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

STCCA: Spatial-Temporal Coupled Cross-Attention Through Hierarchical Network for EEG-Based Speech Recognition.

Sensors (Basel, Switzerland)·2025
Same author

Brain-model neural similarity reveals abstractive summarization performance.

Scientific reports·2025
Same author

TRCCBP: Transformer Network for Radar-Based Contactless Continuous Blood Pressure Monitoring.

Sensors (Basel, Switzerland)·2023
Same author

Epileptic Tissue Localization through Skewness-Based Functional Connectivity in the High-Frequency Band of Intracranial EEG.

Bioengineering (Basel, Switzerland)·2023
Same author

Hierarchical Trajectory Planning for Narrow-Space Automated Parking with Deep Reinforcement Learning: A Federated Learning Scheme.

Sensors (Basel, Switzerland)·2023
Same author

[Study on the target movement in external-beam partial breast irradiation with active breathing control after breast-conserving surgery].

Zhonghua zhong liu za zhi [Chinese journal of oncology]·2008

Related Experiment Video

Updated: Jul 24, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K

Multi-Task Learning Radar Transformer (MLRT): A Personal Identification and Fall Detection Network Based on IR-UWB

Xikang Jiang1, Lin Zhang1, Lei Li1

  • 1School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China.

Sensors (Basel, Switzerland)
|July 8, 2023
PubMed
Summary

This study introduces the Multi-task Learning Radar Transformer (MLRT) for radar-based personal identification and fall detection. MLRT enhances accuracy in smart healthcare by effectively processing radar time-series signals using deep learning.

Keywords:
Impulse Radio Ultra-Wideband (IR-UWB) radarTransformerfall detectionmulti-task learningpersonal identification

More Related Videos

Using a Real-Time Locating System to Measure Walking Activity Associated with Wandering Behaviors Among Institutionalized Older Adults
04:13

Using a Real-Time Locating System to Measure Walking Activity Associated with Wandering Behaviors Among Institutionalized Older Adults

Published on: February 8, 2019

6.8K
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

3.9K

Related Experiment Videos

Last Updated: Jul 24, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K
Using a Real-Time Locating System to Measure Walking Activity Associated with Wandering Behaviors Among Institutionalized Older Adults
04:13

Using a Real-Time Locating System to Measure Walking Activity Associated with Wandering Behaviors Among Institutionalized Older Adults

Published on: February 8, 2019

6.8K
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

3.9K

Area of Science:

  • Smart healthcare technologies
  • Radar sensing applications
  • Deep learning for biometrics

Background:

  • Radar-based personal identification and fall detection are crucial for smart healthcare.
  • Existing Transformer networks struggle with multi-task radar signal analysis.
  • Deep learning enhances non-contact radar sensing performance.

Purpose of the Study:

  • To propose the Multi-task Learning Radar Transformer (MLRT) for integrated personal identification and fall detection using IR-UWB radar.
  • To leverage multi-task learning to improve feature extraction from radar time-series signals.
  • To enhance the discrimination performance for both identification and fall detection tasks.

Main Methods:

  • Utilized the Transformer attention mechanism for automatic feature extraction from radar time-series signals.
  • Applied multi-task learning to exploit correlations between identification and fall detection.
  • Implemented signal processing techniques (DC removal, bandpass filtering, clutter suppression, Kalman filtering) to mitigate noise and interference.

Main Results:

  • The MLRT network demonstrated improved accuracy: 8.5% for personal identification and 3.6% for fall detection.
  • Performance was evaluated on a newly generated indoor radar signal dataset with 11 individuals.
  • Results showed superior performance compared to state-of-the-art algorithms.

Conclusions:

  • The MLRT model effectively extracts temporal features for multi-task radar-based applications.
  • Multi-task learning significantly enhances the accuracy of personal identification and fall detection.
  • The proposed MLRT and dataset are publicly available, facilitating further research in radar sensing for healthcare.