Search research articles

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

rKAN: Rational Kolmogorov-Arnold networks.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

A symbolic dataset for large language models to solve second kind Fredholm integral equations.

Scientific data·2025

Same author

Design, Fabrication, and Validation of a Portable Perturbation Treadmill for Balance Recovery Research.

Journal of medical devices·2024

Same author

Dual Accuracy-Quality-Driven Neural Network for Prediction Interval Generation.

IEEE transactions on neural networks and learning systems·2023

Same author

Automated assessment of the smoothness of retinal layers in optical coherence tomography images using a machine learning algorithm.

BMC medical imaging·2023

Same author

Improved Yield Prediction of Winter Wheat Using a Novel Two-Dimensional Deep Regression Neural Network Trained via Remote Sensing.

Sensors (Basel, Switzerland)·2023

Same journal

Age-related adaptations in acceleration and deceleration control during gait.

Journal of biomechanics·2026

Same journal

Regional mechanical differences in hamstring muscles after removal of surrounding connective tissue.

Journal of biomechanics·2026

Same journal

A novel knee joint laxity measurement device in mice.

Journal of biomechanics·2026

Same journal

Influence of iliofemoral ligament laxity on hip joint contact forces during gait.

Journal of biomechanics·2026

Same journal

Associations of sagittal spinal alignment with shear wave velocity, thickness, and echo intensity of muscles attached to the spine and pelvis in healthy women.

Journal of biomechanics·2026

Same journal

The gait lab effect: symmetry restoration strategy after anterior cruciate ligament reconstruction is different in natural environments than the gait laboratory.

Journal of biomechanics·2026

See all related articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Apr 16, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Automated dual-stream deep network design for activity recognition.

Seyed Mojtaba Mohasel¹, Alireza Afzal Aghaei², John W Sheppard³

¹Department of Mechanical and Industrial Engineering, Montana State University, Bozeman, Montana, USA.

Journal of Biomechanics

|April 14, 2026

Summary

This summary is machine-generated.

This study introduces an automated deep learning (AutoDL) framework for biomechanics, improving sensor data analysis. The AutoDL system outperformed existing methods and human-designed models in activity recognition tasks.

Keywords:

AutoML CNN Class imbalance Genetic algorithm NAS Time and frequency domain features

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Related Experiment Videos

Last Updated: Apr 16, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Area of Science:

Biomechanics
Machine Learning
Sensor Data Analysis

Background:

Multivariate time-series sensor data analysis is crucial in biomechanics.
Existing automated deep learning (AutoDL) systems may not be optimized for biomechanical data.
Activity recognition requires robust feature extraction and classification methods.

Purpose of the Study:

To present an automated deep learning (AutoDL) framework for multivariate time-series sensor data in biomechanics.
To evaluate the impact of time- and frequency-domain features on model performance.
To compare the proposed AutoDL framework against existing AutoDL systems and human-designed models.

Main Methods:

Utilized four public activity recognition datasets with varying sensor placements and class imbalances.
Implemented automated extraction of time- and frequency-domain features.
Employed a dual-stream convolutional neural network with a genetic algorithm for optimization and addressed class imbalance.

Main Results:

Ablation of time- or frequency-domain features significantly reduced model F1-score performance in most datasets.
The proposed AutoDL framework achieved higher F1-scores than existing AutoDL systems and human-designed models in three out of four datasets.
The developed models were successfully deployed on a Raspberry Pi 3 for potential real-world applications.

Conclusions:

Automation and frequency-domain features are vital for capturing biomechanical characteristics in cyclic movements.
The proposed AutoDL framework offers a significant advancement for sensor data analysis in biomechanics.
The open-source release is expected to accelerate biomechanics research and health monitoring tool development.