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

Mining resistance genes of soybean cyst nematode based on genome-wide association study.

Frontiers in plant science·2026
Same author

Corrigendum to "Shengxian decoction mitigate bleomycin-induced pulmonary fibrosis in mice via MerTK mediated macrophage efferocytosis" [J. Ethnopharmacol. 365 (2026) 121583].

Journal of ethnopharmacology·2026
Same author

Kernel PCA for out-of-Distribution Detection: Non-Linear Kernel Selection and Approximation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Hydrochar and pyrochar enhanced soil fungal community diversity in a <i>Quercus acutissima</i> plantation under severe nitric acid-type acid rain stress.

Frontiers in plant science·2026
Same author

A Review of Modelling Test Study on the Effect of Single-Line Tunnelling on Adjacent Piles: Test Materials, Methodologies and Results.

Materials (Basel, Switzerland)·2026
Same author

Tanshinone IIA impairs platelet function and thrombus formation.

Journal of thrombosis and haemostasis : JTH·2026

Related Experiment Video

Updated: Mar 10, 2026

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

5.6K

Wearable Sensor-Based Human Activity Recognition Method with Multi-Features Extracted from Hilbert-Huang Transform.

Huile Xu1,2, Jinyi Liu3,4, Haibo Hu5,6

  • 1Department of Automation, Tsinghua National Laboratory for Information Science and Technology (TNList), Tsinghua University, Beijing 100084, China. hl-xu16@mails.tsinghua.edu.cn.

Sensors (Basel, Switzerland)
|December 6, 2016
PubMed
Summary
This summary is machine-generated.

This study introduces a new multi-feature extraction method using the Hilbert-Huang Transform (HHT) for human activity recognition from wearable sensors. The HHT method effectively handles nonlinear and non-stationary data, significantly improving recognition accuracy.

Keywords:
Hilbert-Huang transformactivity recognitionfeature extractionwearable sensors

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

9.4K
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

12.0K

Related Experiment Videos

Last Updated: Mar 10, 2026

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

5.6K
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
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

12.0K

Area of Science:

  • Biomedical Engineering
  • Signal Processing
  • Machine Learning

Background:

  • Human activity recognition (HAR) using wearable sensors has applications in healthcare and monitoring.
  • Traditional methods using Fourier Transform (FT) and Wavelet Transform (WT) are limited with nonlinear and non-stationary data.
  • There is a need for advanced signal processing techniques to improve HAR accuracy.

Purpose of the Study:

  • To investigate the effectiveness of the Hilbert-Huang Transform (HHT) for nonlinear and non-stationary activity data.
  • To propose a multi-feature extraction method based on HHT to enhance HAR.
  • To evaluate the performance of the proposed method using the PAMAP2 dataset.

Main Methods:

  • Empirical Mode Decomposition (EMD) to extract instantaneous amplitude (IA) and instantaneous frequency (IF).
  • Hilbert spectral analysis to derive instantaneous energy density (IE) and marginal spectrum (MS).
  • Multi-feature combination strategy evaluated against single-feature approaches.

Main Results:

  • The proposed HHT-based multi-feature extraction method significantly improves HAR performance.
  • Combining multiple features derived from HHT yields better results than single features.
  • High performance metrics (recall, precision, F-measure, accuracy ~0.93-0.94) were achieved for both dependent and independent subjects.

Conclusions:

  • The Hilbert-Huang Transform is a suitable method for analyzing nonlinear and non-stationary activity data from wearable sensors.
  • A multi-feature extraction approach based on HHT offers superior performance in human activity recognition.
  • The proposed method demonstrates robust and accurate HAR capabilities, outperforming existing related works.