Feature Identification With a Heuristic Algorithm and an Unsupervised Machine Learning Algorithm for Prior Knowledge of Gait Events

Donahue, Seth R.; Hahn, Michael E.

doi:10.1109/tnsre.2021.3131953

Cited by 6 publications

(3 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Estimation of gait events and foot contacts with IMUs and BD-LSTM. Our approach to estimating gait events used both acceleration and angular velocity data, which differs from previous work, as most studies have made use of only one type of data, either accelerations or angular velocities 5,8,[35][36][37][38][39][40] . Differences between IC IMU and measured IC in the current study occurred in the expected range (− 0.020-0.020 s), due to the iterative corrections algorithm used.…”

Section: Validation Of Ground Reaction Force Variablesmentioning

confidence: 99%

“…Gait event detection algorithms. Gait event estimation, initial contact (IC) and toe off (TO) from IMU data utilized heuristic rules similar to previous work 5,8,36 . Initial contact from the IMUs on the dorsal aspect of the foot (IC IMU ) was identified with two rules.…”

Section: Data Processingmentioning

confidence: 99%

“…Wearable technologies are an alternative to laboratory based methods and have become more widely available for the monitoring of running biomechanics in uncontrolled environments 3,4 . Examples of these are inertial measurement units (IMUs), GPS, and in-shoe force or pressure sensors, which can be used to estimate or measure biomechanical data [5][6][7][8] . Earlier research has utilized IMUs for the estimation of gait events and foot ground contact time both in and out of the laboratory 5,[9][10][11][12][13] .…”

mentioning

confidence: 99%

See 2 more Smart Citations

Estimation of gait events and kinetic waveforms with wearable sensors and machine learning when running in an unconstrained environment

Donahue

Hahn

2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

Wearable sensors and machine learning algorithms are becoming a viable alternative for biomechanical analysis outside of the laboratory. The purpose of this work was to estimate gait events from inertial measurement units (IMUs) and utilize machine learning for the estimation of ground reaction force (GRF) waveforms. Sixteen healthy runners were recruited for this study, with varied running experience. Force sensing insoles were used to measure normal foot-shoe forces, providing a proxy for vertical GRF and a standard for the identification of gait events. Three IMUs were mounted on each participant, two bilaterally on the dorsal aspect of each foot and one clipped to the back of each participant’s waistband, approximating their sacrum. Participants also wore a GPS watch to record elevation and velocity. A Bidirectional Long Short Term Memory Network (BD-LSTM) was used to estimate GRF waveforms from inertial waveforms. Gait event estimation from both IMU data and machine learning algorithms led to accurate estimations of contact time. The GRF magnitudes were generally underestimated by the machine learning algorithm when presented with data from a novel participant, especially at faster running speeds. This work demonstrated that estimation of GRF waveforms is feasible across a range of running velocities and at different grades in an uncontrolled environment.

show abstract