https://m2.mtmt.hu/ hun 2026-10-23 20:50 BookChapter 35773631 ADMIN_APPROVED true Project no. KDP-IKT-2023-900-I1-00000957/0000003 has been implemented with the support provided by the Ministry of Culture and Innovation of Hungary from the National Research, Development and Innovation Fund, financed under the KDP-2023 funding scheme. The research was supported by the European Union within the framework of the National Laboratory for Autonomous Systems. (RRF-2.3.1-21-2022-00002) This work was partially supported by the János Bolyai Research Scholarship of the Hungarian Academy of Sciences. Project no. EKÖP-24-4-I-BME-69 has been implemented with the support provided by the Ministry of Culture and Innovation of Hungary from the National Research, Development and Innovation Fund, financed under the 2024-2.1.1-EKÖP-2024-00003 funding scheme. 0 false 2025-11-18T13:28:28.988+0000 2025-08-22T09:42:38.150+0000 2025-02-20T07:01:00.631+0000 true 10041668 Bécsi Tamás /api/author/10041668 Author Bécsi Tamás (közlekedéstudomány) true 10041668 2025-08-22T09:42:34.875+0000 2025-08-22T09:42:34.875+0000 2025-08-22T09:42:38.154+0000 true 10072271 Andódy Katalin /api/admin/10072271 Admin Andódy Katalin (BME admin4) true true false true 25 25 /api/publicationtype/25 PublicationType Könyvrészlet 2 true 25 BookChapter true 10000312 Conference paper true 25 25 /api/publicationtype/25 PublicationType Könyvrészlet 2 true 25 BookChapter /api/subtype/10000312 Konferenciaközlemény SubType Konferenciaközlemény (Könyvrészlet) 228 true 10000312 true 1 /api/category/1 Category Tudományos true 1 Farkas, Péter 000135 000139 000135 5 2025 Optimizing rail traffic and handling disturbances in the network are essential to minimizing delays and improving system throughput. The high computation burden of conventional solutions can be shifted to training time using machine learning techniques, particularly reinforcement learning (RL), to ensure real-time applicability. In this paper, we combine RL with Graph Attention Networks (GANs) to optimize traffic in multi-line railway networks. By leveraging graph-based representation and attention mechanisms, our model enhances feature extraction by assigning greater importance to traffic elements contributing more to delays. Our approach dynamically adapts both routes and train passing sequences in real-time, enabling more effective disturbance management and improved throughput. ©2025 IEEE. Funding 2049942 /api/funding/2049942 ARNL(RRF-2.3.1-21-2022-00002) Támogató: NKFIH false true true NATIONAL 2025 true true true true true false NONE 2025-11-18 false 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 false false false false 2025-05-21T06:01:01.109+0000 Közlekedés- és Járműirányítási Tanszék (BME / KJK) 3 9 1 3 0 true 547 true 10002 English /api/language/10002 Angol Language Angol true 2 false true 10939 true 10017 /api/country/10017 Country Amerikai Egyesült Államok true 13 /api/city/10939 City Piscataway (NJ), Amerikai Egyesült Államok true 2054246 true 28266592 /api/publicationidentifier/28266592 https://www.worldcat.org/search?q=isbn%3A9798350379365 9798350379365 PublicationIdentifier ISBN: 9798350379365 true 122 ISBN https://www.worldcat.org/search?q=isbn%3A@@@ /api/publicationsource/122 ISBN PlainSource ISBN true true 10002 /api/publicationsourcetype/10002 PublicationSourceType Egyéb true false 122 true false /api/publication/35705765 Szakál Anikó. IEEE 23rd World