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

EEG-based harmful brain activity classification using deep learning and feature fusion.

Scientific reports·2026
Same author

GGAR: gradient guided adaptive regularization enhances deep learning classification of brassica species using codon usage bias.

BMC bioinformatics·2026
Same author

A robust deep learning approach for impulse noise filtering using hybrid auto-encoder with fuzzy median filter.

PloS one·2026
Same author

BAAR: A framework for blockchain-based anonymous and revocable user authentication scheme.

PloS one·2026
Same author

Ensemble Deep Learning-Based High-Precision Framework for Breast Cancer Detection from Histopathological Images.

Diagnostics (Basel, Switzerland)·2026
Same author

Unveiling the black box: Explainable transfer learning for ocular disorder diagnosis.

Digital health·2026
Same journal

Characterization of genomic diversity in bacteriophages infecting Rhodococcus.

PloS one·2026
Same journal

Effectiveness of the Responding to Experienced and Anticipated Discrimination (READ) training on reducing stigma for medical students in Tunisia.

PloS one·2026
Same journal

Cell-cell junction gene signatures as subtype-specific prognostic biomarkers in breast cancer.

PloS one·2026
Same journal

GC-MS based tentative identification of γ-sitosterol from Brassica nigra seeds and evaluation of its anticancer potential: An integrated in vitro and in silico study.

PloS one·2026
Same journal

Ad-based social media interventions increase belief accuracy and generate pro-social opinions among non-news readers.

PloS one·2026
Same journal

Negotiating knowledge: The role of network hedging in the production of high-impact science.

PloS one·2026
See all related articles

Related Experiment Video

Updated: May 10, 2025

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

2.4K

Intelligent recognition of human activities using deep learning techniques.

Shazab Bashir1,2, Arfan Jaffar1,2, Muhammad Rashid3

  • 1Faculty of Computer Science & Information Technology, The Superior University, Lahore, Pakistan.

Plos One
|April 24, 2025
PubMed
Summary
This summary is machine-generated.

This study enhances human action recognition (HAR) in videos using an ensemble of deep learning models. The advanced ensemble method achieves superior accuracy, setting new standards for healthcare and surveillance applications.

More Related Videos

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

8.8K
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.3K

Related Experiment Videos

Last Updated: May 10, 2025

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

2.4K
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

8.8K
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.3K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Machine Learning

Background:

  • Human Action Recognition (HAR) is vital for analyzing human behavior in videos.
  • Deep learning frameworks offer powerful tools for HAR tasks.
  • Existing methods can be improved for greater accuracy and reliability.

Purpose of the Study:

  • To investigate and enhance Human Action Recognition (HAR) in RGB videos using deep learning.
  • To develop an ensemble model integrating 3D-AlexNet-RF and InceptionV3 Google-Net for improved HAR accuracy.
  • To evaluate the ensemble framework's performance on the HMDB51 dataset for diverse human actions.

Main Methods:

  • Utilized an ensemble method combining predictions from 3D-AlexNet-RF and InceptionV3 Google-Net models.
  • Trained Inflated-3D (I3D) video classifiers on the HMDB51 dataset.
  • Employed voting or averaging techniques to merge individual model predictions for a final classification.

Main Results:

  • Achieved an aggregate accuracy of 99.54% on the HMDB51 dataset.
  • Demonstrated high performance across various metrics including precision (97.94%), recall (97.94%), and F1-Score (97.88%).
  • The ensemble model proved highly effective and reliable for HAR tasks.

Conclusions:

  • The proposed ensemble model significantly enhances HAR performance.
  • This approach sets a new standard for applications in healthcare, surveillance, and human-robot interaction.
  • Multi-tiered ensembles show promise for boosting recognition in wearable technology.