{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:46:25Z","timestamp":1760060785056,"version":"build-2065373602"},"reference-count":60,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"European Institute of Innovation and Technology (EIT)","award":["21172"],"award-info":[{"award-number":["21172"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJGI"],"abstract":"<jats:p>Electric micro-mobility modes, such as e-scooters and e-bikes, are increasingly used in urban areas, posing challenges for accurate travel mode detection in mobility studies. Traditional supervised learning approaches require large labeled datasets, which are costly and time-consuming to generate. To address this, we propose xSeCA, a semi-supervised convolutional autoencoder that leverages both labeled and unlabeled trajectory data to detect electric micro-mobility travel modes. The model architecture integrates representation learning and classification in a compact and efficient manner, enabling accurate detection even with limited annotated samples. We evaluate xSeCA on multi-city datasets, including Copenhagen, Tel Aviv, Beijing and San Francisco, and benchmark it against supervised baselines such as XGBoost. Results demonstrate that xSeCA achieves high classification accuracy while exhibiting strong generalization capabilities across different urban contexts. In addition to validating model performance, we examine key travel properties relevant to micro-mobility behavior. This research highlights the benefits of semi-supervised learning for scalable and transferable travel mode detection, offering practical implications for urban planning and smart mobility systems.<\/jats:p>","DOI":"10.3390\/ijgi14090358","type":"journal-article","created":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T14:10:19Z","timestamp":1758118219000},"page":"358","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross-Domain Travel Mode Detection for Electric Micro-Mobility Using Semi-Supervised Learning"],"prefix":"10.3390","volume":"14","author":[{"given":"Eldar","family":"Lev-Ran","sequence":"first","affiliation":[{"name":"Mapping and Geo-Information Engineering, Civil and Environmental Engineering Faculty, Technion\u2014Israel Institute of Technology, Haifa 3200003, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miros\u0142awa","family":"\u0141ukawska","sequence":"additional","affiliation":[{"name":"Department of Technology, Management and Economics, Technical University of Denmark, Akademivej Bygning 358, 2800 Kongens Lyngby, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2208-0350","authenticated-orcid":false,"given":"Valentino","family":"Servizi","sequence":"additional","affiliation":[{"name":"Department of Technology, Management and Economics, Technical University of Denmark, Akademivej Bygning 358, 2800 Kongens Lyngby, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5639-8009","authenticated-orcid":false,"given":"Sagi","family":"Dalyot","sequence":"additional","affiliation":[{"name":"Mapping and Geo-Information Engineering, Civil and Environmental Engineering Faculty, Technion\u2014Israel Institute of Technology, Haifa 3200003, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"100872","DOI":"10.1016\/j.retrec.2020.100872","article-title":"Addressing transportation and environmental externalities with economics: Are policy makers listening?","volume":"82","author":"Lindsey","year":"2020","journal-title":"Res. Transp. Econ."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"103629","DOI":"10.1016\/j.trd.2023.103629","article-title":"Space sharing between pedestrians and micro-mobility vehicles: A systematic review","volume":"116","author":"Zhang","year":"2023","journal-title":"Transp. Res. Part D Transp. Environ."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"102734","DOI":"10.1016\/j.trd.2021.102734","article-title":"The role of micro-mobility in shaping sustainable cities: A systematic literature review","volume":"92","author":"Abduljabbar","year":"2021","journal-title":"Transp. Res. Part D Transp. Environ."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"103795","DOI":"10.1016\/j.trd.2023.103795","article-title":"Passively generated big data for micro-mobility: State-of-the-art and future research directions","volume":"121","author":"Schumann","year":"2023","journal-title":"Transp. Res. Part D Transp. Environ."},{"key":"ref_5","first-page":"102027","article-title":"Designing green and safe micro mobility routes: An advanced geo-analytic decision system based approach to sustainable urban infrastructure","volume":"64","author":"Kaya","year":"2025","journal-title":"Eng. Sci. Technol. Int. J."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"104020","DOI":"10.1016\/j.scs.2022.104020","article-title":"Siting charging stations and identifying safe and convenient routes for environmentally sustainable e-scooter systems","volume":"84","author":"Altintasi","year":"2022","journal-title":"Sustain. Cities Soc."