智能科学与技术学报2025，Vol.7Issue(3)：329-337,9.DOI:10.11959/j.issn.2096-6652.202528
基于选择性深度嵌入聚类的复杂未知雷达信号分选方法
A complex unknown radar signal deinterleaving method based on selective deep embedding clustering
丁宸聪1
作者信息
- 1. 中国人民解放军92728部队,上海 200436
- 折叠
摘要
Abstract
With the continuous advancement of electronic warfare and radar technologies,radar signal in battlefield envi-ronments has become increasingly complex and diverse,which poses severe challenges to signal deinterleaving.Tradi-tional deinterleaving methods typically rely on prior knowledge and a preset number of categories,making them unsuit-able for handling unknown signal sources and dynamically changing features that may arise in real-world applications.To address this issue,a complex unknown radar signal deinterleaving method based on selective deep embedding clustering was proposed.By integrating the feature extraction capabilities of deep learning with the flexibility of a density-based clustering algorithm,this method achieved adaptive embedding and clustering of radar signal parameters without relying on specific prior knowledge.Through automatic feature learning via neural networks coupled with a density-based cluster-ing algorithm,the need for manually defined features with limited generalizability was avoided.Experimental results on radar signal datasets from complex environments indicate that the proposed method achieves a cluster purity of up to 99.46%,demonstrating robust adaptability and extensibility in identifying unknown or dynamically changing signal char-acteristics.Compared with traditional methods,selective deep embedding clustering provides a more universal and reli-able solution for large-scale,complex radar signal processing and offers valuable references for other extensive data min-ing tasks involving unknown signals.关键词
雷达信号分选/电子侦察/聚类/深度学习Key words
radar signal deinterleaving/electronic reconnaissance/clustering/deep learning分类
信息技术与安全科学引用本文复制引用
丁宸聪..基于选择性深度嵌入聚类的复杂未知雷达信号分选方法[J].智能科学与技术学报,2025,7(3):329-337,9.
