Saved in:
Bibliographic Details
Main Authors: Hu, Xianan, Li, Fu, Niu, Kairui, Qi, Peihan, Liang, Zhiyong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.13480
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913742096171008
author Hu, Xianan
Li, Fu
Niu, Kairui
Qi, Peihan
Liang, Zhiyong
author_facet Hu, Xianan
Li, Fu
Niu, Kairui
Qi, Peihan
Liang, Zhiyong
contents Our study proposes a novel embedding method, Wide-Value-Embeddings (WVEmbs), for processing Pulse Descriptor Words (PDWs) as normalized inputs to neural networks. This method adapts to the distribution of interleaved radar signals, ranking original signal features from trivial to useful and stabilizing the learning process. To address the imbalance in radar signal interleaving, we introduce a value dimension masking method on WVEmbs, which automatically and efficiently generates challenging samples, and constructs interleaving scenarios, thereby compelling the model to learn robust features. Experimental results demonstrate that our method is an efficient end-to-end approach, achieving high-granularity, sample-level pulse sorting for high-density interleaved radar pulse sequences in complex and non-ideal environments.
format Preprint
id arxiv_https___arxiv_org_abs_2503_13480
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WVEmbs with its Masking: A Method For Radar Signal Sorting
Hu, Xianan
Li, Fu
Niu, Kairui
Qi, Peihan
Liang, Zhiyong
Signal Processing
Machine Learning
Our study proposes a novel embedding method, Wide-Value-Embeddings (WVEmbs), for processing Pulse Descriptor Words (PDWs) as normalized inputs to neural networks. This method adapts to the distribution of interleaved radar signals, ranking original signal features from trivial to useful and stabilizing the learning process. To address the imbalance in radar signal interleaving, we introduce a value dimension masking method on WVEmbs, which automatically and efficiently generates challenging samples, and constructs interleaving scenarios, thereby compelling the model to learn robust features. Experimental results demonstrate that our method is an efficient end-to-end approach, achieving high-granularity, sample-level pulse sorting for high-density interleaved radar pulse sequences in complex and non-ideal environments.
title WVEmbs with its Masking: A Method For Radar Signal Sorting
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2503.13480