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

Identification and Speed Estimation of a Moving Object in an Indoor Application Based on Visible Light Sensing of Retroreflective Foils.

Micromachines·2021
See all related articles

Related Experiment Video

Updated: Aug 15, 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

4.0K

Improved Spatiotemporal Framework for Human Activity Recognition in Smart Environment.

Ziad Salem1, Andreas Peter Weiss1

  • 1Smart Connected Lighting Research Group, Institute for Surface Technologies and Photonics, Joanneum Research Forschungsgesellschaft mbH, Industriestrasse 6, 7423 Pinkafeld, Austria.

Sensors (Basel, Switzerland)
|January 8, 2023
PubMed
Summary
This summary is machine-generated.

This study enhances human activity recognition (HAR) and localization using inertial sensors and visible light sensing. Advanced feature extraction boosts accuracy to over 90% for industrial applications in real-world conditions.

Keywords:
features extractionhuman activity recognitioninertial measurement unitmachine learningsensor data fusionvisible light sensing

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

9.0K
Trajectory Data Analyses for Pedestrian Space-time Activity Study
16:14

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

13.6K

Related Experiment Videos

Last Updated: Aug 15, 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

4.0K
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
Trajectory Data Analyses for Pedestrian Space-time Activity Study
16:14

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

13.6K

Area of Science:

  • Microsystems technology
  • Machine learning
  • Human activity recognition (HAR)
  • Sensor fusion

Background:

  • Previous spatiotemporal frameworks for HAR combined inertial measurement unit (IMU) and visible light sensing (VLS) data.
  • These systems showed promise for real-time HAR and room identification.

Purpose of the Study:

  • To extend existing HAR systems by incorporating time and frequency domain feature extraction.
  • To improve the accuracy of human activity determination and room localization in industrial settings.
  • To validate the system's applicability under real-world ambient light conditions.

Main Methods:

  • Fusion of data from an inertial measurement unit (IMU) and an RGB photodiode for visible light sensing (VLS).
  • Application of time and frequency domain feature extraction techniques.
  • Evaluation of system performance in industrial scenarios and ambient light.

Main Results:

  • Human activity recognition accuracy increased to over 90%.
  • Improved determination of common human activities in industrial scenarios.
  • Successful demonstration of the system's applicability in real-world operating conditions.

Conclusions:

  • The enhanced HAR system significantly improves activity recognition and localization accuracy.
  • Time and frequency domain features are crucial for robust performance in industrial environments.
  • The developed solution is practical for real-world applications, including those in healthcare and industry 4.0.