demonstrate a significant positive relationship between the relative advantage and amount of demand for the CB services. Furthermore, the CB service primarily serves trips generated during the peak traffic hours of the city and supplements traditional PT service in areas with poor coverage levels.

Multiobjective Optimization Model for Sustainable Waste Management Network Design

Abstract: Inefficient or poorly planned waste management systems are a burden to society and economy. For example, excessively long waste transportation routes can have a negative impact on a large share of the population. This is exacerbated by the rapid urbanization happening worldwide and in developing countries. Sustainability issues should be accounted for at every stage of decision making, from strategic to daily operations. In this paper, we propose a multiobjective optimization model to design a cost-effective waste management supply chain, while considering sustainability issues such as land-use and public health impacts. The model is applied to a case study in Pathum Thani (Thailand) to provide managerial insights.

Optimizing Location of Car-Sharing Stations Based on Potential Travel Demand and Present Operation Characteristics: The Case of Chengdu

Abstract: Car-sharing is becoming an increasingly popular travel mode in China and many companies invest plenty of money on that including vehicle enterprises and Internet companies. But most of them build car-sharing stations by their experience or randomly as long as there is parking space in the early development of their business. This results in many stations with low operational efficiency and causes capital loss. This study aims to use different data source with statistical models and machine learning algorithm to help car-sharing operator to choose the optimal location of new stations and adjust the location of existing stations. We select Chengdu where there are huge amounts of car-sharing travel demand and several large car-sharing operators as the research area and two main operators as the research objects. Chengdu is divided into 58724 squared grids each of which is 0.5km⁎0.5km instead of focusing on the buffers generated by stations. We try to find a model to estimate a potential travel demand value for each small grid with three data sources: order data, population data, and Point of Interest (POI) data. This problem is transformed into a binary form and five different methods, Logistic Regression, Logistic Regression with LASSO, Naive Bayes, Linear Discriminant Analysis, and Quadratic Discriminant Analysis, are implemented. The optimal model, Logistic Regression with LASSO, is chosen to estimate the probability of existence of demand in all grids. With car-sharing order data from different operators, an existing order heat value is also computed for each grid. Then we analyze and classify all the grids into four groups. For different groups of grids, we give different suggestions on the optimal location of stations. This study focuses on a more competitive market and finds the influential factors on order number. Suggestions on the optimal location of stations are given in consideration of competitors. We hope that our research can help operators improve their business and make rational plans.