A New Proxy Measurement Algorithm with Application to the Estimation of Vertical Ground Reaction Forces Using Wearable Sensors

Abstract

Measurement of the ground reaction forces (GRF) during walking is typically limited to laboratory settings, and only short observations using wearable pressure insoles have been reported so far. In this study, a new proxy measurement method is proposed to estimate the vertical component of the GRF (vGRF) from wearable accelerometer signals. The accelerations are used as the proxy variable. An orthogonal forward regression algorithm (OFR) is employed to identify the dynamic relationships between the proxy variables and the measured vGRF using pressure-sensing insoles. The obtained model, which represents the connection between the proxy variable and the vGRF, is then used to predict the latter. The results have been validated using pressure insoles data collected from nine healthy individuals under two outdoor walking tasks in non-laboratory settings. The results show that the vGRFs can be reconstructed with high accuracy (with an average prediction error of less than 5.0%) using only one wearable sensor mounted at the waist (L5, fifth lumbar vertebra). Proxy measures with different sensor positions are also discussed. Results show that the waist acceleration-based proxy measurement is more stable with less inter-task and inter-subject variability than the proxy measures based on forehead level accelerations. The proposed proxy measure provides a promising low-cost method for monitoring ground reaction forces in real-life settings and introduces a novel generic approach for replacing the direct determination of difficult to measure variables in many applications.

Validity of Measurement for Trailing Limb Angle and Propulsion Force during Gait Using a Magnetic Inertial Measurement Unit

“…In addition, similar relationship was observed between acceleration of thorax and lumbar segment obtained by IMU, and acceleration of the center of mass calculated by AGRF. Although previous studies reported that vertical acceleration correlated with vertical trunk acceleration during gait [40,41], no literature investigated the estimation of AGRF by IMU. By Newtonian equation of motion, GRF expresses gravity and acceleration acting on T 4: Relationship between acceleration of trunk (thorax, lumbar spine) obtained by magnetic inertial measurement unit and acceleration of the center of mass calculated from anterior ground reaction force (AGRF) (mean ± SD).…”

Indirect Measurement of Ground Reaction Forces and Moments by Means of Wearable Inertial Sensors: A Systematic Review

“…Guo and colleagues [ 87 ] adopted a different approach to estimate the vertical component of the GRF by using the acceleration, directly measured by wearable IMUs, and used it as a proxy variable. The aim of the study was to find a relationship between the acceleration, used as a proxy variable, and the forces measured by means of pressure insoles without regard to a biomechanical modelling.…”

“…In the same study the authors also tested different placements for the measuring IMU on the subjects’ back: L5, C7 and forehead. Data synchronization was obtained by a vertical jump before trials and, since the acquisitions were relatively long, the time series were re-aligned every two minutes [ 87 ]. This proposed approach is in contrast with approaches based on detailed biomechanical models and it is claimed to simplify modelling and data acquisition strategies.…”

A Machine Learning and Wearable Sensor Based Approach to Estimate External Knee Flexion and Adduction Moments During Various Locomotion Tasks

“…Accurate predictions for new data can be made by learning the relationship between a set of independent variables (e.g., IMU signals) and one or more dependent variables (e.g., KAM) (Lin et al, 2016;Halilaj et al, 2018). Several studies have shown that machine learning techniques, such as artificial neural networks (ANN), are powerful tools to deduce biomechanical variables based on measured accelerations or angular velocities of body segments (Leporace et al, 2015;Guo et al, 2017;Ancillao et al, 2018;Wouda et al, 2018;Stetter et al, 2019). The study by Wouda et al (2018) used an ANN approach to estimate vertical GRFs and sagittal knee kinematics during running, based on three inertial sensors placed at the lower legs and the pelvis.…”