Radar target identification using HRRP-based features and Extreme Learning Machines

摘要

Radar target recognition performance using extreme learning machines (ELM) is examined in this study and comparedwith optimal classifiers. Classification under various adverse scenarios involving additive noise, azimuth ambiguity,azimuth mismatch between library and unknown target, presence of extraneous scatterers, signature occlusion, absolutephase knowledge, etc. are examined. ELM can be trained expeditiously and are suited for radar target recognitionparticularly with large training database. The effectiveness of ELM (single layer or multilayered) as a target recognitiontool is the focus in this study that relies on real radar data collected in a compact range environment using a steppedfrequencysystem.