Saved in:
Bibliographic Details
Main Authors: Yang, Chunyu, Yang, Boyu, Qiu, Kun, Chen, Zhe, Gao, Yue
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.17187
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909591526178816
author Yang, Chunyu
Yang, Boyu
Qiu, Kun
Chen, Zhe
Gao, Yue
author_facet Yang, Chunyu
Yang, Boyu
Qiu, Kun
Chen, Zhe
Gao, Yue
contents The escalating overlap between non-geostationary orbit (NGSO) and geostationary orbit (GSO) satellite frequency allocations necessitates accurate interference detection methods that address two pivotal technical gaps: computationally efficient signal analysis for real-time operation, and robust anomaly discrimination under varying interference patterns. Existing deep learning approaches employ encoder-decoder anomaly detectors that threshold input-output discrepancies for robustness. While the transformer-based TrID model achieves state-of-the-art performance (AUC: 0.8318, F1: 0.8321), its multi-head attention incurs prohibitive computation time, and its decoupled training of time-frequency models overlooks cross-domain dependencies. To overcome these problems, we propose DualAttWaveNet. A bidirectional attention fusion layer dynamically correlates time-domain samples using parameter-efficient cross-attention routing. A wavelet-regularized reconstruction loss enforces multi-scale consistency. We train the model on public dataset which consists of 48 hours of satellite signals. Experiments show that compared to TrID, DualAttWaveNet improves AUC by 12% and reduces inference time by 50% to 540ms per batch while maintaining F1-score.
format Preprint
id arxiv_https___arxiv_org_abs_2504_17187
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DualAttWaveNet: Multiscale Attention Networks for Satellite Interference Detection
Yang, Chunyu
Yang, Boyu
Qiu, Kun
Chen, Zhe
Gao, Yue
Signal Processing
The escalating overlap between non-geostationary orbit (NGSO) and geostationary orbit (GSO) satellite frequency allocations necessitates accurate interference detection methods that address two pivotal technical gaps: computationally efficient signal analysis for real-time operation, and robust anomaly discrimination under varying interference patterns. Existing deep learning approaches employ encoder-decoder anomaly detectors that threshold input-output discrepancies for robustness. While the transformer-based TrID model achieves state-of-the-art performance (AUC: 0.8318, F1: 0.8321), its multi-head attention incurs prohibitive computation time, and its decoupled training of time-frequency models overlooks cross-domain dependencies. To overcome these problems, we propose DualAttWaveNet. A bidirectional attention fusion layer dynamically correlates time-domain samples using parameter-efficient cross-attention routing. A wavelet-regularized reconstruction loss enforces multi-scale consistency. We train the model on public dataset which consists of 48 hours of satellite signals. Experiments show that compared to TrID, DualAttWaveNet improves AUC by 12% and reduces inference time by 50% to 540ms per batch while maintaining F1-score.
title DualAttWaveNet: Multiscale Attention Networks for Satellite Interference Detection
topic Signal Processing
url https://arxiv.org/abs/2504.17187