{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T03:41:10Z","timestamp":1760240470893,"version":"build-2065373602"},"reference-count":57,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2019,6,27]],"date-time":"2019-06-27T00:00:00Z","timestamp":1561593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1734204"],"award-info":[{"award-number":["U1734204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJGI"],"abstract":"<jats:p>Driving modes play vital roles in understanding the stochastic nature of a railway system and can support studies of automatic driving and capacity utilization optimization. Integrated trajectory data containing information such as GPS trajectories and gear changes can be good proxies in the study of driving modes. However, in the absence of labeled data, discovering driving modes is challenging. In this paper, instead of classical models (railway-specified feature extraction and classical clustering), we used five deep unsupervised learning models to overcome this difficulty. In these models, adversarial autoencoders and stacked autoencoders are used as feature extractors, along with generative adversarial network-based and Kullback\u2013Leibler (KL) divergence-based networks as clustering models. An experiment based on real and artificial datasets showed the following: (i) The proposed deep learning models outperform the classical models by 27.64% on average. (ii) Integrated trajectory data can improve the accuracy of unsupervised learning by approximately 13.78%. (iii) The different performance rankings of models based on indices with labeled data and indices without labeled data demonstrate the insufficiency of people\u2019s understanding of the existing modes. This study also analyzes the relationship between the discovered modes and railway carrying capacity.<\/jats:p>","DOI":"10.3390\/ijgi8070294","type":"journal-article","created":{"date-parts":[[2019,6,27]],"date-time":"2019-06-27T09:42:11Z","timestamp":1561628531000},"page":"294","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Automatic Discovery of Railway Train Driving Modes Using Unsupervised Deep Learning"],"prefix":"10.3390","volume":"8","author":[{"given":"Han","family":"Zheng","sequence":"first","affiliation":[{"name":"School of Traffic and Transportation, Beijing Jiaotong University, No.3 Shang Yuan Cun, Hai Dian District, Beijing 100044, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zanyang","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Traffic and Transportation, Beijing Jiaotong University, No.3 Shang Yuan Cun, Hai Dian District, Beijing 100044, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingchen","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Traffic and Transportation, Beijing Jiaotong University, No.3 Shang Yuan Cun, Hai Dian District, Beijing 100044, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2019,6,27]]},"reference":[{"key":"ref_1","unstructured":"Be\u0161inovi\u0107, N. (2017). Integrated Capacity Assessment and Timetabling Models for Dense Railway Networks. [Ph.D. Dissertation, Delft University of Technology]."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Zheng, H., Cui, Z., and Zhang, X. (2018). Identifying modes of driving railway trains from gps trajectory data: An ensemble classifier-based approach. ISPRS Int. J. Geo-Inf., 7.","DOI":"10.3390\/ijgi7080308"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Be\u0161inovi\u0107, N., and Goverde, R.M.P. (2018). Capacity Assessment in Railway Networks, Springer.","DOI":"10.1007\/978-3-319-72153-8_2"},{"key":"ref_4","unstructured":"Besinovic, N., Roberti, R., Quaglietta, E., Cacchiani, V., Toth, P., and Goverde, R.M.P. (2015, January 23\u201326). Micro-macro approach to robust timetabling. Proceedings of the International Seminar on Railway Operations Modelling and Analysis, Tokyo, Japan."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1016\/j.trc.2010.01.002","article-title":"A delay propagation algorithm for large-scale railway traffic networks","volume":"18","author":"Goverde","year":"2010","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_6","unstructured":"Longo, G., Medeossi, G., and Nash, A. (2012, January 22\u201326). Estimating train motion using detailed sensor data. Proceedings of the Transportation Research Board 91st Annual Meeting, Washington, DC, USA."