{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T01:36:19Z","timestamp":1768700179242,"version":"3.49.0"},"reference-count":52,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2022,2,21]],"date-time":"2022-02-21T00:00:00Z","timestamp":1645401600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002428","name":"FWF Austrian Science Fund","doi-asserted-by":"publisher","award":["P 29135-N29"],"award-info":[{"award-number":["P 29135-N29"]}],"id":[{"id":"10.13039\/501100002428","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Trajectory data represent an essential source of information on travel behaviors and human mobility patterns, assuming a central role in a wide range of services related to transportation planning, personalized recommendation strategies, and resource management plans. The main issue when dealing with trajectory recordings, however, is characterized by temporary losses in the data collection, causing possible spatial\u2013temporal gaps and missing trajectory segments. This is especially critical in those use cases based on non-repetitive individual motion traces, when the user\u2019s missing information cannot be directly reconstructed due to the absence of historical individual repetitive routes. Inserted in the context of location-based trajectory modeling, we tackle the problem by proposing a technical parallelism with the natural language processing domain. Specifically, we introduce the use of the Bidirectional Encoder Representations from Transformers (BERT), a state-of-the-art language representation model, into the trajectory processing research field. By training deep bidirectional representations from unlabeled location sequences, jointly conditioned on both left and right context, we derive an explicit predicted estimation of the missing locations along the trace. The proposed framework, named TraceBERT, was tested on a real-world large-scale trajectory dataset of short-term tourists, exploring an effective attempt of adapting advanced language modeling approaches into mobility-based applications and demonstrating a prominent potential on trajectory reconstruction over traditional statistical approaches.<\/jats:p>","DOI":"10.3390\/s22041682","type":"journal-article","created":{"date-parts":[[2022,2,21]],"date-time":"2022-02-21T20:48:41Z","timestamp":1645476521000},"page":"1682","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["TraceBERT\u2014A Feasibility Study on Reconstructing Spatial\u2013Temporal Gaps from Incomplete Motion Trajectories via BERT Training Process on Discrete Location Sequences"],"prefix":"10.3390","volume":"22","author":[{"given":"Alessandro","family":"Crivellari","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2233-6926","authenticated-orcid":false,"given":"Bernd","family":"Resch","sequence":"additional","affiliation":[{"name":"Department of Geoinformatics\u2014Z_GIS, University of Salzburg, 5020 Salzburg, Austria"},{"name":"Center for Geographic Analysis, Harvard University, Cambridge, MA 02138, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8840-723X","authenticated-orcid":false,"given":"Yuhui","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,2,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1038\/nature06958","article-title":"Understanding individual human mobility patterns","volume":"453","author":"Gonzalez","year":"2008","journal-title":"Nature"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"20130246","DOI":"10.1098\/rsif.2013.0246","article-title":"Unravelling daily human mobility motifs","volume":"10","author":"Schneider","year":"2013","journal-title":"J. R Soc. Interface"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2056","DOI":"10.1109\/ACCESS.2016.2553681","article-title":"A survey on trajectory data mining: Techniques and applications","volume":"4","author":"Feng","year":"2016","journal-title":"IEEE Access"},{"key":"ref_4","unstructured":"Jonietz, D., and Bucher, D. (2018, January 15\u201317). Continuous trajectory pattern mining for mobility behaviour change detection. Proceedings of the LBS 2018: 14th International Conference on Location Based Services, Zurich, Switzerland."},{"key":"ref_5","first-page":"61","article-title":"Trajectory data mining: A review of methods and applications","volume":"2016","author":"Mazimpaka","year":"2016","journal-title":"J. Spat. Inf. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2743025","article-title":"Trajectory data mining: An overview","volume":"6","author":"Zheng","year":"2015","journal-title":"ACM Trans. Intell. Syst. Technol. TIST"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Bhargava, P., Phan, T., Zhou, J., and Lee, J. (2015, January 18\u201322). Who, what, when, and where: Multi-dimensional collaborative recommendations using tensor factorization on sparse user-generated data. Proceedings of the 24th International Conference on World Wide Web, Florence, Italy.","DOI":"10.1145\/2736277.2741077"},{"key":"ref_8","unstructured":"Cheng, C., Yang, H., Lyu, M.R., and King, I. (2013, January 3\u20139). Where you like to go next: Successive point-of-interest recommendation. Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence, Beijing, China."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Guo, Y., Wang, S., Zheng, L., and Lu, M. (2017, January 13\u201316). Trajectory Data Driven Transit-Transportation Planning. Proceedings of the 2017 Fifth International Conference on Advanced Cloud and Big Data (CBD), Shanghai, China.","DOI":"10.1109\/CBD.2017.72"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1007\/s42421-021-00040-5","article-title":"Scalable Framework for Enhancing Raw GPS Trajectory Data: Application to Trip Analytics for Transportation Planning","volume":"3","author":"Franz","year":"2021","journal-title":"J. Big Data Anal. Transp."