{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,19]],"date-time":"2026-09-19T14:12:47Z","timestamp":1789827167836,"version":"4.0.1"},"reference-count":38,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T00:00:00Z","timestamp":1740614400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Slips, trips, and falls (STFs) are a major occupational hazard that contributes significantly to workplace injuries and the associated financial costs. The application of traditional fall detection techniques in the real world is limited because they are usually based on simulated falls. By using kinematic data from real near-fall incidents that occurred in physically demanding work environments, this study overcomes this limitation and improves the ecological validity of fall detection algorithms. This study systematically tests several machine-learning architectures for near-fall detection using the Prev-Fall dataset, which consists of high-resolution inertial measurement unit (IMU) data from 110 workers. Convolutional neural networks (CNNs), residual networks (ResNets), convolutional long short-term memory networks (convLSTMs), and InceptionTime models were trained and evaluated over a range of temporal window lengths using a neural architecture search. High-validation F1 scores were achieved by the best-performing models, particularly CNNs and InceptionTime, indicating their effectiveness in near-fall classification. The need for more contextual variables to increase robustness was highlighted by recurrent false positives found in subsequent tests on previously unobserved occupational data, especially during biomechanically demanding activities such as bending and squatting. Nevertheless, our findings suggest the applicability of machine-learning-based STF prevention systems for workplace safety monitoring and, more generally, applications in fall mitigation. To further improve the accuracy and generalizability of the system, future research should investigate multimodal data integration and improved classification techniques.<\/jats:p>","DOI":"10.3390\/s25051468","type":"journal-article","created":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T02:48:37Z","timestamp":1740710917000},"page":"1468","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Enhancing Slip, Trip, and Fall Prevention: Real-World Near-Fall Detection with Advanced Machine Learning Technique"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1789-8593","authenticated-orcid":false,"given":"Moritz","family":"Schneider","sequence":"first","affiliation":[{"name":"Institute for Occupational Safety and Health of the German Social Accident Insurance (IFA), 53757 Sankt Augustin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Seeser-Reich","sequence":"additional","affiliation":[{"name":"Institute for Occupational Safety and Health of the German Social Accident Insurance (IFA), 53757 Sankt Augustin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Armin","family":"Fiedler","sequence":"additional","affiliation":[{"name":"RheinAhrCampus, Koblenz University of Applied Sciences, 53424 Remagen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8325-6324","authenticated-orcid":false,"given":"Udo","family":"Frese","sequence":"additional","affiliation":[{"name":"German Research Center for Artificial Intelligence (DFKI), 28359 Bremen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,2,27]]},"reference":[{"key":"ref_1","unstructured":"Deutsche Gesetzliche Unfallversicherung e.V (2024). Statistik Arbeitsunfallgeschehen 2023, Deutsche Gesetzliche Unfallversicherung e.V."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Wang, S., Miranda, F., Wang, Y., Rasheed, R., and Bhatt, T. (2022). Near-Fall Detection in Unexpected Slips during Over-Ground Locomotion with Body-Worn Sensors among Older Adults. Sensors, 22.","DOI":"10.3390\/s22093334"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Nikolov, I., Liu, J., and Moeslund, T. (2022). Imitating Emergencies: Generating Thermal Surveillance Fall Data Using Low-Cost Human-like Dolls. Sensors, 22.","DOI":"10.3390\/s22030825"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Hsu, W.-W., Guo, J.-M., Chen, C.-Y., and Chang, Y.