Classification of the trained and untrained emitter types based on class probability output networks

Modern airplanes and ships are equipped with radars emitting specific patterns of electromagnetic signals. The radar antennas are detecting these patterns which are required to identify the types of emitters. A conventional way of emitter identification is to categorize the radar patterns according...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) 2017-07, Vol.248, p.67-75
Main Authors: Kim, Lee Suk, Bae, Han Bin, Kil, Rhee Man, Jo, Churl Hee
Format: Article
Language:English
Subjects:
Classification
Conditional class probability
Radar patterns
Trained and untrained emitter types
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Modern airplanes and ships are equipped with radars emitting specific patterns of electromagnetic signals. The radar antennas are detecting these patterns which are required to identify the types of emitters. A conventional way of emitter identification is to categorize the radar patterns according to the sequences of radar frequencies, differences in time of arrivals, and pulse widths of emitting signals by human experts. In this respect, this paper proposes a method of classifying the radar patterns automatically using the network of calculating the p-values for testing the hypotheses of the types of emitters referred to as the class probability output network (CPON). The proposed method also provides a new way of identifying the trained and untrained emitter types. Through the simulation for radar pattern classification, the effectiveness of the proposed approach has been demonstrated.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2017.01.094