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Enami, S., and Shiomoto, K. (2019, January 26\u201329). Spatio-temporal human mobility prediction based on trajectory data mining for resource management in mobile communication networks. Proceedings of the 2019 IEEE 20th International Conference on High Performance Switching and Routing (HPSR), Xi\u2019an, China.","DOI":"10.1109\/HPSR.2019.8808106"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Yao, C., Guo, J., and Yang, C. (2016, January 7\u20139). Achieving high throughput with predictive resource allocation. Proceedings of the 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Washington, DC, USA.","DOI":"10.1109\/GlobalSIP.2016.7905946"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Chen, M., Liu, Y., and Yu, X. (2014, January 13\u201316). Nlpmm: A next location predictor with markov modeling. Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining, Tainan, Taiwan.","DOI":"10.1007\/978-3-319-06605-9_16"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.neucom.2015.02.079","article-title":"Exploiting machine learning techniques for location recognition and prediction with smartphone logs","volume":"176","author":"Cho","year":"2016","journal-title":"Neurocomputing"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Lee, S., Lim, J., Park, J., and Kim, K. (2016). Next place prediction based on spatiotemporal pattern mining of mobile device logs. Sensors, 16.","DOI":"10.3390\/s16020145"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1140\/epjds\/s13688-017-0124-6","article-title":"Are you getting sick? Predicting influenza-like symptoms using human mobility behaviors","volume":"6","author":"Barlacchi","year":"2017","journal-title":"EPJ Data Sci."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1016\/j.trc.2017.11.021","article-title":"Inferring transportation modes from GPS trajectories using a convolutional neural network","volume":"86","author":"Dabiri","year":"2018","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1007\/s10955-014-1024-9","article-title":"Saving human lives: What complexity science and information systems can contribute","volume":"158","author":"Helbing","year":"2015","journal-title":"J. Stat. Phys."},{"key":"ref_19","first-page":"38","article-title":"Generated traffic: Implications for transport planning","volume":"71","author":"Litman","year":"2001","journal-title":"ITE J."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Song, X., Zhang, Q., Sekimoto, Y., and Shibasaki, R. (2014, January 24\u201327). Prediction of human emergency behavior and their mobility following large-scale disaster. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA.","DOI":"10.1145\/2623330.2623628"},{"key":"ref_21","unstructured":"Gao, Q.-B., and Sun, S.-L. (2012, January 15\u201317). Trajectory-based human activity recognition using hidden conditional random fields. Proceedings of the 2012 International Conference on Machine Learning and Cybernetics, Xi\u2019an, China."},{"key":"ref_22","unstructured":"Vail, D.L., Veloso, M.M., and Lafferty, J.D. Conditional random fields for activity recognition. Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1080\/17489725.2016.1169322","article-title":"Understanding movement data quality","volume":"10","author":"Andrienko","year":"2016","journal-title":"J. Locat. Based Serv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1080\/17489725.2021.1900612","article-title":"An exploratory data analysis protocol for identifying problems in continuous movement data","volume":"15","author":"Graser","year":"2021","journal-title":"J. Locat. Based Serv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1391","DOI":"10.1080\/13658816.2018.1423685","article-title":"Segmenting human trajectory data by movement states while addressing signal loss and signal noise","volume":"32","author":"Hwang","year":"2018","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Iovan, C., Olteanu-Raimond, A.-M., Couronn\u00e9, T., and Smoreda, Z. (2013). Moving and calling: Mobile phone data quality measurements and spatiotemporal uncertainty in human mobility studies. Geographic Information Science at the Heart of Europe, Springer.","DOI":"10.1007\/978-3-319-00615-4_14"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2187","DOI":"10.1080\/13658816.2020.1862126","article-title":"Applying frequent-pattern mining and time geography to impute gaps in smartphone-based human-movement data","volume":"35","author":"Zhao","year":"2021","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1016\/j.comcom.2018.03.012","article-title":"Enriching sparse mobility information in call detail records","volume":"122","author":"Chen","year":"2018","journal-title":"Comput. Commun."