Statistically-Guided Meta-Learning for Cross-Deployment Activity Recognition in Distributed Fiber-Optic Sensing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Yifan, Zhang, Haodong, Song, Qiuheng, Lei, Lin, Zeng, Zhenxuan, He, Haoyang, Wu, Hongyan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908994694545408
author He, Yifan
Zhang, Haodong
Song, Qiuheng
Lei, Lin
Zeng, Zhenxuan
He, Haoyang
Wu, Hongyan
author_facet He, Yifan
Zhang, Haodong
Song, Qiuheng
Lei, Lin
Zeng, Zhenxuan
He, Haoyang
Wu, Hongyan
contents Distributed Fiber Optic Sensing (DFOS) is promising for long-range perimeter security, yet practical deployment faces three key obstacles: severe cross-deployment domain shift, scarce or unavailable labels at new sites, and limited within-class coverage even in source deployments. We propose DUPLE, a prototype-based meta-learning framework tailored for cross-deployment DFOS recognition. The core idea is to jointly exploit complementary time- and frequency-domain cues and adapt class representations to sample-specific statistics: (i) a dual-domain learner constructs multi-prototype class representations to cover intra-class heterogeneity; (ii) a lightweight statistical guidance mechanism estimates the reliability of each domain from raw signal statistics; and (iii) a query-adaptive aggregation strategy selects and combines the most relevant prototypes for each query. Extensive experiments on two real-world cross-deployment benchmarks demonstrate consistent improvements over strong deep learning and meta-learning baselines, achieving more accurate and stable recognition under label-scarce target deployments.
format Preprint
id arxiv_https___arxiv_org_abs_2511_17902
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Statistically-Guided Meta-Learning for Cross-Deployment Activity Recognition in Distributed Fiber-Optic Sensing
He, Yifan
Zhang, Haodong
Song, Qiuheng
Lei, Lin
Zeng, Zhenxuan
He, Haoyang
Wu, Hongyan
Machine Learning
Artificial Intelligence
Distributed Fiber Optic Sensing (DFOS) is promising for long-range perimeter security, yet practical deployment faces three key obstacles: severe cross-deployment domain shift, scarce or unavailable labels at new sites, and limited within-class coverage even in source deployments. We propose DUPLE, a prototype-based meta-learning framework tailored for cross-deployment DFOS recognition. The core idea is to jointly exploit complementary time- and frequency-domain cues and adapt class representations to sample-specific statistics: (i) a dual-domain learner constructs multi-prototype class representations to cover intra-class heterogeneity; (ii) a lightweight statistical guidance mechanism estimates the reliability of each domain from raw signal statistics; and (iii) a query-adaptive aggregation strategy selects and combines the most relevant prototypes for each query. Extensive experiments on two real-world cross-deployment benchmarks demonstrate consistent improvements over strong deep learning and meta-learning baselines, achieving more accurate and stable recognition under label-scarce target deployments.
title Statistically-Guided Meta-Learning for Cross-Deployment Activity Recognition in Distributed Fiber-Optic Sensing
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2511.17902