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

Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

130
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
130
Naming Skeletal Muscles01:19

Naming Skeletal Muscles

2.4K
The naming of the approximately 700 muscles in the human body is based on a set of criteria designed to provide descriptive information about each muscle, making it easier to identify and remember them.
The key factors used in naming muscles include:
2.4K
Carbon Skeletons01:12

Carbon Skeletons

108.0K
Life on Earth is carbon-based, as all macromolecules that make up living organisms contain carbon atoms. All organic compounds have a carbon backbone. Each carbon atom is tetravalent and can bond with four other atoms, making it an extraordinarily flexible component of biological molecules. Because carbon’s valence electrons are stable, it rarely becomes an ion. As the carbon chain increases in length, structural modifications such as ring structures, double bonds, and branching side...
108.0K
Classification of Bones01:18

Classification of Bones

5.9K
The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The...
5.9K
Generation of Action Potential in Skeletal Muscles01:24

Generation of Action Potential in Skeletal Muscles

4.7K
Every cell in the body maintains a membrane potential due to an uneven distribution of positive and negative charges across its plasma membrane. The membrane potential is measured in millivolts and quantifies the difference in charge across the membrane.
Like neurons, muscle cells are also regarded as excitable due to their capacity to change in response to stimuli, primarily due to voltage-gated ion channels embedded in their plasma membranes, which get activated by alterations in the...
4.7K
Muscles for Facial Expressions01:14

Muscles for Facial Expressions

2.4K
The craniofacial muscles are a collection of approximately 20 thin skeletal muscles situated beneath the skin of the face and scalp. These muscles, primarily responsible for the vast array of human facial expressions, originate from the bones or fibrous structures of the skull and extend outwards to connect with the skin. While most skeletal muscles in the body are enveloped in thick fascia, facial muscles generally have a more delicate fascial covering, with the buccinator muscle being a...
2.4K

You might also read

Related Articles

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

Sort by
Same author

Automated Food Weight and Content Estimation Using Computer Vision and AI Algorithms: Phase 2.

Sensors (Basel, Switzerland)·2026
Same author

Automated Food Weight and Content Estimation Using Computer Vision and AI Algorithms.

Sensors (Basel, Switzerland)·2024
Same author

Train Station Pedestrian Monitoring Pilot Study Using an Artificial Intelligence Approach.

Sensors (Basel, Switzerland)·2024
Same author

Deep Learning Models to Reduce Stray Light in TJ-II Thomson Scattering Diagnostic.

Sensors (Basel, Switzerland)·2024
Same author

Development and Control of a Real Spherical Robot.

Sensors (Basel, Switzerland)·2023
Same author

3D Object Detection for Self-Driving Cars Using Video and LiDAR: An Ablation Study.

Sensors (Basel, Switzerland)·2023

Related Experiment Video

Updated: Aug 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

3.9K

BERT for Activity Recognition Using Sequences of Skeleton Features and Data Augmentation with GAN.

Heilym Ramirez1, Sergio A Velastin2,3, Sara Cuellar1

  • 1Escuela de Ingeniería Eléctrica, Pontificia Universidad Católica de Valparaíso, Av. Brasil 2147, Valparaíso 2362804, Chile.

Sensors (Basel, Switzerland)
|February 11, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces a deep learning method for human activity recognition using skeleton pose estimation and Bidirectional Encoder Representation of Transformers (BERT). The approach effectively recognizes activities from video, outperforming existing methods on the UP-Fall dataset.

Keywords:
BERTactivity recognitioncomputer visionhuman skeletonpose estimation

More Related Videos

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training
06:20

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Published on: December 6, 2024

2.9K
SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots
11:01

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

Published on: November 24, 2015

13.2K

Related Experiment Videos

Last Updated: Aug 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

3.9K
Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training
06:20

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Published on: December 6, 2024

2.9K
SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots
11:01

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

Published on: November 24, 2015

13.2K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Biomedical Engineering

Background:

  • Human activity recognition is crucial for elderly care and health monitoring.
  • Current methods using body sensors have limitations like discomfort and inaccuracy.
  • Image and video-based recognition offers a more comprehensive solution but requires advanced techniques.

Purpose of the Study:

  • To develop an advanced deep learning model for accurate human activity recognition from video data.
  • To address the limitations of sensor-based methods by utilizing visual information.
  • To improve the detection of subtle human conditions and activities.

Main Methods:

  • Utilized deep learning with attention mechanisms for multi-frame activity recognition.
  • Extracted features through human skeleton pose estimation.
  • Employed a Bidirectional Encoder Representation of Transformers (BERT) neural network for classification.
  • Augmented the UP-Fall dataset using Generative Adversarial Networks (GANs) for balanced training data.

Main Results:

  • The proposed deep learning approach demonstrated superior performance in activity recognition.
  • The model successfully recognized activities from video, outperforming existing methods on the UP-Fall dataset.
  • GAN-generated data improved the model's robustness and balanced the dataset.

Conclusions:

  • Deep learning, particularly with skeleton pose estimation and BERT, is highly effective for human activity recognition.
  • This method offers a promising alternative to sensor-based systems for health and elderly care applications.
  • The integration of GANs enhances dataset quality and model performance.