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"403","DOI":"10.4081\/gh.2016.403","article-title":"Is missing geographic positioning system data in accelerometry studies a problem, and is imputation the solution?","volume":"11","author":"Meseck","year":"2016","journal-title":"Geospat. Health"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"558","DOI":"10.1111\/tgis.12549","article-title":"Path segmentation for movement trajectories with irregular sampling frequency using space-time interpolation and density-based spatial clustering","volume":"23","author":"Song","year":"2019","journal-title":"Trans. GIS"},{"key":"ref_31","unstructured":"Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Crivellari, A., and Beinat, E. (2019). From motion activity to geo-embeddings: Generating and exploring vector representations of locations, traces and visitors through large-scale mobility data. ISPRS Int. J. Geo-Inf., 8.","DOI":"10.3390\/ijgi8030134"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Liu, K., Gao, S., Qiu, P., Liu, X., Yan, B., and Lu, F. (2017). Road2vec: Measuring traffic interactions in urban road system from massive travel routes. ISPRS Int. J. Geo-Inf., 6.","DOI":"10.3390\/ijgi6110321"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"102610","DOI":"10.1016\/j.cities.2020.102610","article-title":"Visualizing and exploring POI configurations of urban regions on POI-type semantic space","volume":"99","author":"Liu","year":"2020","journal-title":"Cities"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Yan, B., Janowicz, K., Mai, G., and Gao, S. (2017, January 7\u201310). From itdl to place2vec: Reasoning about place type similarity and relatedness by learning embeddings from augmented spatial contexts. Proceedings of the 25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Redondo Beach, CA, USA.","DOI":"10.1145\/3139958.3140054"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.compenvurbsys.2018.11.008","article-title":"Beyond Word2vec: An approach for urban functional region extraction and identification by combining Place2vec and POIs","volume":"74","author":"Zhai","year":"2019","journal-title":"Comput. Environ. Urban Syst."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Crivellari, A., and Beinat, E. (2020). Trace2trace\u2014A Feasibility Study on Neural Machine Translation Applied to Human Motion Trajectories. Sensors, 20.","DOI":"10.3390\/s20123503"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1016\/j.neucom.2020.03.080","article-title":"A hierarchical temporal attention-based LSTM encoder-decoder model for individual mobility prediction","volume":"403","author":"Li","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Park, S.H., Kim, B., Kang, C.M., Chung, C.C., and Choi, J.W. (2018, January 26\u201330). Sequence-to-Sequence Prediction of Vehicle Trajectory via LSTM Encoder-Decoder Architecture. Proceedings of the 2018 IEEE Intelligent Vehicles Symposium (IV), Suzhou, China.","DOI":"10.1109\/IVS.2018.8500658"},{"key":"ref_40","unstructured":"Vaswani, A., Shazeer, N.M., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017). Attention is All you Need. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1007\/s00779-003-0240-0","article-title":"Using GPS to learn significant locations and predict movement across multiple users","volume":"7","author":"Ashbrook","year":"2003","journal-title":"Pers. Ubiquitous Comput."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1258","DOI":"10.1109\/18.144706","article-title":"Universal prediction of individual sequences","volume":"38","author":"Feder","year":"1992","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_43","unstructured":"Radford, A., Narasimhan, K., Salimans, T., and Sutskever, I. (2018). Improving Language Understanding with Unsupervised Learning, OpenAI. Technical Report."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., and Zettlemoyer, L. (2018, January 1\u20136). Deep contextualized word representations. Proceedings of the NAACL, New Orleans, LA, USA.","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref_45","unstructured":"Cordonnier, J., Loukas, A., and Jaggi, M. (2019). On the relationship between self-attention and convolutional layers. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Voita, E., Talbot, D., Moiseev, F., Sennrich, R., and Titov, I. (2019). Analyzing multi-head self-attention: Specialized heads do the heavy lifting, the rest can be pruned. arXiv.","DOI":"10.18653\/v1\/P19-1580"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Graves, A. (2013). Generating sequences with recurrent neural networks. arXiv.","DOI":"10.1007\/978-3-642-24797-2_3"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"De Montjoye, Y.-A., Quoidbach, J., Robic, F., and Pentland, A. (2013, January 2\u20135). Predicting Personality Using Novel Mobile Phone-Based Metrics. Proceedings of the International Conference on Social Computing, Behavioral-Cultural Modeling and Prediction, Washington, DC, USA.","DOI":"10.1007\/978-3-642-37210-0_6"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"11576","DOI":"10.1073\/pnas.1203882109","article-title":"Predictability of population displacement after the 2010 Haiti earthquake","volume":"109","author":"Lu","year":"2012","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Hawelka, B., Sitko, I., Kazakopoulos, P., and Beinat, E. (2017). Collective Prediction of Individual Mobility Traces for Users with Short Data History. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0170907"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Sunds\u00f8y, P., Bjelland, J., Reme, B.A., Iqbal, A.M., and Jahani, E. (2016, January 24\u201325). Deep Learning Applied to Mobile Phone Data for Individual Income Classification. Proceedings of the 2016 International Conference on Artificial Intelligence: Technologies and Applications, Bangkok, Thailand.","DOI":"10.2991\/icaita-16.2016.24"},{"key":"ref_52","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/4\/1682\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:24:07Z","timestamp":1760135047000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/4\/1682"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,21]]},"references-count":52,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,2]]}},"alternative-id":["s22041682"],"URL":"https:\/\/doi.org\/10.3390\/s22041682","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,21]]}}}