Unsupervised radar signal recognition based on multi‐block – Multi‐view Low‐Rank Sparse Subspace Clustering

• Published in: IET radar, sonar & navigation Vol. 16; no. 3; pp. 542 - 551
• Main Authors: Liu, Lutao, Xu, Shuai
• Format: Journal Article
• Language: English
• Published: Wiley 01.03.2022
• Subjects: multi‐block; multi‐view subspace clustering; TFIs; unsupervised recognition of radar signals; untagged signals
• ISSN: 1751-8784; 1751-8792; 1751-8792
• DOI: 10.1049/rsn2.12201

In the field of radar reconnaissance, unsupervised recognition of radar signals is a particularly important method for classifying different signals and estimating signal parameters. For untagged signals, a new unsupervised recognition method based on the time‐frequency (TF) analysis and Multi‐view Low‐Rank Sparse Subspace Clustering (MLRSSC) is proposed. Specifically, the authors use image wavelet decomposition to create four views for TF images (TFIs), which introduces the concept of multi‐view subspace clustering into radar signal recognition. Compared with other advanced clustering algorithms, the authors' algorithm pays more attention to combining the inherent properties of TFIs. Aiming at the unique ridgeline distribution phenomenon of TFI, a multi‐block technology capable of robustly distributing TFIs subspaces is proposed. Then, Multi‐block and MLRSSC are combined to propose the Multi‐block Joint Multi‐view Subspace Clustering (M‐MLRSSC). The simulation shows that in the TFIs data set with a certain signal‐to‐noise ratio, M‐MLRSSC has obtained superior results, which is better than a variety of advanced subspace clustering algorithms.