Spatio-Temporal Graphs in Transportation: Challenges, Optimization, and Prospects DOI Creative Commons
Aleksandr Rakhmangulov, Nikita Osintsev, Pavel Mishkurov

et al.

Systems, Journal Year: 2025, Volume and Issue: 13(4), P. 263 - 263

Published: April 8, 2025

Intelligent and information systems in transportation record accumulate large volumes of raw data on dynamic processes. However, these are not fully utilized for forecasting, real-time planning, management. Spatio-temporal graphs allow describing simultaneously both the structure different modes dynamics flows. Optimization such makes it possible to justify management decisions real time, as well forecast parameters traffic flows The purpose study is identify trends use spatio-temporal solving various problems transportation, most common methods optimization graphs. sample papers studied include 114 publications from Scopus database over 25 years, 1999 2024. First, a bibliometric analysis was conducted establish increase number publications, journals, countries, institutions, subject areas, articles, authors, keyword matches, understand amount literature generated. Secondly, review based content predict future research directions field. We have found that development deep learning approaches designing graph neural networks promising direction. Such mostly used solve tasks control urban systems. There fewer areas require in-depth knowledge technology, air, sea, rail transportation. This contributes expansion scientific about transport analysis.

Language: Английский

Spatio-Temporal Graphs in Transportation: Challenges, Optimization, and Prospects DOI Creative Commons
Aleksandr Rakhmangulov, Nikita Osintsev, Pavel Mishkurov

et al.

Systems, Journal Year: 2025, Volume and Issue: 13(4), P. 263 - 263

Published: April 8, 2025

Intelligent and information systems in transportation record accumulate large volumes of raw data on dynamic processes. However, these are not fully utilized for forecasting, real-time planning, management. Spatio-temporal graphs allow describing simultaneously both the structure different modes dynamics flows. Optimization such makes it possible to justify management decisions real time, as well forecast parameters traffic flows The purpose study is identify trends use spatio-temporal solving various problems transportation, most common methods optimization graphs. sample papers studied include 114 publications from Scopus database over 25 years, 1999 2024. First, a bibliometric analysis was conducted establish increase number publications, journals, countries, institutions, subject areas, articles, authors, keyword matches, understand amount literature generated. Secondly, review based content predict future research directions field. We have found that development deep learning approaches designing graph neural networks promising direction. Such mostly used solve tasks control urban systems. There fewer areas require in-depth knowledge technology, air, sea, rail transportation. This contributes expansion scientific about transport analysis.

Language: Английский

Citations

0