-C. (2022). Fall Detection with the Spatial-Temporal Correlation Encoded by a Sequence-to-Sequence Denoised GAN. Sensors, 22.","DOI":"10.3390\/s22114194"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Rahemtulla, Z., Turner, A., Oliveira, C., Kaner, J., Dias, T., and Hughes-Riley, T. (2023). The Design and Engineering of a Fall and Near-Fall Detection Electronic Textile. Materials, 16.","DOI":"10.3390\/ma16051920"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Schumann, P., Scholz, M., Trentzsch, K., Jochim, T., \u015aliwi\u0144ski, G., Malberg, H., and Ziemssen, T. (2022). Detection of Fall Risk in Multiple Sclerosis by Gait Analysis\u2014An Innovative Approach Using Feature Selection Ensemble and Machine Learning Algorithms. Brain Sci., 12.","DOI":"10.3390\/brainsci12111477"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Schneider, M., Reich, K., Hartmann, U., Hermanns, I., Kaufmann, M., Kluge, A., Fiedler, A., Frese, U., and Ellegast, R. (2024). Acquisition of Data on Kinematic Responses to Unpredictable Gait Perturbations: Collection and Quality Assurance of Data for Use in Machine Learning Algorithms for (Near-)Fall Detection. Sensors, 24.","DOI":"10.3390\/s24165381"},{"key":"ref_8","first-page":"2055668317732945","article-title":"Falls are unintentional: Studying simulations is a waste of faking time","volume":"4","author":"Stack","year":"2017","journal-title":"J. Rehabil. Assist. Technol. Eng."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Sucerquia, A., L\u00f3pez, J.D., and Vargas-Bonilla, J.F. (2017). SisFall: A Fall and Movement Dataset. Sensors, 17.","DOI":"10.3390\/s17010198"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Mart\u00ednez-Villase\u00f1or, L., Ponce, H., Brieva, J., Moya-Albor, E., N\u00fa\u00f1ez-Mart\u00ednez, J., and Pe\u00f1afort-Asturiano, C. (2019). UP-Fall Detection Dataset: A Multimodal Approach. Sensors, 19.","DOI":"10.3390\/s19091988"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Yu, X., Jang, J., and Xiong, S. (2021). A Large-Scale Open Motion Dataset (KFall) and Benchmark Algorithms for Detecting Pre-impact Fall of the Elderly Using Wearable Inertial Sensors. Front. Aging Neurosci., 13.","DOI":"10.3389\/fnagi.2021.692865"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ramachandran, A., and Karuppiah, A. (2020). A Survey on Recent Advances in Wearable Fall Detection Systems. BioMed Res. Int., 2020.","DOI":"10.1155\/2020\/2167160"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Wang, X., Ellul, J., and Azzopardi, G. (2020). Elderly Fall Detection Systems: A Literature Survey. Front. Robot. AI, 7.","DOI":"10.3389\/frobt.2020.00071"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Hellmers, S., Krey, E., Gashi, A., Koschate, J., Schmidt, L., Stuckenschneider, T., Hein, A., and Zieschang, T. (2023). Comparison of machine learning approaches for near-fall-detection with motion sensors. Front. Digit. Health, 5.","DOI":"10.3389\/fdgth.2023.1223845"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Schneider, M., Weber, A., Kaufmann, M., Kluge, A., Hartmann, U., Karamanidis, K., and Ellegast, R. (2023). Generation of Consistent Slip, Trip and Fall Kinematic Data via Instability Detection and Recovery Performance Analysis for Use in Machine Learning Algorithms for (Near) Fall Detection. Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management-14th International Conference, Springer Nature. Volume 14029 of Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-031-35748-0_22"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"107937","DOI":"10.1016\/j.engappai.2024.107937","article-title":"Transformer-based fall detection in videos","volume":"132","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_17","unstructured":"Rodriguez, J., Mercuri, M., Karsmakers, P., Soh, P.J., Leroux, P., and Schreurs, D. (2016, January 19\u201320). Automatic fall detector based on sliding window principle. Proceedings of the 34th WIC Symposium on Information Theory in the Benelux and the Third joint WIC\/IEEE SP Symposium on Information Theory and Signal Processing in the Benelux, Louvain-la-Neuve, Belgium."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ntanasis, P., Pippa, E., \u00d6zdemir, A.T., Barshan, B., and Megalooikonomou, V. (2017). Investigation of Sensor Placement for Accurate Fall Detection. Wireless Mobile Communication and Healthcare, 6th International Conference, MobiHealth 2016, Milan, Italy, 14\u201316 November 2016, Proceedings 6, Springer International Publishing.","DOI":"10.1007\/978-3-319-58877-3_30"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Ribeiro, N.F., Pereira, A., Figueiredo, J., Afonso, J.A., and Santos, C.P. (2022). A Machine Learning Approach for Near-Fall Detection Based on Inertial and Force Data While Using a Conventional Rollator. International Conference on NeuroRehabilitation, Springer International Publishing.","DOI":"10.1007\/978-3-030-70316-5_55"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Safira, S.M., Gunawan, P.H., Kurniawan, W.Y., Putra, I.G.K.K., Reganata, G.P., Patrianingsih, N.K.W., Dharma, I.G.W.S., Sugianta, I.K.A., and Udhayana, K.F.R. (2023, January 13\u201315). Comparative Analysis of the K-Nearest Neighbor Method and Support Vector Machine in Human Fall Detection. Proceedings of the 2023 3rd International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA), Denpasar, Bali, Indonesia.","DOI":"10.1109\/ICICyTA60173.2023.10428126"},{"key":"ref_21","first-page":"76","article-title":"Machine learning classifiers for fall detection leveraging LoRa communication network","volume":"13","author":"Reddy","year":"2024","journal-title":"Int. J. Reconfigurable Embed. Syst."