{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T08:31:14Z","timestamp":1786696274429,"version":"build-2736575974"},"reference-count":41,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:00:00Z","timestamp":1786665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"German Federal Ministry of Transport","award":["01FV2035A"],"award-info":[{"award-number":["01FV2035A"]}]},{"award":["01FV2035A"],"award-info":[{"award-number":["01FV2035A"]}],"id":[{"id":"https:\/\/ror.org\/00e3ns026","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Cycling is increasingly promoted as part of sustainable transport strategies, but safety concerns remain an important barrier. Crash-based safety assessment is limited because crashes are reactive indicators and cycling crashes are often underreported. This study evaluates whether smartphone inertial sensor data can be used to detect selected potentially critical cycling manoeuvres that may support proactive safety screening. A two-stage workflow intended for possible future smartphone implementation was evaluated offline. In Stage 1, kinematic thresholds were applied to identify short candidate sensor windows when a high-dynamic manoeuvre was detected. In Stage 2, a machine learning classifier was applied to these candidate windows to classify the manoeuvre type and reduce false positives. The workflow was evaluated using three datasets collected in Germany from 10 riders, including controlled test-track manoeuvres and urban rides in Aachen and Bonn. The dataset included 148 hard-braking and 132 abrupt-swerving manoeuvres. In addition, 45 bicycle-only crash-like reference sequences were collected to compare low-speed impact-like signal patterns. In leave-one-dataset-out evaluation, the Support Vector Machine achieved mean precision\u2013recall areas under the curve of 0.954 for hard braking and 0.884 for abrupt swerving. The corresponding mean F1-scores were 0.924 and 0.876. The offline evaluation showed that smartphone sensor data can support the detection of selected high-dynamic cycling manoeuvres with good classification performance under controlled and semi-controlled conditions. However, most target manoeuvres were controlled or rider-initiated proxy manoeuvres rather than confirmed traffic conflicts. The results should therefore be interpreted as manoeuvre detection, not as direct crash-risk validation. In future naturalistic studies, the workflow could help identify candidate locations where cyclists frequently brake hard or swerve abruptly. These locations can then be prioritised for site inspections, video-based conflict analysis, or comparison with crash records.<\/jats:p>","DOI":"10.3390\/s26165138","type":"journal-article","created":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T08:08:29Z","timestamp":1786694909000},"page":"5138","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Smartphone-Based Detection of Potentially Critical Cycling Manoeuvres for Proactive Cycling Safety Assessment"],"prefix":"10.3390","volume":"26","author":[{"given":"J\u00f6rg","family":"Ehlers","sequence":"first","affiliation":[{"name":"Institute of Highway Engineering, RWTH Aachen University, 52074 Aachen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alvaro","family":"Garc\u00eda-Hern\u00e1ndez","sequence":"additional","affiliation":[{"name":"Institute of Highway Engineering, RWTH Aachen University, 52074 Aachen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arno","family":"Wolter","sequence":"additional","affiliation":[{"name":"Initiative for Safer Roads, Matthias-Gr\u00fcnewald-Str. 1\u20133, 53175 Bonn, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/S0967-070X(97)00011-5","article-title":"The UK National Cycling Strategy: Can Improved Facilities Meet the Targets?","volume":"4","author":"Wardman","year":"1997","journal-title":"Transp. Policy"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Khayesi, M. (2020). Vulnerable Road Users or Vulnerable Transport Planning?. Front. Sustain. Cities, 2.","DOI":"10.3389\/frsc.2020.00025"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1080\/01441647.2017.1340234","article-title":"Cycling towards a More Sustainable Transport Future","volume":"37","author":"Pucher","year":"2017","journal-title":"Transp. Rev."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Hauer, E. (2015). The Art of Regression Modeling in Road Safety, Springer International Publishing.","DOI":"10.1007\/978-3-319-12529-9"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1964","DOI":"10.1016\/j.aap.2008.07.007","article-title":"The Predictive Validity of Empirical Bayes Estimates of Road Safety","volume":"40","author":"Elvik","year":"2008","journal-title":"Accid. Anal. Prev."