Predicting vertical ground reaction forces from 3D accelerometry using reservoir computers leads to accurate gait event detection

Abstract

Accelerometers are low-cost measurement devices that can readily be used outside the lab. However, determining isolated gait events from accelerometer signals, especially foot-off events during running, is an open problem. We outline a two-step approach where machine learning serves to predict vertical ground reaction forces from accelerometer signals, followed by force-based event detection. We collected shank accelerometer signals and ground reaction forces from 21 adults during comfortable walking and running on an instrumented treadmill. We trained one common reservoir computer using segmented data using both walking and running data. Despite being trained on just a small number of strides, this reservoir computer predicted vertical ground reaction forces in continuous gait with high quality. The subsequent foot contact and foot off event detection proved highly accurate when compared to the gold standard based on co-registered ground reaction forces. Our proof-of-concept illustrates the capacity of combining accelerometry with machine learning for detecting isolated gait events irrespective of mode of locomotion.

Unsupervised Gait Event Identification with a Single Wearable Accelerometer and/or Gyroscope: A Comparison of Methods across Running Speeds, Surfaces, and Foot Strike Patterns

“…Overall, we found errors to be higher than reported in the original studies (except [43,44]). This is likely a function of several factors: First, in contrast to some studies, we time synchronized our ground truth force plates with our IMUs with ms accuracy.…”

“…This likely explains the high error observed across the range of running speeds we used here. As a final example, Bach et al [43] trained an Echo State Network to estimate gait events using data from a narrow set of conditions. To replicate their model, we used the full running data set published with their original paper but still observed high errors when estimating gait events from our data.…”

“…Sensors 2023, 23, 5022 3 of 20 11 ≤ n ≤ 20: [36][37][38][39][40][41][42]; n > 20: [43,44]), (2) using a narrow range of, or unreported, running speeds (single speed: [32,36,37,39,43], speeds not reported: [28,30,31,35,38,40]), (3) using a single running surface (all except [44]), (4) without accounting for foot-strike kinematics (foot strike not reported: [27,28,30,31,[33][34][35][36]38,40,41,43]; only one strike pattern studied: [29,32,37,39]), and (5) without adequate synchronization between wearable data and a ground truth reference (no synchronization reported: [27,31,36,39,43]; imprecise synchronization: [33,41,42,…”

Estimation of Kinetics Using IMUs to Monitor and Aid in Clinical Decision-Making during ACL Rehabilitation: A Systematic Review

“…For validation of estimated kinetics, quantities like ground reaction forces were simultaneously measured in all studies using force plates [18,29,31,34,[40][41][42][43][44][45][46][47][48], instrumented treadmills [14,32,38,39,[49][50][51][52][53][54][55][56][57][58], plantar sensors [35], force shoes [59], shoes with loadcell(s) [60,61], or insoles [62][63][64][65]. Additional kinematic data were also measured in some of the studies using systems such as optical motion capture systems [30,33,36,37,, a stereophotogrammetry system [88], or a marker-less video system [89], along with IMUs.…”

“…Studies that placed IMUs on a unilateral side either assumed bilateral symmetry [36] or chose the dominant/injured leg as the leg of interest [32]. A total of 28 articles [14,15,18,35,[39][40][41][42][43][44][45]49,51,52,55,56,58,62,63,66,68,74,75,[88][89][90][91] used fewer than 3 on-body sensors, where 19 of them [14,15,18,[39][40][41]44,45,49,51,52,55,58,62,63,74,88,89,91] only used a single sensor to measure movement kinematics and to develop algorithms estimating kinetics. the second highest number of on-body sensors was 3, and they were found in 12 articles…”