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

Force Classification01:22

Force Classification

2.0K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
2.0K
Aggregates Classification01:29

Aggregates Classification

558
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
558

You might also read

Related Articles

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

Sort by
Same author

RetinoDeep: Leveraging Deep Learning Models for Advanced Retinopathy Diagnostics.

Sensors (Basel, Switzerland)·2025
Same author

Synergistic grasp analysis: A cross-sectional exploration using a multi-sensory data glove.

Wearable technologies·2025
Same author

The 'Sandwich' meta-framework for architecture agnostic deep privacy-preserving transfer learning for non-invasive brainwave decoding.

Journal of neural engineering·2024
Same author

Robust LQR-Based Neural-Fuzzy Tracking Control for a Lower Limb Exoskeleton System with Parametric Uncertainties and External Disturbances.

Applied bionics and biomechanics·2021
Same author

Preliminary design and development of a low-cost lower-limb exoskeleton system for paediatric rehabilitation.

Proceedings of the Institution of Mechanical Engineers. Part H, Journal of engineering in medicine·2021
Same author

Effect of photodynamic therapy alone or combined with posterior subtenon triamcinolone acetonide or intravitreal bevacizumab on choroidal hypofluorescence by indocyanine green angiography.

Retina (Philadelphia, Pa.)·2009

Related Experiment Video

Updated: Nov 20, 2025

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

515

Glove-Net: Enhancing Grasp Classification with Multisensory Data and Deep Learning Approach.

Subhash Pratap1,2, Jyotindra Narayan3,4, Yoshiyuki Hatta2

  • 1Department of Mechanical Engineering, Indian Institute of Technology Guwahati, Guwahati 781039, India.

Sensors (Basel, Switzerland)
|July 13, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces Glove-Net, a hybrid deep learning model for grasp classification using multisensory data gloves. The model effectively combines finger posture and force data for superior grasp recognition in human-robot interaction.

Keywords:
data glovesdeep learninggrasp classificationhuman grasp

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

1.6K
Design and Use of an Apparatus for Presenting Graspable Objects in 3D Workspace
09:11

Design and Use of an Apparatus for Presenting Graspable Objects in 3D Workspace

Published on: August 8, 2019

5.7K

Related Experiment Videos

Last Updated: Nov 20, 2025

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

515
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

1.6K
Design and Use of an Apparatus for Presenting Graspable Objects in 3D Workspace
09:11

Design and Use of an Apparatus for Presenting Graspable Objects in 3D Workspace

Published on: August 8, 2019

5.7K

Area of Science:

  • Robotics and Human-Computer Interaction
  • Machine Learning and Pattern Recognition
  • Biomechanics and Human Movement Analysis

Background:

  • Grasp classification is essential for human-robot interaction, robotics, prosthetics, and rehabilitation.
  • Existing methods often rely on single modalities, limiting grasp dynamic capture.
  • A need exists for advanced models that integrate multisensory data for comprehensive grasp analysis.

Purpose of the Study:

  • To introduce a novel methodology for grasp classification using a multisensory data glove.
  • To propose and evaluate Glove-Net, a hybrid CNN-BiLSTM architecture for grasp pattern recognition.
  • To assess the performance of multimodal grasp classification compared to unimodal approaches.

Main Methods:

  • Collected grasp data from 10 participants using a multisensory data glove capturing finger bending angles and fingertip forces with the YCB object set.
  • Developed and trained a hybrid Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) network, termed Glove-Net.
  • Evaluated classification performance using grasp posture data, grasp force data, and combined multimodal data.

Main Results:

  • The hybrid CNN-BiLSTM Glove-Net achieved the highest testing accuracies: 90.83% (posture), 73.12% (force), and 98.75% (combined).
  • Unimodal CNN achieved 88.09% (posture) and 69.38% (force), while LSTM achieved 86.02% (posture) and 70.52% (force).
  • Combined multimodal data significantly outperformed single modalities across all evaluated models.

Conclusions:

  • Multimodal grasp classification significantly enhances recognition accuracy compared to unimodal approaches.
  • The proposed Glove-Net architecture effectively leverages spatio-temporal features from multisensory data for precise grasp recognition.
  • This research advances human-machine interaction capabilities with potential applications in advanced robotics and assistive technologies.