Symposium on Applied Machine Intelligence and Informatics SAMI 2025. (2025) ISBN:9798350379365 true true 23 23 /api/publicationtype/23 PublicationType Könyv 3 true 23 Book false true 35705765 true true true true true 10000144 Conference proceedings true 23 23 /api/publicationtype/23 PublicationType Könyv 3 true 23 Book /api/subtype/10000144 Konferenciakötet SubType Konferenciakötet (Könyv) 345 true 10000144 false Book 2025 true 1 /api/category/1 Category Tudományos true 1 false Language 10002 /api/language/10002 Angol Angol English true 2 true PersonAuthorship 123422355 /api/authorship/123422355 Farkas, Péter [Farkas, Péter (Közlekedés- és já...), szerző] Közlekedés- és Járműirányítási Tanszék (BME / KJK) 1 0.333 true false false Author 10089067 /api/author/10089067 Farkas Péter (Közlekedés- és járműtudomány) Farkas Péter true true Farkas Péter true false false AuthorshipType 1 /api/authorshiptype/1 Szerző 0 true 0 true false true PersonAuthorship 123422356 /api/authorship/123422356 Szőke, László [Szőke, László, szerző] Közlekedés- és Járműirányítási Tanszék (BME / KJK) 2 0.333 false false false Author 10077729 /api/author/10077729 Szőke László Szőke László true true Szőke László true false false AuthorshipType 1 /api/authorshiptype/1 Szerző 0 true 0 true false true PersonAuthorship 123422357 /api/authorship/123422357 Aradi, Szilárd [Aradi, Szilárd (Közlekedési), szerző] Közlekedés- és Járműirányítási Tanszék (BME / KJK) 3 0.333 false true false Author 10041667 /api/author/10041667 Aradi Szilárd (Közlekedési) Aradi Szilárd DUPLUM true 10041667 true Aradi Szilárd true false false AuthorshipType 1 /api/authorshiptype/1 Szerző 0 true 0 true false true PublicationIdentifier 28434396 /api/publicationidentifier/28434396 DOI: 10.1109/SAMI63904.2025.10883318 PlainSource 6 /api/publicationsource/6 DOI PublicationSourceType 10001 /api/publicationsourcetype/10001 DOI true true true DOI DOI https://doi.org/@@@ true true 6 true IDENTICAL 10.1109/SAMI63904.2025.10883318 https://doi.org/10.1109/SAMI63904.2025.10883318 false true PublicationIdentifier 29730901 /api/publicationidentifier/29730901 Scopus: 105013052330 PlainSource 3 /api/publicationsource/3 Scopus PublicationSourceType 10003 /api/publicationsourcetype/10003 Indexelő adatbázis false true true Scopus Scopus http://www.scopus.com/record/display.url?origin=inward&eid=2-s2.0-@@@ true true 3 true 105013052330 http://www.scopus.com/record/display.url?origin=inward&eid=2-s2.0-105013052330 false true PublicationIdentifier 28434397 /api/publicationidentifier/28434397 Egyéb URL: https://ieeexplore.ieee.org/document/10883318/ PlainSource 40 /api/publicationsource/40 Egyéb URL PublicationSourceType 10006 /api/publicationsourcetype/10006 Link true true true Egyéb URL Other URL @@@ true true 40 true https://ieeexplore.ieee.org/document/10883318/ https://ieeexplore.ieee.org/document/10883318/ false true Keyword 12390 /api/keyword/12390 machine learning true 12390 true Keyword 12426 /api/keyword/12426 reinforcement learning true 12426 true Keyword 12510 /api/keyword/12510 intelligent systems true 12510 true Keyword 16030 /api/keyword/16030 Signal processing true 16030 true Keyword 1014520 /api/keyword/1014520 Learning algorithms true 1014520 true Keyword 1138144 /api/keyword/1138144 Railroads true 1138144 true Keyword 1724792 /api/keyword/1724792 Railroad transportation true true Keyword 1849378 /api/keyword/1849378 rail transportation true true