MAEPD: A Foundation Model for Distributed Acoustic Sensing Signal Recognition via Masked Autoencoder Pre-Training and Adapter-Based Prompt Tuning
Sensors · 25.03.2026 · 26 (7) · 2057
DOI: 10.3390/s26072057 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 25.03.2026. Verfasst von Kun Gui und 7 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou 310023, China. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Zhejiang Province, National Natural Science Foundation of China, Open Fund of the State Key Laboratory of Advanced Optical Communication Systems and Networks.
Abstract (Originalsprache)
Artificial intelligence (AI) algorithms enhance distributed acoustic sensing (DAS) signal interpretation by leveraging large-scale acoustic data. However, heterogeneous deployment environments hinder model generalization ability and exacerbate label scarcity. To overcome these challenges, we propose MAEPD, a foundation model for DAS signal recognition trained via masked autoencoder pre-training on large-scale, unlabeled DAS data collected from diverse domains. The pre-trained model is subsequently adapted to downstream tasks using adapter-based prompt tuning (APT) with only minimal labeled samples. In the DAS gait identity recognition task, with only 240 image signals per class, APT achieves 94.75% accuracy, a 4.46% improvement over full fine-tuning while updating only 2.77% of parameters. Inference latency of 2.74 ms per image meets real-time requirements. Compared to pre-training with gait data only (35.6 k samples), MAEPD improves accuracy by 3.88%, demonstrating the advantage of diverse pre-training data. The method shows robust performance across water pipe leakage, perimeter security, and public datasets, with low sensitivity to labeled data quantity. Results demonstrate an efficient and scalable solution for DAS signal recognition.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou 310023, China.
- Binjiang Institute of Artificial Intelligence, Zhejiang University of Technology, Hangzhou 310056, China.
- College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, China.
- Information Engineering School, Hangzhou Dianzi University, Hangzhou 310018, China.
- College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023, China.
ORCID-Profile: Kun Gui
Förderung
- Natural Science Foundation of Zhejiang Province
- National Natural Science Foundation of China
- Open Fund of the State Key Laboratory of Advanced Optical Communication Systems and Networks
- Horizontal Projects of Public Institutions
- Natural Science Foundation of Zhejiang Province https://ror.org/04aqat463
- National Natural Science Foundation of China https://ror.org/01h0zpd94
- Open Fund of the State Key Laboratory of Advanced Optical Communication Systems and Networks https://ror.org/02a9key75
Zitieren
APA
Gui, K., Ren, H., Shi, S., Lu, J., Yu, C., Cao, Q., Gu, G., & Xuan, Q. (2026). MAEPD: A Foundation Model for Distributed Acoustic Sensing Signal Recognition via Masked Autoencoder Pre-Training and Adapter-Based Prompt Tuning. Sensors, 26(7), 2057. https://doi.org/10.3390/s26072057
Vancouver
Gui K, Ren H, Shi S, Lu J, Yu C, Cao Q, et al. MAEPD: A Foundation Model for Distributed Acoustic Sensing Signal Recognition via Masked Autoencoder Pre-Training and Adapter-Based Prompt Tuning. Sensors. 2026;26(7):2057. doi:10.3390/s26072057
BibTeX
@article{Gui2026,
author = {Gui, Kun and Ren, Hongliang and Shi, Shang and Lu, Jin and Yu, Changqiu and Cao, Quanjun and Gu, Guomin and Xuan, Qi},
title = {MAEPD: A Foundation Model for Distributed Acoustic Sensing Signal Recognition via Masked Autoencoder Pre-Training and Adapter-Based Prompt Tuning},
journal = {Sensors},
year = {2026},
volume = {26},
number = {7},
pages = {2057},
doi = {10.3390/s26072057}
}
EUVIMED