Skip to main content

Über dieses Buch

This book gathers selected papers presented at the KES International Symposium on Smart Transportation Systems (KES-STS 2021). Modern transportation systems have undergone a rapid transformation in recent years, producing a range of technological innovations such as connected vehicles, self-driving cars, electric vehicles, Hyperloop, and even flying cars, and with them, fundamental changes in transport systems around the world. The book discusses current challenges, innovations, and breakthroughs in smart transportation systems, as well as transport infrastructure modelling, safety analysis, freeway operations, intersection analysis, and other related cutting-edge topics.



Scheduling Shore Power Usage at Port

In shipping industry, ships typically use their auxiliary engines to generate electrical power for lighting, ventilation and other on-board equipment and as a result emit harmful gases and particles at berth. Using shore power to power ships is a way to reduce the emissions and realize the objective of green port when ships dock at ports. But how to allocate ships to shore power is unresolved. Therefore, this paper aims to determine the allocation of shore power to maximize shore power usage and thus reduce air emissions when ship berth at the ports. An integer programming model for shore power allocation problem is proposed and it is validated by numerical experiments.
Yu Guo, Yiwei Wu, Wei Wang, Shuaian Wang

Security Analysis Using Deep Learning in IoT and Intelligent Transport System

Cloud computing is an embryonic and vast field. It is cost effective, flexible and customized solution provided to customers according to their needs. Due to cloud computing customers need of having their own data centers storages and services became truncated. Cloud service providers serves customers with infrastructure, storages, security, computation resources and fault rectifications. Due to the customized and flexible in nature cloud computing created many security concerns meanwhile security is the first requirement of customer. Storages, infrastructure, software and network need security measures. In this paper we deliver different defense techniques by using which cloud computing infrastructure could be made secure. It includes different protocols, encryption techniques, and hardware and software solutions for different level of security.
Gwanggil Jeon, Abdellah Chehri

Drone-Based Image Processing for Construction Site Safety, Transportation, and Progress Management

Construction plays a pivotal role in securing prosperity in many countries through the deployment of new infrastructure, as the need to deliver higher-quality products more efficiently and safely is stronger than ever. Current construction management primarily relies on human assessment due to lack of automated project data collection, communication or distribution of important information, and is often reactive to accidents, inefficiencies, and progress delays. This study will tackle these problems by developing a methodological framework on automated tracking, inspection, and monitoring to increase accessibility, efficiency and safety to improve infrastructure project delivery, which integrates cost-effective unmanned aerial vehicles (UAVs, or drones) data collection, real-time analysis and segmentation of UAV visual data, and proactive dynamic planning.
Wen Yi, Xiaobo Qu

Public Transport Passenger Count Forecasting in Pandemic Scenarios Using Regression Tsetlin Machine. Case Study of Agder, Norway

Challenged by the effects of the COVID-19 pandemic, public transport is suffering from low ridership and staggering economic losses. One of the factors which triggered such losses was the lack of preparedness among governments and public transport providers. The losses can be minimized if the passenger count can be predicted with a higher accuracy and the public transport provision adapted to the demand in real time. The present paper explores the use of a novel machine learning algorithm, namely Regression Tsetlin Machine, in using historical passenger transport data from the current COVID-19 pandemic and pre-pandemic period, combined with a calendar of pandemic-related events (e.g. daily number of new cases and deaths, restrictive measures for pandemic containment), to forecast public transport patronage variations in a pandemic scenario. Results show that the Regression Tsetlin Machine has the best accuracy of forecasts when compared to four other models usually employed in the public transport forecasting field. We also observed variations of the prediction accuracy in relation to the period of the pandemic in which the trained models are applied. The underlying reasons for the relative passenger count variations are also examined using the properties of the Tsetlin Machine.
K. Darshana Abeyrathna, Sinziana Rasca, Karin Markvica, Ole-Christoffer Granmo

Travel Time Reliability Analysis of Arterial Road Based on Burr Distribution

Travel time distribution has been widely used to characterize the arterial road traffic conditions and help to analyze travel time reliability. Based on automatic number plate recognition (ANPR) data, this paper studies the travel time distribution and reliability of urban arterial roads and analyzes the relationship between the number of intersections and travel time characteristics. Firstly, the ANPR data is fitted by Burr distribution, and conducted the goodness-of-fit tests. Then, the coefficient of variation, buffer index and planning time index are used as reliability evaluation indexes to evaluate the travel time reliability. The results indicate that Burr distribution has a high acceptance rate. With the increase of the number of intersections, the route travel time distribution tends to a stable unimodal distribution, and the goodness of fit of Burr distribution increases, and the values of the three reliability evaluation indexes decrease, indicating that the travel time fluctuation decreases and the reliability increases.
Yixiao Lu, Fujian Wang