Keyword 1938598 /api/keyword/1938598 Rails true true Keyword 1948290 /api/keyword/1948290 system throughput true true Keyword 2177133 /api/keyword/2177133 Training time true true Keyword 2286367 /api/keyword/2286367 Graph attention networks true true Keyword 2352081 /api/keyword/2352081 Real- time true true Keyword 2354220 /api/keyword/2354220 Rail traffic true true Keyword 2354394 /api/keyword/2354394 Computation burden true true Keyword 2370093 /api/keyword/2370093 Reinforcement learnings true true Keyword 2384034 /api/keyword/2384034 Improving systems true true Keyword 2627264 /api/keyword/2627264 Graph attention network true true Keyword 2719138 /api/keyword/2719138 delays system true true Reference 63830370 /api/reference/63830370 1. Commission 2021: Sustainable and smart mobility strategy - putting european transport on track for the future 1 false true Reference 63830371 /api/reference/63830371 2. DOI: 10.1038/s42256-023-00779-2 2 10.1038/s42256-023-00779-2 false true Reference 63830372 /api/reference/63830372 3. DOI: 10.1109/TSMC.2023.3344883 3 10.1109/TSMC.2023.3344883 false true Reference 63830373 /api/reference/63830373 4. DOI: 10.1109/TASE.2024.3432405 4 10.1109/TASE.2024.3432405 false true Reference 63830374 /api/reference/63830374 5. Fang 2023: Universal prompt tuning for graph neural networks., Advances in Neural Information Processing Systems, 36, p. 52464 5 false true Reference 63830375 /api/reference/63830375 6. DOI: 10.1016/j.inffus.2024.102250 6 10.1016/j.inffus.2024.102250 false true Reference 63830376 /api/reference/63830376 7. DOI: 10.1109/TITS.2014.2358392 7 10.1109/TITS.2014.2358392 false true Reference 63830377 /api/reference/63830377 8. DOI: 10.1016/j.trb.2014.01.009 8 10.1016/j.trb.2014.01.009 false true Reference 63830378 /api/reference/63830378 9. DOI: 10.1109/TITS.2021.3131202 9 10.1109/TITS.2021.3131202 false true Reference 63830379 /api/reference/63830379 10. DOI: 10.3311/PPtr.18582 10 10.3311/PPtr.18582 false true Reference 63830380 /api/reference/63830380 11. DOI: 10.1016/j.trb.2013.10.013 11 10.1016/j.trb.2013.10.013 false true Reference 63830381 /api/reference/63830381 12. DOI: 10.1002/net.20384 12 10.1002/net.20384 false true Reference 63830382 /api/reference/63830382 13. Pellegrini 2012: Real time railway traffic management modeling track-circuits., OpenAccess Series in Informatics, 25, p. 12 13 false true Reference 63830383 /api/reference/63830383 14. DOI: 10.1109/TITS.2021.3071153 14 10.1109/TITS.2021.3071153 false true Reference 63830384 /api/reference/63830384 15. DOI: 10.1145/3449726.3459436 15 10.1145/3449726.3459436 false true Reference 63830385 /api/reference/63830385 16. DOI: 10.1109/TITS.2015.2414294 16 10.1109/TITS.2015.2414294 false true Reference 63830386 /api/reference/63830386 17. DOI: 10.1002/net.21528 17 10.1002/net.21528 false true Reference 63830387 /api/reference/63830387 18. DOI: 10.1016/j.asoc.2023.111158 18 10.1016/j.asoc.2023.111158 false true Reference 63830388 /api/reference/63830388 19. DOI: 10.1016/j.trb.2006.02.006 19 10.1016/j.trb.2006.02.006 false true Reference 63830389 /api/reference/63830389 20. DOI: 10.1016/j.jrtpm.2011.09.003 20 10.1016/j.jrtpm.2011.09.003 false true Reference 63830390 /api/reference/63830390 21. DOI: 10.1016/j.simpat.2021.102449 21 10.1016/j.simpat.2021.102449 false true Reference 63830391 /api/reference/63830391 22. DOI: 10.1109/ITSC.2019.8917180 22 10.1109/ITSC.2019.8917180 false true