当前位置: X-MOL 学术Microprocess. Microsyst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Analyzing gait symmetry with automatically synchronized wearable sensors in daily life
Microprocessors and Microsystems ( IF 2.6 ) Pub Date : 2020-05-15 , DOI: 10.1016/j.micpro.2020.103118
Tobias Steinmetzer , Sandro Wilberg , Ingrid Bönninger , Carlos M. Travieso

Gait deviations such as asymmetry are one of the characteristic symptoms of motor dysfunctions that contribute to the risk of falls. Our objective is to measure gait abnormalities such as asymmetry of the lower limbs in order to evaluate the diagnosis more objectively. For the measurement we use inertial measurement unit (IMU) sensors and force sensors, which are integrated in wristbands and insoles. To extend the battery life of wearable devices, we only save data of the activity gait within the wearables. Therefore we perform activity recognition with a smartphone. Using convolutional neural network (CNN) we achieved an accuracy of 94.7 % of the activity gait recognition. Before recording we synchronize the wearable sensors and reach a maximum latencies of 3 ms. Before the analysis of the symmetry we detect the strides by using a CNN with an accuracy of 98.8 %. For the symmetry evaluation we used dynamic time warping (DTW). The DTW enables us to calculate symmetry of the complete time series of human gait.



中文翻译:

在日常生活中使用自动同步的可穿戴式传感器分析步态对称性

步态偏差(例如不对称性)是运动功能障碍的典型症状之一,会导致跌倒的风险。我们的目标是测量步态异常(例如下肢不对称),以便更客观地评估诊断。对于测量,我们使用惯性测量单元(IMU)传感器和力传感器,它们集成在腕带和鞋垫中。为了延长可穿戴设备的电池寿命,我们仅将活动步态数据保存在可穿戴设备中。因此,我们使用智能手机进行活动识别。使用卷积神经网络(CNN),我们达到了94.7%的活动步态识别精度。在记录之前,我们会同步可穿戴式传感器,并最大延迟3 毫秒。在分析对称性之前,我们使用精度为98.8%的CNN来检测步幅。对于对称性评估,我们使用动态时间规整(DTW)。DTW使我们能够计算人类步态的完整时间序列的对称性。

更新日期:2020-05-15
down
wechat
bug