{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T13:57:05Z","timestamp":1791295025892,"version":"4.1.0"},"reference-count":91,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T00:00:00Z","timestamp":1677542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"SBB"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Monitoring information can facilitate the condition assessment of railway infrastructure, via delivery of data that is informative on condition. A primary instance of such data is found in Axle Box Accelerations (ABAs), which track the dynamic vehicle\/track interaction. Such sensors have been installed on specialized monitoring trains, as well as on in-service On-Board Monitoring (OBM) vehicles across Europe, enabling a continuous assessment of railway track condition. However, ABA measurements come with uncertainties that stem from noise corrupt data and the non-linear rail\u2013wheel contact dynamics, as well as variations in environmental and operational conditions. These uncertainties pose a challenge for the condition assessment of rail welds through existing assessment tools. In this work, we use expert feedback as a complementary information source, which allows the narrowing down of these uncertainties, and, ultimately, refines assessment. Over the past year, with the support of the Swiss Federal Railways (SBB), we have assembled a database of expert evaluations on the condition of rail weld samples that have been diagnosed as critical via ABA monitoring. In this work, we fuse features derived from the ABA data with expert feedback, in order to refine defection of faulty (defect) welds. Three models are employed to this end; Binary Classification and Random Forest (RF) models, as well as a Bayesian Logistic Regression (BLR) scheme. The RF and BLR models proved superior to the Binary Classification model, while the BLR model further delivered a probability of prediction, quantifying the confidence we might attribute to the assigned labels. We explain that the classification task necessarily suffers high uncertainty, which is a result of faulty ground truth labels, and explain the value of continuously tracking the weld condition.<\/jats:p>","DOI":"10.3390\/s23052672","type":"journal-article","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T02:02:56Z","timestamp":1677636176000},"page":"2672","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Fusing Expert Knowledge with Monitoring Data for Condition Assessment of Railway Welds"],"prefix":"10.3390","volume":"23","author":[{"given":"Cyprien","family":"Hoelzl","sequence":"first","affiliation":[{"name":"Department of Civil, Environmental and Geomatic Engineering, ETH Z\u00fcrich, Stefano-Franscini Platz 5, 8093 Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8213-8323","authenticated-orcid":false,"given":"Giacomo","family":"Arcieri","sequence":"additional","affiliation":[{"name":"Department of Civil, Environmental and Geomatic Engineering, ETH Z\u00fcrich, Stefano-Franscini Platz 5, 8093 Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lucian","family":"Ancu","sequence":"additional","affiliation":[{"name":"Metrology Department, Swiss Federal Railways (SBB), 3018 Bern, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stanislaw","family":"Banaszak","sequence":"additional","affiliation":[{"name":"Metrology Department, Swiss Federal Railways (SBB), 3018 Bern, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aurelia","family":"Kollros","sequence":"additional","affiliation":[{"name":"Metrology Department, Swiss Federal Railways (SBB), 3018 Bern, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4671-1962","authenticated-orcid":false,"given":"Vasilis","family":"Dertimanis","sequence":"additional","affiliation":[{"name":"Department of Civil, Environmental and Geomatic Engineering, ETH Z\u00fcrich, Stefano-Franscini Platz 5, 8093 Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6870-240X","authenticated-orcid":false,"given":"Eleni","family":"Chatzi","sequence":"additional","affiliation":[{"name":"Department of Civil, Environmental and Geomatic Engineering, ETH Z\u00fcrich, Stefano-Franscini Platz 5, 8093 Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,2,28]]},"reference":[{"key":"ref_1","first-page":"214","article-title":"Monitoring und Zustandsorientierte Instandhaltung von Schienenfahrzeugen und -fahrweg mittels Mustererkennung in Ereignisdaten","volume":"140","author":"Linke","year":"2016","journal-title":"Tag. Mod. Schienenfahrzeuge"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"15543","DOI":"10.1109\/ACCESS.2020.2967436","article-title":"Requirements for Big Data Adoption for Railway Asset Management","volume":"8","author":"Mcmahon","year":"2020","journal-title":"IEEE Access"},{"key":"ref_3","unstructured":"Schweizerische Bundesbahnen AG (2023, January 17). SBB Gesch\u00e4ftsbericht 2021. Available online: https:\/\/company.sbb.ch\/content\/dam\/internet\/corporate\/de\/medien\/publikationen\/geschaeftsbericht\/SBB-Geschaeftsbericht-2021.pdf.sbbdownload.pdf."