Optimal Vehicle Performance Parameters Selection for Electric Bus Routes

Electric buses (EBs) have the characteristics of zero emission and low noise, which plays an important role in reducing air and noise pollution and improving air quality in metropolitan areas. Choosing the appropriate electric buses type to meet the passenger demand and own interests is an important practical problem faced by many bus companies, among many types of electric buses. This paper conducts an optimization study on the vehicle and charger performance parameters selection for electric bus routes, with the objectives of minimizing the total operating cost of the bus company, including the annual average electric bus purchase cost, annual average charging facilities cost, and annual charging cost of electric bus fleet, and considers the passenger travel demand and integrity of bus service. Finally, two real electric bus routes are taken as an example to validate the proposed method. Results show that the optimized scheme is more conducive to saving the operation cost of bus companies compared with the current scheme.
Jinhua Ji, Mingjie Hao, Yiming Bie

Evaluation and Optimization of Driver’s Training Methods in View of Public Awareness

In order to improve the training level of drivers, assist drivers to adapt to the actual driving environment, and effectively prevent traffic accidents. This paper based on a questionnaire survey of drivers and applicants for motor vehicle driving licenses and made the investigation of status quo of driver’s training, public cognition analysis and driver’s character analysis. This paper set about the public’s willingness to drive, investigated the public’s general awareness of safety, and collected the data of satisfaction survey. Through by comparison the state of before and after training, it considered the problems existing in current driver’s training methods, as well as the nodes that can be optimized. This paper restored the cognition of drivers in different scenes, and acquired the psychological perception and cognition of the crowd through before and after the training. Specifically, it was divided into stress value, emotional value, caution and attention of psychological characteristics, visual sense, auditory sense, tactile sense and health status of physiological characteristics, and behavioral characteristics in different scenes. This paper summarized the driver’s psychological and physiological characteristics, established the path among the driver’s basic attributes, psychological characteristics, psychological characteristics, and traffic accidents, and established the structural equation model (SEM) model of driver’s characteristics including recessive factors. Based on this, this paper proposed a classified driver’s training method based on public cognition. According to the characteristics of the investigated population, the basic attributes are gender, age and education level, and then the types are classified according to the analysis of personality characteristics, so as to transfer the driving training from general training to targeted training. According to the characteristics of different drivers to be trained, the training intensity is different. It can make drivers develop more driving skills, more sufficient driving experience, enough safety awareness and high-quality driving character in the trainee stage to deal with the real driving environment.
Zhuoxin Sun, Wanqing Long, Weiwei Qi

Optimization of Pure Electric Bus Scheduling Based on Immune Optimization Algorithm

In the past two decades, more and more people have gathered in cities, which are facing serious traffic congestion and environmental pollution. Shenzhen has taken the lead in completing the upgrade from fuel buses to fully electric buses, proving that it is inevitable for urban public transportation companies to adopt pure electric buses. However, due to the limitations of the current level of technological development, electric buses are marked by short cruising distance and long charging time, and traditional fuel bus scheduling models are no longer feasible. Research on the application of pure electric bus dispatching is imminent and difficult. Depending on the characteristics of pure-electric bus dispatch, this paper constructs an optimization model of vehicle dispatching with minimum cost from the perspective of operating enterprises and designs a solution process based on immune optimization algorithm. Finally, four bus routes are selected for example analysis to obtain driving dispatching schemes with different battery capacities and charging characteristics. The example results show that with the increase of the cruising distance and charging speed, the minimum fleet size required for dispatch and the corresponding dispatch cost have all decreased, but when it increases to a certain value, the characteristics of the bus no longer affect the dispatch plan.
Lianjie Ruan, Xiaoni Hao, Weiwei Qi

Optimal Design of Mixed Charging Station for Electric Transit with Joint Consideration of Normal Charging and Fast Charging

In this paper, we propose a bi-level model to optimize the design of mixed charging station deployed at the terminal station for electric transit. At the lower level, the service schedule and charging strategy of electric buses is optimized under the given design of mixed charging station. The lower-level model is a management optimization at the operational level, aiming at minimizing the total daily operational cost. The model is formulated as a mixed integer programing subject to limited charging facilities of multiple types. At the upper level, the design of charging station is optimized based upon the results obtained at the lower level. It is a kind of decision making at the tactical level, with the objective of minimizing the sum of operational cost of electric bus fleet (i.e., objective function of the lower-level model) and installation cost of charging infrastructure. We conducted numerical cases to validate the applicability of the proposed model and some managerial insights stemmed from the numerical case studies are discussed, which can help transit agencies design charging station scientifically.
Le Zhang, Ziling Zeng, Kun Gao

Impact of Ambient Temperature on Electric Bus Energy Consumption in Cold Regions: Case Study of Meihekou City, China

