An individualized gait pattern prediction model based on the least absolute shrinkage and selection operator
Xinyao Hu1, Fei Shen1, Zhong Zhao1
1Institute of Human Factors and Ergonomics, College of Mechatronics and Control Engineering, Shenzhen University, China.
Journal of Biomechanics
|October 11, 2020
Summary
This study introduces a new gait pattern prediction model using LASSO regression for lower-limb exoskeleton control. The model accurately predicts joint kinematics, offering a solution for individualized gait analysis and reducing overfitting.
Area of Science:
- Biomechanics
- Robotics
- Machine Learning
Background:
- Individualized motion control for lower-limb exoskeletons relies on accurate gait pattern prediction.
- Existing models may suffer from overfitting, limiting personalized application.
Purpose of the Study:
- To develop and validate a novel gait pattern prediction model for lower-limb exoskeleton control.
- To utilize LASSO regression for accurate estimation of lower-limb joint kinematics during gait.
Main Methods:
- Collected gait data from 120 healthy adults walking on a platform.
- Processed lower-limb joint angular kinematics into Fourier coefficients.
- Trained a LASSO regression model using demographic and anthropometric parameters to predict Fourier coefficients for trajectory reconstruction.
Main Results:
- The proposed LASSO regression model achieved root mean square errors between 3.41° and 4.55° for joint angle prediction.
- Linear fit analysis confirmed waveform similarity between actual and predicted joint angle time series.
- The model demonstrated accurate prediction of lower-limb joint kinematics during gait.
Conclusions:
- The developed LASSO regression model accurately predicts lower-limb joint kinematics for individualized gait analysis.
- This approach offers a new solution for gait pattern prediction in lower-limb exoskeleton control, mitigating overfitting issues.
Related Concept Videos
01:11Residuals and Least-Squares Property
8.7K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
8.7K
01:23Mechanistic Models: Compartment Models in Individual and Population Analysis
172
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
172