Recognition of Gait Phases with a Single Knee Electrogoniometer: A Deep Learning Approach

Abstract

Artificial neural networks were satisfactorily implemented for assessing gait events from different walking data. This study aims to propose a novel approach for recognizing gait phases and events, based on deep-learning analysis of only sagittal knee-joint angle measured by a single electrogoniometer per leg. Promising classification/prediction performances have been previously achieved by surface-EMG studies; thus, a further aim is to test if adding electrogoniometer data could improve classification performances of state-of-the-art methods. Gait data are measured in about 10,000 strides from 23 healthy adults, during ground walking. A multi-layer perceptron model is implemented, composed of three hidden layers and a one-dimensional output. Classification/prediction accuracy is tested vs. ground truth represented by foot–floor-contact signals, through samples acquired from subjects not seen during training phase. Average classification-accuracy of 90.6 ± 2.9% and mean absolute value (MAE) of 29.4 ± 13.7 and 99.5 ± 28.9 ms in assessing heel-strike and toe-off timing are achieved in unseen subjects. Improvement of classification-accuracy (four points) and reduction of MAE (at least 35%) are achieved when knee-angle data are used to enhance sEMG-data prediction. Comparison of the two approaches shows as the reduction of set-up complexity implies a worsening of mainly toe-off prediction. Thus, the present electrogoniometer approach is particularly suitable for the classification tasks where only heel-strike event is involved, such as stride recognition, stride-time computation, and identification of toe walking.

A Review of Gait Phase Detection Algorithms for Lower Limb Prostheses

“…Firstly, the domain based on the threshold method [ 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 , 17 ], time-frequency analysis [ 18 , 19 , 20 , 21 ], and peak heuristic algorithms [ 16 , 19 , 22 , 23 , 24 , 25 ], which are also variations of the threshold method. Secondly, Machine Learning (ML) approaches are now among the most popular techniques to detect phases and events with various models such as Hidden Markov Models (HMM) [ 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 ], or several of the latest studies published based on the Artificial Neural Network technique (ANN) [ 35 , 36 , 37 , 38 ], Deep Learning Neural Network (DLNN) [ 39 , 40 , 41 , 42 , 43 ], a Convolutional Neural Network (CNN) [ 44 , 45 , 46 ], or [ 28 ] proposed a hybrid method that combined HMM and Fully connected Neural Networks (FNN). Different computation methodologies provide different performances regarding the parameters such as the number of detectable phases, events, and detection delay, which will be discussed in the next section.…”

Joint Torque Closed-Loop Estimation Using NARX Neural Network Based on sEMG Signals

“…The EMG signal contains a wealth of motion information that precedes actual joint motion and is often used as a control signal to predict joint motion. Previous studies have focused on feature extraction and classification of EMG signals for identifying movement patterns [30], gait analysis [31], and joint angle estimation [32], [33]. Joint torque measurements are more complicated relative to joint angles due to the complexity of the human joint structure.…”

A Survey of Human Gait-Based Artificial Intelligence Applications

“…Other considerations in carefully selecting the input features are avoiding overfitting ( Zhang et al, 2020a ), improving interpretability, especially in medical applications ( Dindorf et al, 2020b ), ( Horst et al, 2019 ), reducing the energy expenditure of wearable sensors ( Lan et al, 2020 ), ( Russell et al, 2021 ), improving patient comfort ( Di Nardo et al, 2020 ), fairness to people with disabilities ( Trewin et al, 2019 ) and user experience ( Kim et al, 2020 ). To achieve the highest possible accuracy, usually, more complex sensing technology is required.…”

“…Depending on the reason for gait analysis, detecting just these two phases can be enough. That simplification permits less complex and cheaper gait analysis, which is desirable, especially in wearable systems ( Di Nardo et al, 2020 ). A more common four-phase cycle includes initial contact, mid-stance, pre-swing, and swing ( Jiang et al, 2018 ).…”

“…There is generally a trade-off between the complexity of sensing technology in smart gait devices and the accuracy of the intelligent task they perform ( Khademi et al, 2019 ). Depending on the task and granted sufficient accuracy, one can stop the chase for performance and focus on patient comfort ( Di Nardo et al, 2020 ). A multi-object optimization (MOO) technique is implemented ( Khademi et al, 2019 ) to navigate this trade-off: it selects an optimal feature subset that maximizes accuracy while minimizing sensing hardware.…”