{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T11:06:16Z","timestamp":1768993576220,"version":"3.49.0"},"reference-count":20,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2024,4,19]],"date-time":"2024-04-19T00:00:00Z","timestamp":1713484800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Escuela T\u00e9cnica Superior de Ingenieros (ETSI) Telecomunicaci\u00f3n of the Universidad Polit\u00e9cnica de Madrid","award":["PID2020-112502RB\/AEI\/10.13039\/501100011033"],"award-info":[{"award-number":["PID2020-112502RB\/AEI\/10.13039\/501100011033"]}]},{"name":"Escuela T\u00e9cnica Superior de Ingenieros (ETSI) Telecomunicaci\u00f3n of the Universidad Polit\u00e9cnica de Madrid","award":["TED2021-129189B-C21"],"award-info":[{"award-number":["TED2021-129189B-C21"]}]},{"name":"Escuela T\u00e9cnica Superior de Ingenieros (ETSI) Telecomunicaci\u00f3n of the Universidad Polit\u00e9cnica de Madrid","award":["TED2021-129189B-C22"],"award-info":[{"award-number":["TED2021-129189B-C22"]}]},{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n of Spain","doi-asserted-by":"publisher","award":["PID2020-112502RB\/AEI\/10.13039\/501100011033"],"award-info":[{"award-number":["PID2020-112502RB\/AEI\/10.13039\/501100011033"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n of Spain","doi-asserted-by":"publisher","award":["TED2021-129189B-C21"],"award-info":[{"award-number":["TED2021-129189B-C21"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n of Spain","doi-asserted-by":"publisher","award":["TED2021-129189B-C22"],"award-info":[{"award-number":["TED2021-129189B-C22"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MCIN\/AEI\/10.13039\/501100011033","award":["PID2020-112502RB\/AEI\/10.13039\/501100011033"],"award-info":[{"award-number":["PID2020-112502RB\/AEI\/10.13039\/501100011033"]}]},{"name":"MCIN\/AEI\/10.13039\/501100011033","award":["TED2021-129189B-C21"],"award-info":[{"award-number":["TED2021-129189B-C21"]}]},{"name":"MCIN\/AEI\/10.13039\/501100011033","award":["TED2021-129189B-C22"],"award-info":[{"award-number":["TED2021-129189B-C22"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Predicting vehicle mobility is crucial in domains such as ride-hailing, where the balance between offer and demand is paramount. Since city road networks can be easily represented as graphs, recent works have exploited graph neural networks (GNNs) to produce more accurate predictions on real traffic data. However, a better understanding of the characteristics and limitations of this approach is needed. In this work, we compare several GNN aggregated mobility prediction schemes to a selection of other approaches in a very restricted and controlled simulation scenario. The city graph employed represents roads as directed edges and road intersections as nodes. Individual vehicle mobility is modeled as transitions between nodes in the graph. A time series of aggregated mobility is computed by counting vehicles in each node at any given time. Three main approaches are employed to construct the aggregated mobility predictors. First, the behavior of the moving individuals is assumed to follow a Markov chain (MC) model whose transition matrix is inferred via a least squares estimation procedure; the recurrent application of this MC provides the aggregated mobility prediction values. Second, a multilayer perceptron (MLP) is trained so that\u2014given the node occupation at a given time\u2014it can recursively provide predictions for the next values of the time series. Third, we train a GNN (according to the city graph) with the time series data via a supervised learning formulation that computes\u2014through an embedding construction for each node in the graph\u2014the aggregated mobility predictions. Some mobility patterns are simulated in the city to generate different time series for testing purposes. The proposed schemes are comparatively assessed compared to different baseline prediction procedures. The comparison illustrates several limitations of the GNN approaches in the selected scenario and uncovers future lines of investigation.<\/jats:p>","DOI":"10.3390\/a17040166","type":"journal-article","created":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T03:57:07Z","timestamp":1713758227000},"page":"166","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Predicting the Aggregate Mobility of a Vehicle Fleet within a City Graph"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3545-9252","authenticated-orcid":false,"given":"J. Fernando","family":"S\u00e1nchez-Rada","sequence":"first","affiliation":[{"name":"Departamento de Ingenier\u00eda de Sistemas Telem\u00e1ticos, ETSI Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid, 28006 Madrid, Spain"},{"name":"C\u00e1tedra Cabify, ETSI Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid, 28040 Madrid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raquel","family":"Vila-Rodr\u00edguez","sequence":"additional","affiliation":[{"name":"C\u00e1tedra Cabify, ETSI Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid, 28040 