Electric buses are more environment-friendly due to their low noise and less air pollution. However, their electricity consumption on the route will change with operating conditions. According to field investigations, ambient temperature is one main contributing factor to energy consumption of an electric bus. When the temperature is very low, the energy consumption would increase significantly. The operational performance of the electric bus in cold regions should be examined carefully based on real world operation data. Thus, we choose Meihekou city, China which belongs to cold regions to collect ambient temperature and corresponding electricity consumption for six buses on a bus line. We gathered ambient temperature and corresponding electricity consumption of a trip in one day for six buses around a year to test the relationship between them. Pearson Correlation Coefficient is applied to verify the relevance of ambient temperature and electricity consumption. Results prove a negative correlation between them. After that, temperature and corresponding electricity consumption of the whole day for a year are studied. Ultimately, results illustrate electricity consumption variation is diverse during different seasons, and the largest electricity consumption is in winter. Results also show that when ambient temperature range drops from [−2, 3] to [−10, −2], change of electricity consumption is unstable and violent, which rises from 0.45 to 0.7 kWh/km. However, when ambient temperature ranges from −10 to −25.5 °C, the fluctuation of electricity consumption is small, which is dispersed between 0.6 and 0.7 kWh/km.
Mingjie Hao, Jinhua Ji, Yiming Bie

Impacts Analysis of Rainfall on Road Traffic Operation

The rapid development of cities puts forward higher requirements for the resilience of the road network. As one of the unfavorable weathers, rainfall has a great impact on the operation of road traffic. Using weather and vehicle speed data of a city in China, this paper compares and analyzes changes in traffic operation indicators such as the standard speed and the percentage reduction of the standard speed under different rainfall intensities. Results indicate that under the same rainfall conditions and time period, the traffic operation of the elevated road is least affected by rainfall, and the traffic operation of underpass tunnels and flat roads is more affected by rainfall. With the increase of rainfall intensity, the reduction percentage of the standard speed of the underpass tunnel shows an increasing trend; however, it is less affected in light rain and moderate rain, and more affected in heavy rain and rainstorm. With the increase of rainfall intensity, the standard speed of the elevated road has no obvious change trend, and it is less affected by light rain and moderate rain, but more by rainstorm. In each time period, the standard speed reduction percentage of flat roads shows an obvious increasing trend with the increase of rainfall intensity.
Shengyue Lyu, Wei Guo, Yadan Yan

Modeling Seafarer Change at Seaports in COVID-19

Shipping is the most cost-effective way to transport large volumes of goods over long distances, and over 80% of goods traded worldwide are carried by sea. To keep our economy running, especially in difficult times of epidemics, such as the coronavirus disease 2019 (COVID-19), it is of utmost importance to keep ships sailing, moving the bulk of goods including medical supplies and food. Every month, around 100,000 seafarers need to disembark from the ships that they operate to comply with regulations governing safe working hours and crew welfare, and another 100,000 seafarers will embark to continue to move the global trade safely. However, as countries around the world tighten border controls in against the spread of the coronavirus outbreak, seafarers are prohibited from boarding or leaving ships at most ports, with the exception of just a few. This situation is leading seafarers to serve onboard vessels beyond their contracted shifts. Given that more than a quarter of seafarers suffer from depression because of their long time spent at sea and being away from family and friends, banning crew changes will put their mental health at risk. This will further increase the likelihood of marine accidents, jeopardize global supply chains, and ultimately exacerbate current hardships. To tackle this emergency, the International Maritime Organization and the European Commission, amongst others, call on governments to coordinate efforts to designate ports for crew changes while preventing the potential spread of the coronavirus. The aim of the study is to develop a framework that integrates big data, machine learning, and operational research for governments and supranational organizations to choose ports for crew changes, safeguarding seafarers’ welfare, and strengthening the global response to the threats of epidemics.
Yu Guo, Ran Yan, Yiwei Wu, Shuaian Wang

Driving Style Recognition Incorporating Risk Surrogate by Support Vector Machine

Accurate driving style recognition is a crucial component for advanced driver assistance systems and vehicle control systems to reduce potential rear-end collision risk. This study aims to develop a driving style recognition method incorporating matching learning algorithms and vehicle trajectory data. A risk surrogate, Modified Margin to Collision (MMTC), is proposed to evaluate the collision risk level of each driver’s trajectory. Particularly, the traffic level is considered when labelling the driving style, while it has a great impact on driving preference. Afterwards, each driver’s driving style is labelled based on their collision risk level using the K-means algorithm. Driving behavior features, including acceleration, relative speed, and relative distance, are extracted from vehicle trajectory and processed by time-sequence analysis. Finally, Supporting Vector Machine (SVM) is applied to recognize driving style based on the extracted features and labelled data. The performance of Random Forest (RF), K-Nearest Neighbor (KNN), and Multi-Layer Perceptron (MLP) are also compared with SVM. The “leave-one-out” method is used to validate the performance and effectiveness of the proposed model. The results show that SVM over performs others with 91.7% accuracy. This recognition model could effectively recognize the aggressive driving style, which can better support ADAS.
Qingwen Xue, Jianjohn Lu, Kun Gao

