Machine-Learning Based Determination of Gait Events from Foot-Mounted Inertial Units

Abstract

A promising but still scarcely explored strategy for the estimation of gait parameters based on inertial sensors involves the adoption of machine learning techniques. However, existing approaches are reliable only for specific conditions, inertial measurements unit (IMU) placement on the body, protocols, or when combined with additional devices. In this paper, we tested an alternative gait-events estimation approach which is fully data-driven and does not rely on a priori models or assumptions. High-frequency (512 Hz) data from a commercial inertial unit were recorded during 500 steps performed by 40 healthy participants. Sensors’ readings were synchronized with a reference ground reaction force system to determine initial/terminal contacts. Then, we extracted a set of features from windowed data labeled according to the reference. Two gray-box approaches were evaluated: (1) classifiers (decision trees) returning the presence of a gait event in each time window and (2) a classifier discriminating between stance and swing phases. Both outputs were submitted to a deterministic algorithm correcting spurious clusters of predictions. The stance vs. swing approach estimated the stride time duration with an average error lower than 20 ms and confidence bounds between ±50 ms. These figures are suitable to detect clinically meaningful differences across different populations.

A deep-learning approach for automatically detecting gait-events based on foot-marker kinematics in children with cerebral palsy—Which markers work best for which gait patterns?

“…Still, in recent years, there have been new models that potentially reach better performance, such as applying the attention model in LSTM. Furthermore, several studies [35][36][37][38][39][40] have also been conducted on hybrid deep learning architecture in other fields. Thus, one could speculate that using such a new model could enhance performance, and might therefore be worth to evaluate in a future study.…”

Machine Learning-Based Estimation of Ground Reaction Forces and Knee Joint Kinetics from Inertial Sensors While Performing a Vertical Drop Jump

“…In fact, the detection of the events defining the beginning and the end of each landing phase was not implemented by using data directly from the IMUs, such as in Zago et al, (2021) [43], but it needed to be done via the data recorded by the force plates and processed with Visual3D (or an equivalent biomechanics software) afterwards.…”

Characterizing Bodyweight-Supported Treadmill Walking on Land and Underwater Using Foot-Worn Inertial Measurement Units and Machine Learning for Gait Event Detection

“…A possible solution to overcome these challenges is to rely on machine learning algorithms that can be trained on event-labeled ground truth IMU data to detect gait events in another dataset. This method can improve accuracy and automate event detection procedures [ 14 , 15 ] but is dependent on sensor placement, orientation, and the selected IMU signal component [ 16 , 17 ]. The placement of an IMU sensor under the arch of the foot, within the sole of the shoe, achieved better gait event detection accuracy compared to other locations on the lower limb during running [ 18 ] and walking [ 19 ].…”