Madrid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1454-4784","authenticated-orcid":false,"given":"Jes\u00fas","family":"Montes","sequence":"additional","affiliation":[{"name":"Cabify, 28002 Madrid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1217-1216","authenticated-orcid":false,"given":"Pedro J.","family":"Zufiria","sequence":"additional","affiliation":[{"name":"C\u00e1tedra Cabify, ETSI Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid, 28040 Madrid, Spain"},{"name":"Departamento Matem\u00e1tica Aplicada a las TIC, Information Processing and Telecommunications Center (IPTC), ETSI Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid, 28040 Madrid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,4,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/j.comnet.2018.12.016","article-title":"Mobility prediction-based efficient clustering scheme for connected and automated vehicles in VANETs","volume":"150","author":"Fahmy","year":"2019","journal-title":"Comput. Netw."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"10227","DOI":"10.1109\/TVT.2019.2937825","article-title":"Edge-assisted vehicle mobility prediction to support V2X communications","volume":"68","author":"Liu","year":"2019","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3997","DOI":"10.1109\/TII.2019.2936507","article-title":"DeepVM: RNN-based vehicle mobility prediction to support intelligent vehicle applications","volume":"16","author":"Liu","year":"2020","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2661","DOI":"10.1007\/s12652-019-01327-w","article-title":"Nextroute: A lossless model for accurate mobility prediction","volume":"11","author":"Amirat","year":"2020","journal-title":"J. Ambient. Intell. Humaniz. Comput."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"4648","DOI":"10.1109\/TITS.2020.3023446","article-title":"A deep learning-based mobile crowdsensing scheme by predicting vehicle mobility","volume":"22","author":"Zhu","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"13671","DOI":"10.1109\/ACCESS.2021.3052071","article-title":"An adaptive learning-based approach for vehicle mobility prediction","volume":"9","author":"Irio","year":"2021","journal-title":"IEEE Access"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"117921","DOI":"10.1016\/j.eswa.2022.117921","article-title":"Graph neural network for traffic forecasting: A survey","volume":"207","author":"Jiang","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_8","unstructured":"Gomes, D., Ruelens, F., Efthymiadis, K., Nowe, A., and Vrancx, P. When Are Graph Neural Networks Better Than Structure-Agnostic Methods? In Proceedings of the I Can\u2019t Believe It\u2019s Not Better Workshop: Understanding Deep Learning through Empirical Falsification, New Orleans, LA, USA, 28 November\u20139 December 2022."},{"key":"ref_9","unstructured":"Kemeny, J.G., and Snell, J.L. (1960). Finite Markov Chains, Springer."},{"key":"ref_10","unstructured":"Haykin, S. (1998). Neural Networks: A Comprehensive Foundation, Prentice Hall PTR."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2008","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1002\/wcm.72","article-title":"A survey of mobility models for ad hoc network research","volume":"2","author":"Camp","year":"2002","journal-title":"Wirel. Commun. Mob. Comput."},{"key":"ref_13","first-page":"147","article-title":"A survey of mobility models","volume":"Volume 206","author":"Bai","year":"2004","journal-title":"Wireless Adhoc Networks"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"9746","DOI":"10.1109\/TVT.2023.3253695","article-title":"Spatiotemporal capsule neural network for vehicle trajectory prediction","volume":"72","author":"Qin","year":"2023","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_15","unstructured":"Jin, M., Koh, H.Y., Wen, Q., Zambon, D., Alippi, C., Webb, G.I., King, I., and Pan, S. (2023). A survey on graph neural networks for time series: Forecasting, classification, imputation, and anomaly detection. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Ibe, O. (2013). Markov Processes for Stochastic Modeling, Academic Press.","DOI":"10.1016\/B978-0-12-407795-9.00015-3"},{"key":"ref_17","unstructured":"Mendel, J.M. (1995). Lessons in Estimation Theory for Signal Processing, Communications, and Control, Pearson Education."},{"key":"ref_18","unstructured":"Kipf, T.N., and Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/s40649-019-0069-y","article-title":"Graph convolutional networks: A comprehensive review","volume":"6","author":"Zhang","year":"2019","journal-title":"Comput. Soc. Netw."},{"key":"ref_20","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., and Bengio, Y. (2018). Graph Attention Networks. arXiv."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/17\/4\/166\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:31:23Z","timestamp":1760106683000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/17\/4\/166"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,19]]},"references-count":20,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,4]]}},"alternative-id":["a17040166"],"URL":"https:\/\/doi.org\/10.3390\/a17040166","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,19]]}}}