Journal Menu
► Journal MenuJournal Browser
► Journal BrowserSpecial Issue "Application of Statistical and Machine Learning Techniques for Sustainable Transport Systems"
A special issue of Sustainability (ISSN 2071-1050). This special issue belongs to the section "Sustainable Transportation".
Deadline for manuscript submissions: 31 December 2021.
Special Issue Editors
Interests: pavement design; maintenance and rehabilitation; pavement materials; traffic operation and control
Special Issue Information
Dear Colleagues,
Sustainable transport refers to transport modes that meet sustainability standards in various aspects, such as safety and environmental. Extensive research has focused on studying the underlying factors behind the various aspects of transportation that prevent sustainability. Statistical methods have been employed to achieve those goals. For instance, studies have investigated the factors behind the choices that commuters make, e.g., why they choose rail transport over other modes of transport, and the impacts of the various aspects of a transport mode on commuters’ decision-making behaviors. Transport choices are obviously not set in stone and depend not just on the advantages and disadvantages of a specific mode of transport but also the personal circumstances of an individual commuter. Thus, techniques such as latent class models and mixed logit models, which could account for this heterogeneity, have been employed.
Machine learning techniques have also been employed for various objectives, such as image recognition, crash prediction, or even optimization. For instance, a model may be trained on various aspects of a sustainable transport mode, and consequently, various aspects of the subject may be changed/optimized to see how much money could be saved. Image identification may also be employed for data collection.
In this context, this Special Issue on “Application of Statistical and Machine Learning techniques for Sustainable Transport Systems” welcomes research on state-of-the-art and innovative statistical or machine learning techniques to achieve sustainable transport. We are moving in the direction of an automated and computerized era. Thus, advanced statistical and machine learning techniques will help researchers and scientists to break down the barriers preventing us from meeting our goal of sustainable transportation. Studies may address one or more of the following topics of interest:
- Sustainable transportation
- Traffic safety;
- Road crashes;
- Choice modeling;
- Optimization;
- Machine learning techniques
Prof. Khaled Ksaibati
Dr. Mahdi Rezapour
Guest Editors
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sustainability is an international peer-reviewed open access semimonthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1900 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- sustainable transportation
- traffic safety
- crash severity
- statistics
- machine learning
Planned Papers
The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.
Authors: Jakov Topić, Branimir Škugor and Joško Deur
Author Affiliations: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 10002, Zagreb, Croatia
Abstract: In recent decades, improvement of information and communication technology has enabled the collection of large quantities of driving data for the purpose of monitoring and vehicle fleet operation improvement. An essential component of fleet management systems corresponds to solving vehicle routing problem (VRP), which is aimed at assigning vehicles and routes for accomplishing driving/delivery missions with a minimum number of vehicles and fuel cost. A VRP optimization algorithm requires prediction of vehicle fuel consumption for the given route, period of day, driver, etc. The fuel consumption prediction is based on a model, which should account for both driving behaviours and traffic conditions. Since not all variables affecting vehicle fuel consumption are typically measured on-board (e.g. vehicle weight and ambient conditions), significant efforts are made to model fuel consumption with only a subset of key, standardly available variables. The approaches based on a precise analytical vehicle powertrain models can provide high prediction accuracy, but at the cost of high computation time, which is not suitable for most of optimization tasks. Another disadvantage of physics-based models is that they require tuning of many parameters and thus their parameterization could be time consuming and prone to inaccuracies. Hence, instead of relying on a real-time microscopic model, there is a notable need to develop a computationally fast, macroscopic model that predict the fuel consumption for the entire driving cycle at once to make VRO feasible in time. In order to address this issue, this paper deals with fuel consumption prediction based on vehicle velocity, acceleration, and road slope time series inputs. Several data-driven models are considered for this purpose, including linear regression models and neural network-based ones. The emphasis is on accounting for the road slope impact when forming the model inputs to improve prediction accuracy. Special effort is also devoted to conversion of driving cycles that varies in length into a fixed dimension inputs suitable for neural networks. The proposed prediction algorithms are parameterized and tested based on GPS- and CAN-based tracking data recorded on a number of city buses during their regular operation.