},{"key":"ref_7","first-page":"1","article-title":"A method for using stochastic blocking times to improve timetable planning","volume":"1","author":"Medeossi","year":"2011","journal-title":"J. Rail Transp. Plan. Manag."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.trb.2016.02.004","article-title":"An integrated micro\u2013macro approach to robust railway timetabling","volume":"87","author":"Goverde","year":"2016","journal-title":"Transp. Res. Part B Methodol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/j.trb.2017.01.002","article-title":"Joint optimization of high-speed train timetables and speed profiles: A unified modeling approach using space-time-speed grid networks","volume":"97","author":"Zhou","year":"2017","journal-title":"Transp. Res. Part B Methodol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"727","DOI":"10.1016\/j.ejor.2011.11.003","article-title":"Nominal and robust train timetabling problems","volume":"219","author":"Cacchiani","year":"2012","journal-title":"Eur. J. Oper. Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cor.2014.06.025","article-title":"Recovery-to-optimality: A new two-stage approach to robustness with an application to aperiodic timetabling","volume":"52","author":"Goerigk","year":"2014","journal-title":"Comput. Oper. Res."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"644","DOI":"10.1016\/j.sbspro.2012.04.138","article-title":"A monitoring data mining based approach to measuring and correcting timetable parameters","volume":"43","author":"Chen","year":"2012","journal-title":"Procedia-Soc. Behav. Sci."},{"key":"ref_13","first-page":"117","article-title":"Method for the measurement and correction of train diagram parameters based on monitoring data mining","volume":"32","author":"Wang","year":"2011","journal-title":"China Railw. Sci."},{"key":"ref_14","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_15","unstructured":"Fabris, S.D., Longo, G., and Medeossi, G. (September, January 31). Automated Analysis of Train Event Recorder Data to Improve Micro-Simulation Models. Proceedings of the COMPRAIL 2010 Conference, Beijing, China."},{"key":"ref_16","first-page":"927","article-title":"Driving style for ertms level 2 and conventional lineside signalling: An exploratory study","volume":"71","author":"Powell","year":"2016","journal-title":"Ing. Ferrov."},{"key":"ref_17","first-page":"473","article-title":"Automatic identification of route conflict occurrences and their consequences","volume":"103","author":"Goverde","year":"2008","journal-title":"Comput. Railw. XI"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Albrecht, T., Goverde, R.M.P., Weeda, V.A., and Luipen, J.V. (September, January 31). Reconstruction of Train Trajectories from Track Occupation Data to Determine the Effects of a Driver Information System. Proceedings of the COMPRAIL 2006 Conference, Prague, Czech Republic.","DOI":"10.2495\/CR060211"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1016\/j.compenvurbsys.2009.07.008","article-title":"Revealing the physics of movement: Comparing the similarity of movement characteristics of different types of moving objects","volume":"33","author":"Dodge","year":"2009","journal-title":"Comput. Environ. Urban Syst."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1002\/navi.120","article-title":"Online motion mode recognition for portable navigation using low-cost sensors","volume":"62","author":"Elhoushi","year":"2016","journal-title":"Navigation"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"28","DOI":"10.3141\/2105-04","article-title":"Processing gps raw data without additional information","volume":"2105","author":"Schuessler","year":"2009","journal-title":"Transp. Res. Rec."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Liu, L., Wang, L., and Xie, X. (2008, January 21\u201325). Learning transportation mode from raw gps data for geographic applications on the web. Proceedings of the International Conference on World Wide Web, WWW 2008, Beijing, China.","DOI":"10.1145\/1367497.1367532"},{"key":"ref_23","unstructured":"Wagner, D.P. (1997). Lexington Area Travel Data Collection Test: Gps for Personal Travel Surveys, Battelle Transporation Division."