CyclePro: A Robust Framework for Domain-Agnostic Gait Cycle Detection
CyclePro: A Robust Framework for Domain-Agnostic Gait Cycle Detection
复制标题
DOI：
10.1109/jsen.2019.2893225
复制
发表时间：
2019-05-15
影响因子：
4.3
通讯作者：
Ghasemzadeh, Hassan
中科院分区：
文献类型：
--
作者：
Ma, Yuchao;Ashari, Zhila Esna;Ghasemzadeh, Hassan
用于连续步态监测的可穿戴传感器的实用性大幅增长，从而实现了医疗保健中移动性评估的新应用。用于步态周期检测的现有方法依赖于预定义的或实验调谐的平台参数，并且通常是平台特定的、参数敏感的，并且在具有受限的概括性的噪声环境中不可靠。为了解决这些挑战，我们引入了CyclePro，（1）一个可靠的和平台无关的步态周期检测的新框架。CyclePro提供独特的功能：1）它利用人类步态的物理特性来学习模型参数; 2）捕获的信号被转换为信号幅度，并通过归一化互相关模块进行处理，以补偿噪声并在没有预定义参数的情况下搜索重复模式;以及3）开发了最佳峰值检测算法，以准确地找到运动传感器数据中的步幅。为了证明CyclePro的有效性，进行了三个实验：一个临床研究，包括一组视力受损的青光眼患者和一组健康参与者;一个临床研究，涉及儿童Rett综合征;和一个实验，涉及健康参与者。CyclePro的性能在不同的平台设置下进行评估，并证明在噪声信号，不同的命中分辨率和采样频率变化下保持超过93%的准确度。这意味着平均召回率为95.3%，准确率为93.4%。此外，CyclePro可以使用来自不同传感器的数据检测步幅和估计节奏，准确率高于95%，并且对随机传感器方向具有鲁棒性，平均召回率为91.5%，精确度为99.2%。
The utility of wearable sensors for continuous gait monitoring has grown substantially, enabling novel applications on mobility assessment in healthcare. Existing approaches for gait cycle detection rely on predefined or experimentally tuned platform parameters and are often platform specific, parameter sensitive, and unreliable in noisy environments with constrained generalizability. To address these challenges, we introduce CyclePro,(1) a novel framework for reliable and platform-independent gait cycle detection. CyclePro offers unique features: 1) it leverages physical properties of human gait to learn model parameters; 2) captured signals are transformed into signal magnitude and processed through a normalized cross-correlation module to compensate for noise and search for repetitive patterns without predefined parameters; and 3) an optimal peak detection algorithm is developed to accurately find strides within the motion sensor data. To demonstrate the efficiency of CyclePro, three experiments are conducted: a clinical study including a visually impaired group of patients with glaucoma and a control group of healthy participants; a clinical study involving children with Rett syndrome; and an experiment involving healthy participants. The performance of CyclePro is assessed under varying platform settings and demonstrates to maintain over 93% accuracy under noisy signal, varying hit resolutions, and changes in sampling frequency. This translates into a recall of 95.3% and a precision of 93.4%, on average. Moreover, CyclePro can detect strides and estimate cadence using data from different sensors, with accuracy higher than 95%, and it is robust to random sensor orientations with a recall of 91.5% and a precision of 99.2%, on average.