},{"key":"ref_4","unstructured":"Hoelzl, C., Dertimanis, V., Landgraf, M., Ancu, L., Zurkirchen, M., and Chatzi, E. (2022). The Rise of Smart Cities, Elsevier."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1177\/1475921705049764","article-title":"Structural Health Monitoring in the Railway Industry: A Review","volume":"4","author":"Barke","year":"2005","journal-title":"Struct. Health Monit."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1007\/s10712-019-09544-w","article-title":"Non-destructive Assessment and Health Monitoring of Railway Infrastructures","volume":"41","author":"Artagan","year":"2019","journal-title":"Surv. Geophys."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Yan, T.H., De Almeida Costa, M., and Corman, F. (2023, January 8\u201312). Developing and extending status prediction models for railway tracks based on on-board monitoring data. Proceedings of the 102nd Annual Meeting of the Transportation Research Board (TRB 2023), Washington, DC, USA. OMISM (MI Mobility Initiative Project).","DOI":"10.1177\/03611981221150245"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Xie, J., Huang, J., Zeng, C., Jiang, S.H., and Podlich, N. (2020). Systematic literature review on data-driven models for predictive maintenance of railway track: Implications in geotechnical engineering. Geosciences, 10.","DOI":"10.3390\/geosciences10110425"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"128218","DOI":"10.1016\/j.conbuildmat.2022.128218","article-title":"Railway ballast material selection and evaluation: A review","volume":"344","author":"Guo","year":"2022","journal-title":"Constr. Build. Mater."},{"key":"ref_10","unstructured":"Group V\u00f6V (2006). Schweissarbeiten an Schienen und Weichenbauteilen, V\u00f6V."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"103746","DOI":"10.1109\/ACCESS.2020.2999385","article-title":"Rail Weld Defect Prediction and Related Condition-Based Maintenance","volume":"8","author":"Yao","year":"2020","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.trc.2019.07.020","article-title":"Data-driven predictive maintenance scheduling policies for railways","volume":"107","author":"Gerum","year":"2019","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"106516","DOI":"10.1016\/j.ijfatigue.2021.106516","article-title":"Fatigue fracture and fatigue life assessment of railway wheel using non-linear model for fatigue crack growth","volume":"153","author":"Nejad","year":"2021","journal-title":"Int. J. Fatigue"},{"key":"ref_14","unstructured":"(2002). Rail Defects, International Union of Railways. [4th ed.]. UIC Code 712."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"203139","DOI":"10.1016\/j.wear.2019.203139","article-title":"Understanding and treatment of squat defects in a railway network","volume":"442\u2013443","author":"Zhu","year":"2020","journal-title":"Wear"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"106280","DOI":"10.1016\/j.ijfatigue.2021.106280","article-title":"Comparison of fatigue crack growth rate: Pearlitic rail versus bainitic rail","volume":"149","author":"Lesiuk","year":"2021","journal-title":"Int. J. Fatigue"},{"key":"ref_17","first-page":"42","article-title":"K\u00fcnstliche Intelligenz auf Schienen","volume":"9","author":"Schmid","year":"2019","journal-title":"Bulletin"},{"key":"ref_18","unstructured":"Liu, Y., and Wei, X. (2018). Lecture Notes in Electrical Engineering, Springer."},{"key":"ref_19","first-page":"1","article-title":"Smartphone\u2019s Sensing Capabilities for On-Board Railway Track Monitoring: Structural Performance and Geometrical Degradation Assessment","volume":"2019","author":"Fortunato","year":"2019","journal-title":"Adv. Civ. Eng."