RESUMEN

In laboratory experiments, biomechanical data collections with wearable technologies and machine learning have been promising. Despite the development of lightweight portable sensors and algorithms for the identification of gait events and estimation of kinetic waveforms, machine learning models have yet to be used to full potential. We propose the use of a Long Short Term Memory network to map inertial data to ground reaction force data gathered in a semi-uncontrolled environment. Fifteen healthy runners were recruited for this study, with varied running experience: novice to highly trained runners (<15 min 5 km race), and ages ranging from 18 to 64 years old. Force sensing insoles were used to measure normal foot-shoe forces, providing the standard for identification of gait events and measurement of kinetic waveforms. Three inertial measurement units (IMUs) were mounted to each participant, two bilaterally on the dorsal aspect of the foot and one clipped to the back of each participant's waistband, approximating their sacrum. Data input into the Long Short Term Memory network were from the three IMUs and output were estimated kinetic waveforms, compared against the standard of the force sensing insoles. The range of RMSE for each stance phase was from 0.189-0.288 BW, which is similar to multiple previous studies. Estimation of foot contact had an r 2 = 0.795. Estimation of kinetic variables varied, with peak force presenting the best output with an r 2 = 0.614. In conclusion, we have shown that at controlled paces over level ground a Long Short Term Memory network can estimate 4 s temporal windows of ground reaction force data across a range of running speeds.

RESUMEN

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.

Asunto(s)

RESUMEN

The development of lightweight portable sensors and algorithms for the identification of gait events at steady-state running speeds can be translated into the real-world environment. However, the output of these algorithms needs to be validated. The purpose of this study was to validate the identification of running gait events using data from Inertial Measurement Units (IMUs) in a semi-uncontrolled environment. Fifteen healthy runners were recruited for this study, with varied running experience and age. Force-sensing insoles measured normal foot-shoe forces and provided a standard for identification of gait events. Three IMUs were mounted to the participant, two bilaterally on the dorsal aspect of the foot and one clipped to the back of each participant's waistband, approximating their sacrum. The identification of gait events from the foot-mounted IMU was more accurate than from the sacral-mounted IMU. At running speeds <3.57 m s−1, the sacral-mounted IMU identified contact duration as well as the foot-mounted IMU. However, at speeds >3.57 m s−1, the sacral-mounted IMU overestimated foot contact duration. This study demonstrates that at controlled paces over level ground, we can identify gait events and measure contact time across a range of running skill levels.

Asunto(s)

RESUMEN

The purpose of this study was to compare a heuristic feature identification algorithm with output from the Beta Process Auto Regressive Hidden Markov Model (BP-AR-HMM) utilizing minimally sampled (≤ 100 Hz) human locomotion data for identification of gait events prior to their occurrence. Data were collected from 16 participants (21-64 years) using a single gyroscopic sensor in an inertial measurement unit on the dorsum of the foot, across multiple locomotion modes, including level ground walking and running (across speeds 0.8 m s-1 - 3.0 m s-1), ramps and stairs. Identification of gait events, initial contact (IC) and toe off (TO) with the heuristic algorithm, was 94% across locomotion modes. The features identified prior to initial contact had a lead time of 186.32 ± 86.70 ms, while TO had a lead time of 63.96 ± 46.30 ms. The BP-AR-HMM identified features that indicated an impending IC and TO with 99% accuracy, with a lead time of 59.41 ± 54.41 ms for IC and 90.79 ± 35.51 ms for TO. These approaches are consistent in their identification of gait events and have the potential to be utilized for classification and prediction of locomotion mode.

Asunto(s)

RESUMEN

GOAL: The purpose of this study was to provide an initial examination of the utility of the Beta Process - Auto Regressive - Hidden Markov Model (BP-AR-HMM) for the prior identification of gait events. A secondary objective was to determine whether the output of the model could be used for classification and prediction of locomotion states. METHODS: In this study we utilized the output of the BP-AR-HMM to develop user-independent identification of gait events and gait classification from an idealized three-dimensional acceleration signal. The input acceleration data were collected from two walking (1.4 and 1.6 ms-1) and two running (2.6 and 3.0 ms-1) steady state speeds, and during two dynamic walk to run and run to walk transitions (1.8-2.4 and 2.4-1.8 ms-1) on an instrumented force treadmill. RESULTS: The BP-AR-HMM identified 9 unique states. Of these, two states, 4 and 1, were utilized to estimate initial contact and toe off, respectively. The lead time from the first instance of state 4 to initial contact was 0.13 ± 0.02 s. Similarly, the first instance of state 1 occurred 0.14 ± 0.03 s before toe off. Two other states (3 and 7) were examined for possible utilization in a probabilistic model for the prediction of pending locomotion state transitions. CONCLUSION: The identification of gait events prior to their occurrence by the BP-AR-HMM appears to be an approach that can minimize the quantity of sensor data in an offline approach. Furthermore, there is evidence it could also be used as a basis to build a probabilistic model to estimate locomotion transitions.

Asunto(s)