We extract the informative features of gyroscope signals using the discrete wavelet transform (DWT) decomposition and provide them as input to multi-layer feed-forward artificial neural networks (ANNs) for leg motion classification. Since the DWT is based on correlating the analyzed signal with a prototype wavelet function, selection of the wavelet type can influence the performance of wavelet-based applications significantly. We also investigate the effect of selecting different wavelet families on classification accuracy and ANN complexity and provide a comparison between them. The maximum classification accuracy of 97.7% is achieved with the Daubechies wavelet of order 16 and the reverse bi-orthogonal (RBO) wavelet of order 3.1, both with similar ANN complexity. However, the RBO 3.1 wavelet is preferable because of its lower computational complexity in the DWT decomposition and reconstruction.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3274015 | PMC |
| http://dx.doi.org/10.3390/s110201721 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
The Impact of Exercise Play on the Biomechanical Characteristics of Single-Leg Jumping in 5- to 6-Year-Old Preschool Children.
Sensors (Basel)
January 2025
College of P.E. and Sports, Beijing Normal University, Beijing 100875, China.
Objective: This study aimed to investigate the effects of a 12-week self-designed exercise game intervention on the kinematic and kinetic data of the supporting leg in preschool children during the single-leg jump.
Methods: Thirty 5- to 6-year-old preschool children were randomly divided into an experimental group (EG) and a control group (CG). The BTS SMART DX motion capture analysis system was used to collect single-leg jump data before the intervention.
Inchworm Robots Utilizing Friction Changes in Magnetorheological Elastomer Footpads Under Magnetic Field Influence.
Micromachines (Basel)
December 2024
Department of Mechanical Engineering, Inha University, Incheon 22212, Republic of Korea.
The application of smart materials in robots has attracted considerable research attention. This study developed an inchworm robot that integrates smart materials and a bionic design, using the unique properties of magnetorheological elastomers (MREs) to improve the performance of robots in complex environments, as well as their adaptability and movement efficiency. This research stems from solving the problem of the insufficient adaptability of traditional bionic robots on different surfaces.
View Article and Find Full Text PDFA Muscle Physiology-Based Framework for Quantifying Training Load in Resistance Exercises.
Sports (Basel)
January 2025
DMeM, University of Montpellier, INRAE, 34000 Montpellier, France.
Background: Objective training load (TL) indexes used in resistance training lack physiological significance. This study was aimed to provide a muscle physiology-based approach for quantifying TL in resistance exercises (REs).
Methods: Following individual torque-velocity profiling, fifteen participants (11 healthy males, stature: 178.
Bionic Modeling Study on the Landing Mechanism of Flapping Wing Robot Based on the Thoracic Legs of Purple Stem Beetle, .
Biomimetics (Basel)
January 2025
Robotics and Microsystems Center, College of Mechanical and Electrical Engineering, Soochow University, Suzhou 215021, China.
Flapping wing micro aerial vehicles (FWMAVs) are recognized for their significant potential in military and civilian applications, such as military reconnaissance, environmental monitoring, and disaster rescue. However, the lack of takeoff and landing capabilities, particularly in landing behavior, greatly limits their adaptability to the environment during tasks. In this paper, the purple stem beetle (), a natural flying insect, was chosen as the bionic research object.
View Article and Find Full Text PDFOlder Fallers' Comprehensive Neuromuscular and Kinematic Alterations in Reactive Balance Control: Indicators of Balance Decline or Compensation? A Pilot Study.
Bioengineering (Basel)
January 2025
Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong SAR 999077, China.
: Falls and fall consequences in older adults are global health issues. Previous studies have compared postural sways or stepping strategies between older adults with and without fall histories to identify factors associated with falls. However, more in-depth neuromuscular/kinematic mechanisms have remained unclear.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!