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Malekjafarian, A., OBrien, E., Quirke, P., and Bowe, C. (2019). Railway Track Monitoring Using Train Measurements: An Experimental Case Study. Appl. Sci., 9.","DOI":"10.3390\/app9224859"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1038\/s41597-019-0148-9","article-title":"Dynamic responses, GPS positions and environmental conditions of two light rail vehicles in Pittsburgh","volume":"6","author":"Liu","year":"2019","journal-title":"Sci. Data"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"15185","DOI":"10.1109\/JSEN.2020.3011132","article-title":"Ultra-Low Power Sensor Node for On-Board Railway Wagon Monitoring","volume":"20","author":"Bernal","year":"2020","journal-title":"IEEE Sensors J."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3995","DOI":"10.1109\/TITS.2020.3038319","article-title":"Solar Wireless Sensor Nodes for Condition Monitoring of Freight Trains","volume":"23","author":"Cii","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"012087","DOI":"10.1088\/1742-6596\/2369\/1\/012087","article-title":"Small excitation self-powered sensing energy harvester for rail traffic condition monitoring","volume":"2369","author":"Qin","year":"2022","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_25","unstructured":"SBB\/CFF\/FFS (2022). Regelwerk Technik Eisenbahn RTE, SBB."},{"key":"ref_26","unstructured":"Hoelzl, C.A., Dertimanis, V., Ancu, L., Kollros, A., and Chatzi, E. (2022). Vold-Kalman Filter Order tracking of Axle Box Accelerations for Railway Stiffness Assessment. arXiv."},{"key":"ref_27","first-page":"167","article-title":"On-Board monitoring of rail roughness via axle box accelerations of revenue trains with uncertain dynamics","volume":"3","author":"Dertimanis","year":"2019","journal-title":"Model Valid. Uncertain. Quantif."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1170","DOI":"10.1080\/00423114.2020.1850808","article-title":"Condition monitoring of railway track from car-body vibration using time\u2013frequency analysis","volume":"60","author":"Tsunashima","year":"2020","journal-title":"Veh. Syst. Dyn."},{"key":"ref_29","unstructured":"Sas, P., and Bergen, B. (2008, January 15\u201317). An investigation of the possibility to use axle box acceleration for condition monitoring of welds. Proceedings of the 2008 International Conference on Noise and Vibration Engineering, ISMA 2008, Leuven, Belgium."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"An, B., Wang, P., Xu, J., Chen, R., and Cui, D. (2017). Observation and Simulation of Axle Box Acceleration in the Presence of Rail Weld in High-Speed Railway. Appl. Sci., 7.","DOI":"10.3390\/app7121259"},{"key":"ref_31","unstructured":"Esveld, C., and Steenbergen, M. (2005, January 14\u201316). Force-based assessment of weld geometry. Proceedings of the 8th International Heavy Haul Conference, Rio de Janeiro, Brazil."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1243\/09544097JRRT38","article-title":"Rail weld geometry and assessment concepts","volume":"220","author":"Steenbergen","year":"2006","journal-title":"Proc. Inst. Mech. Eng. Part F J. Rail Rapid Transit"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"4385","DOI":"10.1109\/TIE.2015.2389761","article-title":"Improvements in Axle Box Acceleration Measurements for the Detection of Light Squats in Railway Infrastructure","volume":"62","author":"Li","year":"2015","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_34","unstructured":"Li, S., N\u00fa\u00f1ez, A., Li, Z., and Dollevoet, R. (2015). ASME\/IEEE Joint Rail Conference, American Society of Mechanical Engineers."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Cho, H., and Park, J. (2021). Study of Rail Squat Characteristics through Analysis of Train Axle Box Acceleration Frequency. Appl. Sci., 11.","DOI":"10.3390\/app11157022"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Ng, A.K., Martua, L., and Sun, G. (2019, January 5\u20137). Dynamic Modelling and Acceleration Signal Analysis of Rail Surface Defects for Enhanced Rail Condition Monitoring and Diagnosis. Proceedings of the 2019 4th International Conference on Intelligent Transportation Engineering (ICITE), Singapore.","DOI":"10.1109\/ICITE.2019.8880246"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Zuo, Y., Thiery, F., Chandran, P., Odelius, J., and Rantatalo, M. (2022). Squat Detection of Railway Switches and Crossings Using Wavelets and Isolation Forest. Sensors, 22.","DOI":"10.3390\/s22176357"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1167","DOI":"10.1080\/00423114.2019.1610181","article-title":"Squats and corrugation detection of railway track based on time-frequency analysis by using bogie acceleration measurements","volume":"58","author":"Wei","year":"2019","journal-title":"Veh. Syst. Dyn."