Lee Seunghee, Park Changeon, Ha Eunho, Hong Jiseon, Kim Sung Hoon, Kim Youngho
Department of Biomedical Engineering, Yonsei University, Wonju 26493, Republic of Korea.
Division of Data Science, Yonsei University, Wonju 26493, Republic of Korea.
Sensors (Basel). 2025 Jul 14;25(14):4395. doi: 10.3390/s25144395.
This study proposes a hybrid approach combining threshold-based algorithm and deep learning to detect four major gait events-initial contact (IC), toe-off (TO), opposite initial contact (OIC), and opposite toe-off (OTO)-using only a smartphone's built-in inertial sensor placed in the user's pocket. The algorithm enables estimation of spatiotemporal gait parameters such as cadence, stride length, loading response (LR), pre-swing (PSw), single limb support (SLS), double limb support (DLS), and swing phase and symmetry. Gait data were collected from 20 healthy individuals and 13 hemiparetic stroke patients. To reduce sensitivity to sensor orientation and suppress noise, sum vector magnitude (SVM) features were extracted and filtered using a second-order Butterworth low-pass filter at 3 Hz. A deep learning model was further compressed using knowledge distillation, reducing model size by 96% while preserving accuracy. The proposed method achieved error rates in event detection below 2% of the gait cycle for healthy gait and a maximum of 4.4% for patient gait in event detection, with corresponding parameter estimation errors also within 4%. These results demonstrated the feasibility of accurate and real-time gait monitoring using a smartphone. In addition, statistical analysis of gait parameters such as symmetry and DLS revealed significant differences between the normal and patient groups. While this study is not intended to provide or guide rehabilitation treatment, it offers a practical means to regularly monitor patients' gait status and observe gait recovery trends over time.
本研究提出了一种将基于阈值的算法与深度学习相结合的混合方法，仅使用放置在用户口袋中的智能手机内置惯性传感器来检测四个主要步态事件——初始接触（IC）、足趾离地（TO）、对侧初始接触（OIC）和对侧足趾离地（OTO）。该算法能够估计时空步态参数，如步频、步长、负荷反应（LR）、摆动前期（PSw）、单支撑期（SLS）、双支撑期（DLS）、摆动期和对称性。从20名健康个体和13名偏瘫中风患者中收集了步态数据。为了降低对传感器方向的敏感性并抑制噪声，提取了和向量模（SVM）特征，并使用3 Hz的二阶巴特沃斯低通滤波器进行滤波。使用知识蒸馏进一步压缩深度学习模型，在保持准确率的同时将模型大小减少了96%。所提出的方法在健康步态的事件检测中，事件检测的错误率低于步态周期的2%，在患者步态的事件检测中最高为4.4%，相应的参数估计误差也在4%以内。这些结果证明了使用智能手机进行准确实时步态监测的可行性。此外，对对称性和双支撑期等步态参数的统计分析显示，正常组和患者组之间存在显著差异。虽然本研究并非旨在提供或指导康复治疗，但它提供了一种切实可行的方法来定期监测患者的步态状态，并观察步态随时间推移的恢复趋势。
