Determination of gait parameters in real‐world environment using low‐cost inertial sensors

Abstract

The ageing society causes an increasing need for gait monitoring in daily life to preserve the mobility of older people. Therefore, flexible low-cost and easy-to-apply sensor networks are necessary. This study evaluates two in-house developed inertial sensors for their capability of detecting spatial and temporal parameters of gait by using a time-warping algorithm for stride segmentation. Thereby, impaired or wheeled walker supported gait can be analysed using a patient specific template. The results prove the capability to exclude sequences from the motion that do not correspond to strides and to detect spatiotemporal parameters reliably. For the application to geriatric patients, however, further research is necessary.

A Comparison of Three Neural Network Approaches for Estimating Joint Angles and Moments from Inertial Measurement Units

“…The dataset comprised aggregated level walking data, sourced from a series of independent studies [ 14 , 21 , 22 , 23 ]. All data was sourced by the German Sport University Cologne and was approved by the University Ethics Committee (approval no.…”

“…Concurrent with the optical motion capture, 23 of the 116 participants were additionally fitted with five custom inertial sensors to record the linear acceleration and angular rate of the pelvis, and bilateral thigh and shank (100 , TinyCircuits, Akron, OH, USA). An Android based custom application collected the IMU data on a smartphone [ 14 , 23 ].…”

Estimation of Gait Mechanics Based on Simulated and Measured IMU Data Using an Artificial Neural Network

“…Simultaneously, the participants were equipped with five sensors of a custom low cost IMU system (100 Hz, TinyCircuits, Akron, OH, USA) with an associated microcontroller (Atmel ATmega328P) and a WIFI-board (Atmel ATWINC1500). An Android application was developed to collect the data on a smartphone (Mundt et al, 2018b). The marker set and sensor placement are displayed in Figure 2.…”