Deep neural networks (DNNs) and transfer learning (TL) have been used to improve surface electromyogram (sEMG)-based force estimation. However, prior studies focused mostly on applying TL within one joint, which limits dataset size and diversity. Herein, we investigated cross-joint TL between two upper-limb joints with four DNN architectures using sliding windows. We used two feedforward and two recurrent DNN models with feature engineering and feature learning, respectively. We found that the dependencies between sEMG and force are short-term (<400 ms) and that sliding windows are sufficient to capture them, suggesting that more complicated recurrent structures may not be necessary. Also, using DNN architectures reduced the required sliding window length. A model pre-trained on elbow data was fine-tuned on hand-wrist data, improving force estimation accuracy and reducing the required training data amount. A convolutional neural network with a 391 ms sliding window fine-tuned using 20 s of training data had an error of 6.03 ± 0.49% maximum voluntary torque, which is statistically lower than both our multilayer perceptron model with TL and a linear regression model using 40 s of training data. The success of TL between two distinct joints could help enrich the data available for future deep learning-related studies.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11598622 | PMC |
http://dx.doi.org/10.3390/s24227301 | DOI Listing |
J Geriatr Phys Ther
November 2024
Department of Physical Therapy and Rehabilitation Science, University of Maryland School of Medicine, Baltimore, Maryland.
Background And Purpose: Muscle strength, power, and mass decline with aging, leading to functional loss highly correlated with balance and falls in older adults. Lower limb muscle function is critical for fall prevention in older adults, and hip abductor force and rapid force development have been shown to be important during stepping tasks. However, it remains unclear whether hip abductor muscle function changes with aging.
View Article and Find Full Text PDFSci Rep
January 2025
Human Movement Biomechanics Research Group, Department of Movement Sciences, KU Leuven, Leuven, Belgium.
The treatment of Achilles tendinopathy is challenging, as 40% of patients do not respond to existing rehabilitation protocols. These protocols neglect individual Achilles tendon (AT) characteristics, which are crucial for healing of the tendon tissue. Although prior studies suggest an optimal strain for AT regeneration (6% tendon strains), it is unclear if current protocols meet this condition.
View Article and Find Full Text PDFPLoS One
January 2025
Institute of Sport Sciences and Physical Education, Faculty of Sciences, University of Pécs, Pécs, Hungary.
The aim of this study was to investigate the associations among in-water vertical jump and various dry-land physical measures by taking the law of Archimedes into consideration, and by normalizing the dry-land measures both to body density and body mass. Seventeen elite water polo players from Hungarian first league were tested for dry-land counter movement and squat jump mechanical impulse, isometric squat force, and in-water vertical jump height. Body density was estimated by anthropometric measurements.
View Article and Find Full Text PDFEuroIntervention
January 2025
Department of Cardiac-Thoracic-Vascular Sciences, University of Padua, Padua, Italy.
This clinical consensus statement of the European Association of Percutaneous Cardiovascular Interventions was developed in association with the European Society of Cardiology Working Group on Cardiovascular Surgery. It aims to define procedural and contemporary technical requirements that may improve the efficacy and safety of percutaneous coronary intervention (PCI), both in the acute phase and at long-term follow-up, in a high-risk cohort of patients on optimal medical therapy when clinical and anatomical high-risk criteria are present that entail unacceptable surgical risks, precluding the feasibility of coronary artery bypass grafting (CABG). This document pertains to patients with surgical contraindication according to the Heart Team, in whom medical therapy has failed (e.
View Article and Find Full Text PDFSensors (Basel)
December 2024
Laboratory of Bio-Mechatronics, Faculty of Engineering, Kitami Institute of Technology, Koentyo 165, Kitami Shi 090-8507, Hokkaido, Japan.
Harvesting grapes requires a large amount of manual labor. To reduce the labor force for the harvesting job, in this study, we developed a robot harvester for the vine grapes. In this paper, we proposed an algorithm that using multi-cameras, as well as artificial intelligence (AI) object detection methods, to detect the thin stem and decide the cut point.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!