Jove
Visualize
Contact Us

Related Concept Videos

Absolute Motion Analysis- General Plane Motion01:24

Absolute Motion Analysis- General Plane Motion

244
Visualize a drone, with its propellers spinning rapidly, hovering mid-air. The fascinating movements and operations of this drone can be comprehended by applying the principle of general plane motion.
As the drone's propellers rotate, an upward force is generated that counteracts the force of gravity, enabling the drone to lift off from the ground. This initial movement of the drone is along a straight path, representing a form of translational motion. In this phase, every point on the...
244
Force Classification01:22

Force Classification

1.3K
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,...
1.3K

You might also read

Related Articles

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

Sort by
Same author

FedOpenHAR: Federated Multitask Transfer Learning for Sensor-Based Human Activity Recognition.

Journal of computational biology : a journal of computational molecular cell biology·2025
Same author

Multitask Learning for Mental Health: Depression, Anxiety, Stress (DAS) Using Wearables.

Diagnostics (Basel, Switzerland)·2024
Same author

Quantifying Digital Biomarkers for Well-Being: Stress, Anxiety, Positive and Negative Affect via Wearable Devices and Their Time-Based Predictions.

Sensors (Basel, Switzerland)·2023
See all related articles
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: Jul 27, 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

On the Use of a Convolutional Block Attention Module in Deep Learning-Based Human Activity Recognition with Motion

Sumeyye Agac1, Ozlem Durmaz Incel1

  • 1Department of Computer Engineering, Bogazici University, Istanbul 34342, Turkey.

Diagnostics (Basel, Switzerland)
|June 10, 2023
PubMed
Summary

Convolutional Block Attention Module (CBAM) enhances deep learning models for sensor-based human activity recognition. Spatial attention improved the Opportunity dataset, while channel attention boosted the Pamap2 dataset, with minimal parameter increases.

Keywords:
attention mechanismchannel attentionconvolutional neural networkshuman activity recognitionhybrid deep modelsmotion sensorsspatial attention

More Related Videos

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

9.5K
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

9.0K

Related Experiment Videos

Last Updated: Jul 27, 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
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

9.5K
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

9.0K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Sensor-based human activity recognition (HAR) utilizes wearable devices and deep learning models.
  • Attention-based models are increasingly used to improve HAR performance by dynamically tuning features.
  • The impact of Convolutional Block Attention Module (CBAM) on the DeepConvLSTM model for HAR remains understudied.

Purpose of the Study:

  • To investigate the performance of CBAM, including channel and spatial attention, on the DeepConvLSTM architecture for HAR.
  • To analyze the additional parameters required by CBAM modules for resource optimization in wearable devices.
  • To evaluate the effectiveness of CBAM in improving recognition accuracy on benchmark datasets.

Main Methods:

  • Applied individual and combined channel and spatial attention mechanisms of CBAM to the DeepConvLSTM model.
  • Evaluated model performance using the Pamap2 (12 activities) and Opportunity (18 micro-activities) datasets.
  • Compared recognition performance and additional parameter counts against the baseline DeepConvLSTM model.

Main Results:

  • Spatial attention improved the Opportunity dataset's macro F1-score from 0.74 to 0.77.
  • Channel attention improved the Pamap2 dataset's performance from 0.95 to 0.96 with negligible parameter increase.
  • Attention mechanisms boosted performance on activities with lower scores in the baseline model.

Conclusions:

  • CBAM effectively enhances DeepConvLSTM for sensor-based HAR, improving performance on benchmark datasets.
  • The study demonstrates the potential for attention mechanisms to optimize HAR models for resource-constrained wearable devices.
  • The combined CBAM and DeepConvLSTM approach achieved superior results compared to related studies on the same datasets.