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1016\/j.trc.2015.04.022","article-title":"The path most traveled: Travel demand estimation using big data resources","volume":"58","author":"Toole","year":"2015","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1016\/j.trf.2011.01.006","article-title":"A multi-level approach to travel mode choice\u2014How person characteristics and situation specific aspects determine car use in a student sample","volume":"14","author":"Friedrichsmeier","year":"2011","journal-title":"Transp. Res. Part F Traffic Psychol. Behav."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"100037","DOI":"10.1016\/j.multra.2022.100037","article-title":"Analysis of spatiotemporal dynamics of e-scooter usage in Minneapolis: Effects of the built and social environment","volume":"1","author":"Tokey","year":"2022","journal-title":"Multimodal Transp."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1016\/j.jclepro.2019.04.159","article-title":"GPS data in urban online ride-hailing: A comparative analysis on fuel consumption and emissions","volume":"227","author":"Sui","year":"2019","journal-title":"J. Clean. Prod."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1080\/01441647.2016.1246489","article-title":"Transportation mode detection\u2014An in-depth review of applicability and reliability","volume":"37","author":"Prelipcean","year":"2017","journal-title":"Transp. Rev."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"100167","DOI":"10.1016\/j.multra.2024.100167","article-title":"Exploring Micromobility Choice Behavior across Different Mode Users Using Machine Learning Methods","volume":"3","author":"Sarker","year":"2024","journal-title":"Multimodal Transp."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"125","DOI":"10.3141\/1768-15","article-title":"Elimination of the travel diary: Experiment to derive trip purpose from global positioning system travel data","volume":"1768","author":"Wolf","year":"2001","journal-title":"Transp. Res. Rec. J. Transp. Res. Board"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1391","DOI":"10.1080\/10095020.2023.2247446","article-title":"Estimating pedestrian traffic with Bluetooth sensor technology","volume":"27","author":"Angel","year":"2023","journal-title":"Geo-Spat. Inf. Sci."},{"key":"ref_15","unstructured":"Mun, M., Estrin, D., Burke, J., and Hansen, M. (2008, January 2\u20133). Parsimonious mobility classification using GSM and WiFi traces. Proceedings of the Fifth Workshop on Embedded Networked Sensors (HotEmNets), Charlottesville, VA, USA."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"105473","DOI":"10.1016\/j.scs.2024.105473","article-title":"Riding smooth: A cost-benefit assessment of surface quality on Copenhagen\u2019s bicycle network","volume":"108","author":"Argyros","year":"2024","journal-title":"Sustain. Cities Soc."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1016\/j.trc.2008.11.004","article-title":"Deriving and validating trip purposes and travel modes for multi-day GPS-based travel surveys: A large-scale application in the Netherlands","volume":"17","author":"Bohte","year":"2009","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_18","first-page":"467","article-title":"Review and evaluation of methods in transport mode detection based on GPS tracking data","volume":"8","author":"Sadeghian","year":"2021","journal-title":"J. Traffic Transp. Eng. (Engl. Ed.)"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Martin, B.D., Addona, V., Wolfson, J., Adomavicius, G., and Fan, Y. (2017). Methods for real-time prediction of the mode of travel using smartphone-based GPS and accelerometer data. Sensors, 17.","DOI":"10.3390\/s17092058"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.ijtst.2018.08.003","article-title":"An automated approach from GPS traces to complete trip information","volume":"8","author":"Yazdizadeh","year":"2019","journal-title":"Int. J. Transp. Sci. Technol."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zha, W., Guo, Y., Li, B., Liu, D., and Zhang, X. (2019, January 22\u201324). Individual Travel Transportation Modes Identification Based on Deep Learning Algorithm of Attention Mechanism. Proceedings of the 2019 Chinese Automation Congress (CAC), Hangzhou, China.","DOI":"10.1109\/CAC48633.2019.8996457"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.compenvurbsys.2016.03.001","article-title":"Making pervasive sensing possible: Effective travel mode sensing based on smartphones","volume":"58","author":"Zhou","year":"2016","journal-title":"Comput. Environ. Urban Syst."