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

A machine learning study highlighting the challenges of fidgety movement recognition using vision and inertial sensors.

Scientific reports·2026
Same author

Dissecting the Causal Association Between Bulimia Nervosa and Structural Brain Abnormalities: A Two-Sample Bidirectional Mendelian Randomization Study.

Brain and behavior·2025
Same author

PET/CT radiomics for non-invasive prediction of immunotherapy efficacy in cervical cancer.

Journal of X-ray science and technology·2025
Same author

COVID-19CT+: A public dataset of CT images for COVID-19 retrospective analysis.

Journal of X-ray science and technology·2025
Same author

Artificial Intelligence Performance in Image-Based Cancer Identification: Umbrella Review of Systematic Reviews.

Journal of medical Internet research·2025
Same author

A comprehensive survey and comparative analysis of time series data augmentation in medical wearable computing.

PloS one·2025
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles

Related Experiment Video

Updated: Dec 17, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.1K

Rank Pooling Approach for Wearable Sensor-Based ADLs Recognition.

Muhammad Adeel Nisar1, Kimiaki Shirahama2, Frédéric Li1

  • 1Institute of Medical Informatics, University of Lübeck, Ratzeburger Allee 160, 23562 Lübeck, Germany.

Sensors (Basel, Switzerland)
|June 25, 2020
PubMed
Summary
This summary is machine-generated.

This study introduces a hierarchical model for recognizing Activities of Daily Living (ADLs) using wearable sensors. The model effectively identifies atomic actions and their temporal sequences, improving composite activity recognition.

Keywords:
activities of daily lifeatomic activitiescomposite activitieshuman activity recognitionrank pooling

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

5.0K
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

9.2K

Related Experiment Videos

Last Updated: Dec 17, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.1K
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

5.0K
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

9.2K

Area of Science:

  • Human-Computer Interaction
  • Wearable Computing
  • Biomedical Engineering

Background:

  • Activities of Daily Living (ADLs) recognition using wearable sensors is challenging due to the complex temporal dependencies of composite activities.
  • Directly using sensor data for long-term ADL recognition is difficult because of high variability in data sequences for the same activity.
  • Atomic actions, which are shorter and more semantic, offer a more robust basis for recognizing complex ADLs.

Purpose of the Study:

  • To develop a novel two-level hierarchical model for accurate recognition of composite Activities of Daily Living (ADLs).
  • To address the challenge of temporal dependencies and data variability in wearable-based ADL recognition.
  • To introduce and evaluate a temporal pooling method, rank pooling, for encoding atomic action sequences.

Main Methods:

  • A two-level hierarchical model was proposed, starting with the detection of atomic activities and generation of probabilistic scores.
  • A temporal pooling method, specifically rank pooling, was employed at the higher level to encode the ordering of atomic activity scores.
  • A large dataset comprising 61 atomic and 7 composite activities was created for experimental validation.

Main Results:

  • The proposed hierarchical model demonstrated improved recognition of composite Activities of Daily Living (ADLs).
  • Rank pooling significantly enhanced the encoding of temporal transitions between atomic activities.
  • The rank pooling method resulted in a 5-13% performance improvement compared to existing popular techniques.

Conclusions:

  • The hierarchical model effectively leverages atomic actions and their temporal order for robust ADL recognition.
  • Rank pooling is a promising technique for capturing temporal dependencies in sequential data for wearable-based activity recognition.
  • The developed dataset provides a valuable resource for future research in wearable-based ADL recognition.