To objectively assess a patient’s gait, a robust identification of stride borders is one of the first steps in inertial sensor-based mobile gait analysis pipelines. While many different methods for stride segmentation have been presented in the literature, an out-of-lab evaluation of respective algorithms on free-living gait is still missing. To address this issue, we present a comprehensive free-living evaluation dataset, including 146.574 semi-automatic labeled strides of 28 Parkinson’s Disease patients. This dataset was used to evaluate the segmentation performance of a new Hidden Markov Model (HMM) based stride segmentation approach compared to an available dynamic time warping (DTW) based method. The proposed HMM achieved a mean F1-score of 92.1% and outperformed the DTW approach significantly. Further analysis revealed a dependency of segmentation performance to the number of strides within respective walking bouts. Shorter bouts ( $$< 30$$ strides) resulted in worse performance, which could be related to more heterogeneous gait and an increased diversity of different stride types in short free-living walking bouts. In contrast, the HMM reached F1-scores of more than 96.2% for longer bouts ( $$> 50$$ strides). Furthermore, we showed that an HMM, which was trained on at-lab data only, could be transferred to a free-living context with a negligible decrease in performance. The generalizability of the proposed HMM is a promising feature, as fully labeled free-living training data might not be available for many applications. To the best of our knowledge, this is the first evaluation of stride segmentation performance on a large scale free-living dataset. Our proposed HMM-based approach was able to address the increased complexity of free-living gait data, and thus will help to enable a robust assessment of stride parameters in future free-living gait analysis applications.

中文翻译：

---

基于隐马尔可夫模型的帕金森病患者无监督自由生活步态数据的步幅分割

为了客观地评估患者的步态，稳健识别步幅边界是基于惯性传感器的移动步态分析管道的第一步。虽然文献中已经提出了许多不同的步幅分割方法，但仍然缺少对自由生活步态的相应算法的实验室外评估。为了解决这个问题，我们提出了一个全面的自由生活评估数据集，包括 28 名帕金森病患者的 146.574 个半自动标记的步幅。与可用的基于动态时间扭曲 (DTW) 的方法相比，该数据集用于评估基于新的隐马尔可夫模型 (HMM) 的步幅分割方法的分割性能。提议的 HMM 实现了 92.1% 的平均 F1 分数，并且显着优于 DTW 方法。进一步的分析揭示了分割性能与相应步行回合内的步幅数的相关性。较短的回合（$$< 30$$ 步幅）会导致更差的表现，这可能与更多样化的步态和短期自由行走中不同步幅类型的多样性增加有关。相比之下，HMM 在更长的回合（$$> 50$$ 步幅）中达到了超过 96.2% 的 F1 分数。此外，我们表明，仅在实验室数据上训练的 HMM 可以转移到自由生活的环境中，而性能下降可以忽略不计。所提出的 HMM 的普遍性是一个很有前途的特征，因为完全标记的自由生活训练数据可能无法用于许多应用程序。据我们所知，这是对大规模自由生活数据集的步幅分割性能的首次评估。我们提出的基于 HMM 的方法能够解决自由生活步态数据日益增加的复杂性，因此将有助于在未来的自由生活步态分析应用中对步幅参数进行可靠的评估。