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1002\/qre.1634","article-title":"Data Analysis for Condition-Based Railway Infrastructure Maintenance","volume":"31","author":"Bergquist","year":"2014","journal-title":"Qual. Reliab. Eng. Int."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1308","DOI":"10.1080\/15732479.2019.1615963","article-title":"Development of a tram track degradation prediction model based on the acceleration data","volume":"15","author":"Falamarzi","year":"2019","journal-title":"Struct. Infrastruct. Eng."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1757","DOI":"10.1177\/14759217211044492","article-title":"Railway defect detection based on track geometry using supervised and unsupervised machine learning","volume":"21","author":"Sresakoolchai","year":"2022","journal-title":"Struct. Health Monit."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Yang, C., Sun, Y., Ladubec, C., and Liu, Y. (2021). Developing Machine Learning-Based Models for Railway Inspection. Appl. Sci., 11.","DOI":"10.3390\/app11010013"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Bulnes, F. (2022). Recent Advances in Wavelet Transforms and Their Applications, IntechOpen. Chapter 6.","DOI":"10.5772\/intechopen.97926"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2022\/4911952","article-title":"An Index for Rail Weld Health Assessment in Urban Metro Using In-Service Train","volume":"2022","author":"Shadfar","year":"2022","journal-title":"Math. Probl. Eng."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Xiao, B., Mao, X., Liu, J., Niu, L., Xu, X., and Zhang, M. (2021, January 15\u201317). An Improved Marginal Index Method to Diagnose Poor Welded Joints of Heavy-haul Railway. Proceedings of the 2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing), Nanjing, China.","DOI":"10.1109\/PHM-Nanjing52125.2021.9612800"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2022\/3226253","article-title":"Research on Wheel-Rail Local Impact Identification Based on Axle Box Acceleration","volume":"2022","author":"Ji","year":"2022","journal-title":"Shock Vib."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Pappaterra, M.J., Flammini, F., Vittorini, V., and Be\u0161inovi\u0107, N. (2021). A Systematic Review of Artificial Intelligence Public Datasets for Railway Applications. Infrastructures, 6.","DOI":"10.3390\/infrastructures6100136"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Liu, J., Chen, S., Lederman, G., Kramer, D.B., Noh, H.Y., Bielak, J., Garrett, J.H., Kovacevic, J., and Berges, M. (2018). The DR-Train Dataset: Dynamic Responses, GPS Positions and Environmental Conditions of Two Light Rail Vehicles in Pittsburgh, Technologies for Safe and Efficient Transportation University Transportation Center.","DOI":"10.1038\/s41597-019-0148-9"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"04019016","DOI":"10.1061\/AJRUA6.0001024","article-title":"Machine Learning Ensembles and Rail Defects Prediction: Multilayer Stacking Methodology","volume":"5","author":"Lasisi","year":"2019","journal-title":"Asce-Asme J. Risk Uncertain. Eng. Syst. Part A Civ. Eng."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Oh, K., Yoo, M., Jin, N., Ko, J., Seo, J., Joo, H., and Ko, M. (2022). A Review of Deep Learning Applications for Railway Safety. Appl. Sci., 12.","DOI":"10.3390\/app122010572"},{"key":"ref_51","first-page":"91","article-title":"Classification of Rail Irregularities from Axle Box Accelerations Using Random Forests and Convolutional Neural Networks","volume":"Volume 9","author":"Hoelzl","year":"2022","journal-title":"Data Science in Engineering"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"104906","DOI":"10.1016\/j.engfailanal.2020.104906","article-title":"Vibration-based damage detection of rail fastener clip using convolutional neural network: Experiment and simulation","volume":"119","author":"Yuan","year":"2021","journal-title":"Eng. Fail. Anal."