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1016\/j.gaitpost.2013.07.123","article-title":"Introducing a new definition of a near fall: Intra-rater and inter-rater reliability","volume":"39","author":"Maidan","year":"2013","journal-title":"Gait Posture"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Yu, X., Park, S., Kim, D., Kim, E., Kim, J., Kim, W., An, Y., and Xiong, S. (2023). A practical wearable fall detection system based on tiny convolutional neural networks. Biomed. Signal Process. Control, 86.","DOI":"10.1016\/j.bspc.2023.105325"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2385","DOI":"10.1109\/TNSRE.2022.3199068","article-title":"Deep Learning-Based Near-Fall Detection Algorithm for Fall Risk Monitoring System Using a Single Inertial Measurement Unit","volume":"30","author":"Choi","year":"2022","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ramanathan, A., and McDermott, J. (2021, January 18\u201322). Fall detection with accelerometer data using Residual Networks adapted to multi-variate time series classification. Proceedings of the 2021 International Joint Conference on Neural Networks (IJCNN), Shenzhen, China.","DOI":"10.1109\/IJCNN52387.2021.9533670"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1936","DOI":"10.1007\/s10618-020-00710-y","article-title":"InceptionTime: Finding AlexNet for time series classification","volume":"34","author":"Fawaz","year":"2020","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"169","DOI":"10.3233\/AIC-170729","article-title":"Linear discriminant analysis: A detailed tutorial","volume":"30","author":"Tharwat","year":"2017","journal-title":"AI Commun."},{"key":"ref_29","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_30","unstructured":"Gupta, N., Patel, H., Afzal, S., Panwar, N., Mittal, R.S., Guttula, S., Jain, A., Nagalapatti, L., Mehta, S., and Hans, S. (2021). Data Quality Toolkit: Automatic assessment of data quality and remediation for machine learning datasets. arXiv."},{"key":"ref_31","first-page":"5","article-title":"The precise effect of multicollinearity on classification prediction","volume":"40","author":"Lieberman","year":"2014","journal-title":"Mult. Linear Regres. Viewp."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1016\/j.inffus.2022.08.017","article-title":"A unifying view of class overlap and imbalance: Key concepts, multi-view panorama, and open avenues for research","volume":"89","author":"Santos","year":"2023","journal-title":"Inf. Fusion"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1785\/gssrl.81.3.530","article-title":"ObsPy: A Python toolbox for seismology","volume":"81","author":"Beyreuther","year":"2010","journal-title":"Seism. Res. Lett."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"100548","DOI":"10.1016\/j.softx.2020.100548","article-title":"Mcfly: Automated deep learning on time series","volume":"12","author":"Meijer","year":"2020","journal-title":"SoftwareX"},{"key":"ref_35","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Lee, M.C.H., Braet, J., and Springael, J. (2024). Performance Metrics for Multilabel Emotion Classification: Comparing Micro, Macro, and Weighted F1-Scores. Appl. Sci., 14.","DOI":"10.3390\/app14219863"},{"key":"ref_37","unstructured":"Deutsche Gesetzliche Unfallversicherung e. V. (DGUV) (2024, November 16). Evaluation of Physical Loads in Virtual Reality for Conceptual Work Design. Available online: https:\/\/www.dguv.de\/ifa\/forschung\/projektverzeichnis\/ifa0507-2.jsp."},{"key":"ref_38","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"Hinton","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/5\/1468\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:43:50Z","timestamp":1760028230000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/5\/1468"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,27]]},"references-count":38,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["s25051468"],"URL":"https:\/\/doi.org\/10.3390\/s25051468","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,27]]}}}