Estimation of the ankle power during the terminal stance of gait using an inertial sensor

Building Effective Machine Learning Models for Ankle Joint Power Estimation During Walking Using FMG Sensors

Ankle joint power is usually determined by a complex process that involves heavy equipment and complex biomechanical models. Instead of using heavy equipment, we proposed effective machine learning (ML) and deep learning (DL) models to estimate the ankle joint power using force myography (FMG) sensors. In this study, FMG signals were collected from nine young, healthy participants. The task was to walk on a special treadmill for five different velocities with a respective duration of 1 min. FMG signals were collected from an FMG strap that consists of 8 force resisting sensor (FSR) sensors. The strap was positioned around the lower leg. The ground truth value for ankle joint power was determined with the help of a complex biomechanical model. At first, the predictors' value was preprocessed using a rolling mean filter. Following, three sets of features were formed where the first set includes raw FMG signals, and the other two sets contained time-domain and frequency-domain features extracted using the first set. Cat Boost Regressor (CBR), Long-Short Term Memory (LSTM), and Convolutional Neural Network (CNN) were trained and tested using these three features sets. The results presented in this study showed a correlation coefficient of R = 0.91 ± 0.07 for intrasubject testing and were found acceptable when compared to other similar studies. The CNN on raw features and the LSTM on time-domain features outperformed the other variations. Aside from that, a performance gap between the slowest and fastest walking distance was observed. The results from this study showed that it was possible to achieve an acceptable correlation coefficient in the prediction of ankle joint power using FMG sensors with an appropriate combination of feature set and ML model.

Inertial Motion Capture-Based Wearable Systems for Estimation of Joint Kinetics: A Systematic Review

In biomechanics, joint kinetics has an important role in evaluating the mechanical load of the joint and understanding its motor function. Although an optical motion capture (OMC) system has mainly been used to evaluate joint kinetics in combination with force plates, inertial motion capture (IMC) systems have recently been emerging in joint kinetic analysis due to their wearability and ubiquitous measurement capability. In this regard, numerous studies have been conducted to estimate joint kinetics using IMC-based wearable systems. However, these have not been comprehensively addressed yet. Thus, the aim of this review is to explore the methodology of the current studies on estimating joint kinetic variables by means of an IMC system. From a systematic search of the literature, 48 studies were selected. This paper summarizes the content of the selected literature in terms of the (i) study characteristics, (ii) methodologies, and (iii) study results. The estimation methods of the selected studies are categorized into two types: the inverse dynamics-based method and the machine learning-based method. While these two methods presented different characteristics in estimating the kinetic variables, it was demonstrated in the literature that both methods could be applied with good performance for the kinetic analysis of joints in different daily activities.

Assessment of walking disorder in community-dwelling Japanese middle-aged and elderly women using an inertial sensor

BACKGROUND

Decreased walking speed has been revealed to be related to many negative events. Several researchers support the importance of triceps surae function as a cause of decreased walking speed. The purpose of this study was to investigate the relationship between walking speed and plantar flexor power during the terminal stance of gait in community-dwelling middle-aged and elderly women using an inertial sensor.

METHODS

One hundred thirty-six healthy female middle-aged to elderly community-dwelling women were included in this study. We measured two-step score, grip strength, walking speed and accelerometer data from which we estimated ankle power (estimated ankle power) during walking using an inertial sensor. All participants were classified into the four different age strata, fifties (50-59), sixties (60-69), seventies (70-79) and eighties (80-89). The differences in each parameter between the four age groups were compared using repeated analysis of variance and post-hoc Bonferroni corrections for multiple comparisons to establish significance. Multiple regression analysis was carried out using a stepwise method to determine the correlations with comfortable walking speed. Comfortable walking speed was considered a dependent variable.

RESULTS

The normalized estimated ankle power of the eighties group was significantly decreased in comparison with seventies age groups and fifties age groups (P < 0.05), but there were no significant differences in normalized estimated ankle power between the sixties and eighties age-groups. The results of stepwise multiple regression analysis revealed that the normalized estimated ankle power, two-step value and body weight were highly-significant partial regression coefficients (adjusted R 2 = 0.57).