Schneider Moritz, Seeser-Reich Kevin, Fiedler Armin, Frese Udo
Institute for Occupational Safety and Health of the German Social Accident Insurance (IFA), 53757 Sankt Augustin, Germany.
RheinAhrCampus, Koblenz University of Applied Sciences, 53424 Remagen, Germany.
Sensors (Basel). 2025 Feb 27;25(5):1468. doi: 10.3390/s25051468.
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.
滑倒、绊倒和跌倒（STF）是一种主要的职业危害，对工作场所的伤害及相关财务成本有重大影响。传统跌倒检测技术在现实世界中的应用有限，因为它们通常基于模拟跌倒。通过使用在体力要求较高的工作环境中发生的真实近跌倒事件的运动学数据，本研究克服了这一局限性，并提高了跌倒检测算法的生态效度。本研究使用Prev-Fall数据集系统地测试了几种用于近跌倒检测的机器学习架构，该数据集包含110名工人的高分辨率惯性测量单元（IMU）数据。使用神经架构搜索，在一系列时间窗口长度上对卷积神经网络（CNN）、残差网络（ResNet）、卷积长短期记忆网络（convLSTM）和InceptionTime模型进行了训练和评估。表现最佳的模型，特别是CNN和InceptionTime，获得了较高的验证F1分数，表明它们在近跌倒分类方面的有效性。在对以前未观察到的职业数据进行的后续测试中，尤其是在诸如弯腰和蹲下等生物力学要求较高的活动期间，反复出现的误报突出了需要更多上下文变量来提高稳健性。尽管如此，我们的研究结果表明基于机器学习的STF预防系统适用于工作场所安全监测，更广泛地说，适用于跌倒缓解应用。为了进一步提高系统的准确性和通用性，未来的研究应调查多模态数据集成和改进的分类技术。