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"341","DOI":"10.3390\/vibration4020022","article-title":"Detection and Severity Evaluation of Combined Rail Defects Using Deep Learning","volume":"4","author":"Sresakoolchai","year":"2021","journal-title":"Vibration"},{"key":"ref_54","first-page":"1","article-title":"A Comprehensive Detection System for Track Geometry Using Fused Vision and Inertia","volume":"70","author":"Peng","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_55","unstructured":"Hoelzl, C.A., Dertimanis, V., Kollros, A., Ancu, L., and Chatzi, E. (2023). European Workshop on Structural Health Monitoring, Springer International Publishing."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"108760","DOI":"10.1016\/j.apacoust.2022.108760","article-title":"Model-based estimation of rail roughness from axle box acceleration","volume":"193","author":"Pieringer","year":"2022","journal-title":"Appl. Acoust."},{"key":"ref_57","first-page":"251","article-title":"A semi-supervised interpretable machine learning framework for Sensor Fault detection","volume":"29","author":"Martakis","year":"2021","journal-title":"Smart Struct. Syst. Int. J."},{"key":"ref_58","unstructured":"Rees, D. (2020). Essential Statistics, Springer."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1016\/S0022-460X(03)00736-3","article-title":"A double tuned rail damper\u2014Increased damping at the two first pinned\u2013pinned frequencies","volume":"267","author":"Maes","year":"2003","journal-title":"J. Sound Vib."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"1421","DOI":"10.1080\/00423114.2018.1513538","article-title":"Implementation of Timoshenko element local deflection for vertical track modelling","volume":"57","author":"Blanco","year":"2019","journal-title":"Veh. Syst. Dyn."},{"key":"ref_61","doi-asserted-by":"crossref","unstructured":"Goswami, J.C., and Chan, A.K. (2010). Fundamentals of Wavelets: Theory, Algorithms, and Applications, John Wiley & Sons. [2nd ed.].","DOI":"10.1002\/9780470926994"},{"key":"ref_62","doi-asserted-by":"crossref","unstructured":"Gonzalez, R.C. (2009). Digital Image Processing, Pearson Education.","DOI":"10.1117\/1.3115362"},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"108556","DOI":"10.1016\/j.measurement.2020.108556","article-title":"Study of loaded versus unloaded measurements in railway track inspection","volume":"169","author":"Wang","year":"2020","journal-title":"Measurement"},{"key":"ref_64","unstructured":"CEN (2019). EN 13848-1, Railway Applications. Track. Track Geometry Quality. Characterization of Track Geometry, BSI."},{"key":"ref_65","doi-asserted-by":"crossref","first-page":"555","DOI":"10.3846\/16484142.2017.1342101","article-title":"Condition monitoring of railway track systems by using acceleration signals on wheelset axle-boxes","volume":"33","author":"Chudzikiewicz","year":"2017","journal-title":"Transport"},{"key":"ref_66","doi-asserted-by":"crossref","first-page":"2841","DOI":"10.1016\/j.cma.2005.07.006","article-title":"Modelling ballast behaviour under dynamic loading. Part 1: A 2D polygonal discrete element method approach","volume":"195","author":"Saussine","year":"2006","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"ref_67","first-page":"1","article-title":"Railway track stiffness variations\u2014Consequences and countermeasures","volume":"8","author":"Dahlberg","year":"2010","journal-title":"Int. J. Civ. Eng."},{"key":"ref_68","doi-asserted-by":"crossref","first-page":"604053","DOI":"10.3389\/fphy.2020.604053","article-title":"The Three Extreme Value Distributions: An Introductory Review","volume":"8","author":"Hansen","year":"2020","journal-title":"Front. Phys."},{"key":"ref_69","doi-asserted-by":"crossref","first-page":"2093","DOI":"10.1029\/2019GL081967","article-title":"Added Value of Large Ensemble Simulations for Assessing Extreme River Discharge in a 2 \u00b0C Warmer World","volume":"46","author":"Wanders","year":"2019","journal-title":"Geophys. Res. Lett."},{"key":"ref_70","doi-asserted-by":"crossref","unstructured":"Coles, S. (2001). An Introduction to Statistical Modeling of Extreme Values, Springer.","DOI":"10.1007\/978-1-4471-3675-0"},{"key":"ref_71","unstructured":"Chatzi, E., Abdallah, I., Tatsis, K., Osmani, S., and Robles, I. (2022). Bridge Safety, Maintenance, Management, Life-Cycle, Resilience and Sustainability, CRC Press."},{"key":"ref_72","unstructured":"Abdallah, I., Dertimanis, V., Mylonas, H., Tatsis, K., Chatzi, E., Dervili, N., Worden, K., and Maguire, E. (2018). Safety and Reliability\u2013Safe Societies in a Changing World, CRC Press."