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

AutoRV: Automated Assessment of Right Ventricular Structure and Function Using Transesophageal Echocardiography in Mechanically Ventilated Patients.

Ultrasound in medicine & biology·2026
Same author

Recent Advances in Thermo- and Photostabilities of Organic Solar Cells: Material Design and Morphology Control.

Polymer science & technology (Washington, D.C.)·2026
Same author

Automatic monitoring of single-wall MAPSE by transesophageal echocardiography for tracking global left ventricular function irrespective of regional hypokinesia: a secondary analysis.

Intensive care medicine experimental·2026
Same author

Fast calibration algorithm for output beams in optical waveguide phased arrays using the rotating electric field vector fitting.

Applied optics·2026
Same author

Clinical effect of double level osteotomy combined with arthroscopy in the treatment of severe varus deformity of knee joint.

Journal of orthopaedics·2026
Same author

Research on the dynamic modeling method of beam control for liquid crystal optical phased array based on the fractional-order generalized Kelvin model.

Optics express·2025

Related Experiment Video

Updated: Jul 7, 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

3.8K

A Novel Lightweight Human Activity Recognition Method Via L-CTCN.

Xue Ding1, Zhiwei Li2, Jinyang Yu1

  • 1Mobile and Terminal Technology Research Department, China Telecom Research Institute, Beijing 100876, China.

Sensors (Basel, Switzerland)
|December 23, 2023
PubMed
Summary

This study introduces a new Lightweight-Complex Temporal Convolution Network (L-CTCN) for Wi-Fi-based human activity recognition. The model achieves high accuracy with significantly reduced complexity, making it ideal for Internet of Things devices.

Keywords:
L-CTCNWi-Fi sensinghuman activity recognitionlightweight

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

8.9K
Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT
08:04

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Published on: April 23, 2020

6.8K

Related Experiment Videos

Last Updated: Jul 7, 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

3.8K
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

8.9K
Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT
08:04

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Published on: April 23, 2020

6.8K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Signal Processing

Background:

  • Wi-Fi-based human activity recognition (HAR) is crucial for various applications.
  • Deep learning models offer high performance but demand substantial resources and data.
  • Existing methods struggle with lightweight Internet of Things (IoT) device constraints and data dependency.

Purpose of the Study:

  • To develop a lightweight and efficient HAR model suitable for IoT devices.
  • To reduce the model's dependence on large, high-quality datasets.
  • To enhance feature extraction capabilities with limited data.

Main Methods:

  • Proposed a novel Lightweight-Complex Temporal Convolution Network (L-CTCN).
  • Integrated complex convolution for richer feature extraction from raw data.
  • Utilized a Temporal Convolution Network (TCN) framework with 1D convolutions and residual blocks for lightweight design.

Main Results:

  • Achieved an average recognition accuracy of 96.6%.
  • The model has a small parameter size of only 0.17 million.
  • Demonstrated robust performance with low sampling rates, few subcarriers, and limited samples.

Conclusions:

  • The L-CTCN effectively balances recognition performance and model complexity.
  • This approach enables efficient HAR on resource-constrained IoT devices.
  • The method reduces the need for extensive data collection and annotation.