Reference 63830392 /api/reference/63830392 23. DOI: 10.1016/j.trb.2016.01.004 23 10.1016/j.trb.2016.01.004 false true Reference 63830393 /api/reference/63830393 24. DOI: 10.1109/itsc45102.2020.9294188 24 10.1109/itsc45102.2020.9294188 false true Reference 63830394 /api/reference/63830394 25. Mohanty 2020: Flatland-rl: Multi-agent reinforcement learning on trains 25 false true Reference 63830395 /api/reference/63830395 26. DOI: 10.1109/SACI58269.2023.10158653 26 10.1109/SACI58269.2023.10158653 false true Reference 63830396 /api/reference/63830396 27. DOI: 10.1016/j.trb.2022.05.001 27 10.1016/j.trb.2022.05.001 false true Reference 63830397 /api/reference/63830397 28. DOI: 10.1016/j.jrtpm.2023.100394 28 10.1016/j.jrtpm.2023.100394 false true Reference 63830398 /api/reference/63830398 29. DOI: 10.1109/TITS.2023.3344468 29 10.1109/TITS.2023.3344468 false true Reference 63830399 /api/reference/63830399 30. DOI: 10.1109/BigData.2018.8622214 30 10.1109/BigData.2018.8622214 false true Reference 63830400 /api/reference/63830400 31. DOI: 10.3390/app13179547 31 10.3390/app13179547 false true Reference 63830401 /api/reference/63830401 32. Veličković 2017: Graph attention networks., 6th International Conference on Learning Representations, ICLR 2018 - Conference Track Proceedings 32 false true Reference 63830402 /api/reference/63830402 33. Rllib: Industry-grade reinforcement learning - ray., Ray 33 false true /api/publication/35773631 Farkas Péter et al. Optimizing Rail Traffic with Reinforcement Learning and Graph Attention Networks. (2025) Megjelent: IEEE 23rd World Symposium on Applied Machine Intelligence and Informatics SAMI 2025 pp. 000135-000139<div class="BookChapter Publication long-list"> <div class="authors"> <img title="Forrásközlemény" style="float: left" src="/frontend/resources/grid/publication-core-icon.png"> <div class="autype autype0"> <span class="author-name" mtid="10089067"><a href="/gui2/?type=authors&mode=browse&sel=10089067" target="_blank">Farkas Péter (<span class="authorship-author-name">Farkas Péter</span> <span class="authorAux-mtmt"> Közlekedés- és járműtudomány</span>) </a> </span> <span class="author-affil"><span title="Budapesti Műszaki és Gazdaságtudományi Egyetem">BME</span>/<span title="Közlekedésmérnöki és Járműmérnöki Kar">KJK</span>/Közlekedés- és Járműirányítási Tanszék</span> ;&nbsp;&nbsp;&nbsp; <span class="author-name" mtid="10077729"><a href="/gui2/?type=authors&mode=browse&sel=10077729" target="_blank">Szőke László (<span class="authorship-author-name">Szőke László</span> <span class="authorAux-mtmt"> </span>) </a> </span> <span class="author-affil"><span title="Budapesti Műszaki és Gazdaságtudományi Egyetem">BME</span>/<span title="Közlekedésmérnöki és Járműmérnöki Kar">KJK</span>/Közlekedés- és Járműirányítási Tanszék</span> ;&nbsp;&nbsp;&nbsp; <span class="author-name" mtid="10041667"><a href="/gui2/?type=authors&mode=browse&sel=10041667" target="_blank">Aradi Szilárd (<span class="authorship-author-name">Aradi Szilárd</span> <span class="authorAux-mtmt"> Közlekedési</span>) </a> </span> <span class="author-affil"><span title="Budapesti Műszaki és Gazdaságtudományi Egyetem">BME</span>/<span title="Közlekedésmérnöki és Járműmérnöki Kar">KJK</span>/Közlekedés- és Járműirányítási Tanszék</span> </div> </div> <div class="title"><a href="/gui2/?mode=browse&params=publication;35773631" target="_blank">Optimizing Rail Traffic with Reinforcement Learning