Risk Prediction for Ship Encounter Situation Awareness Using Long Short-Term Memory Based Deep Learning on Intership BehaviorsRead the full article
Journal of Advanced Transportation publishes theoretical and innovative papers on analysis, design, operations, optimization and planning of multi-modal transport networks, transit & traffic systems, transport technology and traffic safety.
Journal of Advanced Transportation maintains an Editorial Board of practicing researchers from around the world, to ensure manuscripts are handled by editors who are experts in the field of study.
Latest ArticlesMore articles
Passenger Volume Prediction by a Combined Input-Output and Distributed Lag Model and Data Analytics of Industrial Investment
In order to sketch the transport infrastructure construction in an economy or a region, the government has to predict the passenger volume, under the local policy of industrial investment. In this paper, we propose a combined input-output and distributed lag prediction model of passenger volume in a province in P. R. China, under a certain policy of industrial investment called Silk Road Economic Belt. Specifically, the relationships between the passenger volume, GDP (gross domestic product), gross output, and transportation consumption are analyzed, and then the industrial development speed analysis and classification are used to calculate the average development speeds and the GDP contributions of 42 industries. Combining the input-output table, the provincial transportation consumption under the Silk Road Economic Belt policy is predicted, and the passenger volumes of the cities and the province in the future are predicted by the distributed lag models. Considering the uncertainty of the investment, the elastic ranges of the cities and the province’s passenger volumes are determined. The results show that the correlation between the passenger volume and transportation consumption is the highest, and it is equal to 0.975. In 2020, the passenger volume in Shaanxi is 1,641,305 thousands, and the error between the predicted value and the value obtained by summing the cities’ passenger volumes is smaller than 0.002%.
Design, Validation, and Comparative Analysis of a Private Bus Location Tracking Information System
This paper addresses various aspects related to the design, development, and validation of a web-based information system that is intended to facilitate the management of a bus transportation service offered by a Jordanian university to its staff and students. Passengers can use this system to track bus trips to find out how far a desired bus is from a specific location. Also, they can know about arrivals and departures of buses managed using this system. Specifically, this work explores UI design, data structures, database design, system architecture, and development methods to realize the required features (e.g., user roles, bus setup, driver assignment, bus routes, bus schedules, and trip monitoring) in the proposed bus location tracking system. It also suggests using the free open-source API, rather than the proprietary Google Maps API, to develop the interactive maps. The system also records trip information and solicits passenger feedback to allow reviewing and analyzing that data to enhance the quality of service, reduce operation cost, and improve passenger satisfaction. The conducted comparative analysis results illustrate that the open-source API is accurate, fast, and responsive similar to the proprietary API. Furthermore, the user survey output confirms that the deployed system is easy to use, helpful, fast, responsive, and accurate.
Machine Learning Approach to Quantity Management for Long-Term Sustainable Development of Dockless Public Bike: Case of Shenzhen in China
Since the number of bicycles is critical to the sustainable development of dockless PBS, this research practiced the introduction of a machine learning approach to quantity management using OFO bike operation data in Shenzhen. First, two clustering algorithms were used to identify the bicycle gathering area, and the available bike number and coefficient of available bike number variation were analyzed in each bicycle gathering area’s type. Second, five classification algorithms were compared in the accuracy of distinguishing the type of bicycle gathering areas using 25 impact factors. Finally, the application of the knowledge gained from the existing dockless bicycle operation data to guide the number planning and management of public bicycles was explored. We found the following. (1) There were 492 OFO bicycle gathering areas that can be divided into four types: high inefficient, normal inefficient, high efficient, and normal efficient. The high inefficient and normal inefficient areas gathered about 110,000 bicycles with low usage. (2) More types of bicycle gathering area will affect the accuracy of the classification algorithm. The random forest classification had the best performance in identifying bicycle gathering area types in five classification algorithms with an accuracy of more than 75%. (3) There were obvious differences in the characteristics of 25 impact factors in four types of bicycle gathering areas. It is feasible to use these factors to predict area type to optimize the number of available bicycles, reduce operating costs, and improve utilization efficiency. This work helps operators and government understand the characteristics of dockless PBS and contributes to promoting long-term sustainable development of the system through a machine learning approach.
Mathematical Optimization Model for Truck Scheduling in a Distribution Center with a Mixed Service-Mode Dock Area
Cross-docking is a logistics strategy in which products arriving at a distribution center are unloaded from inbound trucks and sorted for transfer directly to outbound trucks, reducing costs and storage and product handling times. This paper addresses a cross-docking problem by designing a mixed-integer linear programming (MILP) model to determine a schedule for inbound and outbound trucks in a mixed service-mode dock area that minimizes the time from when the first inbound truck arrives until the last outbound truck departs (makespan). The model is developed using AMPL software with the CPLEX and Gurobi solvers, which provide results for different instances, most of these with actual shift data from an integrated distribution center of a multinational food company located in Concepción, Chile. The results obtained from the case study are notable and show the effectiveness of the proposed mathematical model.
Generative Adversarial Network-based Missing Data Handling and Remaining Useful Life Estimation for Smart Train Control and Monitoring Systems
As railway is considered one of the most significant transports, sudden malfunction of train components or delayed maintenance may considerably disrupt societal activities. To prevent this issue, various railway maintenance frameworks, from “periodic time-based and distance-based traditional maintenance frameworks” to “monitoring/conditional-based maintenance systems,” have been proposed and developed. However, these maintenance frameworks depend on the current status and situations of trains and cars. To overcome these issues, several predictive frameworks have been proposed. This study proposes a new and effective remaining useful life (RUL) estimation framework using big data from a train control and monitoring system (TCMS). TCMS data is classified into two types: operation data and alarm data. Alarm or RUL information is extracted from the alarm data. Subsequently, a deep learning model achieves the mapping relationship between operation data and the extracted RUL. However, a number of TCMS data have missing values due to malfunction of embedded sensors and/or low life of monitoring modules. This issue is addressed in the proposed generative adversarial network (GAN) framework. Both deep neural network (DNN) models for a generator and a predictor estimate missing values and predict train fault, simultaneously. To prove the effectiveness of the proposed GAN-based predictive maintenance framework, TCMS data-based case studies and comparisons with other methods were carried out.
Multiple‐Factor Influence on Air Quality of Road Motor Vehicles Tail Number Limit in Administrative Area of Beijing, China
From December 2, 2013, to October 31, 2019 (total 2160 days), Beijing official air quality data was used as the research object. The article analyzes the end of days 4 and 9 and the end of the nonrestricted 4 and 9 days, working and nonworking days, restricted and nonrestricted working days, long holidays (Spring Festival and National Day), and nonlong holidays (short holidays other than the Spring Festival and National Day and working days) of AQI, PM2.5, PM10, SO2, CO, NO2, and O3. According to the statistical analysis of the data, the air quality of the 4 and 9 limit is worse than that of the non-4 and 9 limit. Motor vehicles restricted in traffic had an objective effect on air AQI, PM2.5, PM10, CO, and NO2, whereas there was almost no difference in O3. Some peak values of AQI, PM2.5, PM10, SO2, CO, and NO2 on nonrestricted working days were significantly higher than those on restricted working days. At the same time, there was a peak time of the impact of motor vehicles on AQI, PM2.5, PM10, SO2, CO, and NO2 in Beijing. This time should be between 3 and 5 days, or 72 and 120 hours.