Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Nov 7, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Study on Human Activity Recognition Using Semi-Supervised Active Transfer Learning.

Seungmin Oh¹, Akm Ashiquzzaman¹, Dongsu Lee¹

¹Department of ICT Convergence System Engineering, Chonnam National University, Gwangju 61186, Korea.

Sensors (Basel, Switzerland)

|April 30, 2021

Summary

This summary is machine-generated.

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

Digital Literacy and Interpersonal Trust as Predictors of Willingness to Share Patient-Generated Health Data Among Korean Internet Users: Cross-Sectional Study Using Privacy Calculus and Communication Privacy Management Theories.

Journal of medical Internet research·2026

Same author

Juvenile-to-adult refinement of thalamic reticular circuits via LRRTM3 enables high-resolution sensory encoding.

Neuron·2026

Same author

Ovonic Switches Enable Energy-Efficient Dendrite-like Computing.

Nano letters·2025

Same author

Frequency multiplexing with dispersion-engineered elastic metasurfaces.

Nature communications·2025

Same author

Microglial VRK2 Regulates Astrocytic GABA Synthesis and Tonic Inhibition in the Thalamus.

Glia·2025

Same author

Automatic detection of trapping events of postnatal piglets in loose housing pen: comparison of YOLO versions 4, 5, and 8.

Journal of animal science and technology·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

Deep learning for human activity recognition (HAR) is hindered by the need for extensive labeled data. A novel semi-supervised active transfer learning method significantly reduces labeling efforts and achieves 95.9% performance in HAR.

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Deep learning models are increasingly used for human activity recognition (HAR).
Training these models requires substantial labeled data, which is costly and time-consuming to acquire in HAR.
Current methods suffer from slow data collection and human bias in labeling.

Purpose of the Study:

To address the challenges of data collection and labeling in HAR.
To propose a novel method that reduces manual labeling requirements for deep learning models.
To improve the efficiency and reduce bias in HAR data processing.

Main Methods:

Implemented a semi-supervised active transfer learning approach.
Reduced the reliance on manual labeling for new datasets.

Keywords:

active transfer learning human activity recognition labeling reduction semi-supervised active transfer learning semi-supervised learning

More Related Videos

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

Related Experiment Videos

Last Updated: Nov 7, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

Utilized learned data from existing datasets to improve model training.

Main Results:

Achieved a performance accuracy of 95.9% in human activity recognition.
Significantly reduced the amount of manual labeling required compared to traditional methods.
Demonstrated superior performance over random sampling and standard active transfer learning.

Conclusions:

The proposed semi-supervised active transfer learning method is effective for HAR.
This approach mitigates the data scarcity and labeling bottleneck in deep learning for HAR.
Offers a more efficient and less biased solution for HAR research and applications.