and Graph Attention Networks</a></div> <div class="InBook"><div class="chapter-in">In:</div> <div class="authors"> <div class="autype autype-1"> <span class="author-name" mtid="10039071"><a href="/gui2/?type=authors&mode=browse&sel=10039071" target="_blank">Szakál Anikó (<span class="authorship-author-name">Szakál Anikó</span> <span class="authorAux-mtmt"> műszaki informatika</span>) </a> </span> <span class="author-affil">Óbudai Egyetem</span> (szerk.) </div> </div> <div class="booktitle"><a href="/gui2/?mode=browse&params=publication;35705765" target="_blank">IEEE 23rd World Symposium on Applied Machine Intelligence and Informatics SAMI 2025 </a></div> <div class="conference"> Konferencia helye, ideje: <span class="location">Stará Lesna, Szlovákia <span class="conference-date">2025.01.23. - 2025.01.25.</span> </div> <span class="publishedAt">Piscataway (NJ): <span class="publishers">Institute of Electrical and Electronics Engineers (IEEE)</span>, <span class="page"> pp 000135-000139 </span> <span class="year">(2025)</span> ( <span class="seriesTitle">Proceedings - International Symposium on Applied Machine Intelligence and Informatics, SAMI</span> <span class="issn">2836-0834</span> <span class="issn">2767-9438</span> ) </div> <div class="pub-footer"> <span class="language" xmlns="http://www.w3.org/1999/html">Nyelv: Angol | </span> <span class="identifiers"> <span class="id identifier oa_none" title="none"> <a style="color:blue" title="10.1109/SAMI63904.2025.10883318" target="_blank" href="https://doi.org/10.1109/SAMI63904.2025.10883318"> DOI </a> </span> <span class="id identifier oa_none" title="none"> <a style="color:black" title="105013052330" target="_blank" href="http://www.scopus.com/record/display.url?origin=inward&eid=2-s2.0-105013052330"> Scopus </a> </span> <span class="id identifier oa_none" title="none"> <a style="color:black" title="https://ieeexplore.ieee.org/document/10883318/" target="_blank" href="https://ieeexplore.ieee.org/document/10883318/"> Egyéb URL </a> </span> </span> <span class="bookchapter-ids">Befoglaló link(ek):</span> <span class="identifiers"> <span class="id identifier oa_none" title="none"> <span class="isbnOrIssn"> ISBN: </span> <a style="color:black" title="9798350379365" target="_blank" href="https://www.worldcat.org/search?q=isbn%3A9798350379365"> 9798350379365 </a> </span> </span> <div class="mtid"><span class="long-pub-mtid">Közlemény: 35773631</span> | <span class="status-data status-ADMIN_APPROVED"> Admin láttamozott </span> <span class="long-book-mtid">Befoglaló: 35705765</span> Forrás | <span class="type-subtype">Könyvrészlet ( Konferenciaközlemény ) </span> | <span class="pub-category">Tudományos</span> | <span class="publication-sourceOfData">kézi felvitel</span> </div> <div class="funder"> ARNL(RRF-2.3.1-21-2022-00002) Támogató: NKFIH </div> <div class="lastModified">Utolsó módosítás: 2025.08.22. 11:42 Andódy Katalin (BME admin4) </div> <pre class="comment" style="margin-top: 0; margin-bottom: 0;"><u>Megjegyzés</u>: Project no. KDP-IKT-2023-900-I1-00000957/0000003 has been implemented with the support provided by the Ministry of Culture and Innovation of Hungary from the National Research, Development and Innovation Fund, financed under the KDP-2023 funding scheme. The research was supported by the European Union within the framework of the National Laboratory for Autonomous Systems. (RRF-2.3.1-21-2022-00...</pre> </div> </div>