},{"key":"ref_73","doi-asserted-by":"crossref","first-page":"2225","DOI":"10.1016\/j.patrec.2010.03.014","article-title":"Variable selection using random forests","volume":"31","author":"Genuer","year":"2010","journal-title":"Pattern Recognit. Lett."},{"key":"ref_74","doi-asserted-by":"crossref","first-page":"106686","DOI":"10.1016\/j.ymssp.2020.106686","article-title":"Gaussian process models for mitigation of operational variability in the structural health monitoring of wind turbines","volume":"142","author":"Chatzi","year":"2020","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_75","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_76","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","article-title":"A mathematical theory of communication","volume":"27","author":"Shannon","year":"1948","journal-title":"Bell Syst. Tech. J."},{"key":"ref_77","unstructured":"Bishop, C.M., and Nasrabadi, N.M. (2006). Pattern Recognition and Machine Learning, Springer."},{"key":"ref_78","first-page":"1593","article-title":"The No-U-Turn sampler: Adaptively setting path lengths in Hamiltonian Monte Carlo","volume":"15","author":"Hoffman","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_79","doi-asserted-by":"crossref","unstructured":"Salvatier, J., Wiecki, T., and Fonnesbeck, C. (2015). Probabilistic Programming in Python using PyMC. arXiv.","DOI":"10.7287\/peerj.preprints.1686v1"},{"key":"ref_80","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1177\/0954409714523583","article-title":"Parametric study of axle box acceleration at squats","volume":"229","author":"Molodova","year":"2015","journal-title":"Proc. Inst. Mech. Eng. Part F J. Rail Rapid Transit"},{"key":"ref_81","unstructured":"SBB (2019). Surveillance of Installations, ZMON, SBB."},{"key":"ref_82","doi-asserted-by":"crossref","unstructured":"Gong, W., Akbar, M.F., Jawad, G.N., Mohamed, M.F.P., and Wahab, M.N.A. (2022). Nondestructive Testing Technologies for Rail Inspection: A Review. Coatings, 12.","DOI":"10.3390\/coatings12111790"},{"key":"ref_83","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.gltp.2022.04.020","article-title":"A review: Data pre-processing and data augmentation techniques","volume":"3","author":"Maharana","year":"2022","journal-title":"Glob. Transitions Proc."},{"key":"ref_84","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_85","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5121\/ijdkp.2015.5201","article-title":"A Review on Evaluation Metrics for Data Classification Evaluations","volume":"5","author":"Hossin","year":"2015","journal-title":"Int. J. Data Min. Knowl. Manag. Process"},{"key":"ref_86","doi-asserted-by":"crossref","unstructured":"McElreath, R. (2020). Statistical Rethinking: A Bayesian Course with Examples in R and Stan, Chapman and Hall\/CRC.","DOI":"10.1201\/9780429029608"},{"key":"ref_87","unstructured":"Gal, Y., and Ghahramani, Z. (2016, January 20\u201322). Dropout as a bayesian approximation: Representing model uncertainty in deep learning. Proceedings of the International Conference on Machine Learning, PMLR, New York, NY, USA."},{"key":"ref_88","first-page":"5580","article-title":"What uncertainties do we need in bayesian deep learning for computer vision?","volume":"30","author":"Kendall","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_89","first-page":"41","article-title":"SwissTAMP\u2014Big data in proactive track asset management","volume":"2","author":"Nerlich","year":"2016","journal-title":"Eur. Railw. Rev."},{"key":"ref_90","first-page":"1373","article-title":"Confident Learning: Estimating Uncertainty in Dataset Labels","volume":"70","author":"Northcutt","year":"2021","journal-title":"J. Artif. Int. Res."},{"key":"ref_91","unstructured":"Arcieri, G., Hoelzl, C., Schwery, O., Straub, D., Papakonstantinou, K.G., and Chatzi, E. (2022). Bridging POMDPs and Bayesian decision making for robust maintenance planning under model uncertainty: An application to railway systems. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/5\/2672\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:44:31Z","timestamp":1760121871000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/5\/2672"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,28]]},"references-count":91,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2023,3]]}},"alternative-id":["s23052672"],"URL":"https:\/\/doi.org\/10.3390\/s23052672","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,28]]}}}