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Stenneth, L., Wolfson, O., Yu, P.S., and Xu, B. (2011, January 1\u20134). Transportation mode detection using mobile phones and GIS information. Proceedings of the 19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Chicago, IL, USA.","DOI":"10.1145\/2093973.2093982"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Roy, A., Fuller, D., Stanley, K., and Nelson, T. (2020). Classifying transport mode from global positioning systems and accelerometer data: A machine learning approach. Findings, 1\u20138.","DOI":"10.32866\/001c.14520"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"116741","DOI":"10.1109\/ACCESS.2019.2936443","article-title":"Detecting travel modes using rule-based classification system and Gaussian process classifier","volume":"7","author":"Xiao","year":"2019","journal-title":"IEEE Access"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Xiao, Z., Wang, Y., Fu, K., and Wu, F. (2017). Identifying different transportation modes from trajectory data using tree-based ensemble classifiers. ISPRS Int. J. Geo-Inf., 6.","DOI":"10.3390\/ijgi6020057"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1547","DOI":"10.1109\/TITS.2017.2723523","article-title":"Travel mode detection using GPS data and socioeconomic attributes based on a random forest classifier","volume":"19","author":"Wang","year":"2017","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2232","DOI":"10.1109\/TITS.2019.2918923","article-title":"Ensemble convolutional neural networks for mode inference in smartphone travel survey","volume":"21","author":"Yazdizadeh","year":"2019","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_29","first-page":"87","article-title":"Multi-stage approach to travel-mode segmentation and classification of GPS traces. Geospatial Data Infrastructure: From Data Acquisition and Updating to Smarter Services","volume":"W25","author":"Zhang","year":"2011","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1010","DOI":"10.1109\/TKDE.2019.2896985","article-title":"Semi-supervised deep learning approach for transportation mode identification using GPS trajectory data","volume":"32","author":"Dabiri","year":"2019","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/j.trc.2020.01.003","article-title":"Semi-supervised deep ensemble learning for travel mode identification","volume":"112","author":"James","year":"2020","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1016\/j.tra.2020.04.005","article-title":"Coupled application of generative adversarial networks and conventional neural networks for travel mode detection using GPS data","volume":"136","author":"Li","year":"2020","journal-title":"Transp. Res. Part A Policy Pract."},{"key":"ref_33","unstructured":"Wood, J., Bradley, S., and Hamidi, S. (2023, May 23). Preparing for Progress: Establishing Guidelines for the Regulation, Safe Integration, and Equitable Usage of Dockless Electric Scooters in American Cities, Available online: https:\/\/rosap.ntl.bts.gov\/view\/dot\/54415."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1186\/s13705-018-0149-0","article-title":"Evaluation of various means of transport for urban areas","volume":"8","author":"Brunner","year":"2018","journal-title":"Energy Sustain. Soc."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"100677","DOI":"10.1016\/j.rineng.2022.100677","article-title":"E-Scooter Rider detection and classification in dense urban environments","volume":"16","author":"Gilroy","year":"2022","journal-title":"Results Eng."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.compenvurbsys.2015.05.005","article-title":"Travel mode detection based on GPS track data and Bayesian networks","volume":"54","author":"Xiao","year":"2015","journal-title":"Comput. Environ. Urban Syst."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Liu, L., Li, Y., Gruyer, D., and Tu, M. (Int. J. Transp. Sci. Technol., 2024). Non-linear relationship between built environment and active travel: A hybrid model considering spatial heterogeneity, Int. J. Transp. Sci. Technol., in press.","DOI":"10.1016\/j.ijtst.2024.08.008"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Fang, Z., Wu, D., Pan, L., Chen, L., and Gao, Y. (2022, January 23\u201329). When Transfer Learning Meets Cross-City Urban Flow Prediction: Spatio-Temporal Adaptation Matters. Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, Vienna, Austria.","DOI":"10.24963\/ijcai.2022\/282"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Jain, Y., and Pandey, K. (2025). Transforming Urban Mobility: A Systematic Review of AI-Based Traffic Optimization Techniques. Arch. Comput. Methods Eng., 1\u201337.","DOI":"10.1007\/s11831-025-10297-6"},{"key":"ref_40","first-page":"81","article-title":"Kick-scooters detection in sensor-based transportation mode classification methods","volume":"54","author":"Alaoui","year":"2021","journal-title":"IFAC-Pap."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Matkovic, V., Waltereit, M., Zdankin, P., and Weis, T. (2020, January 7\u20139). Towards bike type and e-scooter classification with smartphone sensors. Proceedings of the MobiQuitous 2020\u201417th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, Darmstadt, Germany.","DOI":"10.1145\/3448891.3448897"},{"key":"ref_42","first-page":"32","article-title":"GeoLife: A collaborative social networking service among user, location and trajectory","volume":"33","author":"Zheng","year":"2010","journal-title":"IEEE Data Eng. Bull."