Institute for Medical Engineering and Mechatronic, Ulm University of Applied Sciences, 89081 Ulm, Germany.
Sensors (Basel). 2021 Jan 25;21(3):789. doi: 10.3390/s21030789.
With an ageing society comes the increased prevalence of gait disorders. The restriction of mobility leads to a considerable reduction in the quality of life, because associated falls increase morbidity and mortality. Consideration of gait analysis data often alters surgical recommendations. For that reason, the early and systematic diagnostic treatment of gait disorders can spare a lot of suffering. As modern gait analysis systems are, in most cases, still very costly, many patients are not privileged enough to have access to comparable therapies. Low-cost systems such as inertial measurement units (IMUs) still pose major challenges, but offer possibilities for automatic real-time motion analysis. In this paper, we present a new approach to reliably detect human gait phases, using IMUs and machine learning methods. This approach should form the foundation of a new medical device to be used for gait analysis. A model is presented combining deep 2D-convolutional and LSTM networks to perform a classification task; it predicts the current gait phase with an accuracy of over 92% on an unseen subject, differentiating between five different phases. In the course of the paper, different approaches to optimize the performance of the model are presented and evaluated.
随着社会老龄化，步态障碍的发病率越来越高。活动受限导致生活质量显著下降，因为相关的跌倒会增加发病率和死亡率。考虑步态分析数据通常会改变手术建议。因此，早期和系统的步态障碍诊断治疗可以避免很多痛苦。由于现代步态分析系统在大多数情况下仍然非常昂贵，许多患者没有足够的特权获得可比的治疗。惯性测量单元（IMU）等低成本系统仍然存在重大挑战，但为自动实时运动分析提供了可能性。在本文中，我们提出了一种使用 IMU 和机器学习方法可靠检测人体步态阶段的新方法。该方法应成为用于步态分析的新型医疗设备的基础。提出了一种结合深度 2D 卷积和 LSTM 网络的模型来执行分类任务；它在未见过的受试者上以超过 92%的准确率预测当前步态阶段，区分五个不同阶段。在本文的过程中，提出并评估了不同的方法来优化模型的性能。
