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

Relapsing Blastic Plasmacytoid Dendritic Cell Neoplasm With Neurologic Involvement.

Cureus·2026
Same author

Sensor Driven Resource Optimization Framework for Intelligent Fog Enabled IoHT Systems.

Sensors (Basel, Switzerland)·2026
Same author

Corrigendum to "Selection of appropriate location based on signed distance based ranking approach with interval type-2 trapezoidal fuzzy preference relations" [Heliyon Volume 10, Issue 15, August 2024, Article e34422].

Heliyon·2025
Same author

Motor-Sensory Coupled Learning for Motor Imagery Decoding.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Correction: Mohamed et al. The Effect of Drinking Ionized Water on the Productive Performance, Physiological Status, and Carcass Characteristics of Broiler Chicks. <i>Animals</i> 2025, <i>15</i>, 229.

Animals : an open access journal from MDPI·2025
Same author

Introducing a Standardized Clinical Investigation Sheet for Medical Documentation at Dongola Specialized Hospital, Sudan: A Quality Improvement Project.

Cureus·2025

Related Experiment Video

Updated: Aug 29, 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

Stochastic Recognition of Human Physical Activities via Augmented Feature Descriptors and Random Forest Model.

Sheikh Badar Ud Din Tahir1, Abdul Basit Dogar2, Rubia Fatima3

  • 1Department of Software Engineering, Capital University of Science and Technology (CUST), Islamabad 44000, Pakistan.

Sensors (Basel, Switzerland)
|September 9, 2022
PubMed
Summary

This study presents a new Human Physical Activity Recognition (HPAR) system using inertial sensors and machine learning. The HPAR model effectively recognizes daily living activities with high accuracy, benefiting healthcare and smart environments.

Keywords:
Hilbert–Huang transform (HHT)human physical activity recognition (HPAR)inertial measurement unit (IMU)stochastic gradient descent (SGD)

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
Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification
07:47

Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification

Published on: February 14, 2018

11.4K

Related Experiment Videos

Last Updated: Aug 29, 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
Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification
07:47

Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification

Published on: February 14, 2018

11.4K

Area of Science:

  • Computer Science
  • Biomedical Engineering
  • Machine Learning

Background:

  • Human physical activity recognition using inertial sensors is crucial for monitoring elderly individuals and children.
  • Developing advanced machine learning methods for inertial sensor data is a key research area.
  • Accurate activity recognition supports decision-making in various monitoring scenarios.

Purpose of the Study:

  • To enhance the recognition and classification of human physical activities.
  • To introduce a novel model integrating data preprocessing and domain-specific features.
  • To improve the performance of activity recognition using machine learning.

Main Methods:

  • A data-driven approach was employed for human daily living activity recognition.
  • A model integrating denoising, time, frequency, wavelet, and time-frequency features was developed.
  • Stochastic gradient descent (SGD) was utilized for feature optimization, feeding into a random forest classifier for Human Physical Activity Recognition (HPAR).

Main Results:

  • The HPAR system achieved high recognition rates across five benchmark datasets: IM-WSHA (90.18%), PAMAP-2 (91.25%), UCI HAR (91.83%), MobiAct (90.46%), and MOTIONSENSE (92.16%).
  • The proposed HPAR system demonstrated superior performance compared to existing state-of-the-art methods.
  • Experimental validation confirmed the effectiveness of the integrated feature extraction and classification approach.

Conclusions:

  • The developed HPAR system offers a robust solution for accurate human physical activity recognition.
  • The model's high performance indicates its potential for real-world applications.
  • Potential applications span healthcare, gaming, smart homes, security, and surveillance systems.