Clustered Multi-Task Learning for Automatic Radar Target Recognition

Model training is a key technique for radar target recognition. Traditional model training algorithms in the framework of single task leaning ignore the relationships among multiple tasks, which degrades the recognition performance. In this paper, we propose a clustered multi-task learning, which ca...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Sensors (Basel, Switzerland) Jg. 17; H. 10; S. 2218
Hauptverfasser:	Li, Cong, Bao, Weimin, Xu, Luping, Zhang, Hua
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Switzerland MDPI AG 27.09.2017 MDPI
Schlagworte:	Algorithms clustered multi-task learning high-resolution range profile (HRRP) radar automatic target recognition (RATR) synthetic aperture radar (SAR) Target recognition synthetic aperture radar (SAR) radar automatic target recognition (RATR) high-resolution range profile (HRRP) clustered multi-task learning
ISSN:	1424-8220, 1424-8220
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Model training is a key technique for radar target recognition. Traditional model training algorithms in the framework of single task leaning ignore the relationships among multiple tasks, which degrades the recognition performance. In this paper, we propose a clustered multi-task learning, which can reveal and share the multi-task relationships for radar target recognition. To further make full use of these relationships, the latent multi-task relationships in the projection space are taken into consideration. Specifically, a constraint term in the projection space is proposed, the main idea of which is that multiple tasks within a close cluster should be close to each other in the projection space. In the proposed method, the cluster structures and multi-task relationships can be autonomously learned and utilized in both of the original and projected space. In view of the nonlinear characteristics of radar targets, the proposed method is extended to a non-linear kernel version and the corresponding non-linear multi-task solving method is proposed. Comprehensive experimental studies on simulated high-resolution range profile dataset and MSTAR SAR public database verify the superiority of the proposed method to some related algorithms.
Bibliographie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ISSN:	1424-8220 1424-8220
DOI:	10.3390/s17102218