Graph-Based Learning Methods in Intelligent Transportation Systems

Dear Colleagues,

Traffic forecasting is a crucial component of intelligent transportation systems, affecting various applications such as navigation, ride-hailing, and route planning. Traditional methods for traffic forecasting rely on subjective judgments, limited data sources, and straightforward modeling techniques. Due to recent advances in data mining and machine learning, numerous data-driven methods are being adopted to address the problems that occur in traditional schemes, resulting in exceptional performance. In addition, traffic prediction methods, e.g., graph-based methods, have attracted remarkable attention from the intelligent transportation community. Benefiting from the fact that road networks inherently resemble graph structures, i.e., data collection devices on roads are represented as nodes and the connections between the roads are represented as edges, graph-based learning methods are intuitively more suitable to capture the non-Euclidean spatial features of road networks.

Since large amounts of traffic data are collected by interconnected stationery or dynamic traffic devices, current research is investigating the development of suitable traffic prediction techniques to improve the efficiency of ITS management. One critical issue is how to process vast traffic information data for the purpose of designing effective graph-based learning methods to predict the traffic environment. To this end, a suitable prediction method is needed to address the large qualities of multi-modal traffic data in urban city applications. On the other hand, considering high maintenance costs, medium and small cities are unable to deploy or maintain a large number of traffic sensors in the long term to collect sufficient available traffic data; data imbalance in traffic data collection among different cities is another core issue. Therefore, devising a reliable traffic forecasting algorithm based on scarce and imbalanced data is essential for small and medium cities.

In this Special Issue, original research articles and reviews are welcome. Research areas may include (but are not limited to) the following:

• Graph-based learning for traffic big data analysis in ITS
• Graph embedding methods for ITS
• Graph-based machine learning for traffic prediction
• Graph representation learning for ITS
• Graph transfer learning for ITS
• Graph-based privacy preserving model in ITS
• Learning from homogenous/heterogeneous transportation networks.

Dr. Shiyao Zhang
Dr. James Jianqiao Yu
Dr. Chenhan Zhang
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 submissions that pass pre-check are 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 250 words) can be sent to the Editorial Office for assessment.

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. Electronics 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 2400 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.