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"58","DOI":"10.3141\/1660-08","article-title":"Analysis of global positioning system-based data collection methods for capturing multistop trip-chaining behavior","volume":"1660","author":"Yalamanchili","year":"1999","journal-title":"Transp. Res. Rec. J. Transp. Res. Board"},{"key":"ref_25","first-page":"147","article-title":"Global positioning system as data collection method for travel research","volume":"1719","author":"Draijer","year":"2000","journal-title":"Opt. Express"},{"key":"ref_26","unstructured":"Wolf, J.L. (2000). Using Gps Data Loggers to Replace Travel Diaries in the Collection of Travel Data. [Ph.D. Dissertation, Georgia Institute of Technology, School of Civil and Environmental Engineering]."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1689239.1689243","article-title":"Using mobile phones to determine transportation modes","volume":"6","author":"Reddy","year":"2010","journal-title":"ACM Trans. Sens. Netw."},{"key":"ref_28","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 ACM Sigspatial International Symposium on Advances in Geographic Information Systems, Acm-Gis 2011, Chicago, IL, USA.","DOI":"10.1145\/2093973.2093982"},{"key":"ref_29","unstructured":"Widhalm, P., Nitsche, P., and Br\u00e4ndle, N. (2012, January 11\u201315). Transport mode detection with realistic smartphone sensor data. Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), Tsukuba, Japan."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Das, R.D., and Winter, S. (2016). Detecting urban transport modes using a hybrid knowledge driven framework from gps trajectory. Int. J. Geo-Inf., 5.","DOI":"10.3390\/ijgi5110207"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Mardia, K.V., and Jupp, P.E. (2000). Directional Statistics, Wiley.","DOI":"10.1002\/9780470316979"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Li, Q., Chen, Y., Xie, X., and Ma, W.Y. (2008, January 21\u201324). Understanding mobility based on gps data. Proceedings of the International Conference on Ubiquitous Computing, Seoul, Korea.","DOI":"10.1145\/1409635.1409677"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1016\/j.ins.2013.02.030","article-title":"A time series forest for classification and feature extraction","volume":"239","author":"Deng","year":"2013","journal-title":"Inf. Sci."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wang, Y., and Zhao, W. (2017). An improved hybrid method for enhanced road feature selection in map generalization. Int. J. Geo-Inf., 6.","DOI":"10.3390\/ijgi6070196"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Qian, H., and Lu, Y. (2017). Simplifying gps trajectory data with enhanced spatial-temporal constraints. Int. J. Geo-Inf., 6.","DOI":"10.3390\/ijgi6110329"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Ma, C., Zhang, Y., Wang, A., Wang, Y., and Chen, G. (2018). Traffic command gesture recognition for virtual urban scenes based on a spatiotemporal convolution neural network. ISPRS Int. J. Geo-Inf., 7.","DOI":"10.3390\/ijgi7010037"},{"key":"ref_37","unstructured":"Gonzalez, P.A., Weinstein, J.S., Barbeau, S.J., Labrador, M.A., Winters, P.L., Georggi, N.L., and Perez, R. (2008, January 16\u201320). Automating mode detection using neural networks and assisted gps data collected using gps-enabled mobile phones. Proceedings of the 15th World Congress on Intelligent Transport Systems and ITS America\u2019s 2008 Annual Meeting, New York, NY, USA."},{"key":"ref_38","unstructured":"Maaten, L. (2009). Learning a parametric embedding by preserving local structure. Artificial Intelligence and Statistics, Springer."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Dabiri, Z., and Lang, S. (2018). Comparison of independent component analysis, principal component analysis, and minimum noise fraction transformation for tree species classification using apex hyperspectral imagery. ISPRS Int. J. Geo-Inf., 7.","DOI":"10.3390\/ijgi7120488"},{"key":"ref_40","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref_41","unstructured":"Xie, J., Girshick, R., and Farhadi, A. (2016, January 19\u201324). Unsupervised deep embedding for clustering analysis. Proceedings of the 33rd International Conference on Machine Learning, New York, NY, USA."