Online clustering algorithms for radar emitter classification

被引：87

作者：

Liu, J

Lee, JPY

Li, LJ

Luo, ZQ

Wong, KM

机构：

[1] TechnoCom Corp, Encino, CA 91436 USA

[2] Def R&D Canada, Ottawa, ON K1A 0Z4, Canada

[3] McMaster Univ, Dept Elect & Comp Engn, Hamilton, ON L8S 4K1, Canada

[4] Univ Minnesota, Dept Elect & Comp Engn, Minneapolis, MN 55455 USA

来源：

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 2005年 / 27卷 / 08期

关键词：

emitter classification; online process; MDL criterion; cluster validation; clustering; competitive learning; computational complexity;

D O I：

10.1109/TPAMI.2005.166

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Radar emitter classification is a special application of data clustering for classifying unknown radar emitters from received radar pulse samples. The main challenges of this task are the high dimensionality of radar pulse samples, small sample group size, and closely located radar pulse clusters. In this paper, two new online clustering algorithms are developed for radar emitter classification: One is model-based using the Minimum Description Length (MDL) criterion and the other is based on competitive learning. Computational complexity is analyzed for each algorithm and then compared. Simulation results show the superior performance of the model-based algorithm over competitive learning in terms of better classification accuracy, flexibility, and stability.

引用

页码：1185 / 1196

页数：12

共 28 条

[1]

Anderberg M.R., 1973, Probability and Mathematical Statistics

[2]

[Anonymous], [No title captured]

[3]

[Anonymous], J MACHINE LEARNING R

[4]

[Anonymous], SELF ORGANIZING MAPS