Annu Int Conf IEEE Eng Med Biol Soc. 2021 Nov;2021:6835-6840. doi: 10.1109/EMBC46164.2021.9629492.
In this study, we proposed a framework for extracting gait events and extensive temporal features, seamlessly, during walking and running on a treadmill by constructing a finite state machine (FSM) transition rules based on two IMU sensors attached to the back of the shoes. Detailed innerclass states were defined to recognize the double support phase on walking gait and the double flight phase on running gait. Further, an in-depth speed-based analysis of temporal gait features can be performed for each tested speed with an automatic speed change detection algorithm based on the moving average filter applied to motion intensity data. The results have demonstrated that the FSM can accurately distinguish walking gait and running gait while also extract a detailed gait phase, respectively. This finding may contribute to a more flexible gait analysis where a change in speed or transition from walk to run can be anticipated and recognized accordingly.
在这项研究中，我们提出了一个框架，通过构建基于两个附着在鞋后部的 IMU 传感器的有限状态机（FSM）转换规则，在跑步机上行走和跑步时无缝地提取步态事件和广泛的时间特征。定义了详细的内部类状态，以识别行走步态的双支撑阶段和跑步步态的双腾空阶段。此外，还可以通过应用于运动强度数据的移动平均滤波器的自动速度变化检测算法，针对每个测试速度进行深入的基于速度的时间步态特征分析。结果表明，FSM 可以准确地区分行走步态和跑步步态，同时分别提取详细的步态阶段。这一发现可能有助于更灵活的步态分析，其中可以预期速度的变化或从行走到跑步的过渡，并相应地识别。