},{"key":"ref_42","unstructured":"Makhzani, A., Shlens, J., Jaitly, N., and Goodfellow, I.J.C.S. (arXiv, 2015). Adversarial autoencoders, arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Mukherjee, S., Asnani, H., Lin, E., and Kannan, S. (arXiv, 2018). Clustergan: Latent space clustering in generative adversarial networks, arXiv.","DOI":"10.1609\/aaai.v33i01.33014610"},{"key":"ref_44","unstructured":"Springenberg, J.T. (arXiv, 2015). Unsupervised and semi-supervised learning with categorical generative adversarial networks, arXiv."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Lee, J.G., Han, J., and Li, X. (2008, January 7\u201312). Trajectory outlier detection: A partition-and-detect framework. Proceedings of the IEEE International Conference on Data Engineering, Cancun, Mexico.","DOI":"10.1109\/ICDE.2008.4497422"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Goldin, D.Q., and Kanellakis, P.C. (1995). On Similarity Queries for Time-Series Data: Constraint Specification and Implementation, Springer.","DOI":"10.1007\/3-540-60299-2_9"},{"key":"ref_47","unstructured":"Bergstra, J., and Bengio, Y. (2011, January 12\u201315). Algorithms for hyper-parameter optimization. Proceedings of the International Conference on Neural Information Processing Systems, Granada, Spain."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Hutter, F., Hoos, H.H., and Leyton-Brown, K. (2011, January 17\u201321). Sequential model-based optimization for general algorithm configuration. Proceedings of the Learning and Intelligent Optimization\u2014International Conference, Lion 5, Rome, Italy.","DOI":"10.1007\/978-3-642-25566-3_40"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Thornton, C., Hutter, F., Hoos, H.H., and Leytonbrown, K. (2013, January 11\u201314). Auto-weka: Combined selection and hyperparameter optimization of classification algorithms. Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining, Chicago, IL, USA.","DOI":"10.1145\/2487575.2487629"},{"key":"ref_50","first-page":"2951","article-title":"Practical bayesian optimization of machine learning algorithms","volume":"4","author":"Snoek","year":"2012","journal-title":"Adv. Neural Inf. Proc. Syst."},{"key":"ref_51","unstructured":"Goodfellow, I.J. (arXiv, 2016). Nips 2016 tutorial: Generative adversarial networks, arXiv."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"2761","DOI":"10.1109\/TIP.2010.2049235","article-title":"Image clustering using local discriminant models and global integration","volume":"19","author":"Yi","year":"2010","journal-title":"IEEE Trans. Image Proc."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1109\/TETC.2014.2330519","article-title":"A survey of clustering algorithms for big data: Taxonomy and empirical analysis","volume":"2","author":"Fahad","year":"2014","journal-title":"Emerg. Top. Comput. IEEE Trans."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Li, Y., and Yu, F. (2009, January 6\u20137). A new validity function for fuzzy clustering. Proceedings of the International Conference on Computational Intelligence and Natural Computing, Wuhan, China.","DOI":"10.1109\/CINC.2009.100"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"675","DOI":"10.5198\/jtlu.2017.954","article-title":"Analyzing spatiotemporal congestion pattern on urban roads based on taxi gps data","volume":"10","author":"Zhang","year":"2017","journal-title":"J. Transp. Land Use"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"1796","DOI":"10.1109\/TNN.2011.2162000","article-title":"Spectral embedded clustering: A framework for in-sample and out-of-sample spectral clustering","volume":"22","author":"Nie","year":"2011","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Hartigan, J.A., and Wong, M.A. (1979). A K-Means Clustering Algorithm: Algorithm as 136, Wiley.","DOI":"10.2307\/2346830"}],"container-title":["ISPRS International Journal of Geo-Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2220-9964\/8\/7\/294\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:01:37Z","timestamp":1760187697000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2220-9964\/8\/7\/294"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,27]]},"references-count":57,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2019,7]]}},"alternative-id":["ijgi8070294"],"URL":"https:\/\/doi.org\/10.3390\/ijgi8070294","relation":{},"ISSN":["2220-9964"],"issn-type":[{"type":"electronic","value":"2220-9964"}],"subject":[],"published":{"date-parts":[[2019,6,27]]}}}