Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

MultiRetNet: A Lightweight Explainable AI Approach to Diabetic Retinopathy Grading and DME Detection Using Fundus-OCT Fusion.

Journal of imaging·2026
Same author

DiagPat: An Explainable Language Detection Model Using EEG Signals.

Sensors (Basel, Switzerland)·2026
Same author

Arginine-Silicate-Inositol Promotes Femoral Fracture Healing in Rats.

Biological trace element research·2026
Same author

Reply to Dolu, K.O. Comment on "Topaloglu et al. Machine Learning-Driven Lung Sound Analysis: Novel Methodology for Asthma Diagnosis. <i>Adv. Respir. Med.</i> 2025, <i>93</i>, 32".

Advances in respiratory medicine·2026
Same author

TensorCSBP: A Tensor Center-Symmetric Feature Extractor for EEG Odor Detection.

Diagnostics (Basel, Switzerland)·2026
Same author

GPTNeXt: Biomedical Image Classification Investigations.

Diagnostics (Basel, Switzerland)·2026

Related Experiment Video

Updated: Sep 30, 2025

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

797

A Hand-Modeled Feature Extraction-Based Learning Network to Detect Grasps Using sEMG Signal.

Mehmet Baygin1, Prabal Datta Barua2,3,4, Sengul Dogan5

  • 1Department of Computer Engineering, College of Engineering, Ardahan University, Ardahan 75000, Turkey.

Sensors (Basel, Switzerland)
|March 10, 2022
PubMed
Summary
This summary is machine-generated.

A new method, Frustum154, extracts features from electromyography (EMG) signals using geometric shapes and wavelet transforms. This approach enhances classification accuracy for hand movements without deep learning complexities.

Keywords:
Frustum154frustum patterngrasp detectionsEMG signal classification

More Related Videos

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.8K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

666

Related Experiment Videos

Last Updated: Sep 30, 2025

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

797
Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.8K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

666

Area of Science:

  • Biomedical Engineering
  • Machine Learning
  • Signal Processing

Background:

  • Deep learning models offer high performance in classification but demand significant computational resources and specialized hardware.
  • Existing methods for electromyography (EMG) signal classification often require extensive datasets and struggle with generalization across different datasets.
  • There is a need for efficient feature extraction and selection methods that maintain high classification accuracy while reducing computational complexity.

Purpose of the Study:

  • To introduce Frustum154, a novel hybrid feature extraction method for electromyography (EMG) signal analysis.
  • To overcome the computational demands of deep learning models by proposing a hand-modeled feature selection approach.
  • To improve the classification accuracy of hand-movement EMG datasets using a self-organized, multi-level feature generation process.

Main Methods:

  • A shape-based local feature extractor utilizing the geometric properties of a frustum pattern to generate textural features.
  • Fusion of textural and statistical features to create low-level hybrid features, followed by tunable Q factor wavelet transform (TQWT) for high-level feature generation.
  • Automated selection of informative feature vectors using Iterative Neighborhood Component Analysis (INCA) for subsequent classification with shallow models.

Main Results:

  • The Frustum154 method generates 154 feature vectors, enabling automatic selection of the most relevant ones.
  • Testing on three distinct hand-movement EMG datasets demonstrated robust performance.
  • Achieved high classification accuracies of 98.89%, 94.94%, and 95.30% when utilizing shallow classifiers.

Conclusions:

  • Frustum154 effectively extracts and selects informative features from EMG signals, enhancing classification performance.
  • The proposed method offers a computationally efficient alternative to deep learning models for EMG-based classification tasks.
  • Frustum154 demonstrates significant potential for improving the accuracy and generalizability of hand-movement recognition systems in biomedical applications.