An Online Processing Method for the Cooperative Control of Connected and Automated Vehicle Platoons

The recent development of connected and autonomous vehicles (CAVs) makes it increasingly realistic to develop the next generation of transportation systems with the potential to improve operational performance and flexibility. The cooperative control of CAV platoons remains one of the most crucial yet challenging problems before the CAVs can be widely implemented in practice. The present study focuses on an application of CAVs at signalized intersections to realize a well-organized CAV permutation as well as improving the performance of the intersection. An online processing A* (OPA*) algorithm is developed to improve the optimality and computation performance. A comparative analysis between the proposed OPA* algorithm and an existing A* method is made. In summary, the OPA* could result in stable and scalable results which makes it possible for widely industrial usage.
Xiangyu Kong, Jiaming Wu, Xiaobo Qu

Modeling Measurements Towards Effect of Past Behavior on Travel Behavior

The inertia effect of past behavior has attracted attention in the travel behavioral literature because of its bearing on travel choice modeling. Several measurements have been proposed to model the inertia effects. However, no consensus concerning appropriate modelling methods is reached, which leads to potential biases in analysis. The study aims to conduct a comprehensive investigation of modeling measurements regarding inertia effects of past behavior from the perspectives of estimation, behavioral indications and predictions. Differing from existing literature that only focused on estimation performance, we examine the performances of different methods in predictions and behavioral interpretations. To our best knowledge, these aspects are not investigated in the literature based on empirical data. The necessary information for constructing the measurements, underlying consumption, significance in estimation, behaviorally implausible issue, performances in estimation and predictions for these measurements are all compared based on behavioral data. The results shed lights on performances and suitability of different measurements for inertia effects in terms of estimation, behavioral interpretation and prediction, which support the further investigations of past behavior on travelers’ choice behavior.
Kun Gao, Tianshu Zhang, Zhihan Li

Measuring Transportation Accessibility Based on Different Data Sources: A State-of-the-Art Review

Accessibility plays an important role in the field of transportation. In previous studies, due to the limitation of data sources, the research on dynamic accessibility is limited. In recent years, the emergence of new data sources provides possibilities for the dynamic accessibility. This paper summarizes four classic accessibility evaluation models, including the space separation measure, cumulative opportunities measure, potential accessibility measure, and space–time prism. Moreover, this paper introduces the limitations of traditional data sources and analyzes the characteristics of new data sources such as floating car data, smart cards data, mobile phone recording data, and navigation map (API) data. A comprehensive overview of the application of different data sources in transportation accessibility is also developed. Finally, this review study shows opportunities and challenges for transportation accessibility studies.
Ke Ren, Can Cui, Yadan Yan

Modeling Commercial Vehicle Drivers’ Acceptance of Forward Collision Warning System

With the development of computer science, Forward Collision Warning (FCW) systems have been installed in various vehicles in order to improve road safety. Previous studies have been conducted to evaluate the acceptance of FCW systems and explore the contributing factors affecting drivers’ attitudes. However, few research studies have focused on the attitudes of commercial vehicle drivers, though commercial vehicle accidents were proved to be more severe than passenger vehicles. This paper tries to examine the attitudes of commercial vehicle drivers toward FCW systems and identify the contributing factors by using a random forests algorithm. FCW data of 24 commercial vehicles were recorded from November 1st to December 21st, 2018 in Jiangsu province. The acceptance rate (FCW records with response) of commercial vehicle drivers for FCW systems is 69.52%. (Acceptance was measured by identifying drivers who reduced their speed in response to a warning from the FCW system.) The accuracy of random forests model is 0.816 after tuning the parameter. In addition, the most important influence variable in this model is vehicle speed with an importance of 0.37. Duration time and warning hour also have significant influence on driver reaction, with values of 0.20 and 0.17, respectively. The results showed that commercial vehicle drivers’ acceptance of an FCW system decreases with the increase of vehicle speed. The response time for most cases is timely, usually within 2 s. And the response percentage is higher during daytime than at night. These regularities may be attributable to the larger size and heavier weight of commercial vehicles. The results of this study can help researchers to better understand the behavior of commercial vehicle drivers and to develop more effective FCW systems for commercial vehicles.
Yueru Xu, Zhirui Ye, Chao Wang, Kun Gao


Weitere Informationen