},{"key":"ref_43","unstructured":"Bernitt, C. (2017). The Choice Between E-Bike and Car\u2014Economical Decision by Data Mining. [Unpublished Bachelor\u2019s Thesis, Technical University of Denmark]."},{"key":"ref_44","unstructured":"Shankari, K., Fuerst, J., Argerich, M.F., Avramidis, E., and Zhang, J. (2020, January 26). MobilityNet: Towards a Public Dataset for Multi-modal Mobility Research. Proceedings of the ICLR 2020 Workshop on Tackling Climate Change with Machine Learning, Addis Ababa, Ethiopia."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1321","DOI":"10.1111\/tgis.12280","article-title":"Extracting spatial patterns in bicycle routes from crowdsourced data","volume":"21","author":"Sultan","year":"2017","journal-title":"Trans. GIS"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1264","DOI":"10.1111\/tgis.12674","article-title":"Machine-learning prediction models for pedestrian traffic flow levels: Towards optimizing walking routes for blind pedestrians","volume":"24","author":"Cohen","year":"2020","journal-title":"Trans. GIS"},{"key":"ref_47","unstructured":"Loshchilov, I., and Hutter, F. (2017). Decoupled weight decay regularization. arXiv."},{"key":"ref_48","unstructured":"Reddi, S.J., Kale, S., and Kumar, S. (2019). On the convergence of adam and beyond. arXiv."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1177\/0361198120919760","article-title":"Exploratory analysis of real-time e-scooter trip data in Washington, DC","volume":"2674","author":"Zou","year":"2020","journal-title":"Transp. Res. Rec. J. Transp. Res. Board"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"112","DOI":"10.3138\/FM57-6770-U75U-7727","article-title":"Algorithms for the reduction of the number of points required to represent a digitized line or its caricature","volume":"10","author":"Douglas","year":"1973","journal-title":"Cartographica"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1016\/j.jsr.2023.09.019","article-title":"Modeling collision avoidance maneuvers for micromobility vehicles","volume":"87","author":"Li","year":"2023","journal-title":"J. Saf. Res."},{"key":"ref_52","first-page":"1","article-title":"An efficient explanation of individual classifications using game theory","volume":"11","author":"Strumbelj","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref_53","first-page":"e00889","article-title":"Urban road pavements monitoring and assessment using bike and e-scooter as probe vehicles","volume":"16","author":"Cafiso","year":"2022","journal-title":"Case Stud. Constr. Mater."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"19187","DOI":"10.1109\/TITS.2022.3170628","article-title":"A xgboost-based lane change prediction on time series data using feature engineering for autopilot vehicles","volume":"23","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"104112","DOI":"10.1016\/j.trc.2023.104112","article-title":"Intersense: An XGBoost model for traffic regulator identification at intersections through crowdsourced GPS data","volume":"151","author":"Vlachogiannis","year":"2023","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"150891","DOI":"10.1109\/ACCESS.2020.3015242","article-title":"Transportation mode recognition with deep forest based on GPS data","volume":"8","author":"Guo","year":"2020","journal-title":"IEEE Access"},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"105954","DOI":"10.1016\/j.aap.2020.105954","article-title":"E-Scooter safety: The riding risk analysis based on mobile sensing data","volume":"151","author":"Ma","year":"2021","journal-title":"Accid. Anal. Prev."},{"key":"ref_58","unstructured":"Reddi, S., Charles, Z., Zaheer, M., Garrett, Z., Rush, K., Kone\u010dn\u00fd, J., Kumar, S., and McMahan, H.B. (2020). Adaptive federated optimization. arXiv."},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Ezequiel, C.E.J., Gjoreski, M., and Langheinrich, M. (2022). Federated learning for privacy-aware human mobility modeling. Front. Artif. Intell., 5.","DOI":"10.3389\/frai.2022.867046"},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"103330","DOI":"10.1016\/j.jtrangeo.2022.103330","article-title":"Assessing the role of geographic context in transportation mode detection from GPS data","volume":"100","author":"Roy","year":"2022","journal-title":"J. Transp. Geogr."}],"container-title":["ISPRS International Journal of Geo-Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2220-9964\/14\/9\/358\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:47:22Z","timestamp":1760035642000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2220-9964\/14\/9\/358"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"references-count":60,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["ijgi14090358"],"URL":"https:\/\/doi.org\/10.3390\/ijgi14090358","relation":{},"ISSN":["2220-9964"],"issn-type":[{"type":"electronic","value":"2220-9964"}],"subject":[],"published":{"date-parts":[[2025,9,17]]}}}