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2026","DOI":"10.1016\/j.injury.2011.10.016","article-title":"Bicycle Accidents\u2014Do We Only See the Tip of the Iceberg?","volume":"43","author":"Juhra","year":"2012","journal-title":"Injury"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1016\/S0001-4575(99)00007-X","article-title":"Motor Vehicle and Roadway Factors in Pedestrian and Bicyclist Injuries: An Examination Based on Emergency Department Data","volume":"31","author":"Stutts","year":"1999","journal-title":"Accid. Anal. Prev."},{"key":"ref_8","unstructured":"Laureshyn, A., and V\u00e1rhelyi, A. (2018). The Swedish Traffic Conflict Technique: Observer\u2019s Manual, Lund University."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Tarko, A.P. (2020). Traffic Conflicts as Crash Surrogates. Measuring Road Safety Using Surrogate Events, Elsevier.","DOI":"10.1016\/B978-0-12-810504-7.00003-3"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1016\/j.iatssr.2017.02.001","article-title":"Application of Proximal Surrogate Indicators for Safety Evaluation: A Review of Recent Developments and Research Needs","volume":"41","author":"Mahmud","year":"2017","journal-title":"IATSS Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1080\/01441647.2018.1442888","article-title":"In Search of Surrogate Safety Indicators for Vulnerable Road Users: A Review of Surrogate Safety Indicators","volume":"38","author":"Johnsson","year":"2018","journal-title":"Transp. Rev."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ehlers, J., Liebscher, A., Kemper, D., and Garcia-Hernandez, A. (2026). A Holistic Approach for Proactive Safety Assessments of Road Traffic Employing Crowdsourcing and Vehicle Kinematics. J. Traffic Transp. Eng. Engl. Ed., in press.","DOI":"10.1016\/j.jtte.2025.06.004"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/j.trf.2018.02.008","article-title":"Investigating Cycling Kinematics and Braking Maneuvers in the Real World: E-Bikes Make Cyclists Move Faster, Brake Harder, and Experience New Conflicts","volume":"54","author":"Dozza","year":"2018","journal-title":"Transp. Res. Part F Traffic Psychol. Behav."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.trf.2014.04.001","article-title":"Introducing Naturalistic Cycling Data: What Factors Influence Bicyclists\u2019 Safety in the Real World?","volume":"24","author":"Dozza","year":"2014","journal-title":"Transp. Res. Part F Traffic Psychol. Behav."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"100906","DOI":"10.1016\/j.tbs.2024.100906","article-title":"Assessing Bicycle Safety Risks Using Emerging Mobile Sensing Data","volume":"38","author":"Li","year":"2025","journal-title":"Travel. Behav. Soc."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1016\/j.jsr.2024.10.003","article-title":"Comparative Modeling of Risk Factors for Near-Crashes from Crowdsourced Bicycle Airbag Helmet Data and Crashes from Conventional Police Data","volume":"91","author":"Chou","year":"2024","journal-title":"J. Saf. Res."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"101197","DOI":"10.1016\/j.pmcj.2020.101197","article-title":"SimRa: Using Crowdsourcing to Identify near Miss Hotspots in Bicycle Traffic","volume":"67","author":"Karakaya","year":"2020","journal-title":"Pervasive Mob. Comput."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"101779","DOI":"10.1016\/j.pmcj.2023.101779","article-title":"CycleSense: Detecting near Miss Incidents in Bicycle Traffic from Mobile Motion Sensors","volume":"91","author":"Karakaya","year":"2023","journal-title":"Pervasive Mob. Comput."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Saleh, K., Grigorev, A., and Mihaita, A.-S. (2025). Cyclist Near-Miss Detection Using Lightweight Deep Temporal Neural Networks. Proceedings of the 2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), Gold Coast, Australia, 18\u201321 November 2025, IEEE.","DOI":"10.1109\/ITSC60802.2025.11423617"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"104794","DOI":"10.1016\/j.trc.2024.104794","article-title":"Two-Stream Video-Based Deep Learning Model for Crashes and near-Crashes","volume":"166","author":"Shi","year":"2024","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"21151","DOI":"10.1038\/s41598-024-70733-8","article-title":"Computer Vision and Statistical Insights into Cycling near Miss Dynamics","volume":"14","author":"Ibrahim","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"103330","DOI":"10.1016\/j.trf.2025.103330","article-title":"Digital Roads and Data Ethics: Exploring the Road Users\u2019 Perspective","volume":"115","author":"Song","year":"2025","journal-title":"Transp. Res. Part F Traffic Psychol. Behav."},{"key":"ref_23","unstructured":"Amundsen, F.H., and Hyden, C. (1997). Proceedings: First Workshop on Traffic Conflicts, Oslo, 1977, Lund Institute of Technology."},{"key":"ref_24","unstructured":"(2025, October 14). Android Developers Motion Sensors. Available online: https:\/\/developer.android.com\/develop\/sensors-and-location\/sensors\/sensors_motion."},{"key":"ref_25","unstructured":"(2025, October 14). RWTH Aachen University Phyphox Sensor Database. Available online: https:\/\/phyphox.org\/sensordb\/."},{"key":"ref_26","unstructured":"(2025, October 14). Android Developers Sensor Coordinate System. Available online: https:\/\/developer.android.com\/guide\/topics\/sensors\/sensors_overview#sensors-coords."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1016\/j.aap.2018.07.013","article-title":"Surrogate Safety and Network Screening: Modelling Crash Frequency Using GPS Travel Data and Latent Gaussian Spatial Models","volume":"120","author":"Stipancic","year":"2018","journal-title":"Accid. Anal. Prev."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"045009","DOI":"10.1088\/1361-6552\/aac05e","article-title":"Advanced Tools for Smartphone-Based Experiments: Phyphox","volume":"53","author":"Staacks","year":"2018","journal-title":"Phys. Educ."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"103949","DOI":"10.1016\/j.trc.2022.103949","article-title":"Smartphone-Based Hard-Braking Event Detection at Scale for Road Safety Services","volume":"146","author":"Liu","year":"2023","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"100804","DOI":"10.1016\/j.patter.2023.100804","article-title":"Leakage and the Reproducibility Crisis in Machine-Learning-Based Science","volume":"4","author":"Kapoor","year":"2023","journal-title":"Patterns"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Hozhabr Pour, H., Li, F., Wegmeth, L., Trense, C., Doniec, R., Grzegorzek, M., and Wism\u00fcller, R. (2022). A Machine Learning Framework for Automated Accident Detection Based on Multimodal Sensors in Cars. Sensors, 22.","DOI":"10.3390\/s22103634"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"James, G., Witten, D., Hastie, T., and Tibshirani, R. (2021). An Introduction to Statistical Learning: With Applications in R, Springer. [2nd ed.].","DOI":"10.1007\/978-1-0716-1418-1"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Kuhn, M., and Johnson, K. (2019). Feature Engineering and Selection: A Practical Approach for Predictive Models, Chapman and Hall\/CRC. [1st ed.].","DOI":"10.1201\/9781315108230"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Saito, T., and Rehmsmeier, M. (2015). The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0118432"},{"key":"ref_36","unstructured":"Kuhn, M., and Wickham, H. (2026, July 26). Tidymodels: A Collection of Packages for Modeling and Machine Learning Using Tidyverse Principles. Available online: https:\/\/www.tidymodels.org."},{"key":"ref_37","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_38","doi-asserted-by":"crossref","first-page":"1937","DOI":"10.1007\/s10462-020-09896-5","article-title":"A Comparative Analysis of Gradient Boosting Algorithms","volume":"54","year":"2021","journal-title":"Artif. Intell. Rev."},{"key":"ref_39","unstructured":"Caputo, B., Sim, K., Furesjo, F., and Smola, A. (2002, January 14). Appearance-Based Object Recognition Using SVMs: Which Kernel Should I Use?. Proceedings of the NIPS Workshop on Statistical Methods for Computational Experiments in Visual Processing and Computer Vision, Whistler, BC, Canada."},{"key":"ref_40","unstructured":"Jolliffe, I.T. (2002). Principal Component Analysis, Springer. [2nd ed.]."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.jsr.2023.09.010","article-title":"Deep Transfer Learning-Based Anomaly Detection for Cycling Safety","volume":"87","author":"Yaqoob","year":"2023","journal-title":"J. Saf. Res."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5138\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T08:11:56Z","timestamp":1786695116000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5138"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,14]]},"references-count":41,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26165138"],"URL":"https:\/\/doi.org\/10.3390\/s26165138","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,14]]}}}