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 Dataset of University Students' Stress and Anxiety Levels based on Questionnaires and Wearable Sensors.

Scientific data·2026
Same author

OBF-Psychiatric, a motor activity dataset of patients diagnosed with major depression, schizophrenia, and ADHD.

Scientific data·2025
Same author

Urinary Nitric Oxide Levels Are Associated with Blood Pressure, Fruit and Vegetable Intake and Total Polyphenol Excretion in Adolescents from the SI! Program.

Antioxidants (Basel, Switzerland)·2022
Same author

Ingredients for Responsible Machine Learning: A Commented Review of <i>The Hitchhiker's Guide to Responsible Machine Learning</i>.

Journal of statistical theory and applications : JSTA·2022
Same author

Facial Expression Recognition from Multi-Perspective Visual Inputs and Soft Voting.

Sensors (Basel, Switzerland)·2022
Same author

Improved Accuracy in Predicting the Best Sensor Fusion Architecture for Multiple Domains.

Sensors (Basel, Switzerland)·2021
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: Apr 20, 2026

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

9.4K

Long-term activity recognition from wristwatch accelerometer data.

Enrique Garcia-Ceja1, Ramon F Brena2, Jose C Carrasco-Jimenez3

  • 1Tecnológico de Monterrey, Campus Monterrey, Av. Eugenio Garza Sada 2501 Sur, Monterrey 64849, Mexico. A00927248@itesm.mx.

Sensors (Basel, Switzerland)
|December 2, 2014
PubMed
Summary
This summary is machine-generated.

Wearable sensors can identify long-term activities using acceleration data. This study compares Hidden Markov Models and Conditional Random Fields, incorporating prior knowledge for improved activity recognition.

More Related Videos

A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers
07:24

A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers

Published on: April 21, 2017

13.2K
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

5.8K

Related Experiment Videos

Last Updated: Apr 20, 2026

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

9.4K
A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers
07:24

A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers

Published on: April 21, 2017

13.2K
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

5.8K

Area of Science:

  • Human-Computer Interaction
  • Wearable Computing
  • Activity Recognition

Background:

  • Wearable devices with embedded sensors collect user data for personalized services.
  • Existing research often requires obtrusive external sensors for complex activity recognition.
  • Acceleration data from wristwatches offers a non-intrusive method for activity monitoring.

Purpose of the Study:

  • To identify long-term human activities using acceleration data from a wristwatch.
  • To compare the effectiveness of Hidden Markov Models (HMM) and Conditional Random Fields (CRF) for activity segmentation.
  • To enhance activity recognition by incorporating prior knowledge and addressing intra-class fragmentation.

Main Methods:

  • Utilized acceleration data from a wristwatch.
  • Implemented and compared Hidden Markov Models and Conditional Random Fields for time-series segmentation.
  • Integrated prior knowledge about activity durations as constraints.
  • Incorporated sequence patterns as feature functions.
  • Applied subclassing to mitigate intra-class fragmentation.

Main Results:

  • Both HMM and CRF models were evaluated for long-term activity identification.
  • The integration of prior knowledge and subclassing improved the accuracy of activity recognition.
  • Conditional Random Fields showed competitive performance in segmenting and classifying activities.

Conclusions:

  • Wristwatch acceleration data is effective for recognizing long-term activities.
  • Incorporating domain knowledge and advanced modeling techniques like HMM and CRF enhances activity recognition accuracy.
  • The proposed methods offer a promising approach for non-intrusive, personalized activity monitoring.