Jove
Visualize
Contact Us

Related Concept Videos

Force Classification01:22

Force Classification

1.1K
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,...
1.1K
Associative Learning01:27

Associative Learning

285
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
285

You might also read

Related Articles

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

Sort by
Same author

Table-Balancing Cooperative Robot Based on Deep Reinforcement Learning.

Sensors (Basel, Switzerland)·2023
Same author

Reduced Expression of <i>PRX2</i>/<i>ATPRX1</i>, <i>PRX8</i>, <i>PRX35</i>, and <i>PRX73</i> Affects Cell Elongation, Vegetative Growth, and Vasculature Structures in <i>Arabidopsis thaliana</i>.

Plants (Basel, Switzerland)·2022
Same author

Generalized Term Similarity for Feature Selection in Text Classification Using Quadratic Programming.

Entropy (Basel, Switzerland)·2020
Same author

Multi-Population Genetic Algorithm for Multilabel Feature Selection Based on Label Complementary Communication.

Entropy (Basel, Switzerland)·2020
Same author

Competitive Particle Swarm Optimization for Multi-Category Text Feature Selection.

Entropy (Basel, Switzerland)·2020
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 Experiment Video

Updated: May 31, 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

390

Real-Time On-Device Continual Learning Based on a Combined Nearest Class Mean and Replay Method for Smartphone

Heon-Sung Park1, Min-Kyung Sung2, Dae-Won Kim1

  • 1School of Computer Science and Engineering, Chung-Dang University, Heukseok-dong, Dongjak-gu, Seoul 06974, Republic of Korea.

Sensors (Basel, Switzerland)
|January 25, 2025
PubMed
Summary

We developed the first on-device continual learning framework for gesture recognition. This method achieves over 99% accuracy, enabling adaptive human-computer interaction without server reliance.

Keywords:
continual learninggesture recognitionon-device AI

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

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

Published on: December 15, 2023

2.6K
Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

8.9K

Related Experiment Videos

Last Updated: May 31, 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

390
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

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

Published on: December 15, 2023

2.6K
Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

8.9K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Human-Computer Interaction

Background:

  • Sensor-based gesture recognition is crucial for intuitive mobile device interaction.
  • Current methods require server-based retraining, leading to high energy use and latency.
  • On-device adaptation is needed for efficient and responsive gesture recognition.

Purpose of the Study:

  • To introduce the first on-device continual learning framework for gesture recognition.
  • To enable continuous adaptation to new gestures with limited resources.
  • To address energy consumption and latency issues in current approaches.

Main Methods:

  • Utilized a Nearest Class Mean (NCM) classifier.
  • Implemented a replay-based update strategy for continuous learning.
  • Employed replay buffer management to mitigate catastrophic forgetting.

Main Results:

  • Achieved over 99% accuracy on a Samsung Galaxy S10 device.
  • Demonstrated high recognition accuracy entirely on-device.
  • Showcased computational efficiency and stable performance with new gestures.

Conclusions:

  • The developed framework offers a viable solution for resource-constrained, adaptive gesture recognition.
  • On-device continual learning with NCM classifiers and replay techniques is effective.
  • This approach advances intuitive human-computer interaction in mobile applications.