Human knee joint walking pattern generation using computational intelligence techniques

A comparison of machine learning models' accuracy in predicting lower-limb joints' kinematics, kinetics, and muscle forces from wearable sensors

A combination of wearable sensors' data and Machine Learning (ML) techniques has been used in many studies to predict specific joint angles and moments. The aim of this study was to compare the performance of four different non-linear regression ML models to estimate lower-limb joints' kinematics, kinetics, and muscle forces using Inertial Measurement Units (IMUs) and electromyographys' (EMGs) data. Seventeen healthy volunteers (9F, 28 ± 5 years) were asked to walk over-ground for a minimum of 16 trials. For each trial, marker trajectories and three force-plates data were recorded to calculate pelvis, hip, knee, and ankle kinematics and kinetics, and muscle forces (the targets), as well as 7 IMUs and 16 EMGs. The features from sensors' data were extracted using the Tsfresh python package and fed into 4 ML models; Convolutional Neural Networks (CNN), Random Forest (RF), Support Vector Machine, and Multivariate Adaptive Regression Spline for targets' prediction. The RF and CNN models outperformed the other ML models by providing lower prediction errors in all intended targets with a lower computational cost. This study suggested that a combination of wearable sensors' data with an RF or a CNN model is a promising tool to overcome the limitations of traditional optical motion capture for 3D gait analysis.

Lower body kinematics estimation during walking using an accelerometer

Measuring and predicting accurate joint angles are important to developing analytical tools to gauge users' progress. Such measurement is usually performed in laboratory settings, which is difficult and expensive. So, the aim of this study was continuous estimation of lower limb joint angles during walking using an accelerometer and random forest (RF). Thus, 73 subjects (26 women and 47 men) voluntarily participated in this study. The subjects walked at the slow, moderate, and fast speeds on a walkway, which was covered with 10 Vicon camera. Acceleration was used as input for a RF to estimate ankle, knee, and hip angles (in transverse, frontal, and sagittal planes). Pearson correlation coefficient (r) and Mean Square Error (MSE) were computed between the experimental and estimated data. Paired statistical parametric mapping (SPM) t-test was used to compare the experimental and estimated data throughout gait cycle. The results of this study showed that the MSE of joint angles between the experimental and estimated data ranged from 0.04 to 24.29 and r > 0.91. Moreover, the findings of SPM indicated that there was no significant difference between the experimental and estimated data of ankle, knee, and hip angles in all three planes throughout gait cycle. The results of our research developed a more accessible, portable procedure to quantifying lower limb joint angles by an accelerometer and RF. So, such wearable-based joint angles have the potential to be used in outside-laboratory settings to measure walking kinematics.

Gait Trajectory Prediction on an Embedded Microcontroller Using Deep Learning

Achieving a normal gait trajectory for an amputee's active prosthesis is challenging due to its kinematic complexity. Accordingly, lower limb gait trajectory kinematics and gait phase segmentation are essential parameters in controlling an active prosthesis. Recently, the most practiced algorithm in gait trajectory generation is the neural network. Deploying such a complex Artificial Neural Network (ANN) algorithm on an embedded system requires performing the calculations on an external computational device; however, this approach lacks mobility and reliability. In this paper, more simple and reliable ANNs are investigated to be deployed on a single low-cost Microcontroller (MC) and hence provide system mobility. Two neural network configurations were studied: Multi-Layered Perceptron (MLP) and Convolutional Neural Network (CNN); the models were trained on shank and foot IMU data. The data were collected from four subjects and tested on a fifth to predict the trajectory of 200 ms ahead. The prediction was made for two cases: with and without providing the current phase of the gait. Then, the models were deployed on a low-cost microcontroller (ESP32). It was found that with fewer data (excluding the current gait phase), CNN achieved a better correlation coefficient of 0.973 when compared to 0.945 for MLP; when including the current phase, both network configurations achieved better correlation coefficients of nearly 0.98. However, when comparing the execution time required for the prediction on the intended MC, MLP was much faster than CNN, with an execution time of 2.4 ms and 142 ms, respectively. In summary, it was found that when training data are scarce, CNN is more efficient within the acceptable execution time, while MLP achieves relative accuracy with low execution time with enough data.

Role of machine learning in gait analysis: a review

Human biomechanics and gait form an integral part of life. The gait analysis involves a large number of interdependent parameters that were difficult to interpret due to a vast amount of data and their inter-relations. To simplify evaluation, the integration of machine learning (ML) with biomechanics is a promising solution. The purpose of this review is to familiarise the readers with key directions of implementation of ML techniques for gait analysis and gait rehabilitation. An extensive literature survey was based on research articles from nine databases published from 1980 to 2019. With over 943 studies identified, finally, 43 studies met the inclusion criteria. The outcome reported illustrates that supervised ML techniques showed accuracies above 90% in the identified gait analysis domain. The statistical results revealed support vector machine (SVM) as the best classifier (mean-score = 0.87 ± 0.07) with remarkable generalisation capability even on small to medium datasets. It has also been analysed that the control strategies for gait rehabilitation are benefitted from reinforcement learning and (deep) neural-networks due to their ability to capture participants' variability. This review paper shows the success of ML techniques in detecting disorders, predicting rehabilitation length, and control of rehabilitation devices which make them suitable for clinical diagnosis.

An individualized gait pattern prediction model based on the least absolute shrinkage and selection operator regression

Gait pattern prediction is an essential function of individualized motion control of the lower-limb exoskeleton. This paper presents a novel gait pattern prediction model based on the least absolute shrinkage and selection operator (LASSO) regression. Gait data were collected from one hundred and twenty healthy young adults (78 males and 42 females), who were instructed to walk back and forth on a 12-meter-long walking platform while having their heel strike coinciding with the beat of a metronome. The lower-limb joint (i.e., the hip, knee and ankle) angular kinematics were segmented, resampled and transformed into Fourier coefficients. The LASSO regression model with age, gender and 14 anthropometric parameters as prediction variables was trained and used to estimate the Fourier coefficients which were then applied in the lower-limb joint angle trajectory reconstruction. The results showed that the root mean square errors between the actual and predicted joint angle trajectories ranged from 3.41° to 4.55°. The parameters of the linear fit method further revealed the waveform similarity between the actual and predicted joint angle time series. These results suggested that the proposed model was able to accurately predict lower-limb joint kinematics during gait. Application of the proposed model can help resolve the overfitting problem, and provides a new solution to individualized gait pattern prediction.