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

Transferable Deep Reinforcement Learning With Edge-Contour-Depth Fusion for Autonomous Wireless Capsule Endoscopy Navigation.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

How can reasoning capability empower the AI copilot robot in endoscopic surgery.

NPJ digital medicine·2026
Same author

Current validation practice undermines surgical AI development.

ArXiv·2026
Same author

A Real-time Scale-robust Network for Glottis Segmentation in Nasal Transnasal Intubation.

IEEE journal of biomedical and health informatics·2026
Same author

Integrating Dynamic Representation and Multi-Priors for Transnasal Intubation via Visual Foundation Model.

Bioengineering (Basel, Switzerland)·2026
Same author

Inertia-driven amphibious robot with asymmetric microundulatory fin arrays.

Science advances·2026
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

Related Experiment Video

Updated: Apr 15, 2026

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

1.0K

MAEPD: A Foundation Model for Distributed Acoustic Sensing Signal Recognition via Masked Autoencoder Pre-Training and

Kun Gui1,2, Hongliang Ren1,2, Shang Shi1,2

  • 1Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou 310023, China.

Sensors (Basel, Switzerland)
|April 14, 2026
PubMed
Summary
This summary is machine-generated.

A new foundation model, MAEPD, uses masked autoencoder pre-training on diverse, unlabeled acoustic data for improved distributed acoustic sensing (DAS) signal recognition. Adapter-based prompt tuning (APT) enables high accuracy with minimal labeled data, offering an efficient, scalable solution.

Keywords:
DAS signal recognition methodMAE (masked autoencoder)distributed acoustic sensing (DAS)foundation modelgait recognitionparameter-efficient fine-tuning

More Related Videos

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

2.1K
Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

2.1K

Related Experiment Videos

Last Updated: Apr 15, 2026

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

1.0K
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

2.1K
Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

2.1K

Area of Science:

  • Signal Processing
  • Machine Learning
  • Sensor Technology

Background:

  • Distributed Acoustic Sensing (DAS) interpretation is challenged by diverse environments and limited labeled data.
  • Artificial Intelligence (AI) algorithms can enhance DAS signal analysis but struggle with generalization.
  • Label scarcity and heterogeneous deployment hinder the development of robust DAS interpretation models.

Purpose of the Study:

  • To develop a foundation model for Distributed Acoustic Sensing (DAS) signal recognition that overcomes generalization and label scarcity issues.
  • To propose MAEPD, a model pre-trained on diverse, unlabeled DAS data and adapted using adapter-based prompt tuning (APT).
  • To demonstrate the efficiency and scalability of MAEPD for various DAS downstream tasks.

Main Methods:

  • Masked autoencoder pre-training on large-scale, unlabeled DAS data from diverse domains.
  • Adapter-based prompt tuning (APT) for adapting the pre-trained model to downstream tasks with minimal labeled samples.
  • Evaluation on DAS gait identity recognition, water pipe leakage, and perimeter security tasks.

Main Results:

  • MAEPD achieved 94.75% accuracy in DAS gait identity recognition with minimal data, outperforming full fine-tuning by 4.46%.
  • The model demonstrated robust performance across multiple datasets and applications, showing low sensitivity to labeled data quantity.
  • Pre-training on diverse data significantly improved accuracy compared to domain-specific pre-training, highlighting the benefit of varied datasets.

Conclusions:

  • MAEPD provides an efficient and scalable solution for DAS signal recognition, leveraging diverse unlabeled data and minimal labeled samples.
  • Adapter-based prompt tuning (APT) is an effective method for adapting foundation models to specific DAS tasks with limited labeled data.
  • The proposed approach enhances model generalization and addresses the challenge of